adding in code

Code/Arduino/Gesture/examples/Gesture/Gesture.ino

@@ -0,0 +1,43 @@
+#include <Wire.h>
+#include "PAJ7620U2.h"
+
+unsigned short  Gesture_Data;
+void setup() {
+    uint8_t i;
+    Serial.begin(115200);
+    Serial.print("\nGesture Sensor Test Program ...\n");
+    delayMicroseconds(800);
+    Wire.begin();
+    delayMicroseconds(10);
+    while(!PAJ7620U2_init())
+    { Serial.print("\nGesture Sensor Error\n");
+      delay(500);
+    }
+    Serial.print("\nGesture Sensor OK\n");
+    I2C_writeByte(PAJ_BANK_SELECT, 0);//Select Bank 0
+    for (i = 0; i < Gesture_Array_SIZE; i++)
+    {
+      I2C_writeByte(Init_Gesture_Array[i][0], Init_Gesture_Array[i][1]);//Gesture register initializes
+    }
+}
+
+void loop() {
+    Gesture_Data = I2C_readU16(PAJ_INT_FLAG1);
+    if (Gesture_Data)
+    {
+      switch (Gesture_Data)
+      {
+        case PAJ_UP:                   Serial.print("Up\r\n");            break;
+        case PAJ_DOWN:                 Serial.print("Down\r\n");          break;
+        case PAJ_LEFT:                 Serial.print("Left\r\n");          break;
+        case PAJ_RIGHT:                Serial.print("Right\r\n");         break;
+        case PAJ_FORWARD:              Serial.print("Forward\r\n");       break;
+        case PAJ_BACKWARD:             Serial.print("Backward\r\n");      break;
+        case PAJ_CLOCKWISE:            Serial.print("Clockwise\r\n");     break;
+        case PAJ_COUNT_CLOCKWISE:      Serial.print("AntiClockwise\r\n"); break;
+        case PAJ_WAVE:                 Serial.print("Wave\r\n");          break;
+        default: break;
+      }
+      Gesture_Data=0;
+    }
+}

Code/Arduino/Gesture/examples/Gesture/PAJ7620U2.cpp

@@ -0,0 +1,50 @@
+#include <Arduino.h>
+#include <Wire.h>
+#include "PAJ7620U2.h"
+
+
+
+uint8_t I2C_readByte(uint8_t  addr)
+{
+  Wire.beginTransmission(PAJ7620U2_I2C_ADDRESS);
+  Wire.write(addr);
+  Wire.endTransmission();
+  Wire.requestFrom(PAJ7620U2_I2C_ADDRESS, 1);
+  if (Wire.available()) {
+   return Wire.read();
+  }
+  return 0;
+}
+uint16_t I2C_readU16(uint8_t addr)
+{
+ uint16_t x; uint16_t t;
+
+  Wire.beginTransmission(PAJ7620U2_I2C_ADDRESS);
+  Wire.write(addr); 
+  Wire.endTransmission();
+  Wire.requestFrom(PAJ7620U2_I2C_ADDRESS, 2);
+  t = Wire.read();
+  x = Wire.read();
+  x <<= 8;
+  x |= t;
+  return x;
+}
+void I2C_writeByte(uint8_t addr, uint8_t data)
+{
+  Wire.beginTransmission(PAJ7620U2_I2C_ADDRESS);
+  Wire.write(addr);
+  Wire.write(data & 0xFF);
+  Wire.endTransmission();
+}
+uint8_t PAJ7620U2_init()
+{
+  uint8_t i,State;
+  State =I2C_readByte(0x00);                       //Read State
+  if (State != 0x20) return 0;                      //Wake up failed
+  I2C_writeByte(PAJ_BANK_SELECT, 0);                    //Select Bank 0
+  for (i=0;i< Init_Array;i++)
+  {
+    I2C_writeByte(Init_Register_Array[i][0], Init_Register_Array[i][1]);//Power up initialize
+  }
+  return 1;
+}

Code/Arduino/Gesture/examples/Gesture/PAJ7620U2.h

@@ -0,0 +1,178 @@
+#ifndef _PAJ7620U2_
+#define _PAJ7620U2_
+
+//i2c address
+#define PAJ7620U2_I2C_ADDRESS		0x73
+//Register Bank select
+#define PAJ_BANK_SELECT			0xEF		/*Bank0=0x00,Bank1=0x01*/
+//Register Bank 0
+#define PAJ_SUSPEND			 	0x03		/*I2C suspend command (Write 0x01 to enter suspend state). I2C wake-up command is slave ID wake-up. Refer to topic ��I2C Bus Timing Characteristics and Protocol��*/
+#define PAJ_INT_FLAG1_MASK		0x41		/*Gesture detection interrupt flag mask*/
+#define PAJ_INT_FLAG2_MASK		0x42		/*Gesture/PS detection interrupt flag mask*/
+#define PAJ_INT_FLAG1		    0x43		/*Gesture detection interrupt flag*/
+#define PAJ_INT_FLAG2			0x44		/*Gesture/PS detection interrupt flag*/
+#define PAJ_STATE				0x45		/*State indicator for gesture detection (Only functional at gesture detection mode)*/
+#define PAJ_PS_HIGH_THRESHOLD	0x69		/*PS hysteresis high threshold (Only functional at proximity detection mode)*/		
+#define PAJ_PS_LOW_THRESHOLD	0x6A		/*PS hysteresis low threshold (Only functional at proximity detection mode)*/
+#define PAJ_PS_APPROACH_STATE	0x6B		/*PS approach state,  Approach = 1 , (8 bits PS data >= PS high threshold),  Not Approach = 0 , (8 bits PS data <= PS low threshold)(Only functional at proximity detection mode)*/
+#define PAJ_PS_DATA				0x6C		/*PS 8 bit data(Only functional at gesture detection mode)*/
+#define PAJ_OBJ_BRIGHTNESS		0xB0		/*Object Brightness (Max. 255)*/
+#define PAJ_OBJ_SIZE_L			0xB1		/*Object Size(Low 8 bit)*/		
+#define PAJ_OBJ_SIZE_H			0xB2		/*Object Size(High 8 bit)*/	
+
+//Register Bank 1
+#define PAJ_PS_GAIN				0x44		/*PS gain setting (Only functional at proximity detection mode)*/
+#define PAJ_IDLE_S1_STEP_L		0x67		/*IDLE S1 Step, for setting the S1, Response Factor(Low 8 bit)*/
+#define PAJ_IDLE_S1_STEP_H		0x68		/*IDLE S1 Step, for setting the S1, Response Factor(High 8 bit)*/	
+#define PAJ_IDLE_S2_STEP_L		0x69		/*IDLE S2 Step, for setting the S2, Response Factor(Low 8 bit)*/
+#define PAJ_IDLE_S2_STEP_H		0x6A		/*IDLE S2 Step, for setting the S2, Response Factor(High 8 bit)*/
+#define PAJ_OPTOS1_TIME_L		0x6B		/*OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 state(Low 8 bit)*/	
+#define PAJ_OPTOS2_TIME_H		0x6C		/*OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 stateHigh 8 bit)*/	
+#define PAJ_S1TOS2_TIME_L		0x6D		/*S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 state(Low 8 bit)*/	
+#define PAJ_S1TOS2_TIME_H		0x6E		/*S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 stateHigh 8 bit)*/	
+#define PAJ_EN					0x72		/*Enable/Disable PAJ7620U2*/
+//Gesture detection interrupt flag
+#define PAJ_UP				    0x01 
+#define PAJ_DOWN			    0x02
+#define PAJ_LEFT			    0x04 
+#define PAJ_RIGHT			    0x08
+#define PAJ_FORWARD			    0x10 
+#define PAJ_BACKWARD		    0x20
+#define PAJ_CLOCKWISE			0x40
+#define PAJ_COUNT_CLOCKWISE		0x80
+#define PAJ_WAVE				0x100
+//Initialize array size
+#define Init_Array                sizeof(Init_Register_Array)/2
+#define PS_Array_SIZE             sizeof(Init_PS_Array)/2
+#define Gesture_Array_SIZE        sizeof(Init_Gesture_Array)/2
+//Power up initialize array
+const unsigned char Init_Register_Array[][2] = {
+  {0xEF,0x00},
+  {0x37,0x07},
+  {0x38,0x17},
+  {0x39,0x06},
+  {0x41,0x00},
+  {0x42,0x00},
+  {0x46,0x2D},
+  {0x47,0x0F},
+  {0x48,0x3C},
+  {0x49,0x00},
+  {0x4A,0x1E},
+  {0x4C,0x20},
+  {0x51,0x10},
+  {0x5E,0x10},
+  {0x60,0x27},
+  {0x80,0x42},
+  {0x81,0x44},
+  {0x82,0x04},
+  {0x8B,0x01},
+  {0x90,0x06},
+  {0x95,0x0A},
+  {0x96,0x0C},
+  {0x97,0x05},
+  {0x9A,0x14},
+  {0x9C,0x3F},
+  {0xA5,0x19},
+  {0xCC,0x19},
+  {0xCD,0x0B},
+  {0xCE,0x13},
+  {0xCF,0x64},
+  {0xD0,0x21},
+  {0xEF,0x01},
+  {0x02,0x0F},
+  {0x03,0x10},
+  {0x04,0x02},
+  {0x25,0x01},
+  {0x27,0x39},
+  {0x28,0x7F},
+  {0x29,0x08},
+  {0x3E,0xFF},
+  {0x5E,0x3D},
+  {0x65,0x96},
+  {0x67,0x97},
+  {0x69,0xCD},
+  {0x6A,0x01},
+  {0x6D,0x2C},
+  {0x6E,0x01},
+  {0x72,0x01},
+  {0x73,0x35},
+  {0x74,0x00},
+  {0x77,0x01},
+};
+//Approaches register initialization array
+const unsigned char Init_PS_Array[][2] = {
+  {0xEF,0x00},
+  {0x41,0x00},
+  {0x42,0x00},
+  {0x48,0x3C},
+  {0x49,0x00},
+  {0x51,0x13},
+  {0x83,0x20},
+  {0x84,0x20},
+  {0x85,0x00},
+  {0x86,0x10},
+  {0x87,0x00},
+  {0x88,0x05},
+  {0x89,0x18},
+  {0x8A,0x10},
+  {0x9f,0xf8},
+  {0x69,0x96},
+  {0x6A,0x02},
+  {0xEF,0x01},
+  {0x01,0x1E},
+  {0x02,0x0F},
+  {0x03,0x10},
+  {0x04,0x02},
+  {0x41,0x50},
+  {0x43,0x34},
+  {0x65,0xCE},
+  {0x66,0x0B},
+  {0x67,0xCE},
+  {0x68,0x0B},
+  {0x69,0xE9},
+  {0x6A,0x05},
+  {0x6B,0x50},
+  {0x6C,0xC3},
+  {0x6D,0x50},
+  {0x6E,0xC3},
+  {0x74,0x05},
+};
+
+//Gesture register initializes array
+const unsigned char Init_Gesture_Array[][2] = {
+  {0xEF,0x00},
+  {0x41,0x00},
+  {0x42,0x00},
+  {0xEF,0x00},
+  {0x48,0x3C},
+  {0x49,0x00},
+  {0x51,0x10},
+  {0x83,0x20},
+  {0x9F,0xF9},
+  {0xEF,0x01},
+  {0x01,0x1E},
+  {0x02,0x0F},
+  {0x03,0x10},
+  {0x04,0x02},
+  {0x41,0x40},
+  {0x43,0x30},
+  {0x65,0x96},
+  {0x66,0x00},
+  {0x67,0x97},
+  {0x68,0x01},
+  {0x69,0xCD},
+  {0x6A,0x01},
+  {0x6B,0xB0},
+  {0x6C,0x04},
+  {0x6D,0x2C},
+  {0x6E,0x01},
+  {0x74,0x00},
+  {0xEF,0x00},
+  {0x41,0xFF},
+  {0x42,0x01},
+};
+uint8_t I2C_readByte(uint8_t  addr);
+uint16_t I2C_readU16(uint8_t addr);
+void I2C_writeByte(uint8_t add, uint8_t data);
+uint8_t PAJ7620U2_init();
+#endif

Code/Arduino/PS/PAJ7620U2.cpp

@@ -0,0 +1,50 @@
+#include <Arduino.h>
+#include <Wire.h>
+#include "PAJ7620U2.h"
+
+
+
+uint8_t I2C_readByte(uint8_t  addr)
+{
+  Wire.beginTransmission(PAJ7620U2_I2C_ADDRESS);
+  Wire.write(addr);
+  Wire.endTransmission();
+  Wire.requestFrom(PAJ7620U2_I2C_ADDRESS, 1);
+  if (Wire.available()) {
+   return Wire.read();
+  }
+  return 0;
+}
+uint16_t I2C_readU16(uint8_t addr)
+{
+ uint16_t x; uint16_t t;
+
+  Wire.beginTransmission(PAJ7620U2_I2C_ADDRESS);
+  Wire.write(addr); 
+  Wire.endTransmission();
+  Wire.requestFrom(PAJ7620U2_I2C_ADDRESS, 2);
+  t = Wire.read();
+  x = Wire.read();
+  x <<= 8;
+  x |= t;
+  return x;
+}
+void I2C_writeByte(uint8_t addr, uint8_t data)
+{
+  Wire.beginTransmission(PAJ7620U2_I2C_ADDRESS);
+  Wire.write(addr);
+  Wire.write(data & 0xFF);
+  Wire.endTransmission();
+}
+uint8_t PAJ7620U2_init()
+{
+  uint8_t i,State;
+  State =I2C_readByte(0x00);                       //Read State
+  if (State != 0x20) return 0;                      //Wake up failed
+  I2C_writeByte(PAJ_BANK_SELECT, 0);                    //Select Bank 0
+  for (i=0;i< Init_Array;i++)
+  {
+    I2C_writeByte(Init_Register_Array[i][0], Init_Register_Array[i][1]);//Power up initialize
+  }
+  return 1;
+}

Code/Arduino/PS/PAJ7620U2.h

@@ -0,0 +1,178 @@
+#ifndef _PAJ7620U2_
+#define _PAJ7620U2_
+
+//i2c address
+#define PAJ7620U2_I2C_ADDRESS		0x73
+//Register Bank select
+#define PAJ_BANK_SELECT			0xEF		/*Bank0=0x00,Bank1=0x01*/
+//Register Bank 0
+#define PAJ_SUSPEND			 	0x03		/*I2C suspend command (Write 0x01 to enter suspend state). I2C wake-up command is slave ID wake-up. Refer to topic ��I2C Bus Timing Characteristics and Protocol��*/
+#define PAJ_INT_FLAG1_MASK		0x41		/*Gesture detection interrupt flag mask*/
+#define PAJ_INT_FLAG2_MASK		0x42		/*Gesture/PS detection interrupt flag mask*/
+#define PAJ_INT_FLAG1		    0x43		/*Gesture detection interrupt flag*/
+#define PAJ_INT_FLAG2			0x44		/*Gesture/PS detection interrupt flag*/
+#define PAJ_STATE				0x45		/*State indicator for gesture detection (Only functional at gesture detection mode)*/
+#define PAJ_PS_HIGH_THRESHOLD	0x69		/*PS hysteresis high threshold (Only functional at proximity detection mode)*/		
+#define PAJ_PS_LOW_THRESHOLD	0x6A		/*PS hysteresis low threshold (Only functional at proximity detection mode)*/
+#define PAJ_PS_APPROACH_STATE	0x6B		/*PS approach state,  Approach = 1 , (8 bits PS data >= PS high threshold),  Not Approach = 0 , (8 bits PS data <= PS low threshold)(Only functional at proximity detection mode)*/
+#define PAJ_PS_DATA				0x6C		/*PS 8 bit data(Only functional at gesture detection mode)*/
+#define PAJ_OBJ_BRIGHTNESS		0xB0		/*Object Brightness (Max. 255)*/
+#define PAJ_OBJ_SIZE_L			0xB1		/*Object Size(Low 8 bit)*/		
+#define PAJ_OBJ_SIZE_H			0xB2		/*Object Size(High 8 bit)*/	
+
+//Register Bank 1
+#define PAJ_PS_GAIN				0x44		/*PS gain setting (Only functional at proximity detection mode)*/
+#define PAJ_IDLE_S1_STEP_L		0x67		/*IDLE S1 Step, for setting the S1, Response Factor(Low 8 bit)*/
+#define PAJ_IDLE_S1_STEP_H		0x68		/*IDLE S1 Step, for setting the S1, Response Factor(High 8 bit)*/	
+#define PAJ_IDLE_S2_STEP_L		0x69		/*IDLE S2 Step, for setting the S2, Response Factor(Low 8 bit)*/
+#define PAJ_IDLE_S2_STEP_H		0x6A		/*IDLE S2 Step, for setting the S2, Response Factor(High 8 bit)*/
+#define PAJ_OPTOS1_TIME_L		0x6B		/*OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 state(Low 8 bit)*/	
+#define PAJ_OPTOS2_TIME_H		0x6C		/*OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 stateHigh 8 bit)*/	
+#define PAJ_S1TOS2_TIME_L		0x6D		/*S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 state(Low 8 bit)*/	
+#define PAJ_S1TOS2_TIME_H		0x6E		/*S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 stateHigh 8 bit)*/	
+#define PAJ_EN					0x72		/*Enable/Disable PAJ7620U2*/
+//Gesture detection interrupt flag
+#define PAJ_UP				    0x01 
+#define PAJ_DOWN			    0x02
+#define PAJ_LEFT			    0x04 
+#define PAJ_RIGHT			    0x08
+#define PAJ_FORWARD			    0x10 
+#define PAJ_BACKWARD		    0x20
+#define PAJ_CLOCKWISE			0x40
+#define PAJ_COUNT_CLOCKWISE		0x80
+#define PAJ_WAVE				0x100
+//Initialize array size
+#define Init_Array                sizeof(Init_Register_Array)/2
+#define PS_Array_SIZE             sizeof(Init_PS_Array)/2
+#define Gesture_Array_SIZE        sizeof(Init_Gesture_Array)/2
+//Power up initialize array
+const unsigned char Init_Register_Array[][2] = {
+  {0xEF,0x00},
+  {0x37,0x07},
+  {0x38,0x17},
+  {0x39,0x06},
+  {0x41,0x00},
+  {0x42,0x00},
+  {0x46,0x2D},
+  {0x47,0x0F},
+  {0x48,0x3C},
+  {0x49,0x00},
+  {0x4A,0x1E},
+  {0x4C,0x20},
+  {0x51,0x10},
+  {0x5E,0x10},
+  {0x60,0x27},
+  {0x80,0x42},
+  {0x81,0x44},
+  {0x82,0x04},
+  {0x8B,0x01},
+  {0x90,0x06},
+  {0x95,0x0A},
+  {0x96,0x0C},
+  {0x97,0x05},
+  {0x9A,0x14},
+  {0x9C,0x3F},
+  {0xA5,0x19},
+  {0xCC,0x19},
+  {0xCD,0x0B},
+  {0xCE,0x13},
+  {0xCF,0x64},
+  {0xD0,0x21},
+  {0xEF,0x01},
+  {0x02,0x0F},
+  {0x03,0x10},
+  {0x04,0x02},
+  {0x25,0x01},
+  {0x27,0x39},
+  {0x28,0x7F},
+  {0x29,0x08},
+  {0x3E,0xFF},
+  {0x5E,0x3D},
+  {0x65,0x96},
+  {0x67,0x97},
+  {0x69,0xCD},
+  {0x6A,0x01},
+  {0x6D,0x2C},
+  {0x6E,0x01},
+  {0x72,0x01},
+  {0x73,0x35},
+  {0x74,0x00},
+  {0x77,0x01},
+};
+//Approaches register initialization array
+const unsigned char Init_PS_Array[][2] = {
+  {0xEF,0x00},
+  {0x41,0x00},
+  {0x42,0x00},
+  {0x48,0x3C},
+  {0x49,0x00},
+  {0x51,0x13},
+  {0x83,0x20},
+  {0x84,0x20},
+  {0x85,0x00},
+  {0x86,0x10},
+  {0x87,0x00},
+  {0x88,0x05},
+  {0x89,0x18},
+  {0x8A,0x10},
+  {0x9f,0xf8},
+  {0x69,0x96},
+  {0x6A,0x02},
+  {0xEF,0x01},
+  {0x01,0x1E},
+  {0x02,0x0F},
+  {0x03,0x10},
+  {0x04,0x02},
+  {0x41,0x50},
+  {0x43,0x34},
+  {0x65,0xCE},
+  {0x66,0x0B},
+  {0x67,0xCE},
+  {0x68,0x0B},
+  {0x69,0xE9},
+  {0x6A,0x05},
+  {0x6B,0x50},
+  {0x6C,0xC3},
+  {0x6D,0x50},
+  {0x6E,0xC3},
+  {0x74,0x05},
+};
+
+//Gesture register initializes array
+const unsigned char Init_Gesture_Array[][2] = {
+  {0xEF,0x00},
+  {0x41,0x00},
+  {0x42,0x00},
+  {0xEF,0x00},
+  {0x48,0x3C},
+  {0x49,0x00},
+  {0x51,0x10},
+  {0x83,0x20},
+  {0x9F,0xF9},
+  {0xEF,0x01},
+  {0x01,0x1E},
+  {0x02,0x0F},
+  {0x03,0x10},
+  {0x04,0x02},
+  {0x41,0x40},
+  {0x43,0x30},
+  {0x65,0x96},
+  {0x66,0x00},
+  {0x67,0x97},
+  {0x68,0x01},
+  {0x69,0xCD},
+  {0x6A,0x01},
+  {0x6B,0xB0},
+  {0x6C,0x04},
+  {0x6D,0x2C},
+  {0x6E,0x01},
+  {0x74,0x00},
+  {0xEF,0x00},
+  {0x41,0xFF},
+  {0x42,0x01},
+};
+uint8_t I2C_readByte(uint8_t  addr);
+uint16_t I2C_readU16(uint8_t addr);
+void I2C_writeByte(uint8_t add, uint8_t data);
+uint8_t PAJ7620U2_init();
+#endif

Code/Arduino/PS/PS.ino

@@ -0,0 +1,36 @@
+#include <Wire.h>
+#include "PAJ7620U2.h"
+
+unsigned short  Gesture_Data;
+void setup() {
+    uint8_t i;
+    Serial.begin(115200);
+    Serial.print("\nGesture Sensor Test Program ...\n");
+    delayMicroseconds(800);
+    Wire.begin();
+    delayMicroseconds(10);
+    while(!PAJ7620U2_init())
+    { Serial.print("\nGesture Sensor Error\n");
+      delay(200);
+    }
+    Serial.print("\nGesture Sensor OK\n");
+    I2C_writeByte(PAJ_BANK_SELECT, 0);//Select Bank 0
+    for (i = 0; i < PS_Array_SIZE; i++)
+    {
+      I2C_writeByte(Init_PS_Array[i][0], Init_PS_Array[i][1]);//Gesture register initializes
+    }
+    I2C_writeByte(PAJ_BANK_SELECT, 0);  
+}
+void loop() {
+    uint8_t i, OBJ_BRIGHTNESS;
+    unsigned short  OBJ_SIZE;
+    OBJ_BRIGHTNESS  = I2C_readByte(PAJ_OBJ_BRIGHTNESS);
+    OBJ_SIZE    = I2C_readU16(PAJ_OBJ_SIZE_L);
+    Serial.print("Object brightness = ");
+    Serial.print(OBJ_BRIGHTNESS);
+    Serial.print(" ， ");
+    Serial.print("Object size = ");
+    Serial.print(OBJ_SIZE);
+    Serial.print("\r\n");
+    delay(300);
+}

Code/Raspberry Pi/bcm2835/Gesture/Makefile

@@ -0,0 +1,5 @@
+PAJ7620U2:PAJ7620U2.c PAJ7620U2.h
+	gcc -Wall PAJ7620U2.c -o PAJ7620U2 -lbcm2835 -lm
+clean:
+	rm PAJ7620U2
+

Code/Raspberry Pi/bcm2835/Gesture/PAJ7620U2.c

@@ -0,0 +1,81 @@
+#include <bcm2835.h>
+#include <stdio.h>
+#include <math.h>
+#include "PAJ7620U2.h"
+/******************* PAJ7620U2 Driver Interface *****************************/
+char I2C_readByte(char reg)
+{
+	char buf[] = { reg };
+	bcm2835_i2c_read_register_rs(buf, buf, 1);
+	return buf[0];
+}
+unsigned short I2C_readU16(char reg)
+{
+	char buf[] = { reg,0 };
+	bcm2835_i2c_read_register_rs(buf, buf, 2);
+	int value = buf[1] * 0x100 + buf[0];
+	return value;
+}
+void I2C_writeByte(char reg, char val)
+{
+	char buf[] = { reg,val };
+	bcm2835_i2c_write(buf, 2);
+}
+uint8_t PAJ7620U2_init()
+{
+	uint8_t i,State;
+	bcm2835_i2c_begin();
+	bcm2835_i2c_setSlaveAddress(PAJ7620U2_I2C_ADDRESS);
+	bcm2835_i2c_set_baudrate(10000);
+	bcm2835_delay(5);
+	State = I2C_readByte(0x00);												//Read State
+	if (State != 0x20) return 0;											//Wake up failed
+	I2C_writeByte(PAJ_BANK_SELECT, 0);										//Select Bank 0
+	for (i=0;i< Init_Array;i++)
+	{
+		I2C_writeByte(Init_Register_Array[i][0], Init_Register_Array[i][1]);//Power up initialize
+	}
+	return 1;
+}
+
+int main(int argc, char** argv)
+{
+	uint8_t i;
+	unsigned short  Gesture_Data;
+	printf("\nGesture Sensor Test Program ...\n");
+	if (!bcm2835_init()) return 1;
+	bcm2835_delay(5);
+	if(!PAJ7620U2_init())
+	{	printf("\nGesture Sensor Error\n");
+		return 0;
+	}
+	printf("\nGesture Sensor OK\n");
+	I2C_writeByte(PAJ_BANK_SELECT, 0);//Select Bank 0
+	for (i = 0; i < Gesture_Array_SIZE; i++)
+	{
+		I2C_writeByte(Init_Gesture_Array[i][0], Init_Gesture_Array[i][1]);//Gesture register initializes
+	}
+	while (1)
+	{
+		Gesture_Data = I2C_readU16(PAJ_INT_FLAG1);
+		if (Gesture_Data)
+		{
+			switch (Gesture_Data)
+			{
+				case PAJ_UP:			    printf("Up\r\n");				break;
+				case PAJ_DOWN:				printf("Down\r\n");				break;
+				case PAJ_LEFT:				printf("Left\r\n");				break;
+				case PAJ_RIGHT:				printf("Right\r\n"); 			break;
+				case PAJ_FORWARD:			printf("Forward\r\n");			break;
+				case PAJ_BACKWARD:			printf("Backward\r\n"); 		break;
+				case PAJ_CLOCKWISE:			printf("Clockwise\r\n"); 		break;
+				case PAJ_COUNT_CLOCKWISE:	printf("AntiClockwise\r\n"); 	break;
+				case PAJ_WAVE:				printf("Wave\r\n"); 			break;
+				default: break;
+			}
+			Gesture_Data=0;
+			bcm2835_delay(50);
+		}
+	}
+	return 0;
+}

Code/Raspberry Pi/bcm2835/Gesture/PAJ7620U2.h

@@ -0,0 +1,175 @@
+#ifndef _PAJ7620U2_
+#define _PAJ7620U2_
+
+//i2c address
+#define PAJ7620U2_I2C_ADDRESS		0x73
+//Register Bank select
+#define PAJ_BANK_SELECT			0xEF		/*Bank0=0x00,Bank1=0x01*/
+//Register Bank 0
+#define PAJ_SUSPEND			 	0x03		/*I2C suspend command (Write 0x01 to enter suspend state). I2C wake-up command is slave ID wake-up. Refer to topic ¡°I2C Bus Timing Characteristics and Protocol¡±*/
+#define PAJ_INT_FLAG1_MASK		0x41		/*Gesture detection interrupt flag mask*/
+#define PAJ_INT_FLAG2_MASK		0x42		/*Gesture/PS detection interrupt flag mask*/
+#define PAJ_INT_FLAG1		    0x43		/*Gesture detection interrupt flag*/
+#define PAJ_INT_FLAG2			0x44		/*Gesture/PS detection interrupt flag*/
+#define PAJ_STATE				0x45		/*State indicator for gesture detection (Only functional at gesture detection mode)*/
+#define PAJ_PS_HIGH_THRESHOLD	0x69		/*PS hysteresis high threshold (Only functional at proximity detection mode)*/		
+#define PAJ_PS_LOW_THRESHOLD	0x6A		/*PS hysteresis low threshold (Only functional at proximity detection mode)*/
+#define PAJ_PS_APPROACH_STATE	0x6B		/*PS approach state,  Approach = 1 , (8 bits PS data >= PS high threshold),  Not Approach = 0 , (8 bits PS data <= PS low threshold)(Only functional at proximity detection mode)*/
+#define PAJ_PS_DATA				0x6C		/*PS 8 bit data(Only functional at gesture detection mode)*/
+#define PAJ_OBJ_BRIGHTNESS		0xB0		/*Object Brightness (Max. 255)*/
+#define PAJ_OBJ_SIZE_L			0xB1		/*Object Size(Low 8 bit)*/		
+#define PAJ_OBJ_SIZE_H			0xB2		/*Object Size(High 8 bit)*/	
+
+//Register Bank 1
+#define PAJ_PS_GAIN				0x44		/*PS gain setting (Only functional at proximity detection mode)*/
+#define PAJ_IDLE_S1_STEP_L		0x67		/*IDLE S1 Step, for setting the S1, Response Factor(Low 8 bit)*/
+#define PAJ_IDLE_S1_STEP_H		0x68		/*IDLE S1 Step, for setting the S1, Response Factor(High 8 bit)*/	
+#define PAJ_IDLE_S2_STEP_L		0x69		/*IDLE S2 Step, for setting the S2, Response Factor(Low 8 bit)*/
+#define PAJ_IDLE_S2_STEP_H		0x6A		/*IDLE S2 Step, for setting the S2, Response Factor(High 8 bit)*/
+#define PAJ_OPTOS1_TIME_L		0x6B		/*OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 state(Low 8 bit)*/	
+#define PAJ_OPTOS2_TIME_H		0x6C		/*OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 stateHigh 8 bit)*/	
+#define PAJ_S1TOS2_TIME_L		0x6D		/*S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 state(Low 8 bit)*/	
+#define PAJ_S1TOS2_TIME_H		0x6E		/*S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 stateHigh 8 bit)*/	
+#define PAJ_EN					0x72		/*Enable/Disable PAJ7620U2*/
+//Gesture detection interrupt flag
+#define PAJ_UP				    0x01 
+#define PAJ_DOWN			    0x02
+#define PAJ_LEFT			    0x04 
+#define PAJ_RIGHT			    0x08
+#define PAJ_FORWARD			    0x10 
+#define PAJ_BACKWARD		    0x20
+#define PAJ_CLOCKWISE			0x40
+#define PAJ_COUNT_CLOCKWISE		0x80
+#define PAJ_WAVE				0x100
+//Initialize array size
+#define Init_Array sizeof(Init_Register_Array)/2
+#define PS_Array_SIZE sizeof(Init_PS_Array)/2
+#define Gesture_Array_SIZE sizeof(Init_Gesture_Array)/2
+//Power up initialize array
+unsigned char Init_Register_Array[][2] = {
+	{0xEF,0x00},
+	{0x37,0x07},
+	{0x38,0x17},
+	{0x39,0x06},
+	{0x41,0x00},
+	{0x42,0x00},
+	{0x46,0x2D},
+	{0x47,0x0F},
+	{0x48,0x3C},
+	{0x49,0x00},
+	{0x4A,0x1E},
+	{0x4C,0x20},
+	{0x51,0x10},
+	{0x5E,0x10},
+	{0x60,0x27},
+	{0x80,0x42},
+	{0x81,0x44},
+	{0x82,0x04},
+	{0x8B,0x01},
+	{0x90,0x06},
+	{0x95,0x0A},
+	{0x96,0x0C},
+	{0x97,0x05},
+	{0x9A,0x14},
+	{0x9C,0x3F},
+	{0xA5,0x19},
+	{0xCC,0x19},
+	{0xCD,0x0B},
+	{0xCE,0x13},
+	{0xCF,0x64},
+	{0xD0,0x21},
+	{0xEF,0x01},
+	{0x02,0x0F},
+	{0x03,0x10},
+	{0x04,0x02},
+	{0x25,0x01},
+	{0x27,0x39},
+	{0x28,0x7F},
+	{0x29,0x08},
+	{0x3E,0xFF},
+	{0x5E,0x3D},
+	{0x65,0x96},
+	{0x67,0x97},
+	{0x69,0xCD},
+	{0x6A,0x01},
+	{0x6D,0x2C},
+	{0x6E,0x01},
+	{0x72,0x01},
+	{0x73,0x35},
+	{0x74,0x00},
+	{0x77,0x01},
+};
+//Approaches register initialization array
+unsigned char Init_PS_Array[][2] = {
+	{0xEF,0x00},
+	{0x41,0x00},
+	{0x42,0x00},
+	{0x48,0x3C},
+	{0x49,0x00},
+	{0x51,0x13},
+	{0x83,0x20},
+	{0x84,0x20},
+	{0x85,0x00},
+	{0x86,0x10},
+	{0x87,0x00},
+	{0x88,0x05},
+	{0x89,0x18},
+	{0x8A,0x10},
+	{0x9f,0xf8},
+	{0x69,0x96},
+	{0x6A,0x02},
+	{0xEF,0x01},
+	{0x01,0x1E},
+	{0x02,0x0F},
+	{0x03,0x10},
+	{0x04,0x02},
+	{0x41,0x50},
+	{0x43,0x34},
+	{0x65,0xCE},
+	{0x66,0x0B},
+	{0x67,0xCE},
+	{0x68,0x0B},
+	{0x69,0xE9},
+	{0x6A,0x05},
+	{0x6B,0x50},
+	{0x6C,0xC3},
+	{0x6D,0x50},
+	{0x6E,0xC3},
+	{0x74,0x05},
+};
+
+//Gesture register initializes array
+const unsigned char Init_Gesture_Array[][2] = {
+	{0xEF,0x00},
+	{0x41,0x00},
+	{0x42,0x00},
+	{0xEF,0x00},
+	{0x48,0x3C},
+	{0x49,0x00},
+	{0x51,0x10},
+	{0x83,0x20},
+	{0x9F,0xF9},
+	{0xEF,0x01},
+	{0x01,0x1E},
+	{0x02,0x0F},
+	{0x03,0x10},
+	{0x04,0x02},
+	{0x41,0x40},
+	{0x43,0x30},
+	{0x65,0x96},
+	{0x66,0x00},
+	{0x67,0x97},
+	{0x68,0x01},
+	{0x69,0xCD},
+	{0x6A,0x01},
+	{0x6B,0xB0},
+	{0x6C,0x04},
+	{0x6D,0x2C},
+	{0x6E,0x01},
+	{0x74,0x00},
+	{0xEF,0x00},
+	{0x41,0xFF},
+	{0x42,0x01},
+};
+
+#endif

Code/Raspberry Pi/bcm2835/PS/Makefile

@@ -0,0 +1,5 @@
+PAJ7620U2:PAJ7620U2.c PAJ7620U2.h
+	gcc -Wall PAJ7620U2.c -o PAJ7620U2 -lbcm2835 -lm
+clean:
+	rm PAJ7620U2
+

Code/Raspberry Pi/bcm2835/PS/PAJ7620U2.c

@@ -0,0 +1,67 @@
+#include <bcm2835.h>
+#include <stdio.h>
+#include <math.h>
+#include "PAJ7620U2.h"
+/******************* PAJ7620U2 Driver Interface *****************************/
+char I2C_readByte(char reg)
+{
+	char buf[] = { reg };
+	bcm2835_i2c_read_register_rs(buf, buf, 1);
+	return buf[0];
+}
+unsigned short I2C_readU16(char reg)
+{
+	char buf[] = { reg,0 };
+	bcm2835_i2c_read_register_rs(buf, buf, 2);
+	int value = buf[1] * 0x100 + buf[0];
+	return value;
+}
+void I2C_writeByte(char reg, char val)
+{
+	char buf[] = { reg,val };
+	bcm2835_i2c_write(buf, 2);
+}
+uint8_t PAJ7620U2_init()
+{
+	uint8_t i,State;
+	bcm2835_i2c_begin();
+	bcm2835_i2c_setSlaveAddress(PAJ7620U2_I2C_ADDRESS);
+	bcm2835_i2c_set_baudrate(10000);
+	bcm2835_delay(5);
+	State = I2C_readByte(0x00);												//Read State
+	if (State != 0x20) return 0;											//Wake up failed
+	I2C_writeByte(PAJ_BANK_SELECT, 0);										//Select Bank 0
+	for (i=0;i< Init_Array;i++)
+	{
+		I2C_writeByte(Init_Register_Array[i][0], Init_Register_Array[i][1]);//Power up initialize
+	}
+	return 1;
+}
+
+int main(int argc, char** argv)
+{
+	uint8_t i, OBJ_BRIGHTNESS;
+	unsigned short  OBJ_SIZE;
+	printf("\nGesture Sensor Test Program ...\n");
+	if (!bcm2835_init()) return 1;
+	bcm2835_delay(5);
+	if(!PAJ7620U2_init())
+	{	printf("\nGesture Sensor Error\n");
+		return 0;
+	}
+	printf("\nGesture Sensor OK\n");
+	I2C_writeByte(PAJ_BANK_SELECT, 0);//Select Bank 0
+	for (i = 0; i < PS_Array_SIZE; i++)
+	{
+		I2C_writeByte(Init_PS_Array[i][0], Init_PS_Array[i][1]);//Gesture register initializes
+	}
+	I2C_writeByte(PAJ_BANK_SELECT, 0);	
+	while (1)
+	{
+		OBJ_BRIGHTNESS	=	I2C_readByte(PAJ_OBJ_BRIGHTNESS);
+		OBJ_SIZE		=	I2C_readU16(PAJ_OBJ_SIZE_L);
+		printf("Object brightness = %d ,Object size = %d\n", OBJ_BRIGHTNESS, OBJ_SIZE);//Object Brightness (Max. 255),Object Size (Max. 900)
+		delay(50);
+	}
+	return 0;
+}

