init

.gitignore

@@ -0,0 +1,49 @@
+# ---> uVision
+# git ignore file for Keil µVision Project
+
+# µVision 5 and µVision 4 Project screen layout file
+*.uvguix.*
+*.uvgui.*
+
+# Listing Files
+*.i
+*.lst
+*.m51
+*.m66
+*.map
+
+# Object Files
+*.axf
+*.b[0-2][0-9]
+*.b3[0-1]
+*.bak
+*.build_log.htm
+*.crf
+*.d
+*.dep
+*.elf
+*.htm
+*.iex
+*.lnp
+*.o
+*.obj
+*.sbr
+
+# Firmware Files
+*.bin
+*.h86
+*.hex
+
+# Build Files
+.bat
+
+# Debugger Files
+.ini
+
+# JLink Files
+JLinkLog.txt
+
+# Other Files
+
+/BoardExample/MDK-ARM/DebugConfig/
+/BoardExample/MDK-ARM/Output/

AliBoardExample/Core/Inc/gpio.h

@@ -0,0 +1,47 @@
+/**
+  ******************************************************************************
+  * @file    gpio.h
+  * @brief   This file contains all the function prototypes for
+  *          the gpio.c file
+  ******************************************************************************
+  * @attention
+  *
+  * <h2><center>&copy; Copyright (c) Puya Semiconductor Co.
+  * All rights reserved.</center></h2>
+  *
+  * <h2><center>&copy; Copyright (c) 2016 STMicroelectronics.
+  * All rights reserved.</center></h2>
+  *
+  * This software component is licensed by ST under BSD 3-Clause license,
+  * the "License"; You may not use this file except in compliance with the
+  * License. You may obtain a copy of the License at:
+  *                        opensource.org/licenses/BSD-3-Clause
+  *
+  ******************************************************************************
+  */
+
+/* Define to prevent recursive inclusion -------------------------------------*/
+#ifndef __GPIO_H__
+#define __GPIO_H__
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+/* Includes ------------------------------------------------------------------*/
+#include "main.h"
+
+/* Private includes ----------------------------------------------------------*/
+/* Private defines -----------------------------------------------------------*/
+/* Exported variables prototypes ---------------------------------------------*/
+/* Exported functions prototypes ---------------------------------------------*/
+void MX_GPIO_Init(void);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __GPIO_H__ */
+
+/************************ (C) COPYRIGHT Puya *****END OF FILE******************/

AliBoardExample/Core/Inc/main.h

@@ -0,0 +1,51 @@
+/**
+  ******************************************************************************
+  * @file    main.h
+  * @author  MCU Application Team
+  * @brief   Header for main.c file.
+  *          This file contains the common defines of the application.
+  ******************************************************************************
+  * @attention
+  *
+  * <h2><center>&copy; Copyright (c) Puya Semiconductor Co.
+  * All rights reserved.</center></h2>
+  *
+  * <h2><center>&copy; Copyright (c) 2016 STMicroelectronics.
+  * All rights reserved.</center></h2>
+  *
+  * This software component is licensed by ST under BSD 3-Clause license,
+  * the "License"; You may not use this file except in compliance with the
+  * License. You may obtain a copy of the License at:
+  *                        opensource.org/licenses/BSD-3-Clause
+  *
+  ******************************************************************************
+  */
+
+/* Define to prevent recursive inclusion -------------------------------------*/
+#ifndef __MAIN_H
+#define __MAIN_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Includes ------------------------------------------------------------------*/
+#include "py32f0xx_hal.h"
+
+/* Private includes ----------------------------------------------------------*/
+/* Private defines -----------------------------------------------------------*/
+#define GPIO_LED_2 GPIO_PIN_1
+#define GPIO_LED_3 GPIO_PIN_5
+#define GPIO_LED_4 GPIO_PIN_4
+
+/* Exported variables prototypes ---------------------------------------------*/
+/* Exported functions prototypes ---------------------------------------------*/
+void APP_ErrorHandler(void);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __MAIN_H */
+
+/************************ (C) COPYRIGHT Puya *****END OF FILE******************/