Code/Raspberry Pi/bcm2835/PS/PAJ7620U2.h

@@ -0,0 +1,175 @@
+#ifndef _PAJ7620U2_
+#define _PAJ7620U2_
+
+//i2c address
+#define PAJ7620U2_I2C_ADDRESS		0x73
+//Register Bank select
+#define PAJ_BANK_SELECT			0xEF		/*Bank0=0x00,Bank1=0x01*/
+//Register Bank 0
+#define PAJ_SUSPEND			 	0x03		/*I2C suspend command (Write 0x01 to enter suspend state). I2C wake-up command is slave ID wake-up. Refer to topic ¡°I2C Bus Timing Characteristics and Protocol¡±*/
+#define PAJ_INT_FLAG1_MASK		0x41		/*Gesture detection interrupt flag mask*/
+#define PAJ_INT_FLAG2_MASK		0x42		/*Gesture/PS detection interrupt flag mask*/
+#define PAJ_INT_FLAG1		    0x43		/*Gesture detection interrupt flag*/
+#define PAJ_INT_FLAG2			0x44		/*Gesture/PS detection interrupt flag*/
+#define PAJ_STATE				0x45		/*State indicator for gesture detection (Only functional at gesture detection mode)*/
+#define PAJ_PS_HIGH_THRESHOLD	0x69		/*PS hysteresis high threshold (Only functional at proximity detection mode)*/		
+#define PAJ_PS_LOW_THRESHOLD	0x6A		/*PS hysteresis low threshold (Only functional at proximity detection mode)*/
+#define PAJ_PS_APPROACH_STATE	0x6B		/*PS approach state,  Approach = 1 , (8 bits PS data >= PS high threshold),  Not Approach = 0 , (8 bits PS data <= PS low threshold)(Only functional at proximity detection mode)*/
+#define PAJ_PS_DATA				0x6C		/*PS 8 bit data(Only functional at gesture detection mode)*/
+#define PAJ_OBJ_BRIGHTNESS		0xB0		/*Object Brightness (Max. 255)*/
+#define PAJ_OBJ_SIZE_L			0xB1		/*Object Size(Low 8 bit)*/		
+#define PAJ_OBJ_SIZE_H			0xB2		/*Object Size(High 8 bit)*/	
+
+//Register Bank 1
+#define PAJ_PS_GAIN				0x44		/*PS gain setting (Only functional at proximity detection mode)*/
+#define PAJ_IDLE_S1_STEP_L		0x67		/*IDLE S1 Step, for setting the S1, Response Factor(Low 8 bit)*/
+#define PAJ_IDLE_S1_STEP_H		0x68		/*IDLE S1 Step, for setting the S1, Response Factor(High 8 bit)*/	
+#define PAJ_IDLE_S2_STEP_L		0x69		/*IDLE S2 Step, for setting the S2, Response Factor(Low 8 bit)*/
+#define PAJ_IDLE_S2_STEP_H		0x6A		/*IDLE S2 Step, for setting the S2, Response Factor(High 8 bit)*/
+#define PAJ_OPTOS1_TIME_L		0x6B		/*OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 state(Low 8 bit)*/	
+#define PAJ_OPTOS2_TIME_H		0x6C		/*OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 stateHigh 8 bit)*/	
+#define PAJ_S1TOS2_TIME_L		0x6D		/*S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 state(Low 8 bit)*/	
+#define PAJ_S1TOS2_TIME_H		0x6E		/*S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 stateHigh 8 bit)*/	
+#define PAJ_EN					0x72		/*Enable/Disable PAJ7620U2*/
+//Gesture detection interrupt flag
+#define PAJ_UP				    0x01 
+#define PAJ_DOWN			    0x02
+#define PAJ_LEFT			    0x04 
+#define PAJ_RIGHT			    0x08
+#define PAJ_FORWARD			    0x10 
+#define PAJ_BACKWARD		    0x20
+#define PAJ_CLOCKWISE			0x40
+#define PAJ_COUNT_CLOCKWISE		0x80
+#define PAJ_WAVE				0x100
+//Initialize array size
+#define Init_Array sizeof(Init_Register_Array)/2
+#define PS_Array_SIZE sizeof(Init_PS_Array)/2
+#define Gesture_Array_SIZE sizeof(Init_Gesture_Array)/2
+//Power up initialize array
+unsigned char Init_Register_Array[][2] = {
+	{0xEF,0x00},
+	{0x37,0x07},
+	{0x38,0x17},
+	{0x39,0x06},
+	{0x41,0x00},
+	{0x42,0x00},
+	{0x46,0x2D},
+	{0x47,0x0F},
+	{0x48,0x3C},
+	{0x49,0x00},
+	{0x4A,0x1E},
+	{0x4C,0x20},
+	{0x51,0x10},
+	{0x5E,0x10},
+	{0x60,0x27},
+	{0x80,0x42},
+	{0x81,0x44},
+	{0x82,0x04},
+	{0x8B,0x01},
+	{0x90,0x06},
+	{0x95,0x0A},
+	{0x96,0x0C},
+	{0x97,0x05},
+	{0x9A,0x14},
+	{0x9C,0x3F},
+	{0xA5,0x19},
+	{0xCC,0x19},
+	{0xCD,0x0B},
+	{0xCE,0x13},
+	{0xCF,0x64},
+	{0xD0,0x21},
+	{0xEF,0x01},
+	{0x02,0x0F},
+	{0x03,0x10},
+	{0x04,0x02},
+	{0x25,0x01},
+	{0x27,0x39},
+	{0x28,0x7F},
+	{0x29,0x08},
+	{0x3E,0xFF},
+	{0x5E,0x3D},
+	{0x65,0x96},
+	{0x67,0x97},
+	{0x69,0xCD},
+	{0x6A,0x01},
+	{0x6D,0x2C},
+	{0x6E,0x01},
+	{0x72,0x01},
+	{0x73,0x35},
+	{0x74,0x00},
+	{0x77,0x01},
+};
+//Approaches register initialization array
+unsigned char Init_PS_Array[][2] = {
+	{0xEF,0x00},
+	{0x41,0x00},
+	{0x42,0x00},
+	{0x48,0x3C},
+	{0x49,0x00},
+	{0x51,0x13},
+	{0x83,0x20},
+	{0x84,0x20},
+	{0x85,0x00},
+	{0x86,0x10},
+	{0x87,0x00},
+	{0x88,0x05},
+	{0x89,0x18},
+	{0x8A,0x10},
+	{0x9f,0xf8},
+	{0x69,0x96},
+	{0x6A,0x02},
+	{0xEF,0x01},
+	{0x01,0x1E},
+	{0x02,0x0F},
+	{0x03,0x10},
+	{0x04,0x02},
+	{0x41,0x50},
+	{0x43,0x34},
+	{0x65,0xCE},
+	{0x66,0x0B},
+	{0x67,0xCE},
+	{0x68,0x0B},
+	{0x69,0xE9},
+	{0x6A,0x05},
+	{0x6B,0x50},
+	{0x6C,0xC3},
+	{0x6D,0x50},
+	{0x6E,0xC3},
+	{0x74,0x05},
+};
+
+//Gesture register initializes array
+const unsigned char Init_Gesture_Array[][2] = {
+	{0xEF,0x00},
+	{0x41,0x00},
+	{0x42,0x00},
+	{0xEF,0x00},
+	{0x48,0x3C},
+	{0x49,0x00},
+	{0x51,0x10},
+	{0x83,0x20},
+	{0x9F,0xF9},
+	{0xEF,0x01},
+	{0x01,0x1E},
+	{0x02,0x0F},
+	{0x03,0x10},
+	{0x04,0x02},
+	{0x41,0x40},
+	{0x43,0x30},
+	{0x65,0x96},
+	{0x66,0x00},
+	{0x67,0x97},
+	{0x68,0x01},
+	{0x69,0xCD},
+	{0x6A,0x01},
+	{0x6B,0xB0},
+	{0x6C,0x04},
+	{0x6D,0x2C},
+	{0x6E,0x01},
+	{0x74,0x00},
+	{0xEF,0x00},
+	{0x41,0xFF},
+	{0x42,0x01},
+};
+
+#endif

Code/Raspberry Pi/python/Gesture/PAJ7620U2.py

@@ -0,0 +1,231 @@
+#!/usr/bin/python
+# -*- coding:utf-8 -*-
+import time
+import smbus
+
+#i2c address
+PAJ7620U2_I2C_ADDRESS   = 0x73
+#Register Bank select
+PAJ_BANK_SELECT			= 0xEF			#Bank0== 0x00,Bank1== 0x01
+#Register Bank 0
+PAJ_SUSPEND				= 0x03		#I2C suspend command (Write = 0x01 to enter suspend state). I2C wake-up command is slave ID wake-up. Refer to topic “I2C Bus Timing Characteristics and Protocol”
+PAJ_INT_FLAG1_MASK		= 0x41		#Gesture detection interrupt flag mask
+PAJ_INT_FLAG2_MASK		= 0x42		#Gesture/PS detection interrupt flag mask
+PAJ_INT_FLAG1		    = 0x43		#Gesture detection interrupt flag
+PAJ_INT_FLAG2			= 0x44		#Gesture/PS detection interrupt flag
+PAJ_STATE				= 0x45		#State indicator for gesture detection (Only functional at gesture detection mode)
+PAJ_PS_HIGH_THRESHOLD	= 0x69		#PS hysteresis high threshold (Only functional at proximity detection mode)		
+PAJ_PS_LOW_THRESHOLD	= 0x6A		#PS hysteresis low threshold (Only functional at proximity detection mode)
+PAJ_PS_APPROACH_STATE	= 0x6B		#PS approach state,  Approach = 1 , (8 bits PS data >= PS high threshold),  Not Approach = 0 , (8 bits PS data <= PS low threshold)(Only functional at proximity detection mode)
+PAJ_PS_DATA				= 0x6C		#PS 8 bit data(Only functional at gesture detection mode)
+PAJ_OBJ_BRIGHTNESS		= 0xB0		#Object Brightness (Max. 255)
+PAJ_OBJ_SIZE_L			= 0xB1		#Object Size(Low 8 bit)		
+PAJ_OBJ_SIZE_H			= 0xB2		#Object Size(High 8 bit)	
+#Register Bank 1
+PAJ_PS_GAIN				= 0x44	    #PS gain setting (Only functional at proximity detection mode)
+PAJ_IDLE_S1_STEP_L		= 0x67		#IDLE S1 Step, for setting the S1, Response Factor(Low 8 bit)
+PAJ_IDLE_S1_STEP_H		= 0x68		#IDLE S1 Step, for setting the S1, Response Factor(High 8 bit)	
+PAJ_IDLE_S2_STEP_L		= 0x69		#IDLE S2 Step, for setting the S2, Response Factor(Low 8 bit)
+PAJ_IDLE_S2_STEP_H		= 0x6A		#IDLE S2 Step, for setting the S2, Response Factor(High 8 bit)
+PAJ_OPTOS1_TIME_L		= 0x6B		#OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 state(Low 8 bit)	
+PAJ_OPTOS2_TIME_H		= 0x6C		#OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 stateHigh 8 bit)	
+PAJ_S1TOS2_TIME_L		= 0x6D		#S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 state(Low 8 bit)	
+PAJ_S1TOS2_TIME_H		= 0x6E		#S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 stateHigh 8 bit)	
+PAJ_EN					= 0x72		#Enable/Disable PAJ7620U2
+#Gesture detection interrupt flag
+PAJ_UP				    = 0x01 
+PAJ_DOWN			    = 0x02
+PAJ_LEFT			    = 0x04 
+PAJ_RIGHT			    = 0x08
+PAJ_FORWARD		    	= 0x10 
+PAJ_BACKWARD		    = 0x20
+PAJ_CLOCKWISE			= 0x40
+PAJ_COUNT_CLOCKWISE		= 0x80
+PAJ_WAVE				= 0x100
+#Power up initialize array
+Init_Register_Array = (
+	(0xEF,0x00),
+	(0x37,0x07),
+	(0x38,0x17),
+	(0x39,0x06),
+	(0x41,0x00),
+	(0x42,0x00),
+	(0x46,0x2D),
+	(0x47,0x0F),
+	(0x48,0x3C),
+	(0x49,0x00),
+	(0x4A,0x1E),
+	(0x4C,0x20),
+	(0x51,0x10),
+	(0x5E,0x10),
+	(0x60,0x27),
+	(0x80,0x42),
+	(0x81,0x44),
+	(0x82,0x04),
+	(0x8B,0x01),
+	(0x90,0x06),
+	(0x95,0x0A),
+	(0x96,0x0C),
+	(0x97,0x05),
+	(0x9A,0x14),
+	(0x9C,0x3F),
+	(0xA5,0x19),
+	(0xCC,0x19),
+	(0xCD,0x0B),
+	(0xCE,0x13),
+	(0xCF,0x64),
+	(0xD0,0x21),
+	(0xEF,0x01),
+	(0x02,0x0F),
+	(0x03,0x10),
+	(0x04,0x02),
+	(0x25,0x01),
+	(0x27,0x39),
+	(0x28,0x7F),
+	(0x29,0x08),
+	(0x3E,0xFF),
+	(0x5E,0x3D),
+	(0x65,0x96),
+	(0x67,0x97),
+	(0x69,0xCD),
+	(0x6A,0x01),
+	(0x6D,0x2C),
+	(0x6E,0x01),
+	(0x72,0x01),
+	(0x73,0x35),
+	(0x74,0x00),
+	(0x77,0x01),
+)
+#Approaches register initialization array
+Init_PS_Array = (
+	(0xEF,0x00),
+	(0x41,0x00),
+	(0x42,0x00),
+	(0x48,0x3C),
+	(0x49,0x00),
+	(0x51,0x13),
+	(0x83,0x20),
+	(0x84,0x20),
+	(0x85,0x00),
+	(0x86,0x10),
+	(0x87,0x00),
+	(0x88,0x05),
+	(0x89,0x18),
+	(0x8A,0x10),
+	(0x9f,0xf8),
+	(0x69,0x96),
+	(0x6A,0x02),
+	(0xEF,0x01),
+	(0x01,0x1E),
+	(0x02,0x0F),
+	(0x03,0x10),
+	(0x04,0x02),
+	(0x41,0x50),
+	(0x43,0x34),
+	(0x65,0xCE),
+	(0x66,0x0B),
+	(0x67,0xCE),
+	(0x68,0x0B),
+	(0x69,0xE9),
+	(0x6A,0x05),
+	(0x6B,0x50),
+	(0x6C,0xC3),
+	(0x6D,0x50),
+	(0x6E,0xC3),
+	(0x74,0x05),
+)
+#Gesture register initializes array
+Init_Gesture_Array = (
+	(0xEF,0x00),
+	(0x41,0x00),
+	(0x42,0x00),
+	(0xEF,0x00),
+	(0x48,0x3C),
+	(0x49,0x00),
+	(0x51,0x10),
+	(0x83,0x20),
+	(0x9F,0xF9),
+	(0xEF,0x01),
+	(0x01,0x1E),
+	(0x02,0x0F),
+	(0x03,0x10),
+	(0x04,0x02),
+	(0x41,0x40),
+	(0x43,0x30),
+	(0x65,0x96),
+	(0x66,0x00),
+	(0x67,0x97),
+	(0x68,0x01),
+	(0x69,0xCD),
+	(0x6A,0x01),
+	(0x6B,0xB0),
+	(0x6C,0x04),
+	(0x6D,0x2C),
+	(0x6E,0x01),
+	(0x74,0x00),
+	(0xEF,0x00),
+	(0x41,0xFF),
+	(0x42,0x01),
+)
+class PAJ7620U2(object):
+	def __init__(self,address=PAJ7620U2_I2C_ADDRESS):
+		self._address = address
+		self._bus = smbus.SMBus(1)
+		time.sleep(0.5)
+		if self._read_byte(0x00) == 0x20:
+			print("\nGesture Sensor OK\n")
+			for num in range(len(Init_Register_Array)):
+				self._write_byte(Init_Register_Array[num][0],Init_Register_Array[num][1])
+		else:
+			print("\nGesture Sensor Error\n")
+		self._write_byte(PAJ_BANK_SELECT, 0)
+		for num in range(len(Init_Gesture_Array)):
+				self._write_byte(Init_Gesture_Array[num][0],Init_Gesture_Array[num][1])
+	def _read_byte(self,cmd):
+		return self._bus.read_byte_data(self._address,cmd)
+	
+	def _read_u16(self,cmd):
+		LSB = self._bus.read_byte_data(self._address,cmd)
+		MSB = self._bus.read_byte_data(self._address,cmd+1)
+		return (MSB	<< 8) + LSB
+	def _write_byte(self,cmd,val):
+		self._bus.write_byte_data(self._address,cmd,val)
+	def check_gesture(self):
+		Gesture_Data=self._read_u16(PAJ_INT_FLAG1)
+		if Gesture_Data == PAJ_UP:
+			print("Up\r\n")
+		elif Gesture_Data == PAJ_DOWN:
+			print("Down\r\n")
+		elif Gesture_Data == PAJ_LEFT:
+			print("Left\r\n")	
+		elif Gesture_Data == PAJ_RIGHT:
+			print("Right\r\n")	
+		elif Gesture_Data == PAJ_FORWARD:
+			print("Forward\r\n")	
+		elif Gesture_Data == PAJ_BACKWARD:
+			print("Backward\r\n")
+		elif Gesture_Data == PAJ_CLOCKWISE:
+			print("Clockwise\r\n")	
+		elif Gesture_Data == PAJ_COUNT_CLOCKWISE:
+			print("AntiClockwise\r\n")	
+		elif Gesture_Data == PAJ_WAVE:
+			print("Wave\r\n")	
+		return Gesture_Data
+
+if __name__ == '__main__':
+	
+	import time
+
+	print("\nGesture Sensor Test Program ...\n")
+
+	paj7620u2=PAJ7620U2()
+
+	while True:
+		time.sleep(0.05)
+		paj7620u2.check_gesture()
+		
+
+
+
+
+

Code/Raspberry Pi/python/PS/PAJ7620U2.py

@@ -0,0 +1,215 @@
+#!/usr/bin/python
+# -*- coding:utf-8 -*-
+import time
+import smbus
+
+#i2c address
+PAJ7620U2_I2C_ADDRESS   = 0x73
+#Register Bank select
+PAJ_BANK_SELECT			= 0xEF			#Bank0== 0x00,Bank1== 0x01
+#Register Bank 0
+PAJ_SUSPEND				= 0x03		#I2C suspend command (Write = 0x01 to enter suspend state). I2C wake-up command is slave ID wake-up. Refer to topic “I2C Bus Timing Characteristics and Protocol”
+PAJ_INT_FLAG1_MASK		= 0x41		#Gesture detection interrupt flag mask
+PAJ_INT_FLAG2_MASK		= 0x42		#Gesture/PS detection interrupt flag mask
+PAJ_INT_FLAG1		    = 0x43		#Gesture detection interrupt flag
+PAJ_INT_FLAG2			= 0x44		#Gesture/PS detection interrupt flag
+PAJ_STATE				= 0x45		#State indicator for gesture detection (Only functional at gesture detection mode)
+PAJ_PS_HIGH_THRESHOLD	= 0x69		#PS hysteresis high threshold (Only functional at proximity detection mode)		
+PAJ_PS_LOW_THRESHOLD	= 0x6A		#PS hysteresis low threshold (Only functional at proximity detection mode)
+PAJ_PS_APPROACH_STATE	= 0x6B		#PS approach state,  Approach = 1 , (8 bits PS data >= PS high threshold),  Not Approach = 0 , (8 bits PS data <= PS low threshold)(Only functional at proximity detection mode)
+PAJ_PS_DATA				= 0x6C		#PS 8 bit data(Only functional at gesture detection mode)
+PAJ_OBJ_BRIGHTNESS		= 0xB0		#Object Brightness (Max. 255)
+PAJ_OBJ_SIZE_L			= 0xB1		#Object Size(Low 8 bit)		
+PAJ_OBJ_SIZE_H			= 0xB2		#Object Size(High 8 bit)	
+#Register Bank 1
+PAJ_PS_GAIN				= 0x44	    #PS gain setting (Only functional at proximity detection mode)
+PAJ_IDLE_S1_STEP_L		= 0x67		#IDLE S1 Step, for setting the S1, Response Factor(Low 8 bit)
+PAJ_IDLE_S1_STEP_H		= 0x68		#IDLE S1 Step, for setting the S1, Response Factor(High 8 bit)	
+PAJ_IDLE_S2_STEP_L		= 0x69		#IDLE S2 Step, for setting the S2, Response Factor(Low 8 bit)
+PAJ_IDLE_S2_STEP_H		= 0x6A		#IDLE S2 Step, for setting the S2, Response Factor(High 8 bit)
+PAJ_OPTOS1_TIME_L		= 0x6B		#OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 state(Low 8 bit)	
+PAJ_OPTOS2_TIME_H		= 0x6C		#OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 stateHigh 8 bit)	
+PAJ_S1TOS2_TIME_L		= 0x6D		#S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 state(Low 8 bit)	
+PAJ_S1TOS2_TIME_H		= 0x6E		#S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 stateHigh 8 bit)	
+PAJ_EN					= 0x72		#Enable/Disable PAJ7620U2
+#Gesture detection interrupt flag
+PAJ_UP				    = 0x01 
+PAJ_DOWN			    = 0x02
+PAJ_LEFT			    = 0x04 
+PAJ_RIGHT			    = 0x08
+PAJ_FORWARD		    	= 0x10 
+PAJ_BACKWARD		    = 0x20
+PAJ_CLOCKWISE			= 0x40
+PAJ_COUNT_CLOCKWISE		= 0x80
+PAJ_WAVE				= 0x100
+#Power up initialize array
+Init_Register_Array = (
+	(0xEF,0x00),
+	(0x37,0x07),
+	(0x38,0x17),
+	(0x39,0x06),
+	(0x41,0x00),
+	(0x42,0x00),
+	(0x46,0x2D),
+	(0x47,0x0F),
+	(0x48,0x3C),
+	(0x49,0x00),
+	(0x4A,0x1E),
+	(0x4C,0x20),
+	(0x51,0x10),
+	(0x5E,0x10),
+	(0x60,0x27),
+	(0x80,0x42),
+	(0x81,0x44),
+	(0x82,0x04),
+	(0x8B,0x01),
+	(0x90,0x06),
+	(0x95,0x0A),
+	(0x96,0x0C),
+	(0x97,0x05),
+	(0x9A,0x14),
+	(0x9C,0x3F),
+	(0xA5,0x19),
+	(0xCC,0x19),
+	(0xCD,0x0B),
+	(0xCE,0x13),
+	(0xCF,0x64),
+	(0xD0,0x21),
+	(0xEF,0x01),
+	(0x02,0x0F),
+	(0x03,0x10),
+	(0x04,0x02),
+	(0x25,0x01),
+	(0x27,0x39),
+	(0x28,0x7F),
+	(0x29,0x08),
+	(0x3E,0xFF),
+	(0x5E,0x3D),
+	(0x65,0x96),
+	(0x67,0x97),
+	(0x69,0xCD),
+	(0x6A,0x01),
+	(0x6D,0x2C),
+	(0x6E,0x01),
+	(0x72,0x01),
+	(0x73,0x35),
+	(0x74,0x00),
+	(0x77,0x01),
+)
+#Approaches register initialization array
+Init_PS_Array = (
+	(0xEF,0x00),
+	(0x41,0x00),
+	(0x42,0x00),
+	(0x48,0x3C),
+	(0x49,0x00),
+	(0x51,0x13),
+	(0x83,0x20),
+	(0x84,0x20),
+	(0x85,0x00),
+	(0x86,0x10),
+	(0x87,0x00),
+	(0x88,0x05),
+	(0x89,0x18),
+	(0x8A,0x10),
+	(0x9f,0xf8),
+	(0x69,0x96),
+	(0x6A,0x02),
+	(0xEF,0x01),
+	(0x01,0x1E),
+	(0x02,0x0F),
+	(0x03,0x10),
+	(0x04,0x02),
+	(0x41,0x50),
+	(0x43,0x34),
+	(0x65,0xCE),
+	(0x66,0x0B),
+	(0x67,0xCE),
+	(0x68,0x0B),
+	(0x69,0xE9),
+	(0x6A,0x05),
+	(0x6B,0x50),
+	(0x6C,0xC3),
+	(0x6D,0x50),
+	(0x6E,0xC3),
+	(0x74,0x05),
+)
+#Gesture register initializes array
+Init_Gesture_Array = (
+	(0xEF,0x00),
+	(0x41,0x00),
+	(0x42,0x00),
+	(0xEF,0x00),
+	(0x48,0x3C),
+	(0x49,0x00),
+	(0x51,0x10),
+	(0x83,0x20),
+	(0x9F,0xF9),
+	(0xEF,0x01),
+	(0x01,0x1E),
+	(0x02,0x0F),
+	(0x03,0x10),
+	(0x04,0x02),
+	(0x41,0x40),
+	(0x43,0x30),
+	(0x65,0x96),
+	(0x66,0x00),
+	(0x67,0x97),
+	(0x68,0x01),
+	(0x69,0xCD),
+	(0x6A,0x01),
+	(0x6B,0xB0),
+	(0x6C,0x04),
+	(0x6D,0x2C),
+	(0x6E,0x01),
+	(0x74,0x00),
+	(0xEF,0x00),
+	(0x41,0xFF),
+	(0x42,0x01),
+)
+class PAJ7620U2(object):
+	def __init__(self,address=PAJ7620U2_I2C_ADDRESS):
+		self._address = address
+		self._bus = smbus.SMBus(1)
+		time.sleep(0.5)
+		if self._read_byte(0x00) == 0x20:
+			print("\nGesture Sensor OK\n")
+			for num in range(len(Init_Register_Array)):
+				self._write_byte(Init_Register_Array[num][0],Init_Register_Array[num][1])
+		else:
+			print("\nGesture Sensor Error\n")
+		self._write_byte(PAJ_BANK_SELECT, 0)
+		for num in range(len(Init_PS_Array)):
+				self._write_byte(Init_PS_Array[num][0],Init_PS_Array[num][1])
+		self._write_byte(PAJ_BANK_SELECT, 0)
+	def _read_byte(self,cmd):
+		return self._bus.read_byte_data(self._address,cmd)
+	
+	def _read_u16(self,cmd):
+		LSB = self._bus.read_byte_data(self._address,cmd)
+		MSB = self._bus.read_byte_data(self._address,cmd+1)
+		return (MSB	<< 8) + LSB
+	def _write_byte(self,cmd,val):
+		self._bus.write_byte_data(self._address,cmd,val)
+	def check_gesture(self):
+		OBJ_BRIGHTNESS	=	self._read_byte(PAJ_OBJ_BRIGHTNESS)
+		OBJ_SIZE		=	self._read_u16(PAJ_OBJ_SIZE_L)
+		print(' Object brightness = %.f , Object size = %.f'%(OBJ_BRIGHTNESS,OBJ_SIZE))
+
+if __name__ == '__main__':
+	
+	import time
+
+	print("\nGesture Sensor Test Program ...\n")
+
+	paj7620u2=PAJ7620U2()
+
+	while True:
+		time.sleep(0.1)
+		paj7620u2.check_gesture()
+		
+
+
+
+
+

Code/Raspberry Pi/wiringPi/Gesture/Makefile

@@ -0,0 +1,5 @@
+PAJ7620U2:PAJ7620U2.c PAJ7620U2.h
+	gcc -Wall PAJ7620U2.c -o PAJ7620U2 -lwiringPi -lm
+clean:
+	rm PAJ7620U2
+

Code/Raspberry Pi/wiringPi/Gesture/PAJ7620U2.c

@@ -0,0 +1,77 @@
+#include <wiringPi.h>
+#include <wiringPiI2C.h>
+#include <stdio.h>
+#include <math.h>
+#include "PAJ7620U2.h"
+int fd;
+/******************* PAJ7620U2 Driver Interface *****************************/
+char I2C_readByte(int reg)
+{
+	return wiringPiI2CReadReg8(fd, reg);
+}
+
+unsigned short I2C_readU16(int reg)
+{
+	return wiringPiI2CReadReg16(fd, reg);
+}
+void I2C_writeByte(int reg, int val)
+{
+	wiringPiI2CWriteReg8(fd, reg, val);
+}
+unsigned char PAJ7620U2_init()
+{
+	unsigned char i,State;
+	fd=wiringPiI2CSetup(PAJ7620U2_I2C_ADDRESS);
+	delay(5);
+	State = I2C_readByte(0x00);												//Read State
+	if (State != 0x20) return 0;											//Wake up failed
+	I2C_writeByte(PAJ_BANK_SELECT, 0);										//Select Bank 0
+	for (i=0;i< Init_Array;i++)
+	{
+		I2C_writeByte(Init_Register_Array[i][0], Init_Register_Array[i][1]);//Power up initialize
+	}
+	return 1;
+}
+
+int main(int argc, char** argv)
+{
+	unsigned char i;
+	unsigned short  Gesture_Data;
+	printf("\nGesture Sensor Test Program ...\n");
+	if (wiringPiSetup() < 0) return 1;
+	delay(5);
+	if(!PAJ7620U2_init())
+	{	printf("\nGesture Sensor Error\n");
+		return 0;
+	}
+	printf("\nGesture Sensor OK\n");
+	I2C_writeByte(PAJ_BANK_SELECT, 0);//Select Bank 0
+	for (i = 0; i < Gesture_Array_SIZE; i++)
+	{
+		I2C_writeByte(Init_Gesture_Array[i][0], Init_Gesture_Array[i][1]);//Gesture register initializes
+	}
+	while (1)
+	{
+		Gesture_Data = I2C_readU16(PAJ_INT_FLAG1);
+		
+		if (Gesture_Data)
+		{
+			switch (Gesture_Data)
+			{
+				case PAJ_UP:			    printf("Up\r\n");				break;
+				case PAJ_DOWN:				printf("Down\r\n");				break;
+				case PAJ_LEFT:				printf("Left\r\n");				break;
+				case PAJ_RIGHT:				printf("Right\r\n"); 			break;
+				case PAJ_FORWARD:			printf("Forward\r\n");			break;
+				case PAJ_BACKWARD:			printf("Backward\r\n"); 		break;
+				case PAJ_CLOCKWISE:			printf("Clockwise\r\n"); 		break;
+				case PAJ_COUNT_CLOCKWISE:	printf("AntiClockwise\r\n"); 	break;
+				case PAJ_WAVE:				printf("Wave\r\n"); 			break;
+				default: break;
+			}
+			Gesture_Data=0;
+			delay(50);
+		}
+	}
+	return 0;
+}

Code/Raspberry Pi/wiringPi/Gesture/PAJ7620U2.h

@@ -0,0 +1,175 @@
+#ifndef _PAJ7620U2_
+#define _PAJ7620U2_
+
+//i2c address
+#define PAJ7620U2_I2C_ADDRESS	0x73
+//Register Bank select
+#define PAJ_BANK_SELECT			0xEF		/*Bank0=0x00,Bank1=0x01*/
+//Register Bank 0
+#define PAJ_SUSPEND			 	0x03		/*I2C suspend command (Write 0x01 to enter suspend state). I2C wake-up command is slave ID wake-up. Refer to topic ¡°I2C Bus Timing Characteristics and Protocol¡±*/
+#define PAJ_INT_FLAG1_MASK		0x41		/*Gesture detection interrupt flag mask*/
+#define PAJ_INT_FLAG2_MASK		0x42		/*Gesture/PS detection interrupt flag mask*/
+#define PAJ_INT_FLAG1		    0x43		/*Gesture detection interrupt flag*/
+#define PAJ_INT_FLAG2			0x44		/*Gesture/PS detection interrupt flag*/
+#define PAJ_STATE				0x45		/*State indicator for gesture detection (Only functional at gesture detection mode)*/
+#define PAJ_PS_HIGH_THRESHOLD	0x69		/*PS hysteresis high threshold (Only functional at proximity detection mode)*/		
+#define PAJ_PS_LOW_THRESHOLD	0x6A		/*PS hysteresis low threshold (Only functional at proximity detection mode)*/
+#define PAJ_PS_APPROACH_STATE	0x6B		/*PS approach state,  Approach = 1 , (8 bits PS data >= PS high threshold),  Not Approach = 0 , (8 bits PS data <= PS low threshold)(Only functional at proximity detection mode)*/
+#define PAJ_PS_DATA				0x6C		/*PS 8 bit data(Only functional at gesture detection mode)*/
+#define PAJ_OBJ_BRIGHTNESS		0xB0		/*Object Brightness (Max. 255)*/
+#define PAJ_OBJ_SIZE_L			0xB1		/*Object Size(Low 8 bit)*/		
+#define PAJ_OBJ_SIZE_H			0xB2		/*Object Size(High 8 bit)*/	
+
+//Register Bank 1
+#define PAJ_PS_GAIN				0x44		/*PS gain setting (Only functional at proximity detection mode)*/
+#define PAJ_IDLE_S1_STEP_L		0x67		/*IDLE S1 Step, for setting the S1, Response Factor(Low 8 bit)*/
+#define PAJ_IDLE_S1_STEP_H		0x68		/*IDLE S1 Step, for setting the S1, Response Factor(High 8 bit)*/	
+#define PAJ_IDLE_S2_STEP_L		0x69		/*IDLE S2 Step, for setting the S2, Response Factor(Low 8 bit)*/
+#define PAJ_IDLE_S2_STEP_H		0x6A		/*IDLE S2 Step, for setting the S2, Response Factor(High 8 bit)*/
+#define PAJ_OPTOS1_TIME_L		0x6B		/*OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 state(Low 8 bit)*/	
+#define PAJ_OPTOS2_TIME_H		0x6C		/*OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 stateHigh 8 bit)*/	
+#define PAJ_S1TOS2_TIME_L		0x6D		/*S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 state(Low 8 bit)*/	
+#define PAJ_S1TOS2_TIME_H		0x6E		/*S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 stateHigh 8 bit)*/	
+#define PAJ_EN					0x72		/*Enable/Disable PAJ7620U2*/
+//Gesture detection interrupt flag
+#define PAJ_UP				    0x01 
+#define PAJ_DOWN			    0x02
+#define PAJ_LEFT			    0x04 
+#define PAJ_RIGHT			    0x08
+#define PAJ_FORWARD			    0x10 
+#define PAJ_BACKWARD		    0x20
+#define PAJ_CLOCKWISE			0x40
+#define PAJ_COUNT_CLOCKWISE		0x80
+#define PAJ_WAVE				0x100
+//Initialize array size
+#define Init_Array sizeof(Init_Register_Array)/2
+#define PS_Array_SIZE sizeof(Init_PS_Array)/2
+#define Gesture_Array_SIZE sizeof(Init_Gesture_Array)/2
+//Power up initialize array
+unsigned char Init_Register_Array[][2] = {
+	{0xEF,0x00},
+	{0x37,0x07},
+	{0x38,0x17},
+	{0x39,0x06},
+	{0x41,0x00},
+	{0x42,0x00},
+	{0x46,0x2D},
+	{0x47,0x0F},
+	{0x48,0x3C},
+	{0x49,0x00},
+	{0x4A,0x1E},
+	{0x4C,0x20},
+	{0x51,0x10},
+	{0x5E,0x10},
+	{0x60,0x27},
+	{0x80,0x42},
+	{0x81,0x44},
+	{0x82,0x04},
+	{0x8B,0x01},
+	{0x90,0x06},
+	{0x95,0x0A},
+	{0x96,0x0C},
+	{0x97,0x05},
+	{0x9A,0x14},
+	{0x9C,0x3F},
+	{0xA5,0x19},
+	{0xCC,0x19},
+	{0xCD,0x0B},
+	{0xCE,0x13},
+	{0xCF,0x64},
+	{0xD0,0x21},
+	{0xEF,0x01},
+	{0x02,0x0F},
+	{0x03,0x10},
+	{0x04,0x02},
+	{0x25,0x01},
+	{0x27,0x39},
+	{0x28,0x7F},
+	{0x29,0x08},
+	{0x3E,0xFF},
+	{0x5E,0x3D},
+	{0x65,0x96},
+	{0x67,0x97},
+	{0x69,0xCD},
+	{0x6A,0x01},
+	{0x6D,0x2C},
+	{0x6E,0x01},
+	{0x72,0x01},
+	{0x73,0x35},
+	{0x74,0x00},
+	{0x77,0x01},
+};
+//Approaches register initialization array
+unsigned char Init_PS_Array[][2] = {
+	{0xEF,0x00},
+	{0x41,0x00},
+	{0x42,0x00},
+	{0x48,0x3C},
+	{0x49,0x00},
+	{0x51,0x13},
+	{0x83,0x20},
+	{0x84,0x20},
+	{0x85,0x00},
+	{0x86,0x10},
+	{0x87,0x00},
+	{0x88,0x05},
+	{0x89,0x18},
+	{0x8A,0x10},
+	{0x9f,0xf8},
+	{0x69,0x96},
+	{0x6A,0x02},
+	{0xEF,0x01},
+	{0x01,0x1E},
+	{0x02,0x0F},
+	{0x03,0x10},
+	{0x04,0x02},
+	{0x41,0x50},
+	{0x43,0x34},
+	{0x65,0xCE},
+	{0x66,0x0B},
+	{0x67,0xCE},
+	{0x68,0x0B},
+	{0x69,0xE9},
+	{0x6A,0x05},
+	{0x6B,0x50},
+	{0x6C,0xC3},
+	{0x6D,0x50},
+	{0x6E,0xC3},
+	{0x74,0x05},
+};
+
+//Gesture register initializes array
+const unsigned char Init_Gesture_Array[][2] = {
+	{0xEF,0x00},
+	{0x41,0x00},
+	{0x42,0x00},
+	{0xEF,0x00},
+	{0x48,0x3C},
+	{0x49,0x00},
+	{0x51,0x10},
+	{0x83,0x20},
+	{0x9F,0xF9},
+	{0xEF,0x01},
+	{0x01,0x1E},
+	{0x02,0x0F},
+	{0x03,0x10},
+	{0x04,0x02},
+	{0x41,0x40},
+	{0x43,0x30},
+	{0x65,0x96},
+	{0x66,0x00},
+	{0x67,0x97},
+	{0x68,0x01},
+	{0x69,0xCD},
+	{0x6A,0x01},
+	{0x6B,0xB0},
+	{0x6C,0x04},
+	{0x6D,0x2C},
+	{0x6E,0x01},
+	{0x74,0x00},
+	{0xEF,0x00},
+	{0x41,0xFF},
+	{0x42,0x01},
+};
+
+#endif

Code/Raspberry Pi/wiringPi/PS/Makefile

@@ -0,0 +1,5 @@
+PAJ7620U2:PAJ7620U2.c PAJ7620U2.h
+	gcc -Wall PAJ7620U2.c -o PAJ7620U2 -lwiringPi -lm
+clean:
+	rm PAJ7620U2
+

Code/Raspberry Pi/wiringPi/PS/PAJ7620U2.c

@@ -0,0 +1,62 @@
+#include <wiringPi.h>
+#include <wiringPiI2C.h>
+#include <stdio.h>
+#include <math.h>
+#include "PAJ7620U2.h"
+int fd;
+/******************* PAJ7620U2 Driver Interface *****************************/
+char I2C_readByte(int reg)
+{
+	return wiringPiI2CReadReg8(fd, reg);
+}
+
+unsigned short I2C_readU16(int reg)
+{
+	return wiringPiI2CReadReg16(fd, reg);
+}
+void I2C_writeByte(int reg, int val)
+{
+	wiringPiI2CWriteReg8(fd, reg, val);
+}
+unsigned char PAJ7620U2_init()
+{
+	unsigned char i,State;
+	fd=wiringPiI2CSetup(PAJ7620U2_I2C_ADDRESS);
+	delay(5);
+	State = I2C_readByte(0x00);												//Read State
+	if (State != 0x20) return 0;											//Wake up failed
+	I2C_writeByte(PAJ_BANK_SELECT, 0);										//Select Bank 0
+	for (i=0;i< Init_Array;i++)
+	{
+		I2C_writeByte(Init_Register_Array[i][0], Init_Register_Array[i][1]);//Power up initialize
+	}
+	return 1;
+}
+
+int main(int argc, char** argv)
+{
+	unsigned char i, OBJ_BRIGHTNESS;
+	unsigned short  OBJ_SIZE;
+	printf("\nGesture Sensor Test Program ...\n");
+	if (wiringPiSetup() < 0) return 1;
+	delay(5);
+	if(!PAJ7620U2_init())
+	{	printf("\nGesture Sensor Error\n");
+		return 0;
+	}
+	printf("\nGesture Sensor OK\n");
+	I2C_writeByte(PAJ_BANK_SELECT, 0);//Select Bank 0
+	for (i = 0; i < PS_Array_SIZE; i++)
+	{
+		I2C_writeByte(Init_PS_Array[i][0], Init_PS_Array[i][1]);//Gesture register initializes
+	}
+	I2C_writeByte(PAJ_BANK_SELECT, 0);//Select Bank 0
+	while (1)
+	{
+		OBJ_BRIGHTNESS = I2C_readByte(PAJ_OBJ_BRIGHTNESS);
+		OBJ_SIZE = I2C_readU16(PAJ_OBJ_SIZE_L);
+		printf("Object brightness = %d ,Object size = %d\n", OBJ_BRIGHTNESS, OBJ_SIZE);//Object Brightness (Max. 255),Object Size (Max. 900)
+		delay(50);
+	}
+	return 0;
+}

Code/Raspberry Pi/wiringPi/PS/PAJ7620U2.h

@@ -0,0 +1,175 @@
+#ifndef _PAJ7620U2_
+#define _PAJ7620U2_
+
+//i2c address
+#define PAJ7620U2_I2C_ADDRESS	0x73
+//Register Bank select
+#define PAJ_BANK_SELECT			0xEF		/*Bank0=0x00,Bank1=0x01*/
+//Register Bank 0
+#define PAJ_SUSPEND			 	0x03		/*I2C suspend command (Write 0x01 to enter suspend state). I2C wake-up command is slave ID wake-up. Refer to topic ¡°I2C Bus Timing Characteristics and Protocol¡±*/
+#define PAJ_INT_FLAG1_MASK		0x41		/*Gesture detection interrupt flag mask*/
+#define PAJ_INT_FLAG2_MASK		0x42		/*Gesture/PS detection interrupt flag mask*/
+#define PAJ_INT_FLAG1		    0x43		/*Gesture detection interrupt flag*/
+#define PAJ_INT_FLAG2			0x44		/*Gesture/PS detection interrupt flag*/
+#define PAJ_STATE				0x45		/*State indicator for gesture detection (Only functional at gesture detection mode)*/
+#define PAJ_PS_HIGH_THRESHOLD	0x69		/*PS hysteresis high threshold (Only functional at proximity detection mode)*/		
+#define PAJ_PS_LOW_THRESHOLD	0x6A		/*PS hysteresis low threshold (Only functional at proximity detection mode)*/
+#define PAJ_PS_APPROACH_STATE	0x6B		/*PS approach state,  Approach = 1 , (8 bits PS data >= PS high threshold),  Not Approach = 0 , (8 bits PS data <= PS low threshold)(Only functional at proximity detection mode)*/
+#define PAJ_PS_DATA				0x6C		/*PS 8 bit data(Only functional at gesture detection mode)*/
+#define PAJ_OBJ_BRIGHTNESS		0xB0		/*Object Brightness (Max. 255)*/
+#define PAJ_OBJ_SIZE_L			0xB1		/*Object Size(Low 8 bit)*/		
+#define PAJ_OBJ_SIZE_H			0xB2		/*Object Size(High 8 bit)*/	
+
+//Register Bank 1
+#define PAJ_PS_GAIN				0x44		/*PS gain setting (Only functional at proximity detection mode)*/
+#define PAJ_IDLE_S1_STEP_L		0x67		/*IDLE S1 Step, for setting the S1, Response Factor(Low 8 bit)*/
+#define PAJ_IDLE_S1_STEP_H		0x68		/*IDLE S1 Step, for setting the S1, Response Factor(High 8 bit)*/	
+#define PAJ_IDLE_S2_STEP_L		0x69		/*IDLE S2 Step, for setting the S2, Response Factor(Low 8 bit)*/
+#define PAJ_IDLE_S2_STEP_H		0x6A		/*IDLE S2 Step, for setting the S2, Response Factor(High 8 bit)*/
+#define PAJ_OPTOS1_TIME_L		0x6B		/*OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 state(Low 8 bit)*/	
+#define PAJ_OPTOS2_TIME_H		0x6C		/*OPtoS1 Step, for setting the OPtoS1 time of operation state to standby 1 stateHigh 8 bit)*/	
+#define PAJ_S1TOS2_TIME_L		0x6D		/*S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 state(Low 8 bit)*/	
+#define PAJ_S1TOS2_TIME_H		0x6E		/*S1toS2 Step, for setting the S1toS2 time of standby 1 state to standby 2 stateHigh 8 bit)*/	
+#define PAJ_EN					0x72		/*Enable/Disable PAJ7620U2*/
+//Gesture detection interrupt flag
+#define PAJ_UP				    0x01 
+#define PAJ_DOWN			    0x02
+#define PAJ_LEFT			    0x04 
+#define PAJ_RIGHT			    0x08
+#define PAJ_FORWARD			    0x10 
+#define PAJ_BACKWARD		    0x20
+#define PAJ_CLOCKWISE			0x40
+#define PAJ_COUNT_CLOCKWISE		0x80
+#define PAJ_WAVE				0x100
+//Initialize array size
+#define Init_Array sizeof(Init_Register_Array)/2
+#define PS_Array_SIZE sizeof(Init_PS_Array)/2
+#define Gesture_Array_SIZE sizeof(Init_Gesture_Array)/2
+//Power up initialize array
+unsigned char Init_Register_Array[][2] = {
+	{0xEF,0x00},
+	{0x37,0x07},
+	{0x38,0x17},
+	{0x39,0x06},
+	{0x41,0x00},
+	{0x42,0x00},
+	{0x46,0x2D},
+	{0x47,0x0F},
+	{0x48,0x3C},
+	{0x49,0x00},
+	{0x4A,0x1E},
+	{0x4C,0x20},
+	{0x51,0x10},
+	{0x5E,0x10},
+	{0x60,0x27},
+	{0x80,0x42},
+	{0x81,0x44},
+	{0x82,0x04},
+	{0x8B,0x01},
+	{0x90,0x06},
+	{0x95,0x0A},
+	{0x96,0x0C},
+	{0x97,0x05},
+	{0x9A,0x14},
+	{0x9C,0x3F},
+	{0xA5,0x19},
+	{0xCC,0x19},
+	{0xCD,0x0B},
+	{0xCE,0x13},
+	{0xCF,0x64},
+	{0xD0,0x21},
+	{0xEF,0x01},
+	{0x02,0x0F},
+	{0x03,0x10},
+	{0x04,0x02},
+	{0x25,0x01},
+	{0x27,0x39},
+	{0x28,0x7F},
+	{0x29,0x08},
+	{0x3E,0xFF},
+	{0x5E,0x3D},
+	{0x65,0x96},
+	{0x67,0x97},
+	{0x69,0xCD},
+	{0x6A,0x01},
+	{0x6D,0x2C},
+	{0x6E,0x01},
+	{0x72,0x01},
+	{0x73,0x35},
+	{0x74,0x00},
+	{0x77,0x01},
+};
+//Approaches register initialization array
+unsigned char Init_PS_Array[][2] = {
+	{0xEF,0x00},
+	{0x41,0x00},
+	{0x42,0x00},
+	{0x48,0x3C},
+	{0x49,0x00},
+	{0x51,0x13},
+	{0x83,0x20},
+	{0x84,0x20},
+	{0x85,0x00},
+	{0x86,0x10},
+	{0x87,0x00},
+	{0x88,0x05},
+	{0x89,0x18},
+	{0x8A,0x10},
+	{0x9f,0xf8},
+	{0x69,0x96},
+	{0x6A,0x02},
+	{0xEF,0x01},
+	{0x01,0x1E},
+	{0x02,0x0F},
+	{0x03,0x10},
+	{0x04,0x02},
+	{0x41,0x50},
+	{0x43,0x34},
+	{0x65,0xCE},
+	{0x66,0x0B},
+	{0x67,0xCE},
+	{0x68,0x0B},
+	{0x69,0xE9},
+	{0x6A,0x05},
+	{0x6B,0x50},
+	{0x6C,0xC3},
+	{0x6D,0x50},
+	{0x6E,0xC3},
+	{0x74,0x05},
+};
+
+//Gesture register initializes array
+const unsigned char Init_Gesture_Array[][2] = {
+	{0xEF,0x00},
+	{0x41,0x00},
+	{0x42,0x00},
+	{0xEF,0x00},
+	{0x48,0x3C},
+	{0x49,0x00},
+	{0x51,0x10},
+	{0x83,0x20},
+	{0x9F,0xF9},
+	{0xEF,0x01},
+	{0x01,0x1E},
+	{0x02,0x0F},
+	{0x03,0x10},
+	{0x04,0x02},
+	{0x41,0x40},
+	{0x43,0x30},
+	{0x65,0x96},
+	{0x66,0x00},
+	{0x67,0x97},
+	{0x68,0x01},
+	{0x69,0xCD},
+	{0x6A,0x01},
+	{0x6B,0xB0},
+	{0x6C,0x04},
+	{0x6D,0x2C},
+	{0x6E,0x01},
+	{0x74,0x00},
+	{0xEF,0x00},
+	{0x41,0xFF},
+	{0x42,0x01},
+};
+
+#endif

Code/STM32/Gesture/.mxproject

@@ -0,0 +1,14 @@
+[PreviousGenFiles]
+HeaderPath=F:/stm322/Gesture/Inc
+HeaderFiles=gpio.h;usart.h;stm32f1xx_it.h;stm32f1xx_hal_conf.h;main.h;i2c.h;
+SourcePath=F:/stm322/Gesture/Src
+SourceFiles=gpio.c;usart.c;stm32f1xx_it.c;stm32f1xx_hal_msp.c;main.c;i2c.c;
+
+[PreviousLibFiles]
+LibFiles=Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_i2c.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_tim.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_tim_ex.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_uart.h;Drivers/STM32F1xx_HAL_Driver/Inc/Legacy/stm32_hal_legacy.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_def.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_rcc.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_rcc_ex.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_gpio.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_gpio_ex.h;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_gpio_ex.c;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_dma_ex.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_dma.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_cortex.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_pwr.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_flash.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_flash_ex.h;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_i2c.c;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_tim.c;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_tim_ex.c;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_uart.c;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal.c;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_rcc.c;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_rcc_ex.c;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_gpio.c;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_dma.c;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_cortex.c;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_pwr.c;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_flash.c;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_flash_ex.c;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_i2c.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_tim.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_tim_ex.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_uart.h;Drivers/STM32F1xx_HAL_Driver/Inc/Legacy/stm32_hal_legacy.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_def.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_rcc.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_rcc_ex.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_gpio.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_gpio_ex.h;Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_gpio_ex.c;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_dma_ex.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_dma.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_cortex.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_pwr.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_flash.h;Drivers/STM32F1xx_HAL_Driver/Inc/stm32f1xx_hal_flash_ex.h;Drivers/CMSIS/Device/ST/STM32F1xx/Include/stm32f103xb.h;Drivers/CMSIS/Device/ST/STM32F1xx/Include/stm32f1xx.h;Drivers/CMSIS/Device/ST/STM32F1xx/Include/system_stm32f1xx.h;Drivers/CMSIS/Device/ST/STM32F1xx/Source/Templates/system_stm32f1xx.c;Drivers/CMSIS/Include/arm_common_tables.h;Drivers/CMSIS/Include/arm_const_structs.h;Drivers/CMSIS/Include/arm_math.h;Drivers/CMSIS/Include/cmsis_armcc.h;Drivers/CMSIS/Include/cmsis_armcc_V6.h;Drivers/CMSIS/Include/cmsis_gcc.h;Drivers/CMSIS/Include/core_cm0.h;Drivers/CMSIS/Include/core_cm0plus.h;Drivers/CMSIS/Include/core_cm3.h;Drivers/CMSIS/Include/core_cm4.h;Drivers/CMSIS/Include/core_cm7.h;Drivers/CMSIS/Include/core_cmFunc.h;Drivers/CMSIS/Include/core_cmInstr.h;Drivers/CMSIS/Include/core_cmSimd.h;Drivers/CMSIS/Include/core_sc000.h;Drivers/CMSIS/Include/core_sc300.h;
+
+[PreviousUsedKeilFiles]
+SourceFiles=..\Src\main.c;..\Src\gpio.c;..\Src\i2c.c;..\Src\usart.c;..\Src\stm32f1xx_it.c;..\Src\stm32f1xx_hal_msp.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_gpio_ex.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_i2c.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_tim.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_tim_ex.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_uart.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_rcc.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_rcc_ex.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_gpio.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_dma.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_cortex.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_pwr.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_flash.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_flash_ex.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_gpio_ex.c;../\Src/system_stm32f1xx.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_gpio_ex.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_i2c.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_tim.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_tim_ex.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_uart.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_rcc.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_rcc_ex.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_gpio.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_dma.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_cortex.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_pwr.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_flash.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_flash_ex.c;../Drivers/STM32F1xx_HAL_Driver/Src/stm32f1xx_hal_gpio_ex.c;../\Src/system_stm32f1xx.c;../Drivers/CMSIS/Device/ST/STM32F1xx/Source/Templates/system_stm32f1xx.c;null;
+HeaderPath=..\Drivers\STM32F1xx_HAL_Driver\Inc;..\Drivers\STM32F1xx_HAL_Driver\Inc\Legacy;..\Drivers\CMSIS\Device\ST\STM32F1xx\Include;..\Drivers\CMSIS\Include;..\Inc;
+CDefines=USE_HAL_DRIVER;STM32F103xB;
+

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_abs_f32.c

@@ -0,0 +1,165 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_abs_f32.c    
+*    
+* Description:	Vector absolute value.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+#include <math.h>
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup BasicAbs Vector Absolute Value        
+ *        
+ * Computes the absolute value of a vector on an element-by-element basis.        
+ *        
+ * <pre>        
+ *     pDst[n] = abs(pSrc[n]),   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * The functions support in-place computation allowing the source and
+ * destination pointers to reference the same memory buffer.
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
+ */
+
+/**        
+ * @addtogroup BasicAbs        
+ * @{        
+ */
+
+/**        
+ * @brief Floating-point vector absolute value.        
+ * @param[in]       *pSrc points to the input buffer        
+ * @param[out]      *pDst points to the output buffer        
+ * @param[in]       blockSize number of samples in each vector        
+ * @return none.        
+ */
+
+void arm_abs_f32(
+  float32_t * pSrc,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t in1, in2, in3, in4;                  /* temporary variables */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Calculate absolute and then store the results in the destination buffer. */
+    /* read sample from source */
+    in1 = *pSrc;
+    in2 = *(pSrc + 1);
+    in3 = *(pSrc + 2);
+
+    /* find absolute value */
+    in1 = fabsf(in1);
+
+    /* read sample from source */
+    in4 = *(pSrc + 3);
+
+    /* find absolute value */
+    in2 = fabsf(in2);
+
+    /* read sample from source */
+    *pDst = in1;
+
+    /* find absolute value */
+    in3 = fabsf(in3);
+
+    /* find absolute value */
+    in4 = fabsf(in4);
+
+    /* store result to destination */
+    *(pDst + 1) = in2;
+
+    /* store result to destination */
+    *(pDst + 2) = in3;
+
+    /* store result to destination */
+    *(pDst + 3) = in4;
+
+
+    /* Update source pointer to process next sampels */
+    pSrc += 4u;
+
+    /* Update destination pointer to process next sampels */
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /*   #ifndef ARM_MATH_CM0_FAMILY   */
+
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Calculate absolute and then store the results in the destination buffer. */
+    *pDst++ = fabsf(*pSrc++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of BasicAbs group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_abs_q15.c

@@ -0,0 +1,179 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_abs_q15.c    
+*    
+* Description:	Q15 vector absolute value.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicAbs    
+ * @{    
+ */
+
+/**    
+ * @brief Q15 vector absolute value.    
+ * @param[in]       *pSrc points to the input buffer    
+ * @param[out]      *pDst points to the output buffer    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * The Q15 value -1 (0x8000) will be saturated to the maximum allowable positive value 0x7FFF.    
+ */
+
+void arm_abs_q15(
+  q15_t * pSrc,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+  __SIMD32_TYPE *simd;
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  q15_t in1;                                     /* Input value1 */
+  q15_t in2;                                     /* Input value2 */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  simd = __SIMD32_CONST(pDst);
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Read two inputs */
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+
+
+    /* Store the Absolute result in the destination buffer by packing the two values, in a single cycle */
+#ifndef  ARM_MATH_BIG_ENDIAN
+    *simd++ =
+      __PKHBT(((in1 > 0) ? in1 : (q15_t)__QSUB16(0, in1)),
+              ((in2 > 0) ? in2 : (q15_t)__QSUB16(0, in2)), 16);
+
+#else
+
+
+    *simd++ =
+      __PKHBT(((in2 > 0) ? in2 : (q15_t)__QSUB16(0, in2)),
+              ((in1 > 0) ? in1 : (q15_t)__QSUB16(0, in1)), 16);
+
+#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+    *simd++ =
+      __PKHBT(((in1 > 0) ? in1 : (q15_t)__QSUB16(0, in1)),
+              ((in2 > 0) ? in2 : (q15_t)__QSUB16(0, in2)), 16);
+
+#else
+
+
+    *simd++ =
+      __PKHBT(((in2 > 0) ? in2 : (q15_t)__QSUB16(0, in2)),
+              ((in1 > 0) ? in1 : (q15_t)__QSUB16(0, in1)), 16);
+
+#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+  pDst = (q15_t *)simd;
+	
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Read the input */
+    in1 = *pSrc++;
+
+    /* Calculate absolute value of input and then store the result in the destination buffer. */
+    *pDst++ = (in1 > 0) ? in1 : (q15_t)__QSUB16(0, in1);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  q15_t in;                                      /* Temporary input variable */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Read the input */
+    in = *pSrc++;
+
+    /* Calculate absolute value of input and then store the result in the destination buffer. */
+    *pDst++ = (in > 0) ? in : ((in == (q15_t) 0x8000) ? 0x7fff : -in);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of BasicAbs group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_abs_q31.c

@@ -0,0 +1,130 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_abs_q31.c    
+*    
+* Description:	Q31 vector absolute value.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicAbs    
+ * @{    
+ */
+
+
+/**    
+ * @brief Q31 vector absolute value.    
+ * @param[in]       *pSrc points to the input buffer    
+ * @param[out]      *pDst points to the output buffer    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * The Q31 value -1 (0x80000000) will be saturated to the maximum allowable positive value 0x7FFFFFFF.    
+ */
+
+void arm_abs_q31(
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  q31_t in;                                      /* Input value */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t in1, in2, in3, in4;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Calculate absolute of input (if -1 then saturated to 0x7fffffff) and then store the results in the destination buffer. */
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+    in3 = *pSrc++;
+    in4 = *pSrc++;
+
+    *pDst++ = (in1 > 0) ? in1 : (q31_t)__QSUB(0, in1);
+    *pDst++ = (in2 > 0) ? in2 : (q31_t)__QSUB(0, in2);
+    *pDst++ = (in3 > 0) ? in3 : (q31_t)__QSUB(0, in3);
+    *pDst++ = (in4 > 0) ? in4 : (q31_t)__QSUB(0, in4);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /*   #ifndef ARM_MATH_CM0_FAMILY   */
+
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Calculate absolute value of the input (if -1 then saturated to 0x7fffffff) and then store the results in the destination buffer. */
+    in = *pSrc++;
+    *pDst++ = (in > 0) ? in : ((in == INT32_MIN) ? INT32_MAX : -in);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+}
+
+/**    
+ * @} end of BasicAbs group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_abs_q7.c

@@ -0,0 +1,157 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_abs_q7.c    
+*    
+* Description:	Q7 vector absolute value.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @addtogroup BasicAbs        
+ * @{        
+ */
+
+/**        
+ * @brief Q7 vector absolute value.        
+ * @param[in]       *pSrc points to the input buffer        
+ * @param[out]      *pDst points to the output buffer        
+ * @param[in]       blockSize number of samples in each vector        
+ * @return none.        
+ *    
+ * \par Conditions for optimum performance    
+ *  Input and output buffers should be aligned by 32-bit    
+ *    
+ *        
+ * <b>Scaling and Overflow Behavior:</b>        
+ * \par        
+ * The function uses saturating arithmetic.        
+ * The Q7 value -1 (0x80) will be saturated to the maximum allowable positive value 0x7F.        
+ */
+
+void arm_abs_q7(
+  q7_t * pSrc,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  q7_t in;                                       /* Input value1 */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t in1, in2, in3, in4;                      /* temporary input variables */
+  q31_t out1, out2, out3, out4;                  /* temporary output variables */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Read inputs */
+    in1 = (q31_t) * pSrc;
+    in2 = (q31_t) * (pSrc + 1);
+    in3 = (q31_t) * (pSrc + 2);
+
+    /* find absolute value */
+    out1 = (in1 > 0) ? in1 : (q31_t)__QSUB8(0, in1);
+
+    /* read input */
+    in4 = (q31_t) * (pSrc + 3);
+
+    /* find absolute value */
+    out2 = (in2 > 0) ? in2 : (q31_t)__QSUB8(0, in2);
+
+    /* store result to destination */
+    *pDst = (q7_t) out1;
+
+    /* find absolute value */
+    out3 = (in3 > 0) ? in3 : (q31_t)__QSUB8(0, in3);
+
+    /* find absolute value */
+    out4 = (in4 > 0) ? in4 : (q31_t)__QSUB8(0, in4);
+
+    /* store result to destination */
+    *(pDst + 1) = (q7_t) out2;
+
+    /* store result to destination */
+    *(pDst + 2) = (q7_t) out3;
+
+    /* store result to destination */
+    *(pDst + 3) = (q7_t) out4;
+
+    /* update pointers to process next samples */
+    pSrc += 4u;
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+#else
+
+  /* Run the below code for Cortex-M0 */
+  blkCnt = blockSize;
+
+#endif /* #define ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C = |A| */
+    /* Read the input */
+    in = *pSrc++;
+
+    /* Store the Absolute result in the destination buffer */
+    *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? 0x7f : -in);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of BasicAbs group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_f32.c

@@ -0,0 +1,150 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_add_f32.c    
+*    
+* Description:	Floating-point vector addition.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup BasicAdd Vector Addition        
+ *        
+ * Element-by-element addition of two vectors.        
+ *        
+ * <pre>        
+ *     pDst[n] = pSrcA[n] + pSrcB[n],   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup BasicAdd        
+ * @{        
+ */
+
+/**        
+ * @brief Floating-point vector addition.        
+ * @param[in]       *pSrcA points to the first input vector        
+ * @param[in]       *pSrcB points to the second input vector        
+ * @param[out]      *pDst points to the output vector        
+ * @param[in]       blockSize number of samples in each vector        
+ * @return none.        
+ */
+
+void arm_add_f32(
+  float32_t * pSrcA,
+  float32_t * pSrcB,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t inA1, inA2, inA3, inA4;              /* temporary input variabels */
+  float32_t inB1, inB2, inB3, inB4;              /* temporary input variables */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+
+    /* read four inputs from sourceA and four inputs from sourceB */
+    inA1 = *pSrcA;
+    inB1 = *pSrcB;
+    inA2 = *(pSrcA + 1);
+    inB2 = *(pSrcB + 1);
+    inA3 = *(pSrcA + 2);
+    inB3 = *(pSrcB + 2);
+    inA4 = *(pSrcA + 3);
+    inB4 = *(pSrcB + 3);
+
+    /* C = A + B */
+    /* add and store result to destination */
+    *pDst = inA1 + inB1;
+    *(pDst + 1) = inA2 + inB2;
+    *(pDst + 2) = inA3 + inB3;
+    *(pDst + 3) = inA4 + inB4;
+
+    /* update pointers to process next samples */
+    pSrcA += 4u;
+    pSrcB += 4u;
+    pDst += 4u;
+
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = (*pSrcA++) + (*pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of BasicAdd group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q15.c

@@ -0,0 +1,140 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_add_q15.c    
+*    
+* Description:	Q15 vector addition    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicAdd    
+ * @{    
+ */
+
+/**    
+ * @brief Q15 vector addition.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.    
+ */
+
+void arm_add_q15(
+  q15_t * pSrcA,
+  q15_t * pSrcB,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2, inB1, inB2;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    inA1 = *__SIMD32(pSrcA)++;
+    inA2 = *__SIMD32(pSrcA)++;
+    inB1 = *__SIMD32(pSrcB)++;
+    inB2 = *__SIMD32(pSrcB)++;
+
+    *__SIMD32(pDst)++ = __QADD16(inA1, inB1);
+    *__SIMD32(pDst)++ = __QADD16(inA2, inB2);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = (q15_t) __QADD16(*pSrcA++, *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = (q15_t) __SSAT(((q31_t) * pSrcA++ + *pSrcB++), 16);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+
+}
+
+/**    
+ * @} end of BasicAdd group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q31.c

@@ -0,0 +1,148 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_add_q31.c    
+*    
+* Description:	Q31 vector addition.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicAdd    
+ * @{    
+ */
+
+
+/**    
+ * @brief Q31 vector addition.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q31 range[0x80000000 0x7FFFFFFF] will be saturated.    
+ */
+
+void arm_add_q31(
+  q31_t * pSrcA,
+  q31_t * pSrcB,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2, inA3, inA4;
+  q31_t inB1, inB2, inB3, inB4;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    inA1 = *pSrcA++;
+    inA2 = *pSrcA++;
+    inB1 = *pSrcB++;
+    inB2 = *pSrcB++;
+
+    inA3 = *pSrcA++;
+    inA4 = *pSrcA++;
+    inB3 = *pSrcB++;
+    inB4 = *pSrcB++;
+
+    *pDst++ = __QADD(inA1, inB1);
+    *pDst++ = __QADD(inA2, inB2);
+    *pDst++ = __QADD(inA3, inB3);
+    *pDst++ = __QADD(inA4, inB4);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = __QADD(*pSrcA++, *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrcA++ + *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of BasicAdd group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q7.c

@@ -0,0 +1,134 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_add_q7.c    
+*    
+* Description:	Q7 vector addition.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicAdd    
+ * @{    
+ */
+
+/**    
+ * @brief Q7 vector addition.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.    
+ */
+
+void arm_add_q7(
+  q7_t * pSrcA,
+  q7_t * pSrcB,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *__SIMD32(pDst)++ = __QADD8(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = (q7_t) __SSAT(*pSrcA++ + *pSrcB++, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + B */
+    /* Add and then store the results in the destination buffer. */
+    *pDst++ = (q7_t) __SSAT((q15_t) * pSrcA++ + *pSrcB++, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+
+}
+
+/**    
+ * @} end of BasicAdd group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_dot_prod_f32.c

@@ -0,0 +1,135 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_dot_prod_f32.c    
+*    
+* Description:	Floating-point dot product.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath
+ */
+
+/**
+ * @defgroup dot_prod Vector Dot Product
+ *
+ * Computes the dot product of two vectors.
+ * The vectors are multiplied element-by-element and then summed.
+ *
+ * <pre>
+ *     sum = pSrcA[0]*pSrcB[0] + pSrcA[1]*pSrcB[1] + ... + pSrcA[blockSize-1]*pSrcB[blockSize-1]
+ * </pre>     
+ *
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.    
+ */
+
+/**    
+ * @addtogroup dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief Dot product of floating-point vectors.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @param[out]      *result output result returned here    
+ * @return none.    
+ */
+
+
+void arm_dot_prod_f32(
+  float32_t * pSrcA,
+  float32_t * pSrcB,
+  uint32_t blockSize,
+  float32_t * result)
+{
+  float32_t sum = 0.0f;                          /* Temporary result storage */
+  uint32_t blkCnt;                               /* loop counter */
+
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the result in a temporary buffer */
+    sum += (*pSrcA++) * (*pSrcB++);
+    sum += (*pSrcA++) * (*pSrcB++);
+    sum += (*pSrcA++) * (*pSrcB++);
+    sum += (*pSrcA++) * (*pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the result in a temporary buffer. */
+    sum += (*pSrcA++) * (*pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+  /* Store the result back in the destination buffer */
+  *result = sum;
+}
+
+/**    
+ * @} end of dot_prod group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_dot_prod_q15.c

@@ -0,0 +1,140 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_dot_prod_q15.c    
+*    
+* Description:	Q15 dot product.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief Dot product of Q15 vectors.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @param[out]      *result output result returned here    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The intermediate multiplications are in 1.15 x 1.15 = 2.30 format and these    
+ * results are added to a 64-bit accumulator in 34.30 format.    
+ * Nonsaturating additions are used and given that there are 33 guard bits in the accumulator    
+ * there is no risk of overflow.    
+ * The return result is in 34.30 format.    
+ */
+
+void arm_dot_prod_q15(
+  q15_t * pSrcA,
+  q15_t * pSrcB,
+  uint32_t blockSize,
+  q63_t * result)
+{
+  q63_t sum = 0;                                 /* Temporary result storage */
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the result in a temporary buffer. */
+    sum = __SMLALD(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++, sum);
+    sum = __SMLALD(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++, sum);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the results in a temporary buffer. */
+    sum = __SMLALD(*pSrcA++, *pSrcB++, sum);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the results in a temporary buffer. */
+    sum += (q63_t) ((q31_t) * pSrcA++ * *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  /* Store the result in the destination buffer in 34.30 format */
+  *result = sum;
+
+}
+
+/**    
+ * @} end of dot_prod group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_dot_prod_q31.c

@@ -0,0 +1,143 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_dot_prod_q31.c    
+*    
+* Description:	Q31 dot product.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief Dot product of Q31 vectors.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @param[out]      *result output result returned here    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The intermediate multiplications are in 1.31 x 1.31 = 2.62 format and these    
+ * are truncated to 2.48 format by discarding the lower 14 bits.    
+ * The 2.48 result is then added without saturation to a 64-bit accumulator in 16.48 format.    
+ * There are 15 guard bits in the accumulator and there is no risk of overflow as long as    
+ * the length of the vectors is less than 2^16 elements.    
+ * The return result is in 16.48 format.    
+ */
+
+void arm_dot_prod_q31(
+  q31_t * pSrcA,
+  q31_t * pSrcB,
+  uint32_t blockSize,
+  q63_t * result)
+{
+  q63_t sum = 0;                                 /* Temporary result storage */
+  uint32_t blkCnt;                               /* loop counter */
+
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2, inA3, inA4;
+  q31_t inB1, inB2, inB3, inB4;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the result in a temporary buffer. */
+    inA1 = *pSrcA++;
+    inA2 = *pSrcA++;
+    inA3 = *pSrcA++;
+    inA4 = *pSrcA++;
+    inB1 = *pSrcB++;
+    inB2 = *pSrcB++;
+    inB3 = *pSrcB++;
+    inB4 = *pSrcB++;
+
+    sum += ((q63_t) inA1 * inB1) >> 14u;
+    sum += ((q63_t) inA2 * inB2) >> 14u;
+    sum += ((q63_t) inA3 * inB3) >> 14u;
+    sum += ((q63_t) inA4 * inB4) >> 14u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Calculate dot product and then store the result in a temporary buffer. */
+    sum += ((q63_t) * pSrcA++ * *pSrcB++) >> 14u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* Store the result in the destination buffer in 16.48 format */
+  *result = sum;
+}
+
+/**    
+ * @} end of dot_prod group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_dot_prod_q7.c

@@ -0,0 +1,159 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_dot_prod_q7.c    
+*    
+* Description:	Q7 dot product.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief Dot product of Q7 vectors.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @param[out]      *result output result returned here    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The intermediate multiplications are in 1.7 x 1.7 = 2.14 format and these    
+ * results are added to an accumulator in 18.14 format.    
+ * Nonsaturating additions are used and there is no danger of wrap around as long as    
+ * the vectors are less than 2^18 elements long.    
+ * The return result is in 18.14 format.    
+ */
+
+void arm_dot_prod_q7(
+  q7_t * pSrcA,
+  q7_t * pSrcB,
+  uint32_t blockSize,
+  q31_t * result)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+  q31_t sum = 0;                                 /* Temporary variables to store output */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  q31_t input1, input2;                          /* Temporary variables to store input */
+  q31_t inA1, inA2, inB1, inB2;                  /* Temporary variables to store input */
+
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* read 4 samples at a time from sourceA */
+    input1 = *__SIMD32(pSrcA)++;
+    /* read 4 samples at a time from sourceB */
+    input2 = *__SIMD32(pSrcB)++;
+
+    /* extract two q7_t samples to q15_t samples */
+    inA1 = __SXTB16(__ROR(input1, 8));
+    /* extract reminaing two samples */
+    inA2 = __SXTB16(input1);
+    /* extract two q7_t samples to q15_t samples */
+    inB1 = __SXTB16(__ROR(input2, 8));
+    /* extract reminaing two samples */
+    inB2 = __SXTB16(input2);
+
+    /* multiply and accumulate two samples at a time */
+    sum = __SMLAD(inA1, inB1, sum);
+    sum = __SMLAD(inA2, inB2, sum);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Dot product and then store the results in a temporary buffer. */
+    sum = __SMLAD(*pSrcA++, *pSrcB++, sum);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+    /* Dot product and then store the results in a temporary buffer. */
+    sum += (q31_t) ((q15_t) * pSrcA++ * *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+
+  /* Store the result in the destination buffer in 18.14 format */
+  *result = sum;
+}
+
+/**    
+ * @} end of dot_prod group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_mult_f32.c

@@ -0,0 +1,174 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_mult_f32.c    
+*    
+* Description:	Floating-point vector multiplication.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup BasicMult Vector Multiplication        
+ *        
+ * Element-by-element multiplication of two vectors.        
+ *        
+ * <pre>        
+ *     pDst[n] = pSrcA[n] * pSrcB[n],   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup BasicMult        
+ * @{        
+ */
+
+/**        
+ * @brief Floating-point vector multiplication.        
+ * @param[in]       *pSrcA points to the first input vector        
+ * @param[in]       *pSrcB points to the second input vector        
+ * @param[out]      *pDst points to the output vector        
+ * @param[in]       blockSize number of samples in each vector        
+ * @return none.        
+ */
+
+void arm_mult_f32(
+  float32_t * pSrcA,
+  float32_t * pSrcB,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counters */
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t inA1, inA2, inA3, inA4;              /* temporary input variables */
+  float32_t inB1, inB2, inB3, inB4;              /* temporary input variables */
+  float32_t out1, out2, out3, out4;              /* temporary output variables */
+
+  /* loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and store the results in output buffer */
+    /* read sample from sourceA */
+    inA1 = *pSrcA;
+    /* read sample from sourceB */
+    inB1 = *pSrcB;
+    /* read sample from sourceA */
+    inA2 = *(pSrcA + 1);
+    /* read sample from sourceB */
+    inB2 = *(pSrcB + 1);
+
+    /* out = sourceA * sourceB */
+    out1 = inA1 * inB1;
+
+    /* read sample from sourceA */
+    inA3 = *(pSrcA + 2);
+    /* read sample from sourceB */
+    inB3 = *(pSrcB + 2);
+
+    /* out = sourceA * sourceB */
+    out2 = inA2 * inB2;
+
+    /* read sample from sourceA */
+    inA4 = *(pSrcA + 3);
+
+    /* store result to destination buffer */
+    *pDst = out1;
+
+    /* read sample from sourceB */
+    inB4 = *(pSrcB + 3);
+
+    /* out = sourceA * sourceB */
+    out3 = inA3 * inB3;
+
+    /* store result to destination buffer */
+    *(pDst + 1) = out2;
+
+    /* out = sourceA * sourceB */
+    out4 = inA4 * inB4;
+    /* store result to destination buffer */
+    *(pDst + 2) = out3;
+    /* store result to destination buffer */
+    *(pDst + 3) = out4;
+
+
+    /* update pointers to process next samples */
+    pSrcA += 4u;
+    pSrcB += 4u;
+    pDst += 4u;
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and store the results in output buffer */
+    *pDst++ = (*pSrcA++) * (*pSrcB++);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of BasicMult group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_mult_q15.c

@@ -0,0 +1,154 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. October 2015
+* $Revision: 	V.1.4.5 a
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_mult_q15.c    
+*    
+* Description:	Q15 vector multiplication.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicMult    
+ * @{    
+ */
+
+
+/**    
+ * @brief           Q15 vector multiplication    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.    
+ */
+
+void arm_mult_q15(
+  q15_t * pSrcA,
+  q15_t * pSrcB,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counters */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2, inB1, inB2;                  /* temporary input variables */
+  q15_t out1, out2, out3, out4;                  /* temporary output variables */
+  q31_t mul1, mul2, mul3, mul4;                  /* temporary variables */
+
+  /* loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* read two samples at a time from sourceA */
+    inA1 = *__SIMD32(pSrcA)++;
+    /* read two samples at a time from sourceB */
+    inB1 = *__SIMD32(pSrcB)++;
+    /* read two samples at a time from sourceA */
+    inA2 = *__SIMD32(pSrcA)++;
+    /* read two samples at a time from sourceB */
+    inB2 = *__SIMD32(pSrcB)++;
+
+    /* multiply mul = sourceA * sourceB */
+    mul1 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1 >> 16));
+    mul2 = (q31_t) ((q15_t) inA1 * (q15_t) inB1);
+    mul3 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) (inB2 >> 16));
+    mul4 = (q31_t) ((q15_t) inA2 * (q15_t) inB2);
+
+    /* saturate result to 16 bit */
+    out1 = (q15_t) __SSAT(mul1 >> 15, 16);
+    out2 = (q15_t) __SSAT(mul2 >> 15, 16);
+    out3 = (q15_t) __SSAT(mul3 >> 15, 16);
+    out4 = (q15_t) __SSAT(mul4 >> 15, 16);
+
+    /* store the result */
+#ifndef ARM_MATH_BIG_ENDIAN
+
+    *__SIMD32(pDst)++ = __PKHBT(out2, out1, 16);
+    *__SIMD32(pDst)++ = __PKHBT(out4, out3, 16);
+
+#else
+
+    *__SIMD32(pDst)++ = __PKHBT(out2, out1, 16);
+    *__SIMD32(pDst)++ = __PKHBT(out4, out3, 16);
+
+#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and store the result in the destination buffer */
+    *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+}
+
+/**    
+ * @} end of BasicMult group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_mult_q31.c

@@ -0,0 +1,160 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_mult_q31.c    
+*    
+* Description:	Q31 vector multiplication.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicMult    
+ * @{    
+ */
+
+/**    
+ * @brief Q31 vector multiplication.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q31 range[0x80000000 0x7FFFFFFF] will be saturated.    
+ */
+
+void arm_mult_q31(
+  q31_t * pSrcA,
+  q31_t * pSrcB,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counters */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2, inA3, inA4;                  /* temporary input variables */
+  q31_t inB1, inB2, inB3, inB4;                  /* temporary input variables */
+  q31_t out1, out2, out3, out4;                  /* temporary output variables */
+
+  /* loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and then store the results in the destination buffer. */
+    inA1 = *pSrcA++;
+    inA2 = *pSrcA++;
+    inA3 = *pSrcA++;
+    inA4 = *pSrcA++;
+    inB1 = *pSrcB++;
+    inB2 = *pSrcB++;
+    inB3 = *pSrcB++;
+    inB4 = *pSrcB++;
+
+    out1 = ((q63_t) inA1 * inB1) >> 32;
+    out2 = ((q63_t) inA2 * inB2) >> 32;
+    out3 = ((q63_t) inA3 * inB3) >> 32;
+    out4 = ((q63_t) inA4 * inB4) >> 32;
+
+    out1 = __SSAT(out1, 31);
+    out2 = __SSAT(out2, 31);
+    out3 = __SSAT(out3, 31);
+    out4 = __SSAT(out4, 31);
+
+    *pDst++ = out1 << 1u;
+    *pDst++ = out2 << 1u;
+    *pDst++ = out3 << 1u;
+    *pDst++ = out4 << 1u;
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+  
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and then store the results in the destination buffer. */
+    inA1 = *pSrcA++;
+    inB1 = *pSrcB++;
+    out1 = ((q63_t) inA1 * inB1) >> 32;
+    out1 = __SSAT(out1, 31);
+    *pDst++ = out1 << 1u;
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and then store the results in the destination buffer. */
+    *pDst++ =
+      (q31_t) clip_q63_to_q31(((q63_t) (*pSrcA++) * (*pSrcB++)) >> 31);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+  
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+}
+
+/**    
+ * @} end of BasicMult group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_mult_q7.c

@@ -0,0 +1,127 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_mult_q7.c    
+*    
+* Description:	Q7 vector multiplication.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicMult    
+ * @{    
+ */
+
+/**    
+ * @brief           Q7 vector multiplication    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.    
+ */
+
+void arm_mult_q7(
+  q7_t * pSrcA,
+  q7_t * pSrcB,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counters */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q7_t out1, out2, out3, out4;                   /* Temporary variables to store the product */
+
+  /* loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and store the results in temporary variables */
+    out1 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+    out2 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+    out3 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+    out4 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+
+    /* Store the results of 4 inputs in the destination buffer in single cycle by packing */
+    *__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * B */
+    /* Multiply the inputs and store the result in the destination buffer */
+    *pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+}
+
+/**    
+ * @} end of BasicMult group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_negate_f32.c

@@ -0,0 +1,146 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_negate_f32.c    
+*    
+* Description:	Negates floating-point vectors.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup negate Vector Negate        
+ *        
+ * Negates the elements of a vector.        
+ *        
+ * <pre>        
+ *     pDst[n] = -pSrc[n],   0 <= n < blockSize.        
+ * </pre>        
+ *
+ * The functions support in-place computation allowing the source and
+ * destination pointers to reference the same memory buffer.
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
+ */
+
+/**        
+ * @addtogroup negate        
+ * @{        
+ */
+
+/**        
+ * @brief  Negates the elements of a floating-point vector.        
+ * @param[in]  *pSrc points to the input vector        
+ * @param[out]  *pDst points to the output vector        
+ * @param[in]  blockSize number of samples in the vector        
+ * @return none.        
+ */
+
+void arm_negate_f32(
+  float32_t * pSrc,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t in1, in2, in3, in4;                  /* temporary variables */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* read inputs from source */
+    in1 = *pSrc;
+    in2 = *(pSrc + 1);
+    in3 = *(pSrc + 2);
+    in4 = *(pSrc + 3);
+
+    /* negate the input */
+    in1 = -in1;
+    in2 = -in2;
+    in3 = -in3;
+    in4 = -in4;
+
+    /* store the result to destination */
+    *pDst = in1;
+    *(pDst + 1) = in2;
+    *(pDst + 2) = in3;
+    *(pDst + 3) = in4;
+
+    /* update pointers to process next samples */
+    pSrc += 4u;
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Negate and then store the results in the destination buffer. */
+    *pDst++ = -*pSrc++;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of negate group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_negate_q15.c

@@ -0,0 +1,142 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_negate_q15.c    
+*    
+* Description:	Negates Q15 vectors.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @addtogroup negate        
+ * @{        
+ */
+
+/**        
+ * @brief  Negates the elements of a Q15 vector.        
+ * @param[in]  *pSrc points to the input vector        
+ * @param[out]  *pDst points to the output vector        
+ * @param[in]  blockSize number of samples in the vector        
+ * @return none.        
+ *    
+ * \par Conditions for optimum performance    
+ *  Input and output buffers should be aligned by 32-bit    
+ *    
+ *        
+ * <b>Scaling and Overflow Behavior:</b>        
+ * \par        
+ * The function uses saturating arithmetic.        
+ * The Q15 value -1 (0x8000) will be saturated to the maximum allowable positive value 0x7FFF.        
+ */
+
+void arm_negate_q15(
+  q15_t * pSrc,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  q15_t in;
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  q31_t in1, in2;                                /* Temporary variables */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Read two inputs at a time */
+    in1 = _SIMD32_OFFSET(pSrc);
+    in2 = _SIMD32_OFFSET(pSrc + 2);
+
+    /* negate two samples at a time */
+    in1 = __QSUB16(0, in1);
+
+    /* negate two samples at a time */
+    in2 = __QSUB16(0, in2);
+
+    /* store the result to destination 2 samples at a time */
+    _SIMD32_OFFSET(pDst) = in1;
+    /* store the result to destination 2 samples at a time */
+    _SIMD32_OFFSET(pDst + 2) = in2;
+
+
+    /* update pointers to process next samples */
+    pSrc += 4u;
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Negate and then store the result in the destination buffer. */
+    in = *pSrc++;
+    *pDst++ = (in == (q15_t) 0x8000) ? 0x7fff : -in;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of negate group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_negate_q31.c