AliBoardExample/Core/Inc/py32f002b_hal_conf.h

@@ -0,0 +1,214 @@
+/**
+  ******************************************************************************
+  * @file    py32f002b_hal_conf.h
+  * @author  MCU Application Team
+  * @brief   HAL configuration file.
+  ******************************************************************************
+  * @attention
+  *
+  * <h2><center>&copy; Copyright (c) Puya Semiconductor Co.
+  * All rights reserved.</center></h2>
+  *
+  * <h2><center>&copy; Copyright (c) 2016 STMicroelectronics.
+  * All rights reserved.</center></h2>
+  *
+  * This software component is licensed by ST under BSD 3-Clause license,
+  * the "License"; You may not use this file except in compliance with the
+  * License. You may obtain a copy of the License at:
+  *                        opensource.org/licenses/BSD-3-Clause
+  *
+  ******************************************************************************
+  */
+
+/* Define to prevent recursive inclusion -------------------------------------*/
+#ifndef __PY32F002B_HAL_CONF_H
+#define __PY32F002B_HAL_CONF_H
+
+#ifdef __cplusplus
+ extern "C" {
+#endif
+
+/* Exported types ------------------------------------------------------------*/
+/* Exported constants --------------------------------------------------------*/
+
+/* ########################## Module Selection ############################## */
+/**
+  * @brief This is the list of modules to be used in the HAL driver 
+  */
+#define HAL_MODULE_ENABLED  
+#define HAL_RCC_MODULE_ENABLED
+//#define HAL_ADC_MODULE_ENABLED
+//#define HAL_CRC_MODULE_ENABLED
+//#define HAL_COMP_MODULE_ENABLED
+#define HAL_FLASH_MODULE_ENABLED   
+#define HAL_GPIO_MODULE_ENABLED    
+//#define HAL_IWDG_MODULE_ENABLED
+//#define HAL_TIM_MODULE_ENABLED
+//#define HAL_LPTIM_MODULE_ENABLED
+#define HAL_PWR_MODULE_ENABLED
+//#define HAL_I2C_MODULE_ENABLED
+//#define HAL_UART_MODULE_ENABLED
+#define HAL_USART_MODULE_ENABLED
+//#define HAL_SPI_MODULE_ENABLED
+//#define HAL_EXTI_MODULE_ENABLED
+#define HAL_CORTEX_MODULE_ENABLED  
+
+/* ########################## Oscillator Values adaptation ####################*/
+
+#if !defined  (HSI_VALUE) 
+  #define HSI_VALUE              ((uint32_t)24000000)     /*!< Value of the Internal oscillator in Hz */
+#endif /* HSI_VALUE */
+
+/**
+  * @brief Adjust the value of External High Speed oscillator (HSE) used in your application.
+  *        This value is used by the RCC HAL module to compute the system frequency
+  */
+#if !defined  (HSE_VALUE) 
+  #define HSE_VALUE              ((uint32_t)24000000) /*!< Value of the External oscillator in Hz */
+#endif /* HSE_VALUE */
+
+#if !defined  (HSE_STARTUP_TIMEOUT)
+  #define HSE_STARTUP_TIMEOUT    ((uint32_t)200)   /*!< Time out for HSE start up, in ms */
+#endif /* HSE_STARTUP_TIMEOUT */
+
+/**
+  * @brief Internal Low Speed Internal oscillator (LSI) value.
+  */
+#if !defined  (LSI_VALUE) 
+ #define LSI_VALUE               ((uint32_t)32768)    /*!< LSI Typical Value in Hz */
+#endif /* LSI_VALUE */                                /*!< Value of the Internal Low Speed oscillator in Hz
+                                                       The real value may vary depending on the variations
+                                                       in voltage and temperature. */
+
+/**
+  * @brief Adjust the value of External Low Speed oscillator (LSE) used in your application.
+  *        This value is used by the RCC HAL module to compute the system frequency  
+  */
+#if !defined  (LSE_VALUE)
+  #define LSE_VALUE              ((uint32_t)32768) /*!< Value of the External oscillator in Hz*/
+#endif /* LSE_VALUE */
+
+#if !defined  (LSE_STARTUP_TIMEOUT)
+  #define LSE_STARTUP_TIMEOUT    ((uint32_t)5000)   /*!< Time out for LSE start up, in ms */
+#endif /* LSE_STARTUP_TIMEOUT */
+