@@ -0,0 +1,129 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_negate_q31.c    
+*    
+* Description:	Negates Q31 vectors.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup negate    
+ * @{    
+ */
+
+/**    
+ * @brief  Negates the elements of a Q31 vector.    
+ * @param[in]  *pSrc points to the input vector    
+ * @param[out]  *pDst points to the output vector    
+ * @param[in]  blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * The Q31 value -1 (0x80000000) will be saturated to the maximum allowable positive value 0x7FFFFFFF.    
+ */
+
+void arm_negate_q31(
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  q31_t in;                                      /* Temporary variable */
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t in1, in2, in3, in4;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Negate and then store the results in the destination buffer. */
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+    in3 = *pSrc++;
+    in4 = *pSrc++;
+
+    *pDst++ = __QSUB(0, in1);
+    *pDst++ = __QSUB(0, in2);
+    *pDst++ = __QSUB(0, in3);
+    *pDst++ = __QSUB(0, in4);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Negate and then store the result in the destination buffer. */
+    in = *pSrc++;
+    *pDst++ = (in == INT32_MIN) ? INT32_MAX : -in;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**    
+ * @} end of negate group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_negate_q7.c

@@ -0,0 +1,125 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_negate_q7.c    
+*    
+* Description:	Negates Q7 vectors.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup negate    
+ * @{    
+ */
+
+/**    
+ * @brief  Negates the elements of a Q7 vector.    
+ * @param[in]  *pSrc points to the input vector    
+ * @param[out]  *pDst points to the output vector    
+ * @param[in]  blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * The Q7 value -1 (0x80) will be saturated to the maximum allowable positive value 0x7F.    
+ */
+
+void arm_negate_q7(
+  q7_t * pSrc,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  q7_t in;
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t input;                                   /* Input values1-4 */
+  q31_t zero = 0x00000000;
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Read four inputs */
+    input = *__SIMD32(pSrc)++;
+
+    /* Store the Negated results in the destination buffer in a single cycle by packing the results */
+    *__SIMD32(pDst)++ = __QSUB8(zero, input);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C = -A */
+    /* Negate and then store the results in the destination buffer. */ \
+      in = *pSrc++;
+    *pDst++ = (in == (q7_t) 0x80) ? 0x7f : -in;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**    
+ * @} end of negate group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_offset_f32.c

@@ -0,0 +1,165 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_offset_f32.c    
+*    
+* Description:	Floating-point vector offset.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* ---------------------------------------------------------------------------- */
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup offset Vector Offset        
+ *        
+ * Adds a constant offset to each element of a vector.        
+ *        
+ * <pre>        
+ *     pDst[n] = pSrc[n] + offset,   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * The functions support in-place computation allowing the source and
+ * destination pointers to reference the same memory buffer.
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
+ */
+
+/**        
+ * @addtogroup offset        
+ * @{        
+ */
+
+/**        
+ * @brief  Adds a constant offset to a floating-point vector.        
+ * @param[in]  *pSrc points to the input vector        
+ * @param[in]  offset is the offset to be added        
+ * @param[out]  *pDst points to the output vector        
+ * @param[in]  blockSize number of samples in the vector        
+ * @return none.        
+ */
+
+
+void arm_offset_f32(
+  float32_t * pSrc,
+  float32_t offset,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t in1, in2, in3, in4;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the results in the destination buffer. */
+    /* read samples from source */
+    in1 = *pSrc;
+    in2 = *(pSrc + 1);
+
+    /* add offset to input */
+    in1 = in1 + offset;
+
+    /* read samples from source */
+    in3 = *(pSrc + 2);
+
+    /* add offset to input */
+    in2 = in2 + offset;
+
+    /* read samples from source */
+    in4 = *(pSrc + 3);
+
+    /* add offset to input */
+    in3 = in3 + offset;
+
+    /* store result to destination */
+    *pDst = in1;
+
+    /* add offset to input */
+    in4 = in4 + offset;
+
+    /* store result to destination */
+    *(pDst + 1) = in2;
+
+    /* store result to destination */
+    *(pDst + 2) = in3;
+
+    /* store result to destination */
+    *(pDst + 3) = in4;
+
+    /* update pointers to process next samples */
+    pSrc += 4u;
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the result in the destination buffer. */
+    *pDst++ = (*pSrc++) + offset;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of offset group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_offset_q15.c

@@ -0,0 +1,136 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_offset_q15.c    
+*    
+* Description:	Q15 vector offset.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup offset    
+ * @{    
+ */
+
+/**    
+ * @brief  Adds a constant offset to a Q15 vector.    
+ * @param[in]  *pSrc points to the input vector    
+ * @param[in]  offset is the offset to be added    
+ * @param[out]  *pDst points to the output vector    
+ * @param[in]  blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q15 range [0x8000 0x7FFF] are saturated.    
+ */
+
+void arm_offset_q15(
+  q15_t * pSrc,
+  q15_t offset,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t offset_packed;                           /* Offset packed to 32 bit */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* Offset is packed to 32 bit in order to use SIMD32 for addition */
+  offset_packed = __PKHBT(offset, offset, 16);
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the results in the destination buffer, 2 samples at a time. */
+    *__SIMD32(pDst)++ = __QADD16(*__SIMD32(pSrc)++, offset_packed);
+    *__SIMD32(pDst)++ = __QADD16(*__SIMD32(pSrc)++, offset_packed);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the results in the destination buffer. */
+    *pDst++ = (q15_t) __QADD16(*pSrc++, offset);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the results in the destination buffer. */
+    *pDst++ = (q15_t) __SSAT(((q31_t) * pSrc++ + offset), 16);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of offset group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_offset_q31.c

@@ -0,0 +1,140 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_offset_q31.c    
+*    
+* Description:	Q31 vector offset.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup offset    
+ * @{    
+ */
+
+/**    
+ * @brief  Adds a constant offset to a Q31 vector.    
+ * @param[in]  *pSrc points to the input vector    
+ * @param[in]  offset is the offset to be added    
+ * @param[out]  *pDst points to the output vector    
+ * @param[in]  blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] are saturated.    
+ */
+
+void arm_offset_q31(
+  q31_t * pSrc,
+  q31_t offset,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t in1, in2, in3, in4;
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the results in the destination buffer. */
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+    in3 = *pSrc++;
+    in4 = *pSrc++;
+
+    *pDst++ = __QADD(in1, offset);
+    *pDst++ = __QADD(in2, offset);
+    *pDst++ = __QADD(in3, offset);
+    *pDst++ = __QADD(in4, offset);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the result in the destination buffer. */
+    *pDst++ = __QADD(*pSrc++, offset);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the result in the destination buffer. */
+    *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrc++ + offset);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of offset group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_offset_q7.c

@@ -0,0 +1,135 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_offset_q7.c    
+*    
+* Description:	Q7 vector offset.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup offset    
+ * @{    
+ */
+
+/**    
+ * @brief  Adds a constant offset to a Q7 vector.    
+ * @param[in]  *pSrc points to the input vector    
+ * @param[in]  offset is the offset to be added    
+ * @param[out]  *pDst points to the output vector    
+ * @param[in]  blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q7 range [0x80 0x7F] are saturated.    
+ */
+
+void arm_offset_q7(
+  q7_t * pSrc,
+  q7_t offset,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t offset_packed;                           /* Offset packed to 32 bit */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* Offset is packed to 32 bit in order to use SIMD32 for addition */
+  offset_packed = __PACKq7(offset, offset, offset, offset);
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the results in the destination bufferfor 4 samples at a time. */
+    *__SIMD32(pDst)++ = __QADD8(*__SIMD32(pSrc)++, offset_packed);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the result in the destination buffer. */
+    *pDst++ = (q7_t) __SSAT(*pSrc++ + offset, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A + offset */
+    /* Add offset and then store the result in the destination buffer. */
+    *pDst++ = (q7_t) __SSAT((q15_t) * pSrc++ + offset, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of offset group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_scale_f32.c

@@ -0,0 +1,169 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_scale_f32.c    
+*    
+* Description:	Multiplies a floating-point vector by a scalar.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup scale Vector Scale        
+ *        
+ * Multiply a vector by a scalar value.  For floating-point data, the algorithm used is:        
+ *        
+ * <pre>        
+ *     pDst[n] = pSrc[n] * scale,   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * In the fixed-point Q7, Q15, and Q31 functions, <code>scale</code> is represented by        
+ * a fractional multiplication <code>scaleFract</code> and an arithmetic shift <code>shift</code>.        
+ * The shift allows the gain of the scaling operation to exceed 1.0.        
+ * The algorithm used with fixed-point data is:        
+ *        
+ * <pre>        
+ *     pDst[n] = (pSrc[n] * scaleFract) << shift,   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * The overall scale factor applied to the fixed-point data is        
+ * <pre>        
+ *     scale = scaleFract * 2^shift.        
+ * </pre>        
+ *
+ * The functions support in-place computation allowing the source and destination
+ * pointers to reference the same memory buffer.
+ */
+
+/**        
+ * @addtogroup scale        
+ * @{        
+ */
+
+/**        
+ * @brief Multiplies a floating-point vector by a scalar.        
+ * @param[in]       *pSrc points to the input vector        
+ * @param[in]       scale scale factor to be applied        
+ * @param[out]      *pDst points to the output vector        
+ * @param[in]       blockSize number of samples in the vector        
+ * @return none.        
+ */
+
+
+void arm_scale_f32(
+  float32_t * pSrc,
+  float32_t scale,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t in1, in2, in3, in4;                  /* temporary variabels */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A * scale */
+    /* Scale the input and then store the results in the destination buffer. */
+    /* read input samples from source */
+    in1 = *pSrc;
+    in2 = *(pSrc + 1);
+
+    /* multiply with scaling factor */
+    in1 = in1 * scale;
+
+    /* read input sample from source */
+    in3 = *(pSrc + 2);
+
+    /* multiply with scaling factor */
+    in2 = in2 * scale;
+
+    /* read input sample from source */
+    in4 = *(pSrc + 3);
+
+    /* multiply with scaling factor */
+    in3 = in3 * scale;
+    in4 = in4 * scale;
+    /* store the result to destination */
+    *pDst = in1;
+    *(pDst + 1) = in2;
+    *(pDst + 2) = in3;
+    *(pDst + 3) = in4;
+
+    /* update pointers to process next samples */
+    pSrc += 4u;
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * scale */
+    /* Scale the input and then store the result in the destination buffer. */
+    *pDst++ = (*pSrc++) * scale;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of scale group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_scale_q15.c

@@ -0,0 +1,162 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_scale_q15.c    
+*    
+* Description:	Multiplies a Q15 vector by a scalar.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup scale    
+ * @{    
+ */
+
+/**    
+ * @brief Multiplies a Q15 vector by a scalar.    
+ * @param[in]       *pSrc points to the input vector    
+ * @param[in]       scaleFract fractional portion of the scale value    
+ * @param[in]       shift number of bits to shift the result by    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.15 format.    
+ * These are multiplied to yield a 2.30 intermediate result and this is shifted with saturation to 1.15 format.    
+ */
+
+
+void arm_scale_q15(
+  q15_t * pSrc,
+  q15_t scaleFract,
+  int8_t shift,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  int8_t kShift = 15 - shift;                    /* shift to apply after scaling */
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q15_t in1, in2, in3, in4;
+  q31_t inA1, inA2;                              /* Temporary variables */
+  q31_t out1, out2, out3, out4;
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* Reading 2 inputs from memory */
+    inA1 = *__SIMD32(pSrc)++;
+    inA2 = *__SIMD32(pSrc)++;
+
+    /* C = A * scale */
+    /* Scale the inputs and then store the 2 results in the destination buffer        
+     * in single cycle by packing the outputs */
+    out1 = (q31_t) ((q15_t) (inA1 >> 16) * scaleFract);
+    out2 = (q31_t) ((q15_t) inA1 * scaleFract);
+    out3 = (q31_t) ((q15_t) (inA2 >> 16) * scaleFract);
+    out4 = (q31_t) ((q15_t) inA2 * scaleFract);
+
+    /* apply shifting */
+    out1 = out1 >> kShift;
+    out2 = out2 >> kShift;
+    out3 = out3 >> kShift;
+    out4 = out4 >> kShift;
+
+    /* saturate the output */
+    in1 = (q15_t) (__SSAT(out1, 16));
+    in2 = (q15_t) (__SSAT(out2, 16));
+    in3 = (q15_t) (__SSAT(out3, 16));
+    in4 = (q15_t) (__SSAT(out4, 16));
+
+    /* store the result to destination */
+    *__SIMD32(pDst)++ = __PKHBT(in2, in1, 16);
+    *__SIMD32(pDst)++ = __PKHBT(in4, in3, 16);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * scale */
+    /* Scale the input and then store the result in the destination buffer. */
+    *pDst++ = (q15_t) (__SSAT(((*pSrc++) * scaleFract) >> kShift, 16));
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * scale */
+    /* Scale the input and then store the result in the destination buffer. */
+    *pDst++ = (q15_t) (__SSAT(((q31_t) * pSrc++ * scaleFract) >> kShift, 16));
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of scale group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_scale_q31.c

@@ -0,0 +1,239 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_scale_q31.c    
+*    
+* Description:	Multiplies a Q31 vector by a scalar.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**       
+ * @ingroup groupMath       
+ */
+
+/**       
+ * @addtogroup scale       
+ * @{       
+ */
+
+/**       
+ * @brief Multiplies a Q31 vector by a scalar.       
+ * @param[in]       *pSrc points to the input vector       
+ * @param[in]       scaleFract fractional portion of the scale value       
+ * @param[in]       shift number of bits to shift the result by       
+ * @param[out]      *pDst points to the output vector       
+ * @param[in]       blockSize number of samples in the vector       
+ * @return none.       
+ *       
+ * <b>Scaling and Overflow Behavior:</b>       
+ * \par       
+ * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.31 format.       
+ * These are multiplied to yield a 2.62 intermediate result and this is shifted with saturation to 1.31 format.       
+ */
+
+void arm_scale_q31(
+  q31_t * pSrc,
+  q31_t scaleFract,
+  int8_t shift,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  int8_t kShift = shift + 1;                     /* Shift to apply after scaling */
+  int8_t sign = (kShift & 0x80);
+  uint32_t blkCnt;                               /* loop counter */
+  q31_t in, out;
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  q31_t in1, in2, in3, in4;                      /* temporary input variables */
+  q31_t out1, out2, out3, out4;                  /* temporary output variabels */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  if(sign == 0u)
+  {
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.       
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* read four inputs from source */
+      in1 = *pSrc;
+      in2 = *(pSrc + 1);
+      in3 = *(pSrc + 2);
+      in4 = *(pSrc + 3);
+
+      /* multiply input with scaler value */
+      in1 = ((q63_t) in1 * scaleFract) >> 32;
+      in2 = ((q63_t) in2 * scaleFract) >> 32;
+      in3 = ((q63_t) in3 * scaleFract) >> 32;
+      in4 = ((q63_t) in4 * scaleFract) >> 32;
+
+      /* apply shifting */
+      out1 = in1 << kShift;
+      out2 = in2 << kShift;
+
+      /* saturate the results. */
+      if(in1 != (out1 >> kShift))
+        out1 = 0x7FFFFFFF ^ (in1 >> 31);
+
+      if(in2 != (out2 >> kShift))
+        out2 = 0x7FFFFFFF ^ (in2 >> 31);
+
+      out3 = in3 << kShift;
+      out4 = in4 << kShift;
+
+      *pDst = out1;
+      *(pDst + 1) = out2;
+
+      if(in3 != (out3 >> kShift))
+        out3 = 0x7FFFFFFF ^ (in3 >> 31);
+
+      if(in4 != (out4 >> kShift))
+        out4 = 0x7FFFFFFF ^ (in4 >> 31);
+
+      /* Store result destination */
+      *(pDst + 2) = out3;
+      *(pDst + 3) = out4;
+
+      /* Update pointers to process next sampels */
+      pSrc += 4u;
+      pDst += 4u;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+
+  }
+  else
+  {
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.       
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* read four inputs from source */
+      in1 = *pSrc;
+      in2 = *(pSrc + 1);
+      in3 = *(pSrc + 2);
+      in4 = *(pSrc + 3);
+
+      /* multiply input with scaler value */
+      in1 = ((q63_t) in1 * scaleFract) >> 32;
+      in2 = ((q63_t) in2 * scaleFract) >> 32;
+      in3 = ((q63_t) in3 * scaleFract) >> 32;
+      in4 = ((q63_t) in4 * scaleFract) >> 32;
+
+      /* apply shifting */
+      out1 = in1 >> -kShift;
+      out2 = in2 >> -kShift;
+
+      out3 = in3 >> -kShift;
+      out4 = in4 >> -kShift;
+
+      /* Store result destination */
+      *pDst = out1;
+      *(pDst + 1) = out2;
+
+      *(pDst + 2) = out3;
+      *(pDst + 3) = out4;
+
+      /* Update pointers to process next sampels */
+      pSrc += 4u;
+      pDst += 4u;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.       
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  if(sign == 0)
+  {
+	  while(blkCnt > 0u)
+	  {
+		/* C = A * scale */
+		/* Scale the input and then store the result in the destination buffer. */
+		in = *pSrc++;
+		in = ((q63_t) in * scaleFract) >> 32;
+
+		out = in << kShift;
+		
+		if(in != (out >> kShift))
+			out = 0x7FFFFFFF ^ (in >> 31);
+
+		*pDst++ = out;
+
+		/* Decrement the loop counter */
+		blkCnt--;
+	  }
+  }
+  else
+  {
+	  while(blkCnt > 0u)
+	  {
+		/* C = A * scale */
+		/* Scale the input and then store the result in the destination buffer. */
+		in = *pSrc++;
+		in = ((q63_t) in * scaleFract) >> 32;
+
+		out = in >> -kShift;
+
+		*pDst++ = out;
+
+		/* Decrement the loop counter */
+		blkCnt--;
+	  }
+  
+  }
+}
+
+/**       
+ * @} end of scale group       
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_scale_q7.c

@@ -0,0 +1,149 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_scale_q7.c    
+*    
+* Description:	Multiplies a Q7 vector by a scalar.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup scale    
+ * @{    
+ */
+
+/**    
+ * @brief Multiplies a Q7 vector by a scalar.    
+ * @param[in]       *pSrc points to the input vector    
+ * @param[in]       scaleFract fractional portion of the scale value    
+ * @param[in]       shift number of bits to shift the result by    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.7 format.    
+ * These are multiplied to yield a 2.14 intermediate result and this is shifted with saturation to 1.7 format.    
+ */
+
+void arm_scale_q7(
+  q7_t * pSrc,
+  q7_t scaleFract,
+  int8_t shift,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  int8_t kShift = 7 - shift;                     /* shift to apply after scaling */
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q7_t in1, in2, in3, in4, out1, out2, out3, out4;      /* Temporary variables to store input & output */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* Reading 4 inputs from memory */
+    in1 = *pSrc++;
+    in2 = *pSrc++;
+    in3 = *pSrc++;
+    in4 = *pSrc++;
+
+    /* C = A * scale */
+    /* Scale the inputs and then store the results in the temporary variables. */
+    out1 = (q7_t) (__SSAT(((in1) * scaleFract) >> kShift, 8));
+    out2 = (q7_t) (__SSAT(((in2) * scaleFract) >> kShift, 8));
+    out3 = (q7_t) (__SSAT(((in3) * scaleFract) >> kShift, 8));
+    out4 = (q7_t) (__SSAT(((in4) * scaleFract) >> kShift, 8));
+
+    /* Packing the individual outputs into 32bit and storing in    
+     * destination buffer in single write */
+    *__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * scale */
+    /* Scale the input and then store the result in the destination buffer. */
+    *pDst++ = (q7_t) (__SSAT(((*pSrc++) * scaleFract) >> kShift, 8));
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A * scale */
+    /* Scale the input and then store the result in the destination buffer. */
+    *pDst++ = (q7_t) (__SSAT((((q15_t) * pSrc++ * scaleFract) >> kShift), 8));
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of scale group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_shift_q15.c

@@ -0,0 +1,248 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_shift_q15.c    
+*    
+* Description:	Shifts the elements of a Q15 vector by a specified number of bits.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup shift    
+ * @{    
+ */
+
+/**    
+ * @brief  Shifts the elements of a Q15 vector a specified number of bits.    
+ * @param[in]  *pSrc points to the input vector    
+ * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.    
+ * @param[out]  *pDst points to the output vector    
+ * @param[in]  blockSize number of samples in the vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.    
+ */
+
+void arm_shift_q15(
+  q15_t * pSrc,
+  int8_t shiftBits,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  uint8_t sign;                                  /* Sign of shiftBits */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  q15_t in1, in2;                                /* Temporary variables */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* Getting the sign of shiftBits */
+  sign = (shiftBits & 0x80);
+
+  /* If the shift value is positive then do right shift else left shift */
+  if(sign == 0u)
+  {
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* Read 2 inputs */
+      in1 = *pSrc++;
+      in2 = *pSrc++;
+      /* C = A << shiftBits */
+      /* Shift the inputs and then store the results in the destination buffer. */
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in1 << shiftBits), 16),
+                                  __SSAT((in2 << shiftBits), 16), 16);
+
+#else
+
+      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in2 << shiftBits), 16),
+                                  __SSAT((in1 << shiftBits), 16), 16);
+
+#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      in1 = *pSrc++;
+      in2 = *pSrc++;
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in1 << shiftBits), 16),
+                                  __SSAT((in2 << shiftBits), 16), 16);
+
+#else
+
+      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in2 << shiftBits), 16),
+                                  __SSAT((in1 << shiftBits), 16), 16);
+
+#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+     ** No loop unrolling is used. */
+    blkCnt = blockSize % 0x4u;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A << shiftBits */
+      /* Shift and then store the results in the destination buffer. */
+      *pDst++ = __SSAT((*pSrc++ << shiftBits), 16);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+  else
+  {
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* Read 2 inputs */
+      in1 = *pSrc++;
+      in2 = *pSrc++;
+
+      /* C = A >> shiftBits */
+      /* Shift the inputs and then store the results in the destination buffer. */
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      *__SIMD32(pDst)++ = __PKHBT((in1 >> -shiftBits),
+                                  (in2 >> -shiftBits), 16);
+
+#else
+
+      *__SIMD32(pDst)++ = __PKHBT((in2 >> -shiftBits),
+                                  (in1 >> -shiftBits), 16);
+
+#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      in1 = *pSrc++;
+      in2 = *pSrc++;
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      *__SIMD32(pDst)++ = __PKHBT((in1 >> -shiftBits),
+                                  (in2 >> -shiftBits), 16);
+
+#else
+
+      *__SIMD32(pDst)++ = __PKHBT((in2 >> -shiftBits),
+                                  (in1 >> -shiftBits), 16);
+
+#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+     ** No loop unrolling is used. */
+    blkCnt = blockSize % 0x4u;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A >> shiftBits */
+      /* Shift the inputs and then store the results in the destination buffer. */
+      *pDst++ = (*pSrc++ >> -shiftBits);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Getting the sign of shiftBits */
+  sign = (shiftBits & 0x80);
+
+  /* If the shift value is positive then do right shift else left shift */
+  if(sign == 0u)
+  {
+    /* Initialize blkCnt with number of samples */
+    blkCnt = blockSize;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A << shiftBits */
+      /* Shift and then store the results in the destination buffer. */
+      *pDst++ = __SSAT(((q31_t) * pSrc++ << shiftBits), 16);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+  else
+  {
+    /* Initialize blkCnt with number of samples */
+    blkCnt = blockSize;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A >> shiftBits */
+      /* Shift the inputs and then store the results in the destination buffer. */
+      *pDst++ = (*pSrc++ >> -shiftBits);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of shift group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_shift_q31.c

@@ -0,0 +1,203 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_shift_q31.c    
+*    
+* Description:	Shifts the elements of a Q31 vector by a specified number of bits.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+/**        
+ * @defgroup shift Vector Shift        
+ *        
+ * Shifts the elements of a fixed-point vector by a specified number of bits.        
+ * There are separate functions for Q7, Q15, and Q31 data types.        
+ * The underlying algorithm used is:        
+ *        
+ * <pre>        
+ *     pDst[n] = pSrc[n] << shift,   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * If <code>shift</code> is positive then the elements of the vector are shifted to the left.        
+ * If <code>shift</code> is negative then the elements of the vector are shifted to the right.        
+ *
+ * The functions support in-place computation allowing the source and destination
+ * pointers to reference the same memory buffer.
+ */
+
+/**        
+ * @addtogroup shift        
+ * @{        
+ */
+
+/**        
+ * @brief  Shifts the elements of a Q31 vector a specified number of bits.        
+ * @param[in]  *pSrc points to the input vector        
+ * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.        
+ * @param[out]  *pDst points to the output vector        
+ * @param[in]  blockSize number of samples in the vector        
+ * @return none.        
+ *        
+ *        
+ * <b>Scaling and Overflow Behavior:</b>        
+ * \par        
+ * The function uses saturating arithmetic.        
+ * Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] will be saturated.        
+ */
+
+void arm_shift_q31(
+  q31_t * pSrc,
+  int8_t shiftBits,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  uint8_t sign = (shiftBits & 0x80);             /* Sign of shiftBits */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  q31_t in1, in2, in3, in4;                      /* Temporary input variables */
+  q31_t out1, out2, out3, out4;                  /* Temporary output variables */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+
+  if(sign == 0u)
+  {
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* C = A  << shiftBits */
+      /* Shift the input and then store the results in the destination buffer. */
+      in1 = *pSrc;
+      in2 = *(pSrc + 1);
+      out1 = in1 << shiftBits;
+      in3 = *(pSrc + 2);
+      out2 = in2 << shiftBits;
+      in4 = *(pSrc + 3);
+      if(in1 != (out1 >> shiftBits))
+        out1 = 0x7FFFFFFF ^ (in1 >> 31);
+
+      if(in2 != (out2 >> shiftBits))
+        out2 = 0x7FFFFFFF ^ (in2 >> 31);
+
+      *pDst = out1;
+      out3 = in3 << shiftBits;
+      *(pDst + 1) = out2;
+      out4 = in4 << shiftBits;
+
+      if(in3 != (out3 >> shiftBits))
+        out3 = 0x7FFFFFFF ^ (in3 >> 31);
+
+      if(in4 != (out4 >> shiftBits))
+        out4 = 0x7FFFFFFF ^ (in4 >> 31);
+
+      *(pDst + 2) = out3;
+      *(pDst + 3) = out4;
+
+      /* Update destination pointer to process next sampels */
+      pSrc += 4u;
+      pDst += 4u;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+  else
+  {
+
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* C = A >>  shiftBits */
+      /* Shift the input and then store the results in the destination buffer. */
+      in1 = *pSrc;
+      in2 = *(pSrc + 1);
+      in3 = *(pSrc + 2);
+      in4 = *(pSrc + 3);
+
+      *pDst = (in1 >> -shiftBits);
+      *(pDst + 1) = (in2 >> -shiftBits);
+      *(pDst + 2) = (in3 >> -shiftBits);
+      *(pDst + 3) = (in4 >> -shiftBits);
+
+
+      pSrc += 4u;
+      pDst += 4u;
+
+      blkCnt--;
+    }
+
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+
+  while(blkCnt > 0u)
+  {
+    /* C = A (>> or <<) shiftBits */
+    /* Shift the input and then store the result in the destination buffer. */
+    *pDst++ = (sign == 0u) ? clip_q63_to_q31((q63_t) * pSrc++ << shiftBits) :
+      (*pSrc++ >> -shiftBits);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+
+}
+
+/**        
+ * @} end of shift group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_shift_q7.c

@@ -0,0 +1,220 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_shift_q7.c    
+*    
+* Description:	Processing function for the Q7 Shifting    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @addtogroup shift        
+ * @{        
+ */
+
+
+/**        
+ * @brief  Shifts the elements of a Q7 vector a specified number of bits.        
+ * @param[in]  *pSrc points to the input vector        
+ * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.        
+ * @param[out]  *pDst points to the output vector        
+ * @param[in]  blockSize number of samples in the vector        
+ * @return none.        
+ *    
+ * \par Conditions for optimum performance    
+ *  Input and output buffers should be aligned by 32-bit    
+ *    
+ *        
+ * <b>Scaling and Overflow Behavior:</b>        
+ * \par        
+ * The function uses saturating arithmetic.        
+ * Results outside of the allowable Q7 range [0x8 0x7F] will be saturated.        
+ */
+
+void arm_shift_q7(
+  q7_t * pSrc,
+  int8_t shiftBits,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  uint8_t sign;                                  /* Sign of shiftBits */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q7_t in1;                                      /* Input value1 */
+  q7_t in2;                                      /* Input value2 */
+  q7_t in3;                                      /* Input value3 */
+  q7_t in4;                                      /* Input value4 */
+
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* Getting the sign of shiftBits */
+  sign = (shiftBits & 0x80);
+
+  /* If the shift value is positive then do right shift else left shift */
+  if(sign == 0u)
+  {
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* C = A << shiftBits */
+      /* Read 4 inputs */
+      in1 = *pSrc;
+      in2 = *(pSrc + 1);
+      in3 = *(pSrc + 2);
+      in4 = *(pSrc + 3);
+
+      /* Store the Shifted result in the destination buffer in single cycle by packing the outputs */
+      *__SIMD32(pDst)++ = __PACKq7(__SSAT((in1 << shiftBits), 8),
+                                   __SSAT((in2 << shiftBits), 8),
+                                   __SSAT((in3 << shiftBits), 8),
+                                   __SSAT((in4 << shiftBits), 8));
+      /* Update source pointer to process next sampels */
+      pSrc += 4u;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+     ** No loop unrolling is used. */
+    blkCnt = blockSize % 0x4u;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A << shiftBits */
+      /* Shift the input and then store the result in the destination buffer. */
+      *pDst++ = (q7_t) __SSAT((*pSrc++ << shiftBits), 8);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+  else
+  {
+    shiftBits = -shiftBits;
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(blkCnt > 0u)
+    {
+      /* C = A >> shiftBits */
+      /* Read 4 inputs */
+      in1 = *pSrc;
+      in2 = *(pSrc + 1);
+      in3 = *(pSrc + 2);
+      in4 = *(pSrc + 3);
+
+      /* Store the Shifted result in the destination buffer in single cycle by packing the outputs */
+      *__SIMD32(pDst)++ = __PACKq7((in1 >> shiftBits), (in2 >> shiftBits),
+                                   (in3 >> shiftBits), (in4 >> shiftBits));
+
+
+      pSrc += 4u;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+     ** No loop unrolling is used. */
+    blkCnt = blockSize % 0x4u;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A >> shiftBits */
+      /* Shift the input and then store the result in the destination buffer. */
+      in1 = *pSrc++;
+      *pDst++ = (in1 >> shiftBits);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Getting the sign of shiftBits */
+  sign = (shiftBits & 0x80);
+
+  /* If the shift value is positive then do right shift else left shift */
+  if(sign == 0u)
+  {
+    /* Initialize blkCnt with number of samples */
+    blkCnt = blockSize;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A << shiftBits */
+      /* Shift the input and then store the result in the destination buffer. */
+      *pDst++ = (q7_t) __SSAT(((q15_t) * pSrc++ << shiftBits), 8);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+  else
+  {
+    /* Initialize blkCnt with number of samples */
+    blkCnt = blockSize;
+
+    while(blkCnt > 0u)
+    {
+      /* C = A >> shiftBits */
+      /* Shift the input and then store the result in the destination buffer. */
+      *pDst++ = (*pSrc++ >> -shiftBits);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+}
+
+/**        
+ * @} end of shift group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_sub_f32.c

@@ -0,0 +1,150 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sub_f32.c    
+*    
+* Description:	Floating-point vector subtraction.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupMath        
+ */
+
+/**        
+ * @defgroup BasicSub Vector Subtraction        
+ *        
+ * Element-by-element subtraction of two vectors.        
+ *        
+ * <pre>        
+ *     pDst[n] = pSrcA[n] - pSrcB[n],   0 <= n < blockSize.        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q7, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup BasicSub        
+ * @{        
+ */
+
+
+/**        
+ * @brief Floating-point vector subtraction.        
+ * @param[in]       *pSrcA points to the first input vector        
+ * @param[in]       *pSrcB points to the second input vector        
+ * @param[out]      *pDst points to the output vector        
+ * @param[in]       blockSize number of samples in each vector        
+ * @return none.        
+ */
+
+void arm_sub_f32(
+  float32_t * pSrcA,
+  float32_t * pSrcB,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t inA1, inA2, inA3, inA4;              /* temporary variables */
+  float32_t inB1, inB2, inB3, inB4;              /* temporary variables */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the results in the destination buffer. */
+    /* Read 4 input samples from sourceA and sourceB */
+    inA1 = *pSrcA;
+    inB1 = *pSrcB;
+    inA2 = *(pSrcA + 1);
+    inB2 = *(pSrcB + 1);
+    inA3 = *(pSrcA + 2);
+    inB3 = *(pSrcB + 2);
+    inA4 = *(pSrcA + 3);
+    inB4 = *(pSrcB + 3);
+
+    /* dst = srcA - srcB */
+    /* subtract and store the result */
+    *pDst = inA1 - inB1;
+    *(pDst + 1) = inA2 - inB2;
+    *(pDst + 2) = inA3 - inB3;
+    *(pDst + 3) = inA4 - inB4;
+
+
+    /* Update pointers to process next sampels */
+    pSrcA += 4u;
+    pSrcB += 4u;
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the results in the destination buffer. */
+    *pDst++ = (*pSrcA++) - (*pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of BasicSub group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_sub_q15.c

@@ -0,0 +1,140 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sub_q15.c    
+*    
+* Description:	Q15 vector subtraction.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicSub    
+ * @{    
+ */
+
+/**    
+ * @brief Q15 vector subtraction.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.    
+ */
+
+void arm_sub_q15(
+  q15_t * pSrcA,
+  q15_t * pSrcB,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2;
+  q31_t inB1, inB2;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the results in the destination buffer two samples at a time. */
+    inA1 = *__SIMD32(pSrcA)++;
+    inA2 = *__SIMD32(pSrcA)++;
+    inB1 = *__SIMD32(pSrcB)++;
+    inB2 = *__SIMD32(pSrcB)++;
+
+    *__SIMD32(pDst)++ = __QSUB16(inA1, inB1);
+    *__SIMD32(pDst)++ = __QSUB16(inA2, inB2);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the result in the destination buffer. */
+    *pDst++ = (q15_t) __QSUB16(*pSrcA++, *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the result in the destination buffer. */
+    *pDst++ = (q15_t) __SSAT(((q31_t) * pSrcA++ - *pSrcB++), 16);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+
+}
+
+/**    
+ * @} end of BasicSub group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_sub_q31.c

@@ -0,0 +1,146 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sub_q31.c    
+*    
+* Description:	Q31 vector subtraction.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicSub    
+ * @{    
+ */
+
+/**    
+ * @brief Q31 vector subtraction.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] will be saturated.    
+ */
+
+void arm_sub_q31(
+  q31_t * pSrcA,
+  q31_t * pSrcB,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inA1, inA2, inA3, inA4;
+  q31_t inB1, inB2, inB3, inB4;
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the results in the destination buffer. */
+    inA1 = *pSrcA++;
+    inA2 = *pSrcA++;
+    inB1 = *pSrcB++;
+    inB2 = *pSrcB++;
+
+    inA3 = *pSrcA++;
+    inA4 = *pSrcA++;
+    inB3 = *pSrcB++;
+    inB4 = *pSrcB++;
+
+    *pDst++ = __QSUB(inA1, inB1);
+    *pDst++ = __QSUB(inA2, inB2);
+    *pDst++ = __QSUB(inA3, inB3);
+    *pDst++ = __QSUB(inA4, inB4);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the result in the destination buffer. */
+    *pDst++ = __QSUB(*pSrcA++, *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the result in the destination buffer. */
+    *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrcA++ - *pSrcB++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of BasicSub group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_sub_q7.c

@@ -0,0 +1,131 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sub_q7.c    
+*    
+* Description:	Q7 vector subtraction.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupMath    
+ */
+
+/**    
+ * @addtogroup BasicSub    
+ * @{    
+ */
+
+/**    
+ * @brief Q7 vector subtraction.    
+ * @param[in]       *pSrcA points to the first input vector    
+ * @param[in]       *pSrcB points to the second input vector    
+ * @param[out]      *pDst points to the output vector    
+ * @param[in]       blockSize number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.    
+ */
+
+void arm_sub_q7(
+  q7_t * pSrcA,
+  q7_t * pSrcB,
+  q7_t * pDst,
+  uint32_t blockSize)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+/* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  /*loop Unrolling */
+  blkCnt = blockSize >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the results in the destination buffer 4 samples at a time. */
+    *__SIMD32(pDst)++ = __QSUB8(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = blockSize % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the result in the destination buffer. */
+    *pDst++ = __SSAT(*pSrcA++ - *pSrcB++, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
+
+  while(blkCnt > 0u)
+  {
+    /* C = A - B */
+    /* Subtract and then store the result in the destination buffer. */
+    *pDst++ = (q7_t) __SSAT((q15_t) * pSrcA++ - *pSrcB++, 8);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+
+}
+
+/**    
+ * @} end of BasicSub group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/CommonTables/arm_const_structs.c

@@ -0,0 +1,156 @@
+/* ---------------------------------------------------------------------- 
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved. 
+* 
+* $Date:        19. March 2015 
+* $Revision: 	V.1.4.5
+* 
+* Project: 	    CMSIS DSP Library 
+* Title:	    arm_const_structs.c 
+* 
+* Description:	This file has constant structs that are initialized for
+*              user convenience.  For example, some can be given as 
+*              arguments to the arm_cfft_f32() function.
+* 
+* Target Processor: Cortex-M4/Cortex-M3
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* -------------------------------------------------------------------- */
+
+#include "arm_const_structs.h"
+
+//Floating-point structs
+
+const arm_cfft_instance_f32 arm_cfft_sR_f32_len16 = {
+	16, twiddleCoef_16, armBitRevIndexTable16, ARMBITREVINDEXTABLE__16_TABLE_LENGTH
+};
+
+const arm_cfft_instance_f32 arm_cfft_sR_f32_len32 = {
+	32, twiddleCoef_32, armBitRevIndexTable32, ARMBITREVINDEXTABLE__32_TABLE_LENGTH
+};
+
+const arm_cfft_instance_f32 arm_cfft_sR_f32_len64 = {
+	64, twiddleCoef_64, armBitRevIndexTable64, ARMBITREVINDEXTABLE__64_TABLE_LENGTH
+};
+
+const arm_cfft_instance_f32 arm_cfft_sR_f32_len128 = {
+	128, twiddleCoef_128, armBitRevIndexTable128, ARMBITREVINDEXTABLE_128_TABLE_LENGTH
+};
+
+const arm_cfft_instance_f32 arm_cfft_sR_f32_len256 = {
+	256, twiddleCoef_256, armBitRevIndexTable256, ARMBITREVINDEXTABLE_256_TABLE_LENGTH
+};
+
+const arm_cfft_instance_f32 arm_cfft_sR_f32_len512 = {
+	512, twiddleCoef_512, armBitRevIndexTable512, ARMBITREVINDEXTABLE_512_TABLE_LENGTH
+};
+
+const arm_cfft_instance_f32 arm_cfft_sR_f32_len1024 = {
+	1024, twiddleCoef_1024, armBitRevIndexTable1024, ARMBITREVINDEXTABLE1024_TABLE_LENGTH
+};
+
+const arm_cfft_instance_f32 arm_cfft_sR_f32_len2048 = {
+	2048, twiddleCoef_2048, armBitRevIndexTable2048, ARMBITREVINDEXTABLE2048_TABLE_LENGTH
+};
+
+const arm_cfft_instance_f32 arm_cfft_sR_f32_len4096 = {
+	4096, twiddleCoef_4096, armBitRevIndexTable4096, ARMBITREVINDEXTABLE4096_TABLE_LENGTH
+};
+
+//Fixed-point structs
+
+const arm_cfft_instance_q31 arm_cfft_sR_q31_len16 = {
+	16, twiddleCoef_16_q31, armBitRevIndexTable_fixed_16, ARMBITREVINDEXTABLE_FIXED___16_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q31 arm_cfft_sR_q31_len32 = {
+	32, twiddleCoef_32_q31, armBitRevIndexTable_fixed_32, ARMBITREVINDEXTABLE_FIXED___32_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q31 arm_cfft_sR_q31_len64 = {
+	64, twiddleCoef_64_q31, armBitRevIndexTable_fixed_64, ARMBITREVINDEXTABLE_FIXED___64_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q31 arm_cfft_sR_q31_len128 = {
+	128, twiddleCoef_128_q31, armBitRevIndexTable_fixed_128, ARMBITREVINDEXTABLE_FIXED__128_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q31 arm_cfft_sR_q31_len256 = {
+	256, twiddleCoef_256_q31, armBitRevIndexTable_fixed_256, ARMBITREVINDEXTABLE_FIXED__256_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q31 arm_cfft_sR_q31_len512 = {
+	512, twiddleCoef_512_q31, armBitRevIndexTable_fixed_512, ARMBITREVINDEXTABLE_FIXED__512_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q31 arm_cfft_sR_q31_len1024 = {
+	1024, twiddleCoef_1024_q31, armBitRevIndexTable_fixed_1024, ARMBITREVINDEXTABLE_FIXED_1024_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q31 arm_cfft_sR_q31_len2048 = {
+	2048, twiddleCoef_2048_q31, armBitRevIndexTable_fixed_2048, ARMBITREVINDEXTABLE_FIXED_2048_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q31 arm_cfft_sR_q31_len4096 = {
+	4096, twiddleCoef_4096_q31, armBitRevIndexTable_fixed_4096, ARMBITREVINDEXTABLE_FIXED_4096_TABLE_LENGTH
+};
+
+
+const arm_cfft_instance_q15 arm_cfft_sR_q15_len16 = {
+	16, twiddleCoef_16_q15, armBitRevIndexTable_fixed_16, ARMBITREVINDEXTABLE_FIXED___16_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q15 arm_cfft_sR_q15_len32 = {
+	32, twiddleCoef_32_q15, armBitRevIndexTable_fixed_32, ARMBITREVINDEXTABLE_FIXED___32_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q15 arm_cfft_sR_q15_len64 = {
+	64, twiddleCoef_64_q15, armBitRevIndexTable_fixed_64, ARMBITREVINDEXTABLE_FIXED___64_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q15 arm_cfft_sR_q15_len128 = {
+	128, twiddleCoef_128_q15, armBitRevIndexTable_fixed_128, ARMBITREVINDEXTABLE_FIXED__128_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q15 arm_cfft_sR_q15_len256 = {
+	256, twiddleCoef_256_q15, armBitRevIndexTable_fixed_256, ARMBITREVINDEXTABLE_FIXED__256_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q15 arm_cfft_sR_q15_len512 = {
+	512, twiddleCoef_512_q15, armBitRevIndexTable_fixed_512, ARMBITREVINDEXTABLE_FIXED__512_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q15 arm_cfft_sR_q15_len1024 = {
+	1024, twiddleCoef_1024_q15, armBitRevIndexTable_fixed_1024, ARMBITREVINDEXTABLE_FIXED_1024_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q15 arm_cfft_sR_q15_len2048 = {
+	2048, twiddleCoef_2048_q15, armBitRevIndexTable_fixed_2048, ARMBITREVINDEXTABLE_FIXED_2048_TABLE_LENGTH
+};
+
+const arm_cfft_instance_q15 arm_cfft_sR_q15_len4096 = {
+	4096, twiddleCoef_4096_q15, armBitRevIndexTable_fixed_4096, ARMBITREVINDEXTABLE_FIXED_4096_TABLE_LENGTH
+};

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_conj_f32.c

@@ -0,0 +1,182 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_conj_f32.c    
+*    
+* Description:	Floating-point complex conjugate.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* ---------------------------------------------------------------------------- */
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupCmplxMath        
+ */
+
+/**        
+ * @defgroup cmplx_conj Complex Conjugate        
+ *        
+ * Conjugates the elements of a complex data vector.        
+ *       
+ * The <code>pSrc</code> points to the source data and        
+ * <code>pDst</code> points to the where the result should be written.        
+ * <code>numSamples</code> specifies the number of complex samples        
+ * and the data in each array is stored in an interleaved fashion        
+ * (real, imag, real, imag, ...).        
+ * Each array has a total of <code>2*numSamples</code> values.        
+ * The underlying algorithm is used:        
+ *        
+ * <pre>        
+ * for(n=0; n<numSamples; n++) {        
+ *     pDst[(2*n)+0)] = pSrc[(2*n)+0];     // real part        
+ *     pDst[(2*n)+1)] = -pSrc[(2*n)+1];    // imag part        
+ * }        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup cmplx_conj        
+ * @{        
+ */
+
+/**        
+ * @brief  Floating-point complex conjugate.        
+ * @param  *pSrc points to the input vector        
+ * @param  *pDst points to the output vector        
+ * @param  numSamples number of complex samples in each vector        
+ * @return none.        
+ */
+
+void arm_cmplx_conj_f32(
+  float32_t * pSrc,
+  float32_t * pDst,
+  uint32_t numSamples)
+{
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t inR1, inR2, inR3, inR4;
+  float32_t inI1, inI2, inI3, inI4;
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[0]+jC[1] = A[0]+ j (-1) A[1] */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    /* read real input samples */
+    inR1 = pSrc[0];
+    /* store real samples to destination */
+    pDst[0] = inR1;
+    inR2 = pSrc[2];
+    pDst[2] = inR2;
+    inR3 = pSrc[4];
+    pDst[4] = inR3;
+    inR4 = pSrc[6];
+    pDst[6] = inR4;
+
+    /* read imaginary input samples */
+    inI1 = pSrc[1];
+    inI2 = pSrc[3];
+
+    /* conjugate input */
+    inI1 = -inI1;
+
+    /* read imaginary input samples */
+    inI3 = pSrc[5];
+
+    /* conjugate input */
+    inI2 = -inI2;
+
+    /* read imaginary input samples */
+    inI4 = pSrc[7];
+
+    /* conjugate input */
+    inI3 = -inI3;
+
+    /* store imaginary samples to destination */
+    pDst[1] = inI1;
+    pDst[3] = inI2;
+
+    /* conjugate input */
+    inI4 = -inI4;
+
+    /* store imaginary samples to destination */
+    pDst[5] = inI3;
+
+    /* increment source pointer by 8 to process next sampels */
+    pSrc += 8u;
+
+    /* store imaginary sample to destination */
+    pDst[7] = inI4;
+
+    /* increment destination pointer by 8 to store next samples */
+    pDst += 8u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  blkCnt = numSamples;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* realOut + j (imagOut) = realIn + j (-1) imagIn */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    *pDst++ = *pSrc++;
+    *pDst++ = -*pSrc++;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of cmplx_conj group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_conj_q15.c

@@ -0,0 +1,161 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. October 2015
+* $Revision: 	V.1.4.5 a
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_conj_q15.c    
+*    
+* Description:	Q15 complex conjugate.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup cmplx_conj    
+ * @{    
+ */
+
+/**    
+ * @brief  Q15 complex conjugate.    
+ * @param  *pSrc points to the input vector    
+ * @param  *pDst points to the output vector    
+ * @param  numSamples number of complex samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * The Q15 value -1 (0x8000) will be saturated to the maximum allowable positive value 0x7FFF.    
+ */
+
+void arm_cmplx_conj_q15(
+  q15_t * pSrc,
+  q15_t * pDst,
+  uint32_t numSamples)
+{
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+  q31_t in1, in2, in3, in4;
+  q31_t zero = 0;
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[0]+jC[1] = A[0]+ j (-1) A[1] */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    in1 = *__SIMD32(pSrc)++;
+    in2 = *__SIMD32(pSrc)++;
+    in3 = *__SIMD32(pSrc)++;
+    in4 = *__SIMD32(pSrc)++;
+
+#ifndef ARM_MATH_BIG_ENDIAN
+
+    in1 = __QASX(zero, in1);
+    in2 = __QASX(zero, in2);
+    in3 = __QASX(zero, in3);
+    in4 = __QASX(zero, in4);
+
+#else
+
+    in1 = __QSAX(zero, in1);
+    in2 = __QSAX(zero, in2);
+    in3 = __QSAX(zero, in3);
+    in4 = __QSAX(zero, in4);
+
+#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
+
+    in1 = ((uint32_t) in1 >> 16) | ((uint32_t) in1 << 16);
+    in2 = ((uint32_t) in2 >> 16) | ((uint32_t) in2 << 16);
+    in3 = ((uint32_t) in3 >> 16) | ((uint32_t) in3 << 16);
+    in4 = ((uint32_t) in4 >> 16) | ((uint32_t) in4 << 16);
+
+    *__SIMD32(pDst)++ = in1;
+    *__SIMD32(pDst)++ = in2;
+    *__SIMD32(pDst)++ = in3;
+    *__SIMD32(pDst)++ = in4;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[0]+jC[1] = A[0]+ j (-1) A[1] */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    *pDst++ = *pSrc++;
+    *pDst++ = __SSAT(-*pSrc++, 16);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  q15_t in;
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* realOut + j (imagOut) = realIn+ j (-1) imagIn */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    *pDst++ = *pSrc++;
+    in = *pSrc++;
+    *pDst++ = (in == (q15_t) 0x8000) ? 0x7fff : -in;
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of cmplx_conj group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_conj_q31.c

@@ -0,0 +1,180 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_conj_q31.c    
+*    
+* Description:	Q31 complex conjugate.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.    
+* ---------------------------------------------------------------------------- */
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupCmplxMath        
+ */
+
+/**        
+ * @addtogroup cmplx_conj        
+ * @{        
+ */
+
+/**        
+ * @brief  Q31 complex conjugate.        
+ * @param  *pSrc points to the input vector        
+ * @param  *pDst points to the output vector        
+ * @param  numSamples number of complex samples in each vector        
+ * @return none.        
+ *        
+ * <b>Scaling and Overflow Behavior:</b>        
+ * \par        
+ * The function uses saturating arithmetic.        
+ * The Q31 value -1 (0x80000000) will be saturated to the maximum allowable positive value 0x7FFFFFFF.        
+ */
+
+void arm_cmplx_conj_q31(
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t numSamples)
+{
+  uint32_t blkCnt;                               /* loop counter */
+  q31_t in;                                      /* Input value */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t inR1, inR2, inR3, inR4;                  /* Temporary real variables */
+  q31_t inI1, inI2, inI3, inI4;                  /* Temporary imaginary variables */
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[0]+jC[1] = A[0]+ j (-1) A[1] */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    /* Saturated to 0x7fffffff if the input is -1(0x80000000) */
+    /* read real input sample */
+    inR1 = pSrc[0];
+    /* store real input sample */
+    pDst[0] = inR1;
+
+    /* read imaginary input sample */
+    inI1 = pSrc[1];
+
+    /* read real input sample */
+    inR2 = pSrc[2];
+    /* store real input sample */
+    pDst[2] = inR2;
+
+    /* read imaginary input sample */
+    inI2 = pSrc[3];
+
+    /* negate imaginary input sample */
+    inI1 = __QSUB(0, inI1);
+
+    /* read real input sample */
+    inR3 = pSrc[4];
+    /* store real input sample */
+    pDst[4] = inR3;
+
+    /* read imaginary input sample */
+    inI3 = pSrc[5];
+
+    /* negate imaginary input sample */
+    inI2 = __QSUB(0, inI2);
+
+    /* read real input sample */
+    inR4 = pSrc[6];
+    /* store real input sample */
+    pDst[6] = inR4;
+
+    /* negate imaginary input sample */
+    inI3 = __QSUB(0, inI3);
+
+    /* store imaginary input sample */
+    inI4 = pSrc[7];
+
+    /* store imaginary input samples */
+    pDst[1] = inI1;
+
+    /* negate imaginary input sample */
+    inI4 = __QSUB(0, inI4);
+
+    /* store imaginary input samples */
+    pDst[3] = inI2;
+
+    /* increment source pointer by 8 to proecess next samples */
+    pSrc += 8u;
+
+    /* store imaginary input samples */
+    pDst[5] = inI3;
+    pDst[7] = inI4;
+
+    /* increment destination pointer by 8 to process next samples */
+    pDst += 8u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  blkCnt = numSamples;
+
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C[0]+jC[1] = A[0]+ j (-1) A[1] */
+    /* Calculate Complex Conjugate and then store the results in the destination buffer. */
+    /* Saturated to 0x7fffffff if the input is -1(0x80000000) */
+    *pDst++ = *pSrc++;
+    in = *pSrc++;
+    *pDst++ = (in == INT32_MIN) ? INT32_MAX : -in;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of cmplx_conj group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_dot_prod_f32.c

@@ -0,0 +1,203 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_dot_prod_f32.c    
+*    
+* Description:	Floating-point complex dot product    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.    
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @defgroup cmplx_dot_prod Complex Dot Product    
+ *    
+ * Computes the dot product of two complex vectors.    
+ * The vectors are multiplied element-by-element and then summed.    
+ *   
+ * The <code>pSrcA</code> points to the first complex input vector and    
+ * <code>pSrcB</code> points to the second complex input vector.    
+ * <code>numSamples</code> specifies the number of complex samples    
+ * and the data in each array is stored in an interleaved fashion    
+ * (real, imag, real, imag, ...).    
+ * Each array has a total of <code>2*numSamples</code> values.    
+ *    
+ * The underlying algorithm is used:    
+ * <pre>    
+ * realResult=0;    
+ * imagResult=0;    
+ * for(n=0; n<numSamples; n++) {    
+ *     realResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+0] - pSrcA[(2*n)+1]*pSrcB[(2*n)+1];    
+ *     imagResult += pSrcA[(2*n)+0]*pSrcB[(2*n)+1] + pSrcA[(2*n)+1]*pSrcB[(2*n)+0];    
+ * }    
+ * </pre>    
+ *    
+ * There are separate functions for floating-point, Q15, and Q31 data types.    
+ */
+
+/**    
+ * @addtogroup cmplx_dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief  Floating-point complex dot product    
+ * @param  *pSrcA points to the first input vector    
+ * @param  *pSrcB points to the second input vector    
+ * @param  numSamples number of complex samples in each vector    
+ * @param  *realResult real part of the result returned here    
+ * @param  *imagResult imaginary part of the result returned here    
+ * @return none.    
+ */
+
+void arm_cmplx_dot_prod_f32(
+  float32_t * pSrcA,
+  float32_t * pSrcB,
+  uint32_t numSamples,
+  float32_t * realResult,
+  float32_t * imagResult)
+{
+  float32_t real_sum = 0.0f, imag_sum = 0.0f;    /* Temporary result storage */
+  float32_t a0,b0,c0,d0;
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += a0 * c0;
+      imag_sum += a0 * d0;
+      real_sum -= b0 * d0;
+      imag_sum += b0 * c0;
+    
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++; 
+  
+      real_sum += a0 * c0;
+      imag_sum += a0 * d0;
+      real_sum -= b0 * d0;
+      imag_sum += b0 * c0;
+      
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += a0 * c0;
+      imag_sum += a0 * d0;
+      real_sum -= b0 * d0;
+      imag_sum += b0 * c0;
+    
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++; 
+  
+      real_sum += a0 * c0;
+      imag_sum += a0 * d0;
+      real_sum -= b0 * d0;
+      imag_sum += b0 * c0;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples & 0x3u;
+
+  while(blkCnt > 0u)
+  {
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += a0 * c0;
+      imag_sum += a0 * d0;
+      real_sum -= b0 * d0;
+      imag_sum += b0 * c0;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += a0 * c0;
+      imag_sum += a0 * d0;
+      real_sum -= b0 * d0;
+      imag_sum += b0 * c0;
+
+      /* Decrement the loop counter */
+      numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  /* Store the real and imaginary results in the destination buffers */
+  *realResult = real_sum;
+  *imagResult = imag_sum;
+}
+
+/**    
+ * @} end of cmplx_dot_prod group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_dot_prod_q15.c

@@ -0,0 +1,189 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_dot_prod_q15.c    
+*    
+* Description:	Processing function for the Q15 Complex Dot product    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup cmplx_dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief  Q15 complex dot product    
+ * @param  *pSrcA points to the first input vector    
+ * @param  *pSrcB points to the second input vector    
+ * @param  numSamples number of complex samples in each vector    
+ * @param  *realResult real part of the result returned here    
+ * @param  *imagResult imaginary part of the result returned here    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function is implemented using an internal 64-bit accumulator.    
+ * The intermediate 1.15 by 1.15 multiplications are performed with full precision and yield a 2.30 result.    
+ * These are accumulated in a 64-bit accumulator with 34.30 precision.    
+ * As a final step, the accumulators are converted to 8.24 format.    
+ * The return results <code>realResult</code> and <code>imagResult</code> are in 8.24 format.    
+ */
+
+void arm_cmplx_dot_prod_q15(
+  q15_t * pSrcA,
+  q15_t * pSrcB,
+  uint32_t numSamples,
+  q31_t * realResult,
+  q31_t * imagResult)
+{
+  q63_t real_sum = 0, imag_sum = 0;              /* Temporary result storage */
+  q15_t a0,b0,c0,d0;
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += (q31_t)a0 * c0;
+      imag_sum += (q31_t)a0 * d0;
+      real_sum -= (q31_t)b0 * d0;
+      imag_sum += (q31_t)b0 * c0;
+      
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += (q31_t)a0 * c0;
+      imag_sum += (q31_t)a0 * d0;
+      real_sum -= (q31_t)b0 * d0;
+      imag_sum += (q31_t)b0 * c0;
+      
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += (q31_t)a0 * c0;
+      imag_sum += (q31_t)a0 * d0;
+      real_sum -= (q31_t)b0 * d0;
+      imag_sum += (q31_t)b0 * c0;
+      
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += (q31_t)a0 * c0;
+      imag_sum += (q31_t)a0 * d0;
+      real_sum -= (q31_t)b0 * d0;
+      imag_sum += (q31_t)b0 * c0;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += (q31_t)a0 * c0;
+      imag_sum += (q31_t)a0 * d0;
+      real_sum -= (q31_t)b0 * d0;
+      imag_sum += (q31_t)b0 * c0;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += a0 * c0;
+      imag_sum += a0 * d0;
+      real_sum -= b0 * d0;
+      imag_sum += b0 * c0;
+
+
+      /* Decrement the loop counter */
+      numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  /* Store the real and imaginary results in 8.24 format  */
+  /* Convert real data in 34.30 to 8.24 by 6 right shifts */
+  *realResult = (q31_t) (real_sum >> 6);
+  /* Convert imaginary data in 34.30 to 8.24 by 6 right shifts */
+  *imagResult = (q31_t) (imag_sum >> 6);
+}
+
+/**    
+ * @} end of cmplx_dot_prod group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_dot_prod_q31.c

@@ -0,0 +1,187 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_dot_prod_q31.c    
+*    
+* Description:	Q31 complex dot product    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup cmplx_dot_prod    
+ * @{    
+ */
+
+/**    
+ * @brief  Q31 complex dot product    
+ * @param  *pSrcA points to the first input vector    
+ * @param  *pSrcB points to the second input vector    
+ * @param  numSamples number of complex samples in each vector    
+ * @param  *realResult real part of the result returned here    
+ * @param  *imagResult imaginary part of the result returned here    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function is implemented using an internal 64-bit accumulator.    
+ * The intermediate 1.31 by 1.31 multiplications are performed with 64-bit precision and then shifted to 16.48 format.    
+ * The internal real and imaginary accumulators are in 16.48 format and provide 15 guard bits.    
+ * Additions are nonsaturating and no overflow will occur as long as <code>numSamples</code> is less than 32768.    
+ * The return results <code>realResult</code> and <code>imagResult</code> are in 16.48 format.    
+ * Input down scaling is not required.    
+ */
+
+void arm_cmplx_dot_prod_q31(
+  q31_t * pSrcA,
+  q31_t * pSrcB,
+  uint32_t numSamples,
+  q63_t * realResult,
+  q63_t * imagResult)
+{
+  q63_t real_sum = 0, imag_sum = 0;              /* Temporary result storage */
+  q31_t a0,b0,c0,d0;
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += ((q63_t)a0 * c0) >> 14;
+      imag_sum += ((q63_t)a0 * d0) >> 14;
+      real_sum -= ((q63_t)b0 * d0) >> 14;
+      imag_sum += ((q63_t)b0 * c0) >> 14;
+      
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += ((q63_t)a0 * c0) >> 14;
+      imag_sum += ((q63_t)a0 * d0) >> 14;
+      real_sum -= ((q63_t)b0 * d0) >> 14;
+      imag_sum += ((q63_t)b0 * c0) >> 14;
+      
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += ((q63_t)a0 * c0) >> 14;
+      imag_sum += ((q63_t)a0 * d0) >> 14;
+      real_sum -= ((q63_t)b0 * d0) >> 14;
+      imag_sum += ((q63_t)b0 * c0) >> 14;
+      
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += ((q63_t)a0 * c0) >> 14;
+      imag_sum += ((q63_t)a0 * d0) >> 14;
+      real_sum -= ((q63_t)b0 * d0) >> 14;
+      imag_sum += ((q63_t)b0 * c0) >> 14;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+  }
+
+  /* If the numSamples  is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += ((q63_t)a0 * c0) >> 14;
+      imag_sum += ((q63_t)a0 * d0) >> 14;
+      real_sum -= ((q63_t)b0 * d0) >> 14;
+      imag_sum += ((q63_t)b0 * c0) >> 14;
+
+      /* Decrement the loop counter */
+      blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+      a0 = *pSrcA++;
+      b0 = *pSrcA++;
+      c0 = *pSrcB++;
+      d0 = *pSrcB++;  
+  
+      real_sum += ((q63_t)a0 * c0) >> 14;
+      imag_sum += ((q63_t)a0 * d0) >> 14;
+      real_sum -= ((q63_t)b0 * d0) >> 14;
+      imag_sum += ((q63_t)b0 * c0) >> 14;
+
+      /* Decrement the loop counter */
+      numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  /* Store the real and imaginary results in 16.48 format  */
+  *realResult = real_sum;
+  *imagResult = imag_sum;
+}
+
+/**    
+ * @} end of cmplx_dot_prod group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_f32.c

@@ -0,0 +1,165 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_mag_f32.c    
+*    
+* Description:	Floating-point complex magnitude.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @defgroup cmplx_mag Complex Magnitude    
+ *    
+ * Computes the magnitude of the elements of a complex data vector.    
+ *   
+ * The <code>pSrc</code> points to the source data and    
+ * <code>pDst</code> points to the where the result should be written.    
+ * <code>numSamples</code> specifies the number of complex samples    
+ * in the input array and the data is stored in an interleaved fashion    
+ * (real, imag, real, imag, ...).    
+ * The input array has a total of <code>2*numSamples</code> values;    
+ * the output array has a total of <code>numSamples</code> values.    
+ * The underlying algorithm is used:    
+ *    
+ * <pre>    
+ * for(n=0; n<numSamples; n++) {    
+ *     pDst[n] = sqrt(pSrc[(2*n)+0]^2 + pSrc[(2*n)+1]^2);    
+ * }    
+ * </pre>    
+ *    
+ * There are separate functions for floating-point, Q15, and Q31 data types.    
+ */
+
+/**    
+ * @addtogroup cmplx_mag    
+ * @{    
+ */
+/**    
+ * @brief Floating-point complex magnitude.    
+ * @param[in]       *pSrc points to complex input buffer    
+ * @param[out]      *pDst points to real output buffer    
+ * @param[in]       numSamples number of complex samples in the input vector    
+ * @return none.    
+ *    
+ */
+
+
+void arm_cmplx_mag_f32(
+  float32_t * pSrc,
+  float32_t * pDst,
+  uint32_t numSamples)
+{
+  float32_t realIn, imagIn;                      /* Temporary variables to hold input values */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+
+    /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
+    realIn = *pSrc++;
+    imagIn = *pSrc++;
+    /* store the result in the destination buffer. */
+    arm_sqrt_f32((realIn * realIn) + (imagIn * imagIn), pDst++);
+
+    realIn = *pSrc++;
+    imagIn = *pSrc++;
+    arm_sqrt_f32((realIn * realIn) + (imagIn * imagIn), pDst++);
+
+    realIn = *pSrc++;
+    imagIn = *pSrc++;
+    arm_sqrt_f32((realIn * realIn) + (imagIn * imagIn), pDst++);
+
+    realIn = *pSrc++;
+    imagIn = *pSrc++;
+    arm_sqrt_f32((realIn * realIn) + (imagIn * imagIn), pDst++);
+
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
+    realIn = *pSrc++;
+    imagIn = *pSrc++;
+    /* store the result in the destination buffer. */
+    arm_sqrt_f32((realIn * realIn) + (imagIn * imagIn), pDst++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* out = sqrt((real * real) + (imag * imag)) */
+    realIn = *pSrc++;
+    imagIn = *pSrc++;
+    /* store the result in the destination buffer. */
+    arm_sqrt_f32((realIn * realIn) + (imagIn * imagIn), pDst++);
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of cmplx_mag group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_q15.c

@@ -0,0 +1,153 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_mag_q15.c    
+*    
+* Description:	Q15 complex magnitude.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup cmplx_mag    
+ * @{    
+ */
+
+
+/**    
+ * @brief  Q15 complex magnitude    
+ * @param  *pSrc points to the complex input vector    
+ * @param  *pDst points to the real output vector    
+ * @param  numSamples number of complex samples in the input vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function implements 1.15 by 1.15 multiplications and finally output is converted into 2.14 format.    
+ */
+
+void arm_cmplx_mag_q15(
+  q15_t * pSrc,
+  q15_t * pDst,
+  uint32_t numSamples)
+{
+  q31_t acc0, acc1;                              /* Accumulators */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+  q31_t in1, in2, in3, in4;
+  q31_t acc2, acc3;
+
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+
+    /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
+    in1 = *__SIMD32(pSrc)++;
+    in2 = *__SIMD32(pSrc)++;
+    in3 = *__SIMD32(pSrc)++;
+    in4 = *__SIMD32(pSrc)++;
+
+    acc0 = __SMUAD(in1, in1);
+    acc1 = __SMUAD(in2, in2);
+    acc2 = __SMUAD(in3, in3);
+    acc3 = __SMUAD(in4, in4);
+
+    /* store the result in 2.14 format in the destination buffer. */
+    arm_sqrt_q15((q15_t) ((acc0) >> 17), pDst++);
+    arm_sqrt_q15((q15_t) ((acc1) >> 17), pDst++);
+    arm_sqrt_q15((q15_t) ((acc2) >> 17), pDst++);
+    arm_sqrt_q15((q15_t) ((acc3) >> 17), pDst++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
+    in1 = *__SIMD32(pSrc)++;
+    acc0 = __SMUAD(in1, in1);
+
+    /* store the result in 2.14 format in the destination buffer. */
+    arm_sqrt_q15((q15_t) (acc0 >> 17), pDst++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  q15_t real, imag;                              /* Temporary variables to hold input values */
+
+  while(numSamples > 0u)
+  {
+    /* out = sqrt(real * real + imag * imag) */
+    real = *pSrc++;
+    imag = *pSrc++;
+
+    acc0 = (real * real);
+    acc1 = (imag * imag);
+
+    /* store the result in 2.14 format in the destination buffer. */
+    arm_sqrt_q15((q15_t) (((q63_t) acc0 + acc1) >> 17), pDst++);
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of cmplx_mag group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_q31.c

@@ -0,0 +1,185 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_mag_q31.c    
+*    
+* Description:	Q31 complex magnitude    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupCmplxMath        
+ */
+
+/**        
+ * @addtogroup cmplx_mag        
+ * @{        
+ */
+
+/**        
+ * @brief  Q31 complex magnitude        
+ * @param  *pSrc points to the complex input vector        
+ * @param  *pDst points to the real output vector        
+ * @param  numSamples number of complex samples in the input vector        
+ * @return none.        
+ *        
+ * <b>Scaling and Overflow Behavior:</b>        
+ * \par        
+ * The function implements 1.31 by 1.31 multiplications and finally output is converted into 2.30 format.        
+ * Input down scaling is not required.        
+ */
+
+void arm_cmplx_mag_q31(
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t numSamples)
+{
+  q31_t real, imag;                              /* Temporary variables to hold input values */
+  q31_t acc0, acc1;                              /* Accumulators */
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  q31_t real1, real2, imag1, imag2;              /* Temporary variables to hold input values */
+  q31_t out1, out2, out3, out4;                  /* Accumulators */
+  q63_t mul1, mul2, mul3, mul4;                  /* Temporary variables */
+
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* read complex input from source buffer */
+    real1 = pSrc[0];
+    imag1 = pSrc[1];
+    real2 = pSrc[2];
+    imag2 = pSrc[3];
+
+    /* calculate power of input values */
+    mul1 = (q63_t) real1 *real1;
+    mul2 = (q63_t) imag1 *imag1;
+    mul3 = (q63_t) real2 *real2;
+    mul4 = (q63_t) imag2 *imag2;
+
+    /* get the result to 3.29 format */
+    out1 = (q31_t) (mul1 >> 33);
+    out2 = (q31_t) (mul2 >> 33);
+    out3 = (q31_t) (mul3 >> 33);
+    out4 = (q31_t) (mul4 >> 33);
+
+    /* add real and imaginary accumulators */
+    out1 = out1 + out2;
+    out3 = out3 + out4;
+
+    /* read complex input from source buffer */
+    real1 = pSrc[4];
+    imag1 = pSrc[5];
+    real2 = pSrc[6];
+    imag2 = pSrc[7];
+
+    /* calculate square root */
+    arm_sqrt_q31(out1, &pDst[0]);
+
+    /* calculate power of input values */
+    mul1 = (q63_t) real1 *real1;
+
+    /* calculate square root */
+    arm_sqrt_q31(out3, &pDst[1]);
+
+    /* calculate power of input values */
+    mul2 = (q63_t) imag1 *imag1;
+    mul3 = (q63_t) real2 *real2;
+    mul4 = (q63_t) imag2 *imag2;
+
+    /* get the result to 3.29 format */
+    out1 = (q31_t) (mul1 >> 33);
+    out2 = (q31_t) (mul2 >> 33);
+    out3 = (q31_t) (mul3 >> 33);
+    out4 = (q31_t) (mul4 >> 33);
+
+    /* add real and imaginary accumulators */
+    out1 = out1 + out2;
+    out3 = out3 + out4;
+
+    /* calculate square root */
+    arm_sqrt_q31(out1, &pDst[2]);
+
+    /* increment destination by 8 to process next samples */
+    pSrc += 8u;
+
+    /* calculate square root */
+    arm_sqrt_q31(out3, &pDst[3]);
+
+    /* increment destination by 4 to process next samples */
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  blkCnt = numSamples;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C[0] = sqrt(A[0] * A[0] + A[1] * A[1]) */
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 2.30 format in the destination buffer. */
+    arm_sqrt_q31(acc0 + acc1, pDst++);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of cmplx_mag group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_squared_f32.c

@@ -0,0 +1,215 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_mag_squared_f32.c    
+*    
+* Description:	Floating-point complex magnitude squared.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* ---------------------------------------------------------------------------- */
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupCmplxMath        
+ */
+
+/**        
+ * @defgroup cmplx_mag_squared Complex Magnitude Squared        
+ *        
+ * Computes the magnitude squared of the elements of a complex data vector.        
+ *       
+ * The <code>pSrc</code> points to the source data and        
+ * <code>pDst</code> points to the where the result should be written.        
+ * <code>numSamples</code> specifies the number of complex samples        
+ * in the input array and the data is stored in an interleaved fashion        
+ * (real, imag, real, imag, ...).        
+ * The input array has a total of <code>2*numSamples</code> values;        
+ * the output array has a total of <code>numSamples</code> values.        
+ *        
+ * The underlying algorithm is used:        
+ *        
+ * <pre>        
+ * for(n=0; n<numSamples; n++) {        
+ *     pDst[n] = pSrc[(2*n)+0]^2 + pSrc[(2*n)+1]^2;        
+ * }        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup cmplx_mag_squared        
+ * @{        
+ */
+
+
+/**        
+ * @brief  Floating-point complex magnitude squared        
+ * @param[in]  *pSrc points to the complex input vector        
+ * @param[out]  *pDst points to the real output vector        
+ * @param[in]  numSamples number of complex samples in the input vector        
+ * @return none.        
+ */
+
+void arm_cmplx_mag_squared_f32(
+  float32_t * pSrc,
+  float32_t * pDst,
+  uint32_t numSamples)
+{
+  float32_t real, imag;                          /* Temporary variables to store real and imaginary values */
+  uint32_t blkCnt;                               /* loop counter */
+
+#ifndef ARM_MATH_CM0_FAMILY
+  float32_t real1, real2, real3, real4;          /* Temporary variables to hold real values */
+  float32_t imag1, imag2, imag3, imag4;          /* Temporary variables to hold imaginary values */
+  float32_t mul1, mul2, mul3, mul4;              /* Temporary variables */
+  float32_t mul5, mul6, mul7, mul8;              /* Temporary variables */
+  float32_t out1, out2, out3, out4;              /* Temporary variables to hold output values */
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    /* read real input sample from source buffer */
+    real1 = pSrc[0];
+    /* read imaginary input sample from source buffer */
+    imag1 = pSrc[1];
+
+    /* calculate power of real value */
+    mul1 = real1 * real1;
+
+    /* read real input sample from source buffer */
+    real2 = pSrc[2];
+
+    /* calculate power of imaginary value */
+    mul2 = imag1 * imag1;
+
+    /* read imaginary input sample from source buffer */
+    imag2 = pSrc[3];
+
+    /* calculate power of real value */
+    mul3 = real2 * real2;
+
+    /* read real input sample from source buffer */
+    real3 = pSrc[4];
+
+    /* calculate power of imaginary value */
+    mul4 = imag2 * imag2;
+
+    /* read imaginary input sample from source buffer */
+    imag3 = pSrc[5];
+
+    /* calculate power of real value */
+    mul5 = real3 * real3;
+    /* calculate power of imaginary value */
+    mul6 = imag3 * imag3;
+
+    /* read real input sample from source buffer */
+    real4 = pSrc[6];
+
+    /* accumulate real and imaginary powers */
+    out1 = mul1 + mul2;
+
+    /* read imaginary input sample from source buffer */
+    imag4 = pSrc[7];
+
+    /* accumulate real and imaginary powers */
+    out2 = mul3 + mul4;
+
+    /* calculate power of real value */
+    mul7 = real4 * real4;
+    /* calculate power of imaginary value */
+    mul8 = imag4 * imag4;
+
+    /* store output to destination */
+    pDst[0] = out1;
+
+    /* accumulate real and imaginary powers */
+    out3 = mul5 + mul6;
+
+    /* store output to destination */
+    pDst[1] = out2;
+
+    /* accumulate real and imaginary powers */
+    out4 = mul7 + mul8;
+
+    /* store output to destination */
+    pDst[2] = out3;
+
+    /* increment destination pointer by 8 to process next samples */
+    pSrc += 8u;
+
+    /* store output to destination */
+    pDst[3] = out4;
+
+    /* increment destination pointer by 4 to process next samples */
+    pDst += 4u;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  blkCnt = numSamples;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    real = *pSrc++;
+    imag = *pSrc++;
+
+    /* out = (real * real) + (imag * imag) */
+    /* store the result in the destination buffer. */
+    *pDst++ = (real * real) + (imag * imag);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of cmplx_mag_squared group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_squared_q15.c

@@ -0,0 +1,148 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_mag_squared_q15.c    
+*    
+* Description:	Q15 complex magnitude squared.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup cmplx_mag_squared    
+ * @{    
+ */
+
+/**    
+ * @brief  Q15 complex magnitude squared    
+ * @param  *pSrc points to the complex input vector    
+ * @param  *pDst points to the real output vector    
+ * @param  numSamples number of complex samples in the input vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function implements 1.15 by 1.15 multiplications and finally output is converted into 3.13 format.    
+ */
+
+void arm_cmplx_mag_squared_q15(
+  q15_t * pSrc,
+  q15_t * pDst,
+  uint32_t numSamples)
+{
+  q31_t acc0, acc1;                              /* Accumulators */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+  q31_t in1, in2, in3, in4;
+  q31_t acc2, acc3;
+
+  /*loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    in1 = *__SIMD32(pSrc)++;
+    in2 = *__SIMD32(pSrc)++;
+    in3 = *__SIMD32(pSrc)++;
+    in4 = *__SIMD32(pSrc)++;
+
+    acc0 = __SMUAD(in1, in1);
+    acc1 = __SMUAD(in2, in2);
+    acc2 = __SMUAD(in3, in3);
+    acc3 = __SMUAD(in4, in4);
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ = (q15_t) (acc0 >> 17);
+    *pDst++ = (q15_t) (acc1 >> 17);
+    *pDst++ = (q15_t) (acc2 >> 17);
+    *pDst++ = (q15_t) (acc3 >> 17);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    in1 = *__SIMD32(pSrc)++;
+    acc0 = __SMUAD(in1, in1);
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ = (q15_t) (acc0 >> 17);
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  q15_t real, imag;                              /* Temporary variables to store real and imaginary values */
+
+  while(numSamples > 0u)
+  {
+    /* out = ((real * real) + (imag * imag)) */
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (real * real);
+    acc1 = (imag * imag);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ = (q15_t) (((q63_t) acc0 + acc1) >> 17);
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of cmplx_mag_squared group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mag_squared_q31.c

@@ -0,0 +1,161 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_cmplx_mag_squared_q31.c    
+*    
+* Description:	Q31 complex magnitude squared.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* ---------------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup cmplx_mag_squared    
+ * @{    
+ */
+
+
+/**    
+ * @brief  Q31 complex magnitude squared    
+ * @param  *pSrc points to the complex input vector    
+ * @param  *pDst points to the real output vector    
+ * @param  numSamples number of complex samples in the input vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function implements 1.31 by 1.31 multiplications and finally output is converted into 3.29 format.    
+ * Input down scaling is not required.    
+ */
+
+void arm_cmplx_mag_squared_q31(
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t numSamples)
+{
+  q31_t real, imag;                              /* Temporary variables to store real and imaginary values */
+  q31_t acc0, acc1;                              /* Accumulators */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counter */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[0] = (A[0] * A[0] + A[1] * A[1]) */
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    /* Decrement the loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* out = ((real * real) + (imag * imag)) */
+    real = *pSrc++;
+    imag = *pSrc++;
+    acc0 = (q31_t) (((q63_t) real * real) >> 33);
+    acc1 = (q31_t) (((q63_t) imag * imag) >> 33);
+    /* store the result in 3.29 format in the destination buffer. */
+    *pDst++ = acc0 + acc1;
+
+    /* Decrement the loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of cmplx_mag_squared group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mult_cmplx_f32.c

@@ -0,0 +1,207 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_cmplx_mult_cmplx_f32.c    
+*    
+* Description:	Floating-point complex-by-complex multiplication    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupCmplxMath        
+ */
+
+/**        
+ * @defgroup CmplxByCmplxMult Complex-by-Complex Multiplication        
+ *        
+ * Multiplies a complex vector by another complex vector and generates a complex result.        
+ * The data in the complex arrays is stored in an interleaved fashion        
+ * (real, imag, real, imag, ...).        
+ * The parameter <code>numSamples</code> represents the number of complex        
+ * samples processed.  The complex arrays have a total of <code>2*numSamples</code>        
+ * real values.        
+ *        
+ * The underlying algorithm is used:        
+ *        
+ * <pre>        
+ * for(n=0; n<numSamples; n++) {        
+ *     pDst[(2*n)+0] = pSrcA[(2*n)+0] * pSrcB[(2*n)+0] - pSrcA[(2*n)+1] * pSrcB[(2*n)+1];        
+ *     pDst[(2*n)+1] = pSrcA[(2*n)+0] * pSrcB[(2*n)+1] + pSrcA[(2*n)+1] * pSrcB[(2*n)+0];        
+ * }        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup CmplxByCmplxMult        
+ * @{        
+ */
+
+
+/**        
+ * @brief  Floating-point complex-by-complex multiplication        
+ * @param[in]  *pSrcA points to the first input vector        
+ * @param[in]  *pSrcB points to the second input vector        
+ * @param[out]  *pDst  points to the output vector        
+ * @param[in]  numSamples number of complex samples in each vector        
+ * @return none.        
+ */
+
+void arm_cmplx_mult_cmplx_f32(
+  float32_t * pSrcA,
+  float32_t * pSrcB,
+  float32_t * pDst,
+  uint32_t numSamples)
+{
+  float32_t a1, b1, c1, d1;                      /* Temporary variables to store real and imaginary values */
+  uint32_t blkCnt;                               /* loop counters */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t a2, b2, c2, d2;                      /* Temporary variables to store real and imaginary values */
+  float32_t acc1, acc2, acc3, acc4;
+
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a1 = *pSrcA;                /* A[2 * i] */
+    c1 = *pSrcB;                /* B[2 * i] */
+
+    b1 = *(pSrcA + 1);          /* A[2 * i + 1] */
+    acc1 = a1 * c1;             /* acc1 = A[2 * i] * B[2 * i] */
+
+    a2 = *(pSrcA + 2);          /* A[2 * i + 2] */
+    acc2 = (b1 * c1);           /* acc2 = A[2 * i + 1] * B[2 * i] */
+
+    d1 = *(pSrcB + 1);          /* B[2 * i + 1] */
+    c2 = *(pSrcB + 2);          /* B[2 * i + 2] */
+    acc1 -= b1 * d1;            /* acc1 =      A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1] */
+
+    d2 = *(pSrcB + 3);          /* B[2 * i + 3] */
+    acc3 = a2 * c2;             /* acc3 =       A[2 * i + 2] * B[2 * i + 2] */
+
+    b2 = *(pSrcA + 3);          /* A[2 * i + 3] */
+    acc2 += (a1 * d1);          /* acc2 =      A[2 * i + 1] * B[2 * i] + A[2 * i] * B[2 * i + 1] */
+
+    a1 = *(pSrcA + 4);          /* A[2 * i + 4] */
+    acc4 = (a2 * d2);           /* acc4 =   A[2 * i + 2] * B[2 * i + 3] */
+
+    c1 = *(pSrcB + 4);          /* B[2 * i + 4] */
+    acc3 -= (b2 * d2);          /* acc3 =       A[2 * i + 2] * B[2 * i + 2] - A[2 * i + 3] * B[2 * i + 3] */
+    *pDst = acc1;               /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1] */
+
+    b1 = *(pSrcA + 5);          /* A[2 * i + 5] */
+    acc4 += b2 * c2;            /* acc4 =   A[2 * i + 2] * B[2 * i + 3] + A[2 * i + 3] * B[2 * i + 2] */
+
+    *(pDst + 1) = acc2;         /* C[2 * i + 1] = A[2 * i + 1] * B[2 * i] + A[2 * i] * B[2 * i + 1]  */
+    acc1 = (a1 * c1);
+
+    d1 = *(pSrcB + 5);
+    acc2 = (b1 * c1);
+
+    *(pDst + 2) = acc3;
+    *(pDst + 3) = acc4;
+
+    a2 = *(pSrcA + 6);
+    acc1 -= (b1 * d1);
+
+    c2 = *(pSrcB + 6);
+    acc2 += (a1 * d1);
+
+    b2 = *(pSrcA + 7);
+    acc3 = (a2 * c2);
+
+    d2 = *(pSrcB + 7);
+    acc4 = (b2 * c2);
+
+    *(pDst + 4) = acc1;
+    pSrcA += 8u;
+
+    acc3 -= (b2 * d2);
+    acc4 += (a2 * d2);
+
+    *(pDst + 5) = acc2;
+    pSrcB += 8u;
+
+    *(pDst + 6) = acc3;
+    *(pDst + 7) = acc4;
+
+    pDst += 8u;
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  blkCnt = numSamples;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a1 = *pSrcA++;
+    b1 = *pSrcA++;
+    c1 = *pSrcB++;
+    d1 = *pSrcB++;
+
+    /* store the result in the destination buffer. */
+    *pDst++ = (a1 * c1) - (b1 * d1);
+    *pDst++ = (a1 * d1) + (b1 * c1);
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of CmplxByCmplxMult group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mult_cmplx_q15.c

@@ -0,0 +1,193 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_cmplx_mult_cmplx_q15.c    
+*    
+* Description:	Q15 complex-by-complex multiplication    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup CmplxByCmplxMult    
+ * @{    
+ */
+
+/**    
+ * @brief  Q15 complex-by-complex multiplication    
+ * @param[in]  *pSrcA points to the first input vector    
+ * @param[in]  *pSrcB points to the second input vector    
+ * @param[out]  *pDst  points to the output vector    
+ * @param[in]  numSamples number of complex samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function implements 1.15 by 1.15 multiplications and finally output is converted into 3.13 format.    
+ */
+
+void arm_cmplx_mult_cmplx_q15(
+  q15_t * pSrcA,
+  q15_t * pSrcB,
+  q15_t * pDst,
+  uint32_t numSamples)
+{
+  q15_t a, b, c, d;                              /* Temporary variables to store real and imaginary values */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counters */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17);
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17);
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17);
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17);
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * c) >> 17) - (((q31_t) b * d) >> 17);
+    /* store the result in 3.13 format in the destination buffer. */
+    *pDst++ =
+      (q15_t) (q31_t) (((q31_t) a * d) >> 17) + (((q31_t) b * c) >> 17);
+
+    /* Decrement the blockSize loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of CmplxByCmplxMult group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mult_cmplx_q31.c

@@ -0,0 +1,326 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_cmplx_mult_cmplx_q31.c    
+*    
+* Description:	Q31 complex-by-complex multiplication    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup CmplxByCmplxMult    
+ * @{    
+ */
+
+
+/**    
+ * @brief  Q31 complex-by-complex multiplication    
+ * @param[in]  *pSrcA points to the first input vector    
+ * @param[in]  *pSrcB points to the second input vector    
+ * @param[out]  *pDst  points to the output vector    
+ * @param[in]  numSamples number of complex samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function implements 1.31 by 1.31 multiplications and finally output is converted into 3.29 format.    
+ * Input down scaling is not required.    
+ */
+
+void arm_cmplx_mult_cmplx_q31(
+  q31_t * pSrcA,
+  q31_t * pSrcB,
+  q31_t * pDst,
+  uint32_t numSamples)
+{
+  q31_t a, b, c, d;                              /* Temporary variables to store real and imaginary values */
+  uint32_t blkCnt;                               /* loop counters */
+  q31_t mul1, mul2, mul3, mul4;
+  q31_t out1, out2;
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 1u;
+
+  /* First part of the processing with loop unrolling.  Compute 2 outputs at a time.     
+   ** a second loop below computes the remaining 1 sample. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+  /* If the blockSize is not a multiple of 2, compute any remaining output samples here.     
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x2u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[2 * i] - A[2 * i + 1] * B[2 * i + 1].  */
+    /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i].  */
+    a = *pSrcA++;
+    b = *pSrcA++;
+    c = *pSrcB++;
+    d = *pSrcB++;
+
+    mul1 = (q31_t) (((q63_t) a * c) >> 32);
+    mul2 = (q31_t) (((q63_t) b * d) >> 32);
+    mul3 = (q31_t) (((q63_t) a * d) >> 32);
+    mul4 = (q31_t) (((q63_t) b * c) >> 32);
+
+    mul1 = (mul1 >> 1);
+    mul2 = (mul2 >> 1);
+    mul3 = (mul3 >> 1);
+    mul4 = (mul4 >> 1);
+
+    out1 = mul1 - mul2;
+    out2 = mul3 + mul4;
+
+    /* store the real result in 3.29 format in the destination buffer. */
+    *pDst++ = out1;
+    /* store the imag result in 3.29 format in the destination buffer. */
+    *pDst++ = out2;
+
+    /* Decrement the blockSize loop counter */
+    blkCnt--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of CmplxByCmplxMult group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mult_real_f32.c

@@ -0,0 +1,225 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_cmplx_mult_real_f32.c    
+*    
+* Description:	Floating-point complex by real multiplication    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**        
+ * @ingroup groupCmplxMath        
+ */
+
+/**        
+ * @defgroup CmplxByRealMult Complex-by-Real Multiplication        
+ *        
+ * Multiplies a complex vector by a real vector and generates a complex result.        
+ * The data in the complex arrays is stored in an interleaved fashion        
+ * (real, imag, real, imag, ...).        
+ * The parameter <code>numSamples</code> represents the number of complex        
+ * samples processed.  The complex arrays have a total of <code>2*numSamples</code>        
+ * real values while the real array has a total of <code>numSamples</code>        
+ * real values.        
+ *        
+ * The underlying algorithm is used:        
+ *        
+ * <pre>        
+ * for(n=0; n<numSamples; n++) {        
+ *     pCmplxDst[(2*n)+0] = pSrcCmplx[(2*n)+0] * pSrcReal[n];        
+ *     pCmplxDst[(2*n)+1] = pSrcCmplx[(2*n)+1] * pSrcReal[n];        
+ * }        
+ * </pre>        
+ *        
+ * There are separate functions for floating-point, Q15, and Q31 data types.        
+ */
+
+/**        
+ * @addtogroup CmplxByRealMult        
+ * @{        
+ */
+
+
+/**        
+ * @brief  Floating-point complex-by-real multiplication        
+ * @param[in]  *pSrcCmplx points to the complex input vector        
+ * @param[in]  *pSrcReal points to the real input vector        
+ * @param[out]  *pCmplxDst points to the complex output vector        
+ * @param[in]  numSamples number of samples in each vector        
+ * @return none.        
+ */
+
+void arm_cmplx_mult_real_f32(
+  float32_t * pSrcCmplx,
+  float32_t * pSrcReal,
+  float32_t * pCmplxDst,
+  uint32_t numSamples)
+{
+  float32_t in;                                  /* Temporary variable to store input value */
+  uint32_t blkCnt;                               /* loop counters */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  float32_t inA1, inA2, inA3, inA4;              /* Temporary variables to hold input data */
+  float32_t inA5, inA6, inA7, inA8;              /* Temporary variables to hold input data */
+  float32_t inB1, inB2, inB3, inB4;              /* Temporary variables to hold input data */
+  float32_t out1, out2, out3, out4;              /* Temporary variables to hold output data */
+  float32_t out5, out6, out7, out8;              /* Temporary variables to hold output data */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.        
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[i].            */
+    /* C[2 * i + 1] = A[2 * i + 1] * B[i].        */
+    /* read input from complex input buffer */
+    inA1 = pSrcCmplx[0];
+    inA2 = pSrcCmplx[1];
+    /* read input from real input buffer */
+    inB1 = pSrcReal[0];
+
+    /* read input from complex input buffer */
+    inA3 = pSrcCmplx[2];
+
+    /* multiply complex buffer real input with real buffer input */
+    out1 = inA1 * inB1;
+
+    /* read input from complex input buffer */
+    inA4 = pSrcCmplx[3];
+
+    /* multiply complex buffer imaginary input with real buffer input */
+    out2 = inA2 * inB1;
+
+    /* read input from real input buffer */
+    inB2 = pSrcReal[1];
+    /* read input from complex input buffer */
+    inA5 = pSrcCmplx[4];
+
+    /* multiply complex buffer real input with real buffer input */
+    out3 = inA3 * inB2;
+
+    /* read input from complex input buffer */
+    inA6 = pSrcCmplx[5];
+    /* read input from real input buffer */
+    inB3 = pSrcReal[2];
+
+    /* multiply complex buffer imaginary input with real buffer input */
+    out4 = inA4 * inB2;
+
+    /* read input from complex input buffer */
+    inA7 = pSrcCmplx[6];
+
+    /* multiply complex buffer real input with real buffer input */
+    out5 = inA5 * inB3;
+
+    /* read input from complex input buffer */
+    inA8 = pSrcCmplx[7];
+
+    /* multiply complex buffer imaginary input with real buffer input */
+    out6 = inA6 * inB3;
+
+    /* read input from real input buffer */
+    inB4 = pSrcReal[3];
+
+    /* store result to destination bufer */
+    pCmplxDst[0] = out1;
+
+    /* multiply complex buffer real input with real buffer input */
+    out7 = inA7 * inB4;
+
+    /* store result to destination bufer */
+    pCmplxDst[1] = out2;
+
+    /* multiply complex buffer imaginary input with real buffer input */
+    out8 = inA8 * inB4;
+
+    /* store result to destination bufer */
+    pCmplxDst[2] = out3;
+    pCmplxDst[3] = out4;
+    pCmplxDst[4] = out5;
+
+    /* incremnet complex input buffer by 8 to process next samples */
+    pSrcCmplx += 8u;
+
+    /* store result to destination bufer */
+    pCmplxDst[5] = out6;
+
+    /* increment real input buffer by 4 to process next samples */
+    pSrcReal += 4u;
+
+    /* store result to destination bufer */
+    pCmplxDst[6] = out7;
+    pCmplxDst[7] = out8;
+
+    /* increment destination buffer by 8 to process next sampels */
+    pCmplxDst += 8u;
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.        
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+  blkCnt = numSamples;
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[i].            */
+    /* C[2 * i + 1] = A[2 * i + 1] * B[i].        */
+    in = *pSrcReal++;
+    /* store the result in the destination buffer. */
+    *pCmplxDst++ = (*pSrcCmplx++) * (in);
+    *pCmplxDst++ = (*pSrcCmplx++) * (in);
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+}
+
+/**        
+ * @} end of CmplxByRealMult group        
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mult_real_q15.c

@@ -0,0 +1,203 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. October 2015
+* $Revision: 	V.1.4.5 a
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_cmplx_mult_real_q15.c    
+*    
+* Description:	Q15 complex by real multiplication    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup CmplxByRealMult    
+ * @{    
+ */
+
+
+/**    
+ * @brief  Q15 complex-by-real multiplication    
+ * @param[in]  *pSrcCmplx points to the complex input vector    
+ * @param[in]  *pSrcReal points to the real input vector    
+ * @param[out]  *pCmplxDst points to the complex output vector    
+ * @param[in]  numSamples number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.    
+ */
+
+void arm_cmplx_mult_real_q15(
+  q15_t * pSrcCmplx,
+  q15_t * pSrcReal,
+  q15_t * pCmplxDst,
+  uint32_t numSamples)
+{
+  q15_t in;                                      /* Temporary variable to store input value */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counters */
+  q31_t inA1, inA2;                              /* Temporary variables to hold input data */
+  q31_t inB1;                                    /* Temporary variables to hold input data */
+  q15_t out1, out2, out3, out4;                  /* Temporary variables to hold output data */
+  q31_t mul1, mul2, mul3, mul4;                  /* Temporary variables to hold intermediate data */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[i].            */
+    /* C[2 * i + 1] = A[2 * i + 1] * B[i].        */
+    /* read complex number both real and imaginary from complex input buffer */
+    inA1 = *__SIMD32(pSrcCmplx)++;
+    /* read two real values at a time from real input buffer */
+    inB1 = *__SIMD32(pSrcReal)++;
+    /* read complex number both real and imaginary from complex input buffer */
+    inA2 = *__SIMD32(pSrcCmplx)++;
+
+    /* multiply complex number with real numbers */
+#ifndef ARM_MATH_BIG_ENDIAN
+
+    mul1 = (q31_t) ((q15_t) (inA1) * (q15_t) (inB1));
+    mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1));
+    mul3 = (q31_t) ((q15_t) (inA2) * (q15_t) (inB1 >> 16));
+    mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) (inB1 >> 16));
+
+#else
+
+    mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1 >> 16));
+    mul1 = (q31_t) ((q15_t) inA1 * (q15_t) (inB1 >> 16));
+    mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) inB1);
+    mul3 = (q31_t) ((q15_t) inA2 * (q15_t) inB1);
+
+#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
+
+    /* saturate the result */
+    out1 = (q15_t) __SSAT(mul1 >> 15u, 16);
+    out2 = (q15_t) __SSAT(mul2 >> 15u, 16);
+    out3 = (q15_t) __SSAT(mul3 >> 15u, 16);
+    out4 = (q15_t) __SSAT(mul4 >> 15u, 16);
+
+    /* pack real and imaginary outputs and store them to destination */
+    *__SIMD32(pCmplxDst)++ = __PKHBT(out1, out2, 16);
+    *__SIMD32(pCmplxDst)++ = __PKHBT(out3, out4, 16);
+
+    inA1 = *__SIMD32(pSrcCmplx)++;
+    inB1 = *__SIMD32(pSrcReal)++;
+    inA2 = *__SIMD32(pSrcCmplx)++;
+
+#ifndef ARM_MATH_BIG_ENDIAN
+
+    mul1 = (q31_t) ((q15_t) (inA1) * (q15_t) (inB1));
+    mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1));
+    mul3 = (q31_t) ((q15_t) (inA2) * (q15_t) (inB1 >> 16));
+    mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) (inB1 >> 16));
+
+#else
+
+    mul2 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1 >> 16));
+    mul1 = (q31_t) ((q15_t) inA1 * (q15_t) (inB1 >> 16));
+    mul4 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) inB1);
+    mul3 = (q31_t) ((q15_t) inA2 * (q15_t) inB1);
+
+#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
+
+    out1 = (q15_t) __SSAT(mul1 >> 15u, 16);
+    out2 = (q15_t) __SSAT(mul2 >> 15u, 16);
+    out3 = (q15_t) __SSAT(mul3 >> 15u, 16);
+    out4 = (q15_t) __SSAT(mul4 >> 15u, 16);
+
+    *__SIMD32(pCmplxDst)++ = __PKHBT(out1, out2, 16);
+    *__SIMD32(pCmplxDst)++ = __PKHBT(out3, out4, 16);
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[i].            */
+    /* C[2 * i + 1] = A[2 * i + 1] * B[i].        */
+    in = *pSrcReal++;
+    /* store the result in the destination buffer. */
+    *pCmplxDst++ =
+      (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16);
+    *pCmplxDst++ =
+      (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16);
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* realOut = realA * realB.            */
+    /* imagOut = imagA * realB.                */
+    in = *pSrcReal++;
+    /* store the result in the destination buffer. */
+    *pCmplxDst++ =
+      (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16);
+    *pCmplxDst++ =
+      (q15_t) __SSAT((((q31_t) (*pSrcCmplx++) * (in)) >> 15), 16);
+
+    /* Decrement the numSamples loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of CmplxByRealMult group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ComplexMathFunctions/arm_cmplx_mult_real_q31.c

@@ -0,0 +1,223 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_cmplx_mult_real_q31.c    
+*    
+* Description:	Q31 complex by real multiplication    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupCmplxMath    
+ */
+
+/**    
+ * @addtogroup CmplxByRealMult    
+ * @{    
+ */
+
+
+/**    
+ * @brief  Q31 complex-by-real multiplication    
+ * @param[in]  *pSrcCmplx points to the complex input vector    
+ * @param[in]  *pSrcReal points to the real input vector    
+ * @param[out]  *pCmplxDst points to the complex output vector    
+ * @param[in]  numSamples number of samples in each vector    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * The function uses saturating arithmetic.    
+ * Results outside of the allowable Q31 range[0x80000000 0x7FFFFFFF] will be saturated.    
+ */
+
+void arm_cmplx_mult_real_q31(
+  q31_t * pSrcCmplx,
+  q31_t * pSrcReal,
+  q31_t * pCmplxDst,
+  uint32_t numSamples)
+{
+  q31_t inA1;                                    /* Temporary variable to store input value */
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+  uint32_t blkCnt;                               /* loop counters */
+  q31_t inA2, inA3, inA4;                        /* Temporary variables to hold input data */
+  q31_t inB1, inB2;                              /* Temporary variabels to hold input data */
+  q31_t out1, out2, out3, out4;                  /* Temporary variables to hold output data */
+
+  /* loop Unrolling */
+  blkCnt = numSamples >> 2u;
+
+  /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+   ** a second loop below computes the remaining 1 to 3 samples. */
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[i].            */
+    /* C[2 * i + 1] = A[2 * i + 1] * B[i].        */
+    /* read real input from complex input buffer */
+    inA1 = *pSrcCmplx++;
+    inA2 = *pSrcCmplx++;
+    /* read input from real input bufer */
+    inB1 = *pSrcReal++;
+    inB2 = *pSrcReal++;
+    /* read imaginary input from complex input buffer */
+    inA3 = *pSrcCmplx++;
+    inA4 = *pSrcCmplx++;
+
+    /* multiply complex input with real input */
+    out1 = ((q63_t) inA1 * inB1) >> 32;
+    out2 = ((q63_t) inA2 * inB1) >> 32;
+    out3 = ((q63_t) inA3 * inB2) >> 32;
+    out4 = ((q63_t) inA4 * inB2) >> 32;
+
+    /* sature the result */
+    out1 = __SSAT(out1, 31);
+    out2 = __SSAT(out2, 31);
+    out3 = __SSAT(out3, 31);
+    out4 = __SSAT(out4, 31);
+
+    /* get result in 1.31 format */
+    out1 = out1 << 1;
+    out2 = out2 << 1;
+    out3 = out3 << 1;
+    out4 = out4 << 1;
+
+    /* store the result to destination buffer */
+    *pCmplxDst++ = out1;
+    *pCmplxDst++ = out2;
+    *pCmplxDst++ = out3;
+    *pCmplxDst++ = out4;
+
+    /* read real input from complex input buffer */
+    inA1 = *pSrcCmplx++;
+    inA2 = *pSrcCmplx++;
+    /* read input from real input bufer */
+    inB1 = *pSrcReal++;
+    inB2 = *pSrcReal++;
+    /* read imaginary input from complex input buffer */
+    inA3 = *pSrcCmplx++;
+    inA4 = *pSrcCmplx++;
+
+    /* multiply complex input with real input */
+    out1 = ((q63_t) inA1 * inB1) >> 32;
+    out2 = ((q63_t) inA2 * inB1) >> 32;
+    out3 = ((q63_t) inA3 * inB2) >> 32;
+    out4 = ((q63_t) inA4 * inB2) >> 32;
+
+    /* sature the result */
+    out1 = __SSAT(out1, 31);
+    out2 = __SSAT(out2, 31);
+    out3 = __SSAT(out3, 31);
+    out4 = __SSAT(out4, 31);
+
+    /* get result in 1.31 format */
+    out1 = out1 << 1;
+    out2 = out2 << 1;
+    out3 = out3 << 1;
+    out4 = out4 << 1;
+
+    /* store the result to destination buffer */
+    *pCmplxDst++ = out1;
+    *pCmplxDst++ = out2;
+    *pCmplxDst++ = out3;
+    *pCmplxDst++ = out4;
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+
+  /* If the numSamples is not a multiple of 4, compute any remaining output samples here.    
+   ** No loop unrolling is used. */
+  blkCnt = numSamples % 0x4u;
+
+  while(blkCnt > 0u)
+  {
+    /* C[2 * i] = A[2 * i] * B[i].            */
+    /* C[2 * i + 1] = A[2 * i + 1] * B[i].        */
+    /* read real input from complex input buffer */
+    inA1 = *pSrcCmplx++;
+    inA2 = *pSrcCmplx++;
+    /* read input from real input bufer */
+    inB1 = *pSrcReal++;
+
+    /* multiply complex input with real input */
+    out1 = ((q63_t) inA1 * inB1) >> 32;
+    out2 = ((q63_t) inA2 * inB1) >> 32;
+
+    /* sature the result */
+    out1 = __SSAT(out1, 31);
+    out2 = __SSAT(out2, 31);
+
+    /* get result in 1.31 format */
+    out1 = out1 << 1;
+    out2 = out2 << 1;
+
+    /* store the result to destination buffer */
+    *pCmplxDst++ = out1;
+    *pCmplxDst++ = out2;
+
+    /* Decrement the numSamples loop counter */
+    blkCnt--;
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  while(numSamples > 0u)
+  {
+    /* realOut = realA * realB.            */
+    /* imagReal = imagA * realB.               */
+    inA1 = *pSrcReal++;
+    /* store the result in the destination buffer. */
+    *pCmplxDst++ =
+      (q31_t) clip_q63_to_q31(((q63_t) * pSrcCmplx++ * inA1) >> 31);
+    *pCmplxDst++ =
+      (q31_t) clip_q63_to_q31(((q63_t) * pSrcCmplx++ * inA1) >> 31);
+
+    /* Decrement the numSamples loop counter */
+    numSamples--;
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of CmplxByRealMult group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_pid_init_f32.c

@@ -0,0 +1,87 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_pid_init_f32.c    
+*    
+* Description:	Floating-point PID Control initialization function    
+*				   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* ------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+ /**    
+ * @addtogroup PID    
+ * @{    
+ */
+
+/**    
+ * @brief  Initialization function for the floating-point PID Control.   
+ * @param[in,out] *S points to an instance of the PID structure.   
+ * @param[in]     resetStateFlag  flag to reset the state. 0 = no change in state & 1 = reset the state.   
+ * @return none.   
+ * \par Description:   
+ * \par    
+ * The <code>resetStateFlag</code> specifies whether to set state to zero or not. \n   
+ * The function computes the structure fields: <code>A0</code>, <code>A1</code> <code>A2</code>    
+ * using the proportional gain( \c Kp), integral gain( \c Ki) and derivative gain( \c Kd)    
+ * also sets the state variables to all zeros.    
+ */
+
+void arm_pid_init_f32(
+  arm_pid_instance_f32 * S,
+  int32_t resetStateFlag)
+{
+
+  /* Derived coefficient A0 */
+  S->A0 = S->Kp + S->Ki + S->Kd;
+
+  /* Derived coefficient A1 */
+  S->A1 = (-S->Kp) - ((float32_t) 2.0 * S->Kd);
+
+  /* Derived coefficient A2 */
+  S->A2 = S->Kd;
+
+  /* Check whether state needs reset or not */
+  if(resetStateFlag)
+  {
+    /* Clear the state buffer.  The size will be always 3 samples */
+    memset(S->state, 0, 3u * sizeof(float32_t));
+  }
+
+}
+
+/**    
+ * @} end of PID group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_pid_init_q15.c

@@ -0,0 +1,122 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_pid_init_q15.c    
+*    
+* Description:	Q15 PID Control initialization function    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+ /**    
+ * @addtogroup PID    
+ * @{    
+ */
+
+/**    
+ * @details    
+ * @param[in,out] *S points to an instance of the Q15 PID structure.    
+ * @param[in]     resetStateFlag  flag to reset the state. 0 = no change in state 1 = reset the state.    
+ * @return none.    
+ * \par Description:   
+ * \par    
+ * The <code>resetStateFlag</code> specifies whether to set state to zero or not. \n   
+ * The function computes the structure fields: <code>A0</code>, <code>A1</code> <code>A2</code>    
+ * using the proportional gain( \c Kp), integral gain( \c Ki) and derivative gain( \c Kd)    
+ * also sets the state variables to all zeros.    
+ */
+
+void arm_pid_init_q15(
+  arm_pid_instance_q15 * S,
+  int32_t resetStateFlag)
+{
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  /* Derived coefficient A0 */
+  S->A0 = __QADD16(__QADD16(S->Kp, S->Ki), S->Kd);
+
+  /* Derived coefficients and pack into A1 */
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+  S->A1 = __PKHBT(-__QADD16(__QADD16(S->Kd, S->Kd), S->Kp), S->Kd, 16);
+
+#else
+
+  S->A1 = __PKHBT(S->Kd, -__QADD16(__QADD16(S->Kd, S->Kd), S->Kp), 16);
+
+#endif /*      #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+  /* Check whether state needs reset or not */
+  if(resetStateFlag)
+  {
+    /* Clear the state buffer.  The size will be always 3 samples */
+    memset(S->state, 0, 3u * sizeof(q15_t));
+  }
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  q31_t temp;                                    /*to store the sum */
+
+  /* Derived coefficient A0 */
+  temp = S->Kp + S->Ki + S->Kd;
+  S->A0 = (q15_t) __SSAT(temp, 16);
+
+  /* Derived coefficients and pack into A1 */
+  temp = -(S->Kd + S->Kd + S->Kp);
+  S->A1 = (q15_t) __SSAT(temp, 16);
+  S->A2 = S->Kd;
+
+
+
+  /* Check whether state needs reset or not */
+  if(resetStateFlag)
+  {
+    /* Clear the state buffer.  The size will be always 3 samples */
+    memset(S->state, 0, 3u * sizeof(q15_t));
+  }
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+}
+
+/**    
+ * @} end of PID group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_pid_init_q31.c

@@ -0,0 +1,107 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_pid_init_q31.c    
+*    
+* Description:	Q31 PID Control initialization function     
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* ------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+ /**    
+ * @addtogroup PID    
+ * @{    
+ */
+
+/**    
+ * @brief  Initialization function for the Q31 PID Control.   
+ * @param[in,out] *S points to an instance of the Q31 PID structure.   
+ * @param[in]     resetStateFlag  flag to reset the state. 0 = no change in state 1 = reset the state.   
+ * @return none.    
+ * \par Description:   
+ * \par    
+ * The <code>resetStateFlag</code> specifies whether to set state to zero or not. \n   
+ * The function computes the structure fields: <code>A0</code>, <code>A1</code> <code>A2</code>    
+ * using the proportional gain( \c Kp), integral gain( \c Ki) and derivative gain( \c Kd)    
+ * also sets the state variables to all zeros.    
+ */
+
+void arm_pid_init_q31(
+  arm_pid_instance_q31 * S,
+  int32_t resetStateFlag)
+{
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  /* Derived coefficient A0 */
+  S->A0 = __QADD(__QADD(S->Kp, S->Ki), S->Kd);
+
+  /* Derived coefficient A1 */
+  S->A1 = -__QADD(__QADD(S->Kd, S->Kd), S->Kp);
+
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  q31_t temp;
+
+  /* Derived coefficient A0 */
+  temp = clip_q63_to_q31((q63_t) S->Kp + S->Ki);
+  S->A0 = clip_q63_to_q31((q63_t) temp + S->Kd);
+
+  /* Derived coefficient A1 */
+  temp = clip_q63_to_q31((q63_t) S->Kd + S->Kd);
+  S->A1 = -clip_q63_to_q31((q63_t) temp + S->Kp);
+
+#endif /* #ifndef ARM_MATH_CM0_FAMILY */
+
+  /* Derived coefficient A2 */
+  S->A2 = S->Kd;
+
+  /* Check whether state needs reset or not */
+  if(resetStateFlag)
+  {
+    /* Clear the state buffer.  The size will be always 3 samples */
+    memset(S->state, 0, 3u * sizeof(q31_t));
+  }
+
+}
+
+/**    
+ * @} end of PID group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_pid_reset_f32.c

@@ -0,0 +1,65 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_pid_reset_f32.c    
+*    
+* Description:	Floating-point PID Control reset function   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* ------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+ /**    
+ * @addtogroup PID    
+ * @{    
+ */
+
+/**    
+* @brief  Reset function for the floating-point PID Control.   
+* @param[in] *S	Instance pointer of PID control data structure.   
+* @return none.    
+* \par Description:   
+* The function resets the state buffer to zeros.    
+*/
+void arm_pid_reset_f32(
+  arm_pid_instance_f32 * S)
+{
+
+  /* Clear the state buffer.  The size will be always 3 samples */
+  memset(S->state, 0, 3u * sizeof(float32_t));
+}
+
+/**    
+ * @} end of PID group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_pid_reset_q15.c

@@ -0,0 +1,64 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_pid_reset_q15.c    
+*    
+* Description:	Q15 PID Control reset function   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+ /**    
+ * @addtogroup PID    
+ * @{    
+ */
+
+/**    
+* @brief  Reset function for the Q15 PID Control.   
+* @param[in] *S		Instance pointer of PID control data structure.   
+* @return none.    
+* \par Description:   
+* The function resets the state buffer to zeros.    
+*/
+void arm_pid_reset_q15(
+  arm_pid_instance_q15 * S)
+{
+  /* Reset state to zero, The size will be always 3 samples */
+  memset(S->state, 0, 3u * sizeof(q15_t));
+}
+
+/**    
+ * @} end of PID group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_pid_reset_q31.c

@@ -0,0 +1,65 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_pid_reset_q31.c    
+*    
+* Description:	Q31 PID Control reset function   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.    
+* ------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+ /**    
+ * @addtogroup PID    
+ * @{    
+ */
+
+/**    
+* @brief  Reset function for the Q31 PID Control.   
+* @param[in] *S	Instance pointer of PID control data structure.   
+* @return none.    
+* \par Description:   
+* The function resets the state buffer to zeros.    
+*/
+void arm_pid_reset_q31(
+  arm_pid_instance_q31 * S)
+{
+
+  /* Clear the state buffer.  The size will be always 3 samples */
+  memset(S->state, 0, 3u * sizeof(q31_t));
+}
+
+/**    
+ * @} end of PID group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_sin_cos_f32.c

@@ -0,0 +1,149 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sin_cos_f32.c    
+*    
+* Description:	Sine and Cosine calculation for floating-point values.   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+#include "arm_common_tables.h"
+
+/**    
+ * @ingroup groupController    
+ */
+
+/**    
+ * @defgroup SinCos Sine Cosine   
+ *    
+ * Computes the trigonometric sine and cosine values using a combination of table lookup   
+ * and linear interpolation.     
+ * There are separate functions for Q31 and floating-point data types.   
+ * The input to the floating-point version is in degrees while the   
+ * fixed-point Q31 have a scaled input with the range   
+ * [-1 0.9999] mapping to [-180 +180] degrees.   
+ *
+ * The floating point function also allows values that are out of the usual range. When this happens, the function will
+ * take extra time to adjust the input value to the range of [-180 180].
+ *   
+ * The implementation is based on table lookup using 360 values together with linear interpolation.   
+ * The steps used are:   
+ *  -# Calculation of the nearest integer table index.   
+ *  -# Compute the fractional portion (fract) of the input.   
+ *  -# Fetch the value corresponding to \c index from sine table to \c y0 and also value from \c index+1 to \c y1.      
+ *  -# Sine value is computed as <code> *psinVal = y0 + (fract * (y1 - y0))</code>.    
+ *  -# Fetch the value corresponding to \c index from cosine table to \c y0 and also value from \c index+1 to \c y1.      
+ *  -# Cosine value is computed as <code> *pcosVal = y0 + (fract * (y1 - y0))</code>.    
+ */
+
+ /**    
+ * @addtogroup SinCos    
+ * @{    
+ */
+
+/**    
+ * @brief  Floating-point sin_cos function.   
+ * @param[in]  theta    input value in degrees    
+ * @param[out] *pSinVal points to the processed sine output.    
+ * @param[out] *pCosVal points to the processed cos output.    
+ * @return none.   
+ */
+
+void arm_sin_cos_f32(
+  float32_t theta,
+  float32_t * pSinVal,
+  float32_t * pCosVal)
+{
+  float32_t fract, in;                             /* Temporary variables for input, output */
+  uint16_t indexS, indexC;                         /* Index variable */
+  float32_t f1, f2, d1, d2;                        /* Two nearest output values */
+  int32_t n;
+  float32_t findex, Dn, Df, temp;
+
+  /* input x is in degrees */
+  /* Scale the input, divide input by 360, for cosine add 0.25 (pi/2) to read sine table */
+  in = theta * 0.00277777777778f;
+
+  /* Calculation of floor value of input */
+  n = (int32_t) in;
+
+  /* Make negative values towards -infinity */
+  if(in < 0.0f)
+  {
+    n--;
+  }
+  /* Map input value to [0 1] */
+  in = in - (float32_t) n;
+
+  /* Calculation of index of the table */
+  findex = (float32_t) FAST_MATH_TABLE_SIZE * in;
+  indexS = ((uint16_t)findex) & 0x1ff;
+  indexC = (indexS + (FAST_MATH_TABLE_SIZE / 4)) & 0x1ff;
+
+  /* fractional value calculation */
+  fract = findex - (float32_t) indexS;
+
+  /* Read two nearest values of input value from the cos & sin tables */
+  f1 = sinTable_f32[indexC+0];
+  f2 = sinTable_f32[indexC+1];
+  d1 = -sinTable_f32[indexS+0];
+  d2 = -sinTable_f32[indexS+1];
+
+  Dn = 0.0122718463030f; // delta between the two points (fixed), in this case 2*pi/FAST_MATH_TABLE_SIZE
+  Df = f2 - f1; // delta between the values of the functions
+  temp = Dn*(d1 + d2) - 2*Df;
+  temp = fract*temp + (3*Df - (d2 + 2*d1)*Dn);
+  temp = fract*temp + d1*Dn;
+
+  /* Calculation of cosine value */
+  *pCosVal = fract*temp + f1;
+  
+  /* Read two nearest values of input value from the cos & sin tables */
+  f1 = sinTable_f32[indexS+0];
+  f2 = sinTable_f32[indexS+1];
+  d1 = sinTable_f32[indexC+0];
+  d2 = sinTable_f32[indexC+1];
+
+  Df = f2 - f1; // delta between the values of the functions
+  temp = Dn*(d1 + d2) - 2*Df;
+  temp = fract*temp + (3*Df - (d2 + 2*d1)*Dn);
+  temp = fract*temp + d1*Dn;
+  
+  /* Calculation of sine value */
+  *pSinVal = fract*temp + f1;
+}
+/**    
+ * @} end of SinCos group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/ControllerFunctions/arm_sin_cos_q31.c

@@ -0,0 +1,122 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sin_cos_q31.c    
+*    
+* Description:	Cosine & Sine calculation for Q31 values.   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+#include "arm_common_tables.h"
+
+/**    
+ * @ingroup groupController    
+ */
+
+ /**    
+ * @addtogroup SinCos    
+ * @{    
+ */
+
+/**    
+ * @brief  Q31 sin_cos function.   
+ * @param[in]  theta    scaled input value in degrees    
+ * @param[out] *pSinVal points to the processed sine output.    
+ * @param[out] *pCosVal points to the processed cosine output.    
+ * @return none.   
+ *    
+ * The Q31 input value is in the range [-1 0.999999] and is mapped to a degree value in the range [-180 179].   
+ *    
+ */
+
+void arm_sin_cos_q31(
+  q31_t theta,
+  q31_t * pSinVal,
+  q31_t * pCosVal)
+{
+  q31_t fract;                                 /* Temporary variables for input, output */
+  uint16_t indexS, indexC;                     /* Index variable */
+  q31_t f1, f2, d1, d2;                        /* Two nearest output values */
+  q31_t Dn, Df;
+  q63_t temp;
+  
+  /* Calculate the nearest index */
+  indexS = (uint32_t)theta >> CONTROLLER_Q31_SHIFT;
+  indexC = (indexS + 128) & 0x1ff;
+
+  /* Calculation of fractional value */
+  fract = (theta - (indexS << CONTROLLER_Q31_SHIFT)) << 8;
+  
+  /* Read two nearest values of input value from the cos & sin tables */
+  f1 = sinTable_q31[indexC+0];
+  f2 = sinTable_q31[indexC+1];
+  d1 = -sinTable_q31[indexS+0];
+  d2 = -sinTable_q31[indexS+1];
+
+  Dn = 0x1921FB5; // delta between the two points (fixed), in this case 2*pi/FAST_MATH_TABLE_SIZE
+  Df = f2 - f1; // delta between the values of the functions
+  temp = Dn*((q63_t)d1 + d2);
+  temp = temp - ((q63_t)Df << 32);
+  temp = (q63_t)fract*(temp >> 31);
+  temp = temp + ((3*(q63_t)Df << 31) - (d2 + ((q63_t)d1 << 1))*Dn);
+  temp = (q63_t)fract*(temp >> 31);
+  temp = temp + (q63_t)d1*Dn;
+  temp = (q63_t)fract*(temp >> 31);
+
+  /* Calculation of cosine value */
+  *pCosVal = clip_q63_to_q31((temp >> 31) + (q63_t)f1);
+  
+  /* Read two nearest values of input value from the cos & sin tables */
+  f1 = sinTable_q31[indexS+0];
+  f2 = sinTable_q31[indexS+1];
+  d1 = sinTable_q31[indexC+0];
+  d2 = sinTable_q31[indexC+1];
+
+  Df = f2 - f1; // delta between the values of the functions
+  temp = Dn*((q63_t)d1 + d2);
+  temp = temp - ((q63_t)Df << 32);
+  temp = (q63_t)fract*(temp >> 31);
+  temp = temp + ((3*(q63_t)Df << 31) - (d2 + ((q63_t)d1 << 1))*Dn);
+  temp = (q63_t)fract*(temp >> 31);
+  temp = temp + (q63_t)d1*Dn;
+  temp = (q63_t)fract*(temp >> 31);
+  
+  /* Calculation of sine value */
+  *pSinVal = clip_q63_to_q31((temp >> 31) + (q63_t)f1);
+}
+
+/**    
+ * @} end of SinCos group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_cos_f32.c

@@ -0,0 +1,127 @@
+/* ----------------------------------------------------------------------
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.
+*
+* $Date:        21. September 2015
+* $Revision:    V.1.4.5 a
+*
+* Project:      CMSIS DSP Library
+* Title:        arm_cos_f32.c
+*
+* Description:  Fast cosine calculation for floating-point values.
+*
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*
+* Redistribution and use in source and binary forms, with or without
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+#include "arm_common_tables.h"
+/**
+ * @ingroup groupFastMath
+ */
+
+/**
+ * @defgroup cos Cosine
+ *
+ * Computes the trigonometric cosine function using a combination of table lookup
+ * and linear interpolation.  There are separate functions for
+ * Q15, Q31, and floating-point data types.
+ * The input to the floating-point version is in radians while the
+ * fixed-point Q15 and Q31 have a scaled input with the range
+ * [0 +0.9999] mapping to [0 2*pi).  The fixed-point range is chosen so that a
+ * value of 2*pi wraps around to 0.
+ *
+ * The implementation is based on table lookup using 256 values together with linear interpolation.
+ * The steps used are:
+ *  -# Calculation of the nearest integer table index
+ *  -# Compute the fractional portion (fract) of the table index.
+ *  -# The final result equals <code>(1.0f-fract)*a + fract*b;</code>
+ *
+ * where
+ * <pre>
+ *    b=Table[index+0];
+ *    c=Table[index+1];
+ * </pre>
+ */
+
+ /**
+ * @addtogroup cos
+ * @{
+ */
+
+/**
+ * @brief  Fast approximation to the trigonometric cosine function for floating-point data.
+ * @param[in] x input value in radians.
+ * @return cos(x).
+ */
+
+float32_t arm_cos_f32(
+  float32_t x)
+{
+  float32_t cosVal, fract, in;                   /* Temporary variables for input, output */
+  uint16_t index;                                /* Index variable */
+  float32_t a, b;                                /* Two nearest output values */
+  int32_t n;
+  float32_t findex;
+
+  /* input x is in radians */
+  /* Scale the input to [0 1] range from [0 2*PI] , divide input by 2*pi, add 0.25 (pi/2) to read sine table */
+  in = x * 0.159154943092f + 0.25f;
+
+  /* Calculation of floor value of input */
+  n = (int32_t) in;
+
+  /* Make negative values towards -infinity */
+  if(in < 0.0f)
+  {
+    n--;
+  }
+
+  /* Map input value to [0 1] */
+  in = in - (float32_t) n;
+
+  /* Calculation of index of the table */
+  findex = (float32_t) FAST_MATH_TABLE_SIZE * in;
+  index = ((uint16_t)findex) & 0x1ff;
+
+  /* fractional value calculation */
+  fract = findex - (float32_t) index;
+
+  /* Read two nearest values of input value from the cos table */
+  a = sinTable_f32[index];
+  b = sinTable_f32[index+1];
+
+  /* Linear interpolation process */
+  cosVal = (1.0f-fract)*a + fract*b;
+
+  /* Return the output value */
+  return (cosVal);
+}
+
+/**
+ * @} end of cos group
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_cos_q15.c

@@ -0,0 +1,96 @@
+/* ----------------------------------------------------------------------
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.
+*
+* $Date:        07. September 2015
+* $Revision:    V.1.4.5 a
+*
+* Project:      CMSIS DSP Library
+* Title:        arm_cos_q15.c
+*
+* Description:  Fast cosine calculation for Q15 values.
+*
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*
+* Redistribution and use in source and binary forms, with or without
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+#include "arm_common_tables.h"
+
+/**
+ * @ingroup groupFastMath
+ */
+
+ /**
+ * @addtogroup cos
+ * @{
+ */
+
+/**
+ * @brief Fast approximation to the trigonometric cosine function for Q15 data.
+ * @param[in] x Scaled input value in radians.
+ * @return  cos(x).
+ *
+ * The Q15 input value is in the range [0 +0.9999] and is mapped to a radian
+ * value in the range [0 2*pi).
+ */
+
+q15_t arm_cos_q15(
+  q15_t x)
+{
+  q15_t cosVal;                                  /* Temporary variables for input, output */
+  int32_t index;                                 /* Index variables */
+  q15_t a, b;                                    /* Four nearest output values */
+  q15_t fract;                                   /* Temporary values for fractional values */
+
+  /* add 0.25 (pi/2) to read sine table */
+  x = (uint16_t)x + 0x2000;
+  if(x < 0)
+  {   /* convert negative numbers to corresponding positive ones */
+      x = (uint16_t)x + 0x8000;
+  }
+
+  /* Calculate the nearest index */
+  index = (uint32_t)x >> FAST_MATH_Q15_SHIFT;
+
+  /* Calculation of fractional value */
+  fract = (x - (index << FAST_MATH_Q15_SHIFT)) << 9;
+
+  /* Read two nearest values of input value from the sin table */
+  a = sinTable_q15[index];
+  b = sinTable_q15[index+1];
+
+  /* Linear interpolation process */
+  cosVal = (q31_t)(0x8000-fract)*a >> 16;
+  cosVal = (q15_t)((((q31_t)cosVal << 16) + ((q31_t)fract*b)) >> 16);
+
+  return cosVal << 1;
+}
+
+/**
+ * @} end of cos group
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_cos_q31.c

@@ -0,0 +1,96 @@
+/* ----------------------------------------------------------------------
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.
+*
+* $Date:        07. September 2015
+* $Revision:    V.1.4.5 a
+*
+* Project:      CMSIS DSP Library
+* Title:        arm_cos_q31.c
+*
+* Description: Fast cosine calculation for Q31 values.
+*
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*
+* Redistribution and use in source and binary forms, with or without
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+#include "arm_common_tables.h"
+
+/**
+ * @ingroup groupFastMath
+ */
+
+ /**
+ * @addtogroup cos
+ * @{
+ */
+
+/**
+ * @brief Fast approximation to the trigonometric cosine function for Q31 data.
+ * @param[in] x Scaled input value in radians.
+ * @return  cos(x).
+ *
+ * The Q31 input value is in the range [0 +0.9999] and is mapped to a radian
+ * value in the range [0 2*pi).
+ */
+
+q31_t arm_cos_q31(
+  q31_t x)
+{
+  q31_t cosVal;                                  /* Temporary variables for input, output */
+  int32_t index;                                 /* Index variables */
+  q31_t a, b;                                    /* Four nearest output values */
+  q31_t fract;                                   /* Temporary values for fractional values */
+
+  /* add 0.25 (pi/2) to read sine table */
+  x = (uint32_t)x + 0x20000000;
+  if(x < 0)
+  {   /* convert negative numbers to corresponding positive ones */
+      x = (uint32_t)x + 0x80000000;
+  }
+
+  /* Calculate the nearest index */
+  index = (uint32_t)x >> FAST_MATH_Q31_SHIFT;
+
+  /* Calculation of fractional value */
+  fract = (x - (index << FAST_MATH_Q31_SHIFT)) << 9;
+
+  /* Read two nearest values of input value from the sin table */
+  a = sinTable_q31[index];
+  b = sinTable_q31[index+1];
+
+  /* Linear interpolation process */
+  cosVal = (q63_t)(0x80000000-fract)*a >> 32;
+  cosVal = (q31_t)((((q63_t)cosVal << 32) + ((q63_t)fract*b)) >> 32);
+
+  return cosVal << 1;
+}
+
+/**
+ * @} end of cos group
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_sin_f32.c

@@ -0,0 +1,133 @@
+/* ----------------------------------------------------------------------
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.
+*
+* $Date:        21. September 2015
+* $Revision:    V.1.4.5 a
+*
+* Project:      CMSIS DSP Library
+* Title:        arm_sin_f32.c
+*
+* Description:  Fast sine calculation for floating-point values.
+*
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*
+* Redistribution and use in source and binary forms, with or without
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+#include "arm_common_tables.h"
+#include <math.h>
+
+/**
+ * @ingroup groupFastMath
+ */
+
+/**
+ * @defgroup sin Sine
+ *
+ * Computes the trigonometric sine function using a combination of table lookup
+ * and linear interpolation.  There are separate functions for
+ * Q15, Q31, and floating-point data types.
+ * The input to the floating-point version is in radians while the
+ * fixed-point Q15 and Q31 have a scaled input with the range
+ * [0 +0.9999] mapping to [0 2*pi).  The fixed-point range is chosen so that a
+ * value of 2*pi wraps around to 0.
+ *
+ * The implementation is based on table lookup using 256 values together with linear interpolation.
+ * The steps used are:
+ *  -# Calculation of the nearest integer table index
+ *  -# Compute the fractional portion (fract) of the table index.
+ *  -# The final result equals <code>(1.0f-fract)*a + fract*b;</code>
+ *
+ * where
+ * <pre>
+ *    b=Table[index+0];
+ *    c=Table[index+1];
+ * </pre>
+ */
+
+/**
+ * @addtogroup sin
+ * @{
+ */
+
+/**
+ * @brief  Fast approximation to the trigonometric sine function for floating-point data.
+ * @param[in] x input value in radians.
+ * @return  sin(x).
+ */
+
+float32_t arm_sin_f32(
+  float32_t x)
+{
+  float32_t sinVal, fract, in;                           /* Temporary variables for input, output */
+  uint16_t index;                                        /* Index variable */
+  float32_t a, b;                                        /* Two nearest output values */
+  int32_t n;
+  float32_t findex;
+
+  /* input x is in radians */
+  /* Scale the input to [0 1] range from [0 2*PI] , divide input by 2*pi */
+  in = x * 0.159154943092f;
+
+  /* Calculation of floor value of input */
+  n = (int32_t) in;
+
+  /* Make negative values towards -infinity */
+  if(x < 0.0f)
+  {
+    n--;
+  }
+
+  /* Map input value to [0 1] */
+  in = in - (float32_t) n;
+
+  /* Calculation of index of the table */
+  findex = (float32_t) FAST_MATH_TABLE_SIZE * in;
+  if (findex >= 512.0f) {
+    findex -= 512.0f;
+  }
+
+  index = ((uint16_t)findex) & 0x1ff;
+
+  /* fractional value calculation */
+  fract = findex - (float32_t) index;
+
+  /* Read two nearest values of input value from the sin table */
+  a = sinTable_f32[index];
+  b = sinTable_f32[index+1];
+
+  /* Linear interpolation process */
+  sinVal = (1.0f-fract)*a + fract*b;
+
+  /* Return the output value */
+  return (sinVal);
+}
+
+/**
+ * @} end of sin group
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_sin_q15.c

@@ -0,0 +1,88 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sin_q15.c    
+*    
+* Description:	Fast sine calculation for Q15 values.   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+#include "arm_common_tables.h"
+
+/**    
+ * @ingroup groupFastMath    
+ */
+
+ /**    
+ * @addtogroup sin    
+ * @{    
+ */
+
+/**   
+ * @brief Fast approximation to the trigonometric sine function for Q15 data.   
+ * @param[in] x Scaled input value in radians.   
+ * @return  sin(x).   
+ *   
+ * The Q15 input value is in the range [0 +0.9999] and is mapped to a radian value in the range [0 2*pi).
+ */
+
+q15_t arm_sin_q15(
+  q15_t x)
+{
+  q15_t sinVal;                                  /* Temporary variables for input, output */
+  int32_t index;                                 /* Index variables */
+  q15_t a, b;                                    /* Four nearest output values */
+  q15_t fract;                                   /* Temporary values for fractional values */
+
+  /* Calculate the nearest index */
+  index = (uint32_t)x >> FAST_MATH_Q15_SHIFT;
+
+  /* Calculation of fractional value */
+  fract = (x - (index << FAST_MATH_Q15_SHIFT)) << 9;
+
+  /* Read two nearest values of input value from the sin table */
+  a = sinTable_q15[index];
+  b = sinTable_q15[index+1];
+
+  /* Linear interpolation process */
+  sinVal = (q31_t)(0x8000-fract)*a >> 16;
+  sinVal = (q15_t)((((q31_t)sinVal << 16) + ((q31_t)fract*b)) >> 16);
+
+  return sinVal << 1;
+}
+
+/**    
+ * @} end of sin group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_sin_q31.c

@@ -0,0 +1,87 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:		arm_sin_q31.c    
+*    
+* Description:	Fast sine calculation for Q31 values.   
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+#include "arm_common_tables.h"
+
+/**    
+ * @ingroup groupFastMath    
+ */
+
+ /**    
+ * @addtogroup sin    
+ * @{    
+ */
+
+/**   
+ * @brief Fast approximation to the trigonometric sine function for Q31 data.
+ * @param[in] x Scaled input value in radians.
+ * @return  sin(x).
+ *
+ * The Q31 input value is in the range [0 +0.9999] and is mapped to a radian value in the range [0 2*pi). */
+
+q31_t arm_sin_q31(
+  q31_t x)
+{
+  q31_t sinVal;                                  /* Temporary variables for input, output */
+  int32_t index;                                 /* Index variables */
+  q31_t a, b;                                    /* Four nearest output values */
+  q31_t fract;                                   /* Temporary values for fractional values */
+
+  /* Calculate the nearest index */
+  index = (uint32_t)x >> FAST_MATH_Q31_SHIFT;
+
+  /* Calculation of fractional value */
+  fract = (x - (index << FAST_MATH_Q31_SHIFT)) << 9;
+
+  /* Read two nearest values of input value from the sin table */
+  a = sinTable_q31[index];
+  b = sinTable_q31[index+1];
+
+  /* Linear interpolation process */
+  sinVal = (q63_t)(0x80000000-fract)*a >> 32;
+  sinVal = (q31_t)((((q63_t)sinVal << 32) + ((q63_t)fract*b)) >> 32);
+
+  return sinVal << 1;
+}
+
+/**    
+ * @} end of sin group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_sqrt_q15.c

@@ -0,0 +1,155 @@
+/* ----------------------------------------------------------------------     
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.  
+*     
+* $Date:        19. October 2015
+* $Revision: 	V.1.4.5 a
+*     
+* Project:      CMSIS DSP Library  
+* Title:		arm_sqrt_q15.c     
+*     
+* Description:	Q15 square root function.    
+*     
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+#include "arm_math.h"
+#include "arm_common_tables.h"
+
+
+/**     
+ * @ingroup groupFastMath     
+ */
+
+/**     
+ * @addtogroup SQRT     
+ * @{     
+ */
+
+  /**    
+   * @brief  Q15 square root function.    
+   * @param[in]   in     input value.  The range of the input value is [0 +1) or 0x0000 to 0x7FFF.    
+   * @param[out]  *pOut  square root of input value.    
+   * @return The function returns ARM_MATH_SUCCESS if the input value is positive
+   * and ARM_MATH_ARGUMENT_ERROR if the input is negative.  For
+   * negative inputs, the function returns *pOut = 0.
+   */
+
+arm_status arm_sqrt_q15(
+  q15_t in,
+  q15_t * pOut)
+{
+  q15_t number, temp1, var1, signBits1, half;
+  q31_t bits_val1;
+  float32_t temp_float1;
+  union
+  {
+    q31_t fracval;
+    float32_t floatval;
+  } tempconv;
+
+  number = in;
+
+  /* If the input is a positive number then compute the signBits. */
+  if(number > 0)
+  {
+    signBits1 = __CLZ(number) - 17;
+
+    /* Shift by the number of signBits1 */
+    if((signBits1 % 2) == 0)
+    {
+      number = number << signBits1;
+    }
+    else
+    {
+      number = number << (signBits1 - 1);
+    }
+
+    /* Calculate half value of the number */
+    half = number >> 1;
+    /* Store the number for later use */
+    temp1 = number;
+
+    /* Convert to float */
+    temp_float1 = number * 3.051757812500000e-005f;
+    /*Store as integer */
+    tempconv.floatval = temp_float1;
+    bits_val1 = tempconv.fracval;
+    /* Subtract the shifted value from the magic number to give intial guess */
+    bits_val1 = 0x5f3759df - (bits_val1 >> 1);  /* gives initial guess */
+    /* Store as float */
+    tempconv.fracval = bits_val1;
+    temp_float1 = tempconv.floatval;
+    /* Convert to integer format */
+    var1 = (q31_t) (temp_float1 * 16384);
+
+    /* 1st iteration */
+    var1 = ((q15_t) ((q31_t) var1 * (0x3000 -
+                                     ((q15_t)
+                                      ((((q15_t)
+                                         (((q31_t) var1 * var1) >> 15)) *
+                                        (q31_t) half) >> 15))) >> 15)) << 2;
+    /* 2nd iteration */
+    var1 = ((q15_t) ((q31_t) var1 * (0x3000 -
+                                     ((q15_t)
+                                      ((((q15_t)
+                                         (((q31_t) var1 * var1) >> 15)) *
+                                        (q31_t) half) >> 15))) >> 15)) << 2;
+    /* 3rd iteration */
+    var1 = ((q15_t) ((q31_t) var1 * (0x3000 -
+                                     ((q15_t)
+                                      ((((q15_t)
+                                         (((q31_t) var1 * var1) >> 15)) *
+                                        (q31_t) half) >> 15))) >> 15)) << 2;
+
+    /* Multiply the inverse square root with the original value */
+    var1 = ((q15_t) (((q31_t) temp1 * var1) >> 15)) << 1;
+
+    /* Shift the output down accordingly */
+    if((signBits1 % 2) == 0)
+    {
+      var1 = var1 >> (signBits1 / 2);
+    }
+    else
+    {
+      var1 = var1 >> ((signBits1 - 1) / 2);
+    }
+    *pOut = var1;
+
+    return (ARM_MATH_SUCCESS);
+  }
+  /* If the number is a negative number then store zero as its square root value */
+  else
+  {
+    *pOut = 0;
+    return (ARM_MATH_ARGUMENT_ERROR);
+  }
+}
+
+/**     
+ * @} end of SQRT group     
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FastMathFunctions/arm_sqrt_q31.c

@@ -0,0 +1,153 @@
+/* ----------------------------------------------------------------------     
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.  
+*     
+* $Date:        19. October 2015
+* $Revision: 	V.1.4.5 a
+*     
+* Project:      CMSIS DSP Library  
+* Title:		arm_sqrt_q31.c     
+*     
+* Description:	Q31 square root function.    
+*     
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+#include "arm_math.h"
+#include "arm_common_tables.h"
+
+/**     
+ * @ingroup groupFastMath     
+ */
+
+/**     
+ * @addtogroup SQRT     
+ * @{     
+ */
+
+/**    
+ * @brief Q31 square root function.    
+ * @param[in]   in    input value.  The range of the input value is [0 +1) or 0x00000000 to 0x7FFFFFFF.    
+ * @param[out]  *pOut square root of input value.    
+ * @return The function returns ARM_MATH_SUCCESS if the input value is positive
+ * and ARM_MATH_ARGUMENT_ERROR if the input is negative.  For
+ * negative inputs, the function returns *pOut = 0.
+ */
+
+arm_status arm_sqrt_q31(
+  q31_t in,
+  q31_t * pOut)
+{
+  q31_t number, temp1, bits_val1, var1, signBits1, half;
+  float32_t temp_float1;
+  union
+  {
+      q31_t fracval;
+      float32_t floatval;
+  } tempconv;
+
+  number = in;
+
+  /* If the input is a positive number then compute the signBits. */
+  if(number > 0)
+  {
+    signBits1 = __CLZ(number) - 1;
+
+    /* Shift by the number of signBits1 */
+    if((signBits1 % 2) == 0)
+    {
+      number = number << signBits1;
+    }
+    else
+    {
+      number = number << (signBits1 - 1);
+    }
+
+    /* Calculate half value of the number */
+    half = number >> 1;
+    /* Store the number for later use */
+    temp1 = number;
+
+    /*Convert to float */
+    temp_float1 = number * 4.6566128731e-010f;
+    /*Store as integer */
+    tempconv.floatval = temp_float1;
+    bits_val1 = tempconv.fracval;
+    /* Subtract the shifted value from the magic number to give intial guess */
+    bits_val1 = 0x5f3759df - (bits_val1 >> 1);  /* gives initial guess */
+    /* Store as float */
+    tempconv.fracval = bits_val1;
+    temp_float1 = tempconv.floatval;
+    /* Convert to integer format */
+    var1 = (q31_t) (temp_float1 * 1073741824);
+
+    /* 1st iteration */
+    var1 = ((q31_t) ((q63_t) var1 * (0x30000000 -
+                                     ((q31_t)
+                                      ((((q31_t)
+                                         (((q63_t) var1 * var1) >> 31)) *
+                                        (q63_t) half) >> 31))) >> 31)) << 2;
+    /* 2nd iteration */
+    var1 = ((q31_t) ((q63_t) var1 * (0x30000000 -
+                                     ((q31_t)
+                                      ((((q31_t)
+                                         (((q63_t) var1 * var1) >> 31)) *
+                                        (q63_t) half) >> 31))) >> 31)) << 2;
+    /* 3rd iteration */
+    var1 = ((q31_t) ((q63_t) var1 * (0x30000000 -
+                                     ((q31_t)
+                                      ((((q31_t)
+                                         (((q63_t) var1 * var1) >> 31)) *
+                                        (q63_t) half) >> 31))) >> 31)) << 2;
+
+    /* Multiply the inverse square root with the original value */
+    var1 = ((q31_t) (((q63_t) temp1 * var1) >> 31)) << 1;
+
+    /* Shift the output down accordingly */
+    if((signBits1 % 2) == 0)
+    {
+      var1 = var1 >> (signBits1 / 2);
+    }
+    else
+    {
+      var1 = var1 >> ((signBits1 - 1) / 2);
+    }
+    *pOut = var1;
+
+    return (ARM_MATH_SUCCESS);
+  }
+  /* If the number is a negative number then store zero as its square root value */
+  else
+  {
+    *pOut = 0;
+    return (ARM_MATH_ARGUMENT_ERROR);
+  }
+}
+
+/**     
+ * @} end of SQRT group     
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_32x64_init_q31.c

@@ -0,0 +1,110 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_biquad_cascade_df1_32x64_init_q31.c    
+*    
+* Description:	High precision Q31 Biquad cascade filter initialization function.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1_32x64    
+ * @{    
+ */
+
+/**    
+ * @details    
+ *    
+ * @param[in,out] *S           	points to an instance of the high precision Q31 Biquad cascade filter structure.    
+ * @param[in]     numStages     number of 2nd order stages in the filter.    
+ * @param[in]     *pCoeffs      points to the filter coefficients.    
+ * @param[in]     *pState       points to the state buffer.    
+ * @param[in]     postShift     Shift to be applied after the accumulator.  Varies according to the coefficients format.    
+ * @return        none    
+ *    
+ * <b>Coefficient and State Ordering:</b>    
+ *    
+ * \par    
+ * The coefficients are stored in the array <code>pCoeffs</code> in the following order:    
+ * <pre>    
+ *     {b10, b11, b12, a11, a12, b20, b21, b22, a21, a22, ...}    
+ * </pre>    
+ * where <code>b1x</code> and <code>a1x</code> are the coefficients for the first stage,    
+ * <code>b2x</code> and <code>a2x</code> are the coefficients for the second stage,    
+ * and so on.  The <code>pCoeffs</code> array contains a total of <code>5*numStages</code> values.    
+ *    
+ * \par    
+ * The <code>pState</code> points to state variables array and size of each state variable is 1.63 format.    
+ * Each Biquad stage has 4 state variables <code>x[n-1], x[n-2], y[n-1],</code> and <code>y[n-2]</code>.    
+ * The state variables are arranged in the state array as:    
+ * <pre>    
+ *     {x[n-1], x[n-2], y[n-1], y[n-2]}    
+ * </pre>    
+ * The 4 state variables for stage 1 are first, then the 4 state variables for stage 2, and so on.    
+ * The state array has a total length of <code>4*numStages</code> values.    
+ * The state variables are updated after each block of data is processed; the coefficients are untouched.    
+ */
+
+void arm_biquad_cas_df1_32x64_init_q31(
+  arm_biquad_cas_df1_32x64_ins_q31 * S,
+  uint8_t numStages,
+  q31_t * pCoeffs,
+  q63_t * pState,
+  uint8_t postShift)
+{
+  /* Assign filter stages */
+  S->numStages = numStages;
+
+  /* Assign postShift to be applied to the output */
+  S->postShift = postShift;
+
+  /* Assign coefficient pointer */
+  S->pCoeffs = pCoeffs;
+
+  /* Clear state buffer and size is always 4 * numStages */
+  memset(pState, 0, (4u * (uint32_t) numStages) * sizeof(q63_t));
+
+  /* Assign state pointer */
+  S->pState = pState;
+}
+
+/**    
+ * @} end of BiquadCascadeDF1_32x64 group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_32x64_q31.c

@@ -0,0 +1,561 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. October 2015
+* $Revision: 	V.1.4.5 a
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_biquad_cascade_df1_32x64_q31.c    
+*    
+* Description:	High precision Q31 Biquad cascade filter processing function    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.   
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @defgroup BiquadCascadeDF1_32x64 High Precision Q31 Biquad Cascade Filter    
+ *    
+ * This function implements a high precision Biquad cascade filter which operates on    
+ * Q31 data values.  The filter coefficients are in 1.31 format and the state variables    
+ * are in 1.63 format.  The double precision state variables reduce quantization noise    
+ * in the filter and provide a cleaner output.    
+ * These filters are particularly useful when implementing filters in which the    
+ * singularities are close to the unit circle.  This is common for low pass or high    
+ * pass filters with very low cutoff frequencies.    
+ *    
+ * The function operates on blocks of input and output data    
+ * and each call to the function processes <code>blockSize</code> samples through    
+ * the filter. <code>pSrc</code> and <code>pDst</code> points to input and output arrays    
+ * containing <code>blockSize</code> Q31 values.    
+ *    
+ * \par Algorithm    
+ * Each Biquad stage implements a second order filter using the difference equation:    
+ * <pre>    
+ *     y[n] = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]    
+ * </pre>    
+ * A Direct Form I algorithm is used with 5 coefficients and 4 state variables per stage.    
+ * \image html Biquad.gif "Single Biquad filter stage"    
+ * Coefficients <code>b0, b1, and b2 </code> multiply the input signal <code>x[n]</code> and are referred to as the feedforward coefficients.    
+ * Coefficients <code>a1</code> and <code>a2</code> multiply the output signal <code>y[n]</code> and are referred to as the feedback coefficients.    
+ * Pay careful attention to the sign of the feedback coefficients.    
+ * Some design tools use the difference equation    
+ * <pre>    
+ *     y[n] = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] - a1 * y[n-1] - a2 * y[n-2]    
+ * </pre>    
+ * In this case the feedback coefficients <code>a1</code> and <code>a2</code> must be negated when used with the CMSIS DSP Library.    
+ *    
+ * \par    
+ * Higher order filters are realized as a cascade of second order sections.    
+ * <code>numStages</code> refers to the number of second order stages used.    
+ * For example, an 8th order filter would be realized with <code>numStages=4</code> second order stages.    
+ * \image html BiquadCascade.gif "8th order filter using a cascade of Biquad stages"    
+ * A 9th order filter would be realized with <code>numStages=5</code> second order stages with the coefficients for one of the stages configured as a first order filter (<code>b2=0</code> and <code>a2=0</code>).    
+ *    
+ * \par    
+ * The <code>pState</code> points to state variables array .    
+ * Each Biquad stage has 4 state variables <code>x[n-1], x[n-2], y[n-1],</code> and <code>y[n-2]</code> and each state variable in 1.63 format to improve precision.    
+ * The state variables are arranged in the array as:    
+ * <pre>    
+ *     {x[n-1], x[n-2], y[n-1], y[n-2]}    
+ * </pre>    
+ *    
+ * \par    
+ * The 4 state variables for stage 1 are first, then the 4 state variables for stage 2, and so on.    
+ * The state array has a total length of <code>4*numStages</code> values of data in 1.63 format.    
+ * The state variables are updated after each block of data is processed; the coefficients are untouched.    
+ *    
+ * \par Instance Structure    
+ * The coefficients and state variables for a filter are stored together in an instance data structure.    
+ * A separate instance structure must be defined for each filter.    
+ * Coefficient arrays may be shared among several instances while state variable arrays cannot be shared.    
+ *    
+ * \par Init Function    
+ * There is also an associated initialization function which performs the following operations:    
+ * - Sets the values of the internal structure fields.    
+ * - Zeros out the values in the state buffer.    
+ * To do this manually without calling the init function, assign the follow subfields of the instance structure:
+ * numStages, pCoeffs, postShift, pState. Also set all of the values in pState to zero. 
+ *
+ * \par    
+ * Use of the initialization function is optional.    
+ * However, if the initialization function is used, then the instance structure cannot be placed into a const data section.    
+ * To place an instance structure into a const data section, the instance structure must be manually initialized.    
+ * Set the values in the state buffer to zeros before static initialization.    
+ * For example, to statically initialize the filter instance structure use    
+ * <pre>    
+ *     arm_biquad_cas_df1_32x64_ins_q31 S1 = {numStages, pState, pCoeffs, postShift};    
+ * </pre>    
+ * where <code>numStages</code> is the number of Biquad stages in the filter; <code>pState</code> is the address of the state buffer;    
+ * <code>pCoeffs</code> is the address of the coefficient buffer; <code>postShift</code> shift to be applied which is described in detail below.    
+ * \par Fixed-Point Behavior    
+ * Care must be taken while using Biquad Cascade 32x64 filter function.    
+ * Following issues must be considered:    
+ * - Scaling of coefficients    
+ * - Filter gain    
+ * - Overflow and saturation    
+ *    
+ * \par    
+ * Filter coefficients are represented as fractional values and    
+ * restricted to lie in the range <code>[-1 +1)</code>.    
+ * The processing function has an additional scaling parameter <code>postShift</code>    
+ * which allows the filter coefficients to exceed the range <code>[+1 -1)</code>.    
+ * At the output of the filter's accumulator is a shift register which shifts the result by <code>postShift</code> bits.    
+ * \image html BiquadPostshift.gif "Fixed-point Biquad with shift by postShift bits after accumulator"    
+ * This essentially scales the filter coefficients by <code>2^postShift</code>.    
+ * For example, to realize the coefficients    
+ * <pre>    
+ *    {1.5, -0.8, 1.2, 1.6, -0.9}    
+ * </pre>    
+ * set the Coefficient array to:    
+ * <pre>    
+ *    {0.75, -0.4, 0.6, 0.8, -0.45}    
+ * </pre>    
+ * and set <code>postShift=1</code>    
+ *    
+ * \par    
+ * The second thing to keep in mind is the gain through the filter.    
+ * The frequency response of a Biquad filter is a function of its coefficients.    
+ * It is possible for the gain through the filter to exceed 1.0 meaning that the filter increases the amplitude of certain frequencies.    
+ * This means that an input signal with amplitude < 1.0 may result in an output > 1.0 and these are saturated or overflowed based on the implementation of the filter.    
+ * To avoid this behavior the filter needs to be scaled down such that its peak gain < 1.0 or the input signal must be scaled down so that the combination of input and filter are never overflowed.    
+ *    
+ * \par    
+ * The third item to consider is the overflow and saturation behavior of the fixed-point Q31 version.    
+ * This is described in the function specific documentation below.    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1_32x64    
+ * @{    
+ */
+
+/**    
+ * @details    
+    
+ * @param[in]  *S points to an instance of the high precision Q31 Biquad cascade filter.    
+ * @param[in]  *pSrc points to the block of input data.    
+ * @param[out] *pDst points to the block of output data.    
+ * @param[in]  blockSize number of samples to process.    
+ * @return none.    
+ *    
+ * \par    
+ * The function is implemented using an internal 64-bit accumulator.    
+ * The accumulator has a 2.62 format and maintains full precision of the intermediate multiplication results but provides only a single guard bit.    
+ * Thus, if the accumulator result overflows it wraps around rather than clip.    
+ * In order to avoid overflows completely the input signal must be scaled down by 2 bits and lie in the range [-0.25 +0.25).    
+ * After all 5 multiply-accumulates are performed, the 2.62 accumulator is shifted by <code>postShift</code> bits and the result truncated to    
+ * 1.31 format by discarding the low 32 bits.    
+ *    
+ * \par    
+ * Two related functions are provided in the CMSIS DSP library.    
+ * <code>arm_biquad_cascade_df1_q31()</code> implements a Biquad cascade with 32-bit coefficients and state variables with a Q63 accumulator.    
+ * <code>arm_biquad_cascade_df1_fast_q31()</code> implements a Biquad cascade with 32-bit coefficients and state variables with a Q31 accumulator.    
+ */
+
+void arm_biquad_cas_df1_32x64_q31(
+  const arm_biquad_cas_df1_32x64_ins_q31 * S,
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  q31_t *pIn = pSrc;                             /*  input pointer initialization  */
+  q31_t *pOut = pDst;                            /*  output pointer initialization */
+  q63_t *pState = S->pState;                     /*  state pointer initialization  */
+  q31_t *pCoeffs = S->pCoeffs;                   /*  coeff pointer initialization  */
+  q63_t acc;                                     /*  accumulator                   */
+  q31_t Xn1, Xn2;                                /*  Input Filter state variables        */
+  q63_t Yn1, Yn2;                                /*  Output Filter state variables        */
+  q31_t b0, b1, b2, a1, a2;                      /*  Filter coefficients           */
+  q31_t Xn;                                      /*  temporary input               */
+  int32_t shift = (int32_t) S->postShift + 1;    /*  Shift to be applied to the output */
+  uint32_t sample, stage = S->numStages;         /*  loop counters                     */
+  q31_t acc_l, acc_h;                            /*  temporary output               */
+  uint32_t uShift = ((uint32_t) S->postShift + 1u);
+  uint32_t lShift = 32u - uShift;                /*  Shift to be applied to the output */
+
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  do
+  {
+    /* Reading the coefficients */
+    b0 = *pCoeffs++;
+    b1 = *pCoeffs++;
+    b2 = *pCoeffs++;
+    a1 = *pCoeffs++;
+    a2 = *pCoeffs++;
+
+    /* Reading the state values */
+    Xn1 = (q31_t) (pState[0]);
+    Xn2 = (q31_t) (pState[1]);
+    Yn1 = pState[2];
+    Yn2 = pState[3];
+
+    /* Apply loop unrolling and compute 4 output values simultaneously. */
+    /* The variable acc hold output value that is being computed and    
+     * stored in the destination buffer    
+     * acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]    
+     */
+
+    sample = blockSize >> 2u;
+
+    /* First part of the processing with loop unrolling. Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(sample > 0u)
+    {
+      /* Read the input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+
+      /* acc =  b0 * x[n] */
+      acc = (q63_t) Xn *b0;
+
+      /* acc +=  b1 * x[n-1] */
+      acc += (q63_t) Xn1 *b1;
+
+      /* acc +=  b[2] * x[n-2] */
+      acc += (q63_t) Xn2 *b2;
+
+      /* acc +=  a1 * y[n-1] */
+      acc += mult32x64(Yn1, a1);
+
+      /* acc +=  a2 * y[n-2] */
+      acc += mult32x64(Yn2, a2);
+
+      /* The result is converted to 1.63 , Yn2 variable is reused */
+      Yn2 = acc << shift;
+
+      /* Calc lower part of acc */
+      acc_l = acc & 0xffffffff;
+
+      /* Calc upper part of acc */
+      acc_h = (acc >> 32) & 0xffffffff;
+
+      /* Apply shift for lower part of acc and upper part of acc */
+      acc_h = (uint32_t) acc_l >> lShift | acc_h << uShift;
+
+      /* Store the output in the destination buffer in 1.31 format. */
+      *pOut = acc_h;
+
+      /* Read the second input into Xn2, to reuse the value */
+      Xn2 = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+
+      /* acc +=  b1 * x[n-1] */
+      acc = (q63_t) Xn *b1;
+
+      /* acc =  b0 * x[n] */
+      acc += (q63_t) Xn2 *b0;
+
+      /* acc +=  b[2] * x[n-2] */
+      acc += (q63_t) Xn1 *b2;
+
+      /* acc +=  a1 * y[n-1] */
+      acc += mult32x64(Yn2, a1);
+
+      /* acc +=  a2 * y[n-2] */
+      acc += mult32x64(Yn1, a2);
+
+      /* The result is converted to 1.63, Yn1 variable is reused */
+      Yn1 = acc << shift;
+
+      /* Calc lower part of acc */
+      acc_l = acc & 0xffffffff;
+
+      /* Calc upper part of acc */
+      acc_h = (acc >> 32) & 0xffffffff;
+
+      /* Apply shift for lower part of acc and upper part of acc */
+      acc_h = (uint32_t) acc_l >> lShift | acc_h << uShift;
+
+      /* Read the third input into Xn1, to reuse the value */
+      Xn1 = *pIn++;
+
+      /* The result is converted to 1.31 */
+      /* Store the output in the destination buffer. */
+      *(pOut + 1u) = acc_h;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+
+      /* acc =  b0 * x[n] */
+      acc = (q63_t) Xn1 *b0;
+
+      /* acc +=  b1 * x[n-1] */
+      acc += (q63_t) Xn2 *b1;
+
+      /* acc +=  b[2] * x[n-2] */
+      acc += (q63_t) Xn *b2;
+
+      /* acc +=  a1 * y[n-1] */
+      acc += mult32x64(Yn1, a1);
+
+      /* acc +=  a2 * y[n-2] */
+      acc += mult32x64(Yn2, a2);
+
+      /* The result is converted to 1.63, Yn2 variable is reused  */
+      Yn2 = acc << shift;
+
+      /* Calc lower part of acc */
+      acc_l = acc & 0xffffffff;
+
+      /* Calc upper part of acc */
+      acc_h = (acc >> 32) & 0xffffffff;
+
+      /* Apply shift for lower part of acc and upper part of acc */
+      acc_h = (uint32_t) acc_l >> lShift | acc_h << uShift;
+
+      /* Store the output in the destination buffer in 1.31 format. */
+      *(pOut + 2u) = acc_h;
+
+      /* Read the fourth input into Xn, to reuse the value */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      acc = (q63_t) Xn *b0;
+
+      /* acc +=  b1 * x[n-1] */
+      acc += (q63_t) Xn1 *b1;
+
+      /* acc +=  b[2] * x[n-2] */
+      acc += (q63_t) Xn2 *b2;
+
+      /* acc +=  a1 * y[n-1] */
+      acc += mult32x64(Yn2, a1);
+
+      /* acc +=  a2 * y[n-2] */
+      acc += mult32x64(Yn1, a2);
+
+      /* The result is converted to 1.63, Yn1 variable is reused  */
+      Yn1 = acc << shift;
+
+      /* Calc lower part of acc */
+      acc_l = acc & 0xffffffff;
+
+      /* Calc upper part of acc */
+      acc_h = (acc >> 32) & 0xffffffff;
+
+      /* Apply shift for lower part of acc and upper part of acc */
+      acc_h = (uint32_t) acc_l >> lShift | acc_h << uShift;
+
+      /* Store the output in the destination buffer in 1.31 format. */
+      *(pOut + 3u) = acc_h;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc    */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+
+      /* update output pointer */
+      pOut += 4u;
+
+      /* decrement the loop counter */
+      sample--;
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+     ** No loop unrolling is used. */
+    sample = (blockSize & 0x3u);
+
+    while(sample > 0u)
+    {
+      /* Read the input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+
+      /* acc =  b0 * x[n] */
+      acc = (q63_t) Xn *b0;
+      /* acc +=  b1 * x[n-1] */
+      acc += (q63_t) Xn1 *b1;
+      /* acc +=  b[2] * x[n-2] */
+      acc += (q63_t) Xn2 *b2;
+      /* acc +=  a1 * y[n-1] */
+      acc += mult32x64(Yn1, a1);
+      /* acc +=  a2 * y[n-2] */
+      acc += mult32x64(Yn2, a2);
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc    */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+      Yn2 = Yn1;
+      /* The result is converted to 1.63, Yn1 variable is reused  */
+      Yn1 = acc << shift;
+
+      /* Calc lower part of acc */
+      acc_l = acc & 0xffffffff;
+
+      /* Calc upper part of acc */
+      acc_h = (acc >> 32) & 0xffffffff;
+
+      /* Apply shift for lower part of acc and upper part of acc */
+      acc_h = (uint32_t) acc_l >> lShift | acc_h << uShift;
+
+      /* Store the output in the destination buffer in 1.31 format. */
+      *pOut++ = acc_h;
+      /* Yn1 = acc << shift; */
+
+      /* Store the output in the destination buffer in 1.31 format. */
+/*      *pOut++ = (q31_t) (acc >> (32 - shift));  */
+
+      /* decrement the loop counter */
+      sample--;
+    }
+
+    /*  The first stage output is given as input to the second stage. */
+    pIn = pDst;
+
+    /* Reset to destination buffer working pointer */
+    pOut = pDst;
+
+    /*  Store the updated state variables back into the pState array */
+    /*  Store the updated state variables back into the pState array */
+    *pState++ = (q63_t) Xn1;
+    *pState++ = (q63_t) Xn2;
+    *pState++ = Yn1;
+    *pState++ = Yn2;
+
+  } while(--stage);
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  do
+  {
+    /* Reading the coefficients */
+    b0 = *pCoeffs++;
+    b1 = *pCoeffs++;
+    b2 = *pCoeffs++;
+    a1 = *pCoeffs++;
+    a2 = *pCoeffs++;
+
+    /* Reading the state values */
+    Xn1 = pState[0];
+    Xn2 = pState[1];
+    Yn1 = pState[2];
+    Yn2 = pState[3];
+
+    /* The variable acc hold output value that is being computed and        
+     * stored in the destination buffer            
+     * acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]            
+     */
+
+    sample = blockSize;
+
+    while(sample > 0u)
+    {
+      /* Read the input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      acc = (q63_t) Xn *b0;
+      /* acc +=  b1 * x[n-1] */
+      acc += (q63_t) Xn1 *b1;
+      /* acc +=  b[2] * x[n-2] */
+      acc += (q63_t) Xn2 *b2;
+      /* acc +=  a1 * y[n-1] */
+      acc += mult32x64(Yn1, a1);
+      /* acc +=  a2 * y[n-2] */
+      acc += mult32x64(Yn2, a2);
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc    */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+      Yn2 = Yn1;
+
+      /* The result is converted to 1.63, Yn1 variable is reused  */
+      Yn1 = acc << shift;
+
+      /* Calc lower part of acc */
+      acc_l = acc & 0xffffffff;
+
+      /* Calc upper part of acc */
+      acc_h = (acc >> 32) & 0xffffffff;
+
+      /* Apply shift for lower part of acc and upper part of acc */
+      acc_h = (uint32_t) acc_l >> lShift | acc_h << uShift;
+
+      /* Store the output in the destination buffer in 1.31 format. */
+      *pOut++ = acc_h;
+
+      /* Yn1 = acc << shift; */
+
+      /* Store the output in the destination buffer in 1.31 format. */
+      /* *pOut++ = (q31_t) (acc >> (32 - shift)); */
+
+      /* decrement the loop counter */
+      sample--;
+    }
+
+    /*  The first stage output is given as input to the second stage. */
+    pIn = pDst;
+
+    /* Reset to destination buffer working pointer */
+    pOut = pDst;
+
+    /*  Store the updated state variables back into the pState array */
+    *pState++ = (q63_t) Xn1;
+    *pState++ = (q63_t) Xn2;
+    *pState++ = Yn1;
+    *pState++ = Yn2;
+
+  } while(--stage);
+
+#endif /*    #ifndef ARM_MATH_CM0_FAMILY     */
+}
+
+  /**    
+   * @} end of BiquadCascadeDF1_32x64 group    
+   */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_f32.c

@@ -0,0 +1,425 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_biquad_cascade_df1_f32.c    
+*    
+* Description:	Processing function for the    
+*               floating-point Biquad cascade DirectFormI(DF1) filter.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @defgroup BiquadCascadeDF1 Biquad Cascade IIR Filters Using Direct Form I Structure    
+ *    
+ * This set of functions implements arbitrary order recursive (IIR) filters.    
+ * The filters are implemented as a cascade of second order Biquad sections.    
+ * The functions support Q15, Q31 and floating-point data types.  
+ * Fast version of Q15 and Q31 also supported on CortexM4 and Cortex-M3.    
+ *    
+ * The functions operate on blocks of input and output data and each call to the function    
+ * processes <code>blockSize</code> samples through the filter.    
+ * <code>pSrc</code> points to the array of input data and    
+ * <code>pDst</code> points to the array of output data.    
+ * Both arrays contain <code>blockSize</code> values.    
+ *    
+ * \par Algorithm    
+ * Each Biquad stage implements a second order filter using the difference equation:    
+ * <pre>    
+ *     y[n] = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]    
+ * </pre>    
+ * A Direct Form I algorithm is used with 5 coefficients and 4 state variables per stage.    
+ * \image html Biquad.gif "Single Biquad filter stage"    
+ * Coefficients <code>b0, b1 and b2 </code> multiply the input signal <code>x[n]</code> and are referred to as the feedforward coefficients.    
+ * Coefficients <code>a1</code> and <code>a2</code> multiply the output signal <code>y[n]</code> and are referred to as the feedback coefficients.    
+ * Pay careful attention to the sign of the feedback coefficients.    
+ * Some design tools use the difference equation    
+ * <pre>    
+ *     y[n] = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] - a1 * y[n-1] - a2 * y[n-2]    
+ * </pre>    
+ * In this case the feedback coefficients <code>a1</code> and <code>a2</code> must be negated when used with the CMSIS DSP Library.    
+ *    
+ * \par    
+ * Higher order filters are realized as a cascade of second order sections.    
+ * <code>numStages</code> refers to the number of second order stages used.    
+ * For example, an 8th order filter would be realized with <code>numStages=4</code> second order stages.    
+ * \image html BiquadCascade.gif "8th order filter using a cascade of Biquad stages"    
+ * A 9th order filter would be realized with <code>numStages=5</code> second order stages with the coefficients for one of the stages configured as a first order filter (<code>b2=0</code> and <code>a2=0</code>).    
+ *    
+ * \par    
+ * The <code>pState</code> points to state variables array.    
+ * Each Biquad stage has 4 state variables <code>x[n-1], x[n-2], y[n-1],</code> and <code>y[n-2]</code>.    
+ * The state variables are arranged in the <code>pState</code> array as:    
+ * <pre>    
+ *     {x[n-1], x[n-2], y[n-1], y[n-2]}    
+ * </pre>    
+ *    
+ * \par    
+ * The 4 state variables for stage 1 are first, then the 4 state variables for stage 2, and so on.    
+ * The state array has a total length of <code>4*numStages</code> values.    
+ * The state variables are updated after each block of data is processed, the coefficients are untouched.    
+ *    
+ * \par Instance Structure    
+ * The coefficients and state variables for a filter are stored together in an instance data structure.    
+ * A separate instance structure must be defined for each filter.    
+ * Coefficient arrays may be shared among several instances while state variable arrays cannot be shared.    
+ * There are separate instance structure declarations for each of the 3 supported data types.    
+ *    
+ * \par Init Functions    
+ * There is also an associated initialization function for each data type.    
+ * The initialization function performs following operations:    
+ * - Sets the values of the internal structure fields.    
+ * - Zeros out the values in the state buffer.    
+ * To do this manually without calling the init function, assign the follow subfields of the instance structure:
+ * numStages, pCoeffs, pState. Also set all of the values in pState to zero. 
+ *    
+ * \par    
+ * Use of the initialization function is optional.    
+ * However, if the initialization function is used, then the instance structure cannot be placed into a const data section.    
+ * To place an instance structure into a const data section, the instance structure must be manually initialized.    
+ * Set the values in the state buffer to zeros before static initialization.    
+ * The code below statically initializes each of the 3 different data type filter instance structures    
+ * <pre>    
+ *     arm_biquad_casd_df1_inst_f32 S1 = {numStages, pState, pCoeffs};    
+ *     arm_biquad_casd_df1_inst_q15 S2 = {numStages, pState, pCoeffs, postShift};    
+ *     arm_biquad_casd_df1_inst_q31 S3 = {numStages, pState, pCoeffs, postShift};    
+ * </pre>    
+ * where <code>numStages</code> is the number of Biquad stages in the filter; <code>pState</code> is the address of the state buffer;    
+ * <code>pCoeffs</code> is the address of the coefficient buffer; <code>postShift</code> shift to be applied.    
+ *    
+ * \par Fixed-Point Behavior    
+ * Care must be taken when using the Q15 and Q31 versions of the Biquad Cascade filter functions.    
+ * Following issues must be considered:    
+ * - Scaling of coefficients    
+ * - Filter gain    
+ * - Overflow and saturation    
+ *    
+ * \par    
+ * <b>Scaling of coefficients: </b>    
+ * Filter coefficients are represented as fractional values and    
+ * coefficients are restricted to lie in the range <code>[-1 +1)</code>.    
+ * The fixed-point functions have an additional scaling parameter <code>postShift</code>    
+ * which allow the filter coefficients to exceed the range <code>[+1 -1)</code>.    
+ * At the output of the filter's accumulator is a shift register which shifts the result by <code>postShift</code> bits.    
+ * \image html BiquadPostshift.gif "Fixed-point Biquad with shift by postShift bits after accumulator"    
+ * This essentially scales the filter coefficients by <code>2^postShift</code>.    
+ * For example, to realize the coefficients    
+ * <pre>    
+ *    {1.5, -0.8, 1.2, 1.6, -0.9}    
+ * </pre>    
+ * set the pCoeffs array to:    
+ * <pre>    
+ *    {0.75, -0.4, 0.6, 0.8, -0.45}    
+ * </pre>    
+ * and set <code>postShift=1</code>    
+ *    
+ * \par    
+ * <b>Filter gain: </b>    
+ * The frequency response of a Biquad filter is a function of its coefficients.    
+ * It is possible for the gain through the filter to exceed 1.0 meaning that the filter increases the amplitude of certain frequencies.    
+ * This means that an input signal with amplitude < 1.0 may result in an output > 1.0 and these are saturated or overflowed based on the implementation of the filter.    
+ * To avoid this behavior the filter needs to be scaled down such that its peak gain < 1.0 or the input signal must be scaled down so that the combination of input and filter are never overflowed.    
+ *    
+ * \par    
+ * <b>Overflow and saturation: </b>    
+ * For Q15 and Q31 versions, it is described separately as part of the function specific documentation below.    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1    
+ * @{    
+ */
+
+/**    
+ * @param[in]  *S         points to an instance of the floating-point Biquad cascade structure.    
+ * @param[in]  *pSrc      points to the block of input data.    
+ * @param[out] *pDst      points to the block of output data.    
+ * @param[in]  blockSize  number of samples to process per call.    
+ * @return     none.    
+ *    
+ */
+
+void arm_biquad_cascade_df1_f32(
+  const arm_biquad_casd_df1_inst_f32 * S,
+  float32_t * pSrc,
+  float32_t * pDst,
+  uint32_t blockSize)
+{
+  float32_t *pIn = pSrc;                         /*  source pointer            */
+  float32_t *pOut = pDst;                        /*  destination pointer       */
+  float32_t *pState = S->pState;                 /*  pState pointer            */
+  float32_t *pCoeffs = S->pCoeffs;               /*  coefficient pointer       */
+  float32_t acc;                                 /*  Simulates the accumulator */
+  float32_t b0, b1, b2, a1, a2;                  /*  Filter coefficients       */
+  float32_t Xn1, Xn2, Yn1, Yn2;                  /*  Filter pState variables   */
+  float32_t Xn;                                  /*  temporary input           */
+  uint32_t sample, stage = S->numStages;         /*  loop counters             */
+
+
+#ifndef ARM_MATH_CM0_FAMILY
+
+  /* Run the below code for Cortex-M4 and Cortex-M3 */
+
+  do
+  {
+    /* Reading the coefficients */
+    b0 = *pCoeffs++;
+    b1 = *pCoeffs++;
+    b2 = *pCoeffs++;
+    a1 = *pCoeffs++;
+    a2 = *pCoeffs++;
+
+    /* Reading the pState values */
+    Xn1 = pState[0];
+    Xn2 = pState[1];
+    Yn1 = pState[2];
+    Yn2 = pState[3];
+
+    /* Apply loop unrolling and compute 4 output values simultaneously. */
+    /*      The variable acc hold output values that are being computed:    
+     *    
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]    
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]    
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]    
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]    
+     */
+
+    sample = blockSize >> 2u;
+
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.    
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(sample > 0u)
+    {
+      /* Read the first input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      Yn2 = (b0 * Xn) + (b1 * Xn1) + (b2 * Xn2) + (a1 * Yn1) + (a2 * Yn2);
+
+      /* Store the result in the accumulator in the destination buffer. */
+      *pOut++ = Yn2;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+
+      /* Read the second input */
+      Xn2 = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      Yn1 = (b0 * Xn2) + (b1 * Xn) + (b2 * Xn1) + (a1 * Yn2) + (a2 * Yn1);
+
+      /* Store the result in the accumulator in the destination buffer. */
+      *pOut++ = Yn1;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+
+      /* Read the third input */
+      Xn1 = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      Yn2 = (b0 * Xn1) + (b1 * Xn2) + (b2 * Xn) + (a1 * Yn1) + (a2 * Yn2);
+
+      /* Store the result in the accumulator in the destination buffer. */
+      *pOut++ = Yn2;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as: */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+
+      /* Read the forth input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      Yn1 = (b0 * Xn) + (b1 * Xn1) + (b2 * Xn2) + (a1 * Yn2) + (a2 * Yn1);
+
+      /* Store the result in the accumulator in the destination buffer. */
+      *pOut++ = Yn1;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+
+      /* decrement the loop counter */
+      sample--;
+
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.    
+     ** No loop unrolling is used. */
+    sample = blockSize & 0x3u;
+
+    while(sample > 0u)
+    {
+      /* Read the input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      acc = (b0 * Xn) + (b1 * Xn1) + (b2 * Xn2) + (a1 * Yn1) + (a2 * Yn2);
+
+      /* Store the result in the accumulator in the destination buffer. */
+      *pOut++ = acc;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:    */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+      Yn2 = Yn1;
+      Yn1 = acc;
+
+      /* decrement the loop counter */
+      sample--;
+
+    }
+
+    /*  Store the updated state variables back into the pState array */
+    *pState++ = Xn1;
+    *pState++ = Xn2;
+    *pState++ = Yn1;
+    *pState++ = Yn2;
+
+    /*  The first stage goes from the input buffer to the output buffer. */
+    /*  Subsequent numStages  occur in-place in the output buffer */
+    pIn = pDst;
+
+    /* Reset the output pointer */
+    pOut = pDst;
+
+    /* decrement the loop counter */
+    stage--;
+
+  } while(stage > 0u);
+
+#else
+
+  /* Run the below code for Cortex-M0 */
+
+  do
+  {
+    /* Reading the coefficients */
+    b0 = *pCoeffs++;
+    b1 = *pCoeffs++;
+    b2 = *pCoeffs++;
+    a1 = *pCoeffs++;
+    a2 = *pCoeffs++;
+
+    /* Reading the pState values */
+    Xn1 = pState[0];
+    Xn2 = pState[1];
+    Yn1 = pState[2];
+    Yn2 = pState[3];
+
+    /*      The variables acc holds the output value that is computed:        
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1]   + a2 * y[n-2]        
+     */
+
+    sample = blockSize;
+
+    while(sample > 0u)
+    {
+      /* Read the input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      acc = (b0 * Xn) + (b1 * Xn1) + (b2 * Xn2) + (a1 * Yn1) + (a2 * Yn2);
+
+      /* Store the result in the accumulator in the destination buffer. */
+      *pOut++ = acc;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:    */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+      Yn2 = Yn1;
+      Yn1 = acc;
+
+      /* decrement the loop counter */
+      sample--;
+    }
+
+    /*  Store the updated state variables back into the pState array */
+    *pState++ = Xn1;
+    *pState++ = Xn2;
+    *pState++ = Yn1;
+    *pState++ = Yn2;
+
+    /*  The first stage goes from the input buffer to the output buffer. */
+    /*  Subsequent numStages  occur in-place in the output buffer */
+    pIn = pDst;
+
+    /* Reset the output pointer */
+    pOut = pDst;
+
+    /* decrement the loop counter */
+    stage--;
+
+  } while(stage > 0u);
+
+#endif /*   #ifndef ARM_MATH_CM0_FAMILY         */
+
+}
+
+
+  /**    
+   * @} end of BiquadCascadeDF1 group    
+   */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_fast_q15.c

@@ -0,0 +1,286 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_biquad_cascade_df1_fast_q15.c    
+*    
+* Description:	Fast processing function for the    
+*				Q15 Biquad cascade filter.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1    
+ * @{    
+ */
+
+/**    
+ * @details    
+ * @param[in]  *S points to an instance of the Q15 Biquad cascade structure.    
+ * @param[in]  *pSrc points to the block of input data.    
+ * @param[out] *pDst points to the block of output data.    
+ * @param[in]  blockSize number of samples to process per call.    
+ * @return none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * This fast version uses a 32-bit accumulator with 2.30 format.    
+ * The accumulator maintains full precision of the intermediate multiplication results but provides only a single guard bit.    
+ * Thus, if the accumulator result overflows it wraps around and distorts the result.    
+ * In order to avoid overflows completely the input signal must be scaled down by two bits and lie in the range [-0.25 +0.25).    
+ * The 2.30 accumulator is then shifted by <code>postShift</code> bits and the result truncated to 1.15 format by discarding the low 16 bits.    
+ *    
+ * \par    
+ * Refer to the function <code>arm_biquad_cascade_df1_q15()</code> for a slower implementation of this function which uses 64-bit accumulation to avoid wrap around distortion.  Both the slow and the fast versions use the same instance structure.    
+ * Use the function <code>arm_biquad_cascade_df1_init_q15()</code> to initialize the filter structure.    
+ *    
+ */
+
+void arm_biquad_cascade_df1_fast_q15(
+  const arm_biquad_casd_df1_inst_q15 * S,
+  q15_t * pSrc,
+  q15_t * pDst,
+  uint32_t blockSize)
+{
+  q15_t *pIn = pSrc;                             /*  Source pointer                               */
+  q15_t *pOut = pDst;                            /*  Destination pointer                          */
+  q31_t in;                                      /*  Temporary variable to hold input value       */
+  q31_t out;                                     /*  Temporary variable to hold output value      */
+  q31_t b0;                                      /*  Temporary variable to hold bo value          */
+  q31_t b1, a1;                                  /*  Filter coefficients                          */
+  q31_t state_in, state_out;                     /*  Filter state variables                       */
+  q31_t acc;                                     /*  Accumulator                                  */
+  int32_t shift = (int32_t) (15 - S->postShift); /*  Post shift                                   */
+  q15_t *pState = S->pState;                     /*  State pointer                                */
+  q15_t *pCoeffs = S->pCoeffs;                   /*  Coefficient pointer                          */
+  uint32_t sample, stage = S->numStages;         /*  Stage loop counter                           */
+
+
+
+  do
+  {
+
+    /* Read the b0 and 0 coefficients using SIMD  */
+    b0 = *__SIMD32(pCoeffs)++;
+
+    /* Read the b1 and b2 coefficients using SIMD */
+    b1 = *__SIMD32(pCoeffs)++;
+
+    /* Read the a1 and a2 coefficients using SIMD */
+    a1 = *__SIMD32(pCoeffs)++;
+
+    /* Read the input state values from the state buffer:  x[n-1], x[n-2] */
+    state_in = *__SIMD32(pState)++;
+
+    /* Read the output state values from the state buffer:  y[n-1], y[n-2] */
+    state_out = *__SIMD32(pState)--;
+
+    /* Apply loop unrolling and compute 2 output values simultaneously. */
+    /*      The variable acc hold output values that are being computed:       
+     *    
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]       
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]       
+     */
+    sample = blockSize >> 1u;
+
+    /* First part of the processing with loop unrolling.  Compute 2 outputs at a time.    
+     ** a second loop below computes the remaining 1 sample. */
+    while(sample > 0u)
+    {
+
+      /* Read the input */
+      in = *__SIMD32(pIn)++;
+
+      /* out =  b0 * x[n] + 0 * 0 */
+      out = __SMUAD(b0, in);
+      /* acc =  b1 * x[n-1] + acc +=  b2 * x[n-2] + out */
+      acc = __SMLAD(b1, state_in, out);
+      /* acc +=  a1 * y[n-1] + acc +=  a2 * y[n-2] */
+      acc = __SMLAD(a1, state_out, acc);
+
+      /* The result is converted from 3.29 to 1.31 and then saturation is applied */
+      out = __SSAT((acc >> shift), 16);
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+      /* x[n-N], x[n-N-1] are packed together to make state_in of type q31 */
+      /* y[n-N], y[n-N-1] are packed together to make state_out of type q31 */
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      state_in = __PKHBT(in, state_in, 16);
+      state_out = __PKHBT(out, state_out, 16);
+
+#else
+
+      state_in = __PKHBT(state_in >> 16, (in >> 16), 16);
+      state_out = __PKHBT(state_out >> 16, (out), 16);
+
+#endif /*      #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      /* out =  b0 * x[n] + 0 * 0 */
+      out = __SMUADX(b0, in);
+      /* acc0 =  b1 * x[n-1] , acc0 +=  b2 * x[n-2] + out */
+      acc = __SMLAD(b1, state_in, out);
+      /* acc +=  a1 * y[n-1] + acc +=  a2 * y[n-2] */
+      acc = __SMLAD(a1, state_out, acc);
+
+      /* The result is converted from 3.29 to 1.31 and then saturation is applied */
+      out = __SSAT((acc >> shift), 16);
+
+
+      /* Store the output in the destination buffer. */
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      *__SIMD32(pOut)++ = __PKHBT(state_out, out, 16);
+
+#else
+
+      *__SIMD32(pOut)++ = __PKHBT(out, state_out >> 16, 16);
+
+#endif /*      #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+      /* x[n-N], x[n-N-1] are packed together to make state_in of type q31 */
+      /* y[n-N], y[n-N-1] are packed together to make state_out of type q31 */
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      state_in = __PKHBT(in >> 16, state_in, 16);
+      state_out = __PKHBT(out, state_out, 16);
+
+#else
+
+      state_in = __PKHBT(state_in >> 16, in, 16);
+      state_out = __PKHBT(state_out >> 16, out, 16);
+
+#endif /*      #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+
+      /* Decrement the loop counter */
+      sample--;
+
+    }
+
+    /* If the blockSize is not a multiple of 2, compute any remaining output samples here.    
+     ** No loop unrolling is used. */
+
+    if((blockSize & 0x1u) != 0u)
+    {
+      /* Read the input */
+      in = *pIn++;
+
+      /* out =  b0 * x[n] + 0 * 0 */
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      out = __SMUAD(b0, in);
+
+#else
+
+      out = __SMUADX(b0, in);
+
+#endif /*      #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+      /* acc =  b1 * x[n-1], acc +=  b2 * x[n-2] + out */
+      acc = __SMLAD(b1, state_in, out);
+      /* acc +=  a1 * y[n-1] + acc +=  a2 * y[n-2] */
+      acc = __SMLAD(a1, state_out, acc);
+
+      /* The result is converted from 3.29 to 1.31 and then saturation is applied */
+      out = __SSAT((acc >> shift), 16);
+
+      /* Store the output in the destination buffer. */
+      *pOut++ = (q15_t) out;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc   */
+      /* x[n-N], x[n-N-1] are packed together to make state_in of type q31 */
+      /* y[n-N], y[n-N-1] are packed together to make state_out of type q31 */
+
+#ifndef  ARM_MATH_BIG_ENDIAN
+
+      state_in = __PKHBT(in, state_in, 16);
+      state_out = __PKHBT(out, state_out, 16);
+
+#else
+
+      state_in = __PKHBT(state_in >> 16, in, 16);
+      state_out = __PKHBT(state_out >> 16, out, 16);
+
+#endif /*   #ifndef  ARM_MATH_BIG_ENDIAN    */
+
+    }
+
+    /*  The first stage goes from the input buffer to the output buffer.  */
+    /*  Subsequent (numStages - 1) occur in-place in the output buffer  */
+    pIn = pDst;
+
+    /* Reset the output pointer */
+    pOut = pDst;
+
+    /*  Store the updated state variables back into the state array */
+    *__SIMD32(pState)++ = state_in;
+    *__SIMD32(pState)++ = state_out;
+
+
+    /* Decrement the loop counter */
+    stage--;
+
+  } while(stage > 0u);
+}
+
+
+/**    
+ * @} end of BiquadCascadeDF1 group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_fast_q31.c

@@ -0,0 +1,305 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. October 2015
+* $Revision: 	V.1.4.5 a
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_biquad_cascade_df1_fast_q31.c    
+*    
+* Description:	Processing function for the    
+*				Q31 Fast Biquad cascade DirectFormI(DF1) filter.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE. 
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1    
+ * @{    
+ */
+
+/**    
+ * @details    
+ *    
+ * @param[in]  *S        points to an instance of the Q31 Biquad cascade structure.    
+ * @param[in]  *pSrc     points to the block of input data.    
+ * @param[out] *pDst     points to the block of output data.    
+ * @param[in]  blockSize number of samples to process per call.    
+ * @return 	   none.    
+ *    
+ * <b>Scaling and Overflow Behavior:</b>    
+ * \par    
+ * This function is optimized for speed at the expense of fixed-point precision and overflow protection.    
+ * The result of each 1.31 x 1.31 multiplication is truncated to 2.30 format.    
+ * These intermediate results are added to a 2.30 accumulator.    
+ * Finally, the accumulator is saturated and converted to a 1.31 result.    
+ * The fast version has the same overflow behavior as the standard version and provides less precision since it discards the low 32 bits of each multiplication result.    
+ * In order to avoid overflows completely the input signal must be scaled down by two bits and lie in the range [-0.25 +0.25). Use the intialization function    
+ * arm_biquad_cascade_df1_init_q31() to initialize filter structure.    
+ *    
+ * \par    
+ * Refer to the function <code>arm_biquad_cascade_df1_q31()</code> for a slower implementation of this function which uses 64-bit accumulation to provide higher precision.  Both the slow and the fast versions use the same instance structure.    
+ * Use the function <code>arm_biquad_cascade_df1_init_q31()</code> to initialize the filter structure.    
+ */
+
+void arm_biquad_cascade_df1_fast_q31(
+  const arm_biquad_casd_df1_inst_q31 * S,
+  q31_t * pSrc,
+  q31_t * pDst,
+  uint32_t blockSize)
+{
+  q31_t acc = 0;                                 /*  accumulator                   */
+  q31_t Xn1, Xn2, Yn1, Yn2;                      /*  Filter state variables        */
+  q31_t b0, b1, b2, a1, a2;                      /*  Filter coefficients           */
+  q31_t *pIn = pSrc;                             /*  input pointer initialization  */
+  q31_t *pOut = pDst;                            /*  output pointer initialization */
+  q31_t *pState = S->pState;                     /*  pState pointer initialization */
+  q31_t *pCoeffs = S->pCoeffs;                   /*  coeff pointer initialization  */
+  q31_t Xn;                                      /*  temporary input               */
+  int32_t shift = (int32_t) S->postShift + 1;    /*  Shift to be applied to the output */
+  uint32_t sample, stage = S->numStages;         /*  loop counters                     */
+
+
+  do
+  {
+    /* Reading the coefficients */
+    b0 = *pCoeffs++;
+    b1 = *pCoeffs++;
+    b2 = *pCoeffs++;
+    a1 = *pCoeffs++;
+    a2 = *pCoeffs++;
+
+    /* Reading the state values */
+    Xn1 = pState[0];
+    Xn2 = pState[1];
+    Yn1 = pState[2];
+    Yn2 = pState[3];
+
+    /* Apply loop unrolling and compute 4 output values simultaneously. */
+    /*      The variables acc ... acc3 hold output values that are being computed:       
+     *       
+     *    acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2]       
+     */
+
+    sample = blockSize >> 2u;
+
+    /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.       
+     ** a second loop below computes the remaining 1 to 3 samples. */
+    while(sample > 0u)
+    {
+      /* Read the input */
+      Xn = *pIn;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      /*acc = (q31_t) (((q63_t) b1 * Xn1) >> 32);*/
+      mult_32x32_keep32_R(acc, b1, Xn1);
+      /* acc +=  b1 * x[n-1] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b0 * (Xn))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, b0, Xn);
+      /* acc +=  b[2] * x[n-2] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b2 * (Xn2))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, b2, Xn2);
+      /* acc +=  a1 * y[n-1] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a1 * (Yn1))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, a1, Yn1);
+      /* acc +=  a2 * y[n-2] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a2 * (Yn2))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, a2, Yn2);
+
+      /* The result is converted to 1.31 , Yn2 variable is reused */
+      Yn2 = acc << shift;
+
+      /* Read the second input */
+      Xn2 = *(pIn + 1u);
+
+      /* Store the output in the destination buffer. */
+      *pOut = Yn2;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      /*acc = (q31_t) (((q63_t) b0 * (Xn2)) >> 32);*/
+      mult_32x32_keep32_R(acc, b0, Xn2);
+      /* acc +=  b1 * x[n-1] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b1 * (Xn))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, b1, Xn);
+      /* acc +=  b[2] * x[n-2] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b2 * (Xn1))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, b2, Xn1);
+      /* acc +=  a1 * y[n-1] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a1 * (Yn2))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, a1, Yn2);
+      /* acc +=  a2 * y[n-2] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a2 * (Yn1))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, a2, Yn1);
+
+      /* The result is converted to 1.31, Yn1 variable is reused  */
+      Yn1 = acc << shift;
+
+      /* Read the third input  */
+      Xn1 = *(pIn + 2u);
+
+      /* Store the output in the destination buffer. */
+      *(pOut + 1u) = Yn1;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      /*acc = (q31_t) (((q63_t) b0 * (Xn1)) >> 32);*/
+      mult_32x32_keep32_R(acc, b0, Xn1);
+      /* acc +=  b1 * x[n-1] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b1 * (Xn2))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, b1, Xn2);
+      /* acc +=  b[2] * x[n-2] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b2 * (Xn))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, b2, Xn);
+      /* acc +=  a1 * y[n-1] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a1 * (Yn1))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, a1, Yn1);
+      /* acc +=  a2 * y[n-2] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a2 * (Yn2))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, a2, Yn2);
+
+      /* The result is converted to 1.31, Yn2 variable is reused  */
+      Yn2 = acc << shift;
+
+      /* Read the forth input */
+      Xn = *(pIn + 3u);
+
+      /* Store the output in the destination buffer. */
+      *(pOut + 2u) = Yn2;
+      pIn += 4u;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      /*acc = (q31_t) (((q63_t) b0 * (Xn)) >> 32);*/
+      mult_32x32_keep32_R(acc, b0, Xn);
+      /* acc +=  b1 * x[n-1] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b1 * (Xn1))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, b1, Xn1);
+      /* acc +=  b[2] * x[n-2] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b2 * (Xn2))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, b2, Xn2);
+      /* acc +=  a1 * y[n-1] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a1 * (Yn2))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, a1, Yn2);
+      /* acc +=  a2 * y[n-2] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a2 * (Yn1))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, a2, Yn1);
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      Xn2 = Xn1;
+
+      /* The result is converted to 1.31, Yn1 variable is reused  */
+      Yn1 = acc << shift;
+
+      /* Xn1 = Xn     */
+      Xn1 = Xn;
+
+      /* Store the output in the destination buffer. */
+      *(pOut + 3u) = Yn1;
+      pOut += 4u;
+
+      /* decrement the loop counter */
+      sample--;
+    }
+
+    /* If the blockSize is not a multiple of 4, compute any remaining output samples here.       
+     ** No loop unrolling is used. */
+    sample = (blockSize & 0x3u);
+
+   while(sample > 0u)
+   {
+      /* Read the input */
+      Xn = *pIn++;
+
+      /* acc =  b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */
+      /* acc =  b0 * x[n] */
+      /*acc = (q31_t) (((q63_t) b0 * (Xn)) >> 32);*/
+      mult_32x32_keep32_R(acc, b0, Xn);
+      /* acc +=  b1 * x[n-1] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b1 * (Xn1))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, b1, Xn1);
+      /* acc +=  b[2] * x[n-2] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) b2 * (Xn2))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, b2, Xn2);
+      /* acc +=  a1 * y[n-1] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a1 * (Yn1))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, a1, Yn1);
+      /* acc +=  a2 * y[n-2] */
+      /*acc = (q31_t) ((((q63_t) acc << 32) + ((q63_t) a2 * (Yn2))) >> 32);*/
+      multAcc_32x32_keep32_R(acc, a2, Yn2);
+
+      /* The result is converted to 1.31  */
+      acc = acc << shift;
+
+      /* Every time after the output is computed state should be updated. */
+      /* The states should be updated as:  */
+      /* Xn2 = Xn1    */
+      /* Xn1 = Xn     */
+      /* Yn2 = Yn1    */
+      /* Yn1 = acc    */
+      Xn2 = Xn1;
+      Xn1 = Xn;
+      Yn2 = Yn1;
+      Yn1 = acc;
+
+      /* Store the output in the destination buffer. */
+      *pOut++ = acc;
+
+      /* decrement the loop counter */
+      sample--;
+   }
+
+    /*  The first stage goes from the input buffer to the output buffer. */
+    /*  Subsequent stages occur in-place in the output buffer */
+    pIn = pDst;
+
+    /* Reset to destination pointer */
+    pOut = pDst;
+
+    /*  Store the updated state variables back into the pState array */
+    *pState++ = Xn1;
+    *pState++ = Xn2;
+    *pState++ = Yn1;
+    *pState++ = Yn2;
+
+  } while(--stage);
+}
+
+/**    
+  * @} end of BiquadCascadeDF1 group    
+  */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_init_f32.c

@@ -0,0 +1,109 @@
+/*-----------------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:        arm_biquad_cascade_df1_init_f32.c    
+*    
+* Description:  floating-point Biquad cascade DirectFormI(DF1) filter initialization function.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.    
+* ---------------------------------------------------------------------------*/
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1    
+ * @{    
+ */
+
+/**    
+ * @details    
+ * @brief  Initialization function for the floating-point Biquad cascade filter.    
+ * @param[in,out] *S           points to an instance of the floating-point Biquad cascade structure.    
+ * @param[in]     numStages    number of 2nd order stages in the filter.    
+ * @param[in]     *pCoeffs     points to the filter coefficients array.    
+ * @param[in]     *pState      points to the state array.    
+ * @return        none    
+ *    
+ *    
+ * <b>Coefficient and State Ordering:</b>    
+ *    
+ * \par    
+ * The coefficients are stored in the array <code>pCoeffs</code> in the following order:    
+ * <pre>    
+ *     {b10, b11, b12, a11, a12, b20, b21, b22, a21, a22, ...}    
+ * </pre>    
+ *    
+ * \par    
+ * where <code>b1x</code> and <code>a1x</code> are the coefficients for the first stage,    
+ * <code>b2x</code> and <code>a2x</code> are the coefficients for the second stage,    
+ * and so on.  The <code>pCoeffs</code> array contains a total of <code>5*numStages</code> values.    
+ *    
+ * \par    
+ * The <code>pState</code> is a pointer to state array.    
+ * Each Biquad stage has 4 state variables <code>x[n-1], x[n-2], y[n-1],</code> and <code>y[n-2]</code>.    
+ * The state variables are arranged in the <code>pState</code> array as:    
+ * <pre>    
+ *     {x[n-1], x[n-2], y[n-1], y[n-2]}    
+ * </pre>    
+ * The 4 state variables for stage 1 are first, then the 4 state variables for stage 2, and so on.    
+ * The state array has a total length of <code>4*numStages</code> values.    
+ * The state variables are updated after each block of data is processed; the coefficients are untouched.    
+ *    
+ */
+
+void arm_biquad_cascade_df1_init_f32(
+  arm_biquad_casd_df1_inst_f32 * S,
+  uint8_t numStages,
+  float32_t * pCoeffs,
+  float32_t * pState)
+{
+  /* Assign filter stages */
+  S->numStages = numStages;
+
+  /* Assign coefficient pointer */
+  S->pCoeffs = pCoeffs;
+
+  /* Clear state buffer and size is always 4 * numStages */
+  memset(pState, 0, (4u * (uint32_t) numStages) * sizeof(float32_t));
+
+  /* Assign state pointer */
+  S->pState = pState;
+}
+
+/**    
+ * @} end of BiquadCascadeDF1 group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_init_q15.c

@@ -0,0 +1,111 @@
+/*-----------------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:        arm_biquad_cascade_df1_init_q15.c    
+*    
+* Description:  Q15 Biquad cascade DirectFormI(DF1) filter initialization function.    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.  
+* ---------------------------------------------------------------------------*/
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1    
+ * @{    
+ */
+
+/**    
+ * @details    
+ *    
+ * @param[in,out] *S           points to an instance of the Q15 Biquad cascade structure.    
+ * @param[in]     numStages    number of 2nd order stages in the filter.    
+ * @param[in]     *pCoeffs     points to the filter coefficients.    
+ * @param[in]     *pState      points to the state buffer.    
+ * @param[in]     postShift    Shift to be applied to the accumulator result. Varies according to the coefficients format    
+ * @return        none    
+ *    
+ * <b>Coefficient and State Ordering:</b>    
+ *    
+ * \par    
+ * The coefficients are stored in the array <code>pCoeffs</code> in the following order:    
+ * <pre>    
+ *     {b10, 0, b11, b12, a11, a12, b20, 0, b21, b22, a21, a22, ...}    
+ * </pre>    
+ * where <code>b1x</code> and <code>a1x</code> are the coefficients for the first stage,    
+ * <code>b2x</code> and <code>a2x</code> are the coefficients for the second stage,    
+ * and so on.  The <code>pCoeffs</code> array contains a total of <code>6*numStages</code> values.    
+ * The zero coefficient between <code>b1</code> and <code>b2</code> facilities  use of 16-bit SIMD instructions on the Cortex-M4.    
+ *    
+ * \par    
+ * The state variables are stored in the array <code>pState</code>.    
+ * Each Biquad stage has 4 state variables <code>x[n-1], x[n-2], y[n-1],</code> and <code>y[n-2]</code>.    
+ * The state variables are arranged in the <code>pState</code> array as:    
+ * <pre>    
+ *     {x[n-1], x[n-2], y[n-1], y[n-2]}    
+ * </pre>    
+ * The 4 state variables for stage 1 are first, then the 4 state variables for stage 2, and so on.    
+ * The state array has a total length of <code>4*numStages</code> values.    
+ * The state variables are updated after each block of data is processed; the coefficients are untouched.    
+ */
+
+void arm_biquad_cascade_df1_init_q15(
+  arm_biquad_casd_df1_inst_q15 * S,
+  uint8_t numStages,
+  q15_t * pCoeffs,
+  q15_t * pState,
+  int8_t postShift)
+{
+  /* Assign filter stages */
+  S->numStages = numStages;
+
+  /* Assign postShift to be applied to the output */
+  S->postShift = postShift;
+
+  /* Assign coefficient pointer */
+  S->pCoeffs = pCoeffs;
+
+  /* Clear state buffer and size is always 4 * numStages */
+  memset(pState, 0, (4u * (uint32_t) numStages) * sizeof(q15_t));
+
+  /* Assign state pointer */
+  S->pState = pState;
+}
+
+/**    
+ * @} end of BiquadCascadeDF1 group    
+ */

Code/STM32/Gesture/Drivers/CMSIS/DSP_Lib/Source/FilteringFunctions/arm_biquad_cascade_df1_init_q31.c

@@ -0,0 +1,111 @@
+/* ----------------------------------------------------------------------    
+* Copyright (C) 2010-2014 ARM Limited. All rights reserved.    
+*    
+* $Date:        19. March 2015
+* $Revision: 	V.1.4.5
+*    
+* Project: 	    CMSIS DSP Library    
+* Title:	    arm_biquad_cascade_df1_init_q31.c    
+*    
+* Description:	Q31 Biquad cascade DirectFormI(DF1) filter initialization function.    
+*    
+*    
+* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
+*  
+* Redistribution and use in source and binary forms, with or without 
+* modification, are permitted provided that the following conditions
+* are met:
+*   - Redistributions of source code must retain the above copyright
+*     notice, this list of conditions and the following disclaimer.
+*   - Redistributions in binary form must reproduce the above copyright
+*     notice, this list of conditions and the following disclaimer in
+*     the documentation and/or other materials provided with the 
+*     distribution.
+*   - Neither the name of ARM LIMITED nor the names of its contributors
+*     may be used to endorse or promote products derived from this
+*     software without specific prior written permission.
+*
+* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+* POSSIBILITY OF SUCH DAMAGE.    
+* -------------------------------------------------------------------- */
+
+#include "arm_math.h"
+
+/**    
+ * @ingroup groupFilters    
+ */
+
+/**    
+ * @addtogroup BiquadCascadeDF1    
+ * @{    
+ */
+
+/**    
+ * @details    
+ *    
+ * @param[in,out] *S           points to an instance of the Q31 Biquad cascade structure.    
+ * @param[in]     numStages    number of 2nd order stages in the filter.    
+ * @param[in]     *pCoeffs     points to the filter coefficients buffer.    
+ * @param[in]     *pState      points to the state buffer.    
+ * @param[in]     postShift    Shift to be applied after the accumulator.  Varies according to the coefficients format    
+ * @return        none    
+ *    
+ * <b>Coefficient and State Ordering:</b>    
+ *    
+ * \par    
+ * The coefficients are stored in the array <code>pCoeffs</code> in the following order:    
+ * <pre>    
+ *     {b10, b11, b12, a11, a12, b20, b21, b22, a21, a22, ...}    
+ * </pre>    
+ * where <code>b1x</code> and <code>a1x</code> are the coefficients for the first stage,    
+ * <code>b2x</code> and <code>a2x</code> are the coefficients for the second stage,    
+ * and so on.  The <code>pCoeffs</code> array contains a total of <code>5*numStages</code> values.    
+ *    
+ * \par    
+ * The <code>pState</code> points to state variables array.    
+ * Each Biquad stage has 4 state variables <code>x[n-1], x[n-2], y[n-1],</code> and <code>y[n-2]</code>.    
+ * The state variables are arranged in the <code>pState</code> array as:    
+ * <pre>    
+ *     {x[n-1], x[n-2], y[n-1], y[n-2]}    
+ * </pre>    
+ * The 4 state variables for stage 1 are first, then the 4 state variables for stage 2, and so on.    
+ * The state array has a total length of <code>4*numStages</code> values.    
+ * The state variables are updated after each block of data is processed; the coefficients are untouched.    
+ */
+
+void arm_biquad_cascade_df1_init_q31(
+  arm_biquad_casd_df1_inst_q31 * S,
+  uint8_t numStages,
+  q31_t * pCoeffs,
+  q31_t * pState,
+  int8_t postShift)
+{
+  /* Assign filter stages */
+  S->numStages = numStages;
+
+  /* Assign postShift to be applied to the output */
+  S->postShift = postShift;
+
+  /* Assign coefficient pointer */
+  S->pCoeffs = pCoeffs;
+
+  /* Clear state buffer and size is always 4 * numStages */
+  memset(pState, 0, (4u * (uint32_t) numStages) * sizeof(q31_t));
+
+  /* Assign state pointer */
+  S->pState = pState;
+}
+
+/**    
+ * @} end of BiquadCascadeDF1 group    
+ */