+/* Tip: To avoid modifying this file each time you need to use different HSE,
+   ===  you can define the HSE value in your toolchain compiler preprocessor. */
+
+/* ########################### System Configuration ######################### */
+/**
+  * @brief This is the HAL system configuration section
+  */     
+#define  VDD_VALUE               ((uint32_t)3300) /*!< Value of VDD in mv */           
+#define  PRIORITY_HIGHEST        0
+#define  PRIORITY_HIGH           1
+#define  PRIORITY_LOW            2
+#define  PRIORITY_LOWEST         3
+#define  TICK_INT_PRIORITY       ((uint32_t)PRIORITY_LOWEST)    /*!< tick interrupt priority (lowest by default)  */            
+#define  USE_RTOS                0
+#define  PREFETCH_ENABLE         0
+
+/* ########################## Assert Selection ############################## */
+/**
+  * @brief Uncomment the line below to expanse the "assert_param" macro in the 
+  *        HAL drivers code
+  */
+/* #define USE_FULL_ASSERT       1U */
+
+
+/* Includes ------------------------------------------------------------------*/
+/**
+  * @brief Include module's header file 
+  */
+#ifdef HAL_MODULE_ENABLED
+ #include "py32f0xx_hal.h"
+#endif /* HAL_MODULE_ENABLED */
+
+#ifdef HAL_RCC_MODULE_ENABLED
+ #include "py32f002b_hal_rcc.h"
+#endif /* HAL_RCC_MODULE_ENABLED */
+
+#ifdef HAL_EXTI_MODULE_ENABLED
+ #include "py32f002b_hal_exti.h"
+#endif /* HAL_EXTI_MODULE_ENABLED */
+
+#ifdef HAL_GPIO_MODULE_ENABLED
+ #include "py32f002b_hal_gpio.h"
+#endif /* HAL_GPIO_MODULE_ENABLED */
+
+#ifdef HAL_CORTEX_MODULE_ENABLED
+ #include "py32f002b_hal_cortex.h"
+#endif /* HAL_CORTEX_MODULE_ENABLED */
+
+#ifdef HAL_ADC_MODULE_ENABLED
+ #include "py32f002b_hal_adc.h"
+#endif /* HAL_ADC_MODULE_ENABLED */
+
+#ifdef HAL_CRC_MODULE_ENABLED
+ #include "py32f002b_hal_crc.h"
+#endif /* HAL_CRC_MODULE_ENABLED */
+
+#ifdef HAL_COMP_MODULE_ENABLED
+#include "py32f002b_hal_comp.h"
+#endif /* HAL_COMP_MODULE_ENABLED */
+
+#ifdef HAL_FLASH_MODULE_ENABLED
+ #include "py32f002b_hal_flash.h"
+#endif /* HAL_FLASH_MODULE_ENABLED */
+
+#ifdef HAL_I2C_MODULE_ENABLED
+ #include "py32f002b_hal_i2c.h"
+#endif /* HAL_I2C_MODULE_ENABLED */
+
+#ifdef HAL_IWDG_MODULE_ENABLED
+ #include "py32f002b_hal_iwdg.h"
+#endif /* HAL_IWDG_MODULE_ENABLED */
+
+#ifdef HAL_PWR_MODULE_ENABLED
+ #include "py32f002b_hal_pwr.h"
+#endif /* HAL_PWR_MODULE_ENABLED */
+
+#ifdef HAL_SPI_MODULE_ENABLED
+ #include "py32f002b_hal_spi.h"
+#endif /* HAL_SPI_MODULE_ENABLED */
+
+#ifdef HAL_TIM_MODULE_ENABLED
+ #include "py32f002b_hal_tim.h"
+#endif /* HAL_TIM_MODULE_ENABLED */
+
+#ifdef HAL_LPTIM_MODULE_ENABLED
+ #include "py32f002b_hal_lptim.h" 
+#endif /* HAL_LPTIM_MODULE_ENABLED */
+
+#ifdef HAL_UART_MODULE_ENABLED
+ #include "py32f002b_hal_uart.h"
+#endif /* HAL_UART_MODULE_ENABLED */
+
+#ifdef HAL_USART_MODULE_ENABLED
+ #include "py32f002b_hal_usart.h"
+#endif /* HAL_USART_MODULE_ENABLED */
+
+/* Exported macro ------------------------------------------------------------*/
+#ifdef  USE_FULL_ASSERT
+/**
+  * @brief  The assert_param macro is used for function's parameters check.
+  * @param  expr: If expr is false, it calls assert_failed function
+  *         which reports the name of the source file and the source
+  *         line number of the call that failed. 
+  *         If expr is true, it returns no value.
+  * @retval None
+  */
+  #define assert_param(expr) ((expr) ? (void)0U : assert_failed((uint8_t *)__FILE__, __LINE__))
+/* Exported functions ------------------------------------------------------- */
+  void assert_failed(uint8_t* file, uint32_t line);
+#else
+  #define assert_param(expr) ((void)0U)
+#endif /* USE_FULL_ASSERT */
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __PY32F002B_HAL_CONF_H */
+
+/************************ (C) COPYRIGHT Puya *****END OF FILE******************/

AliBoardExample/Core/Inc/py32f002b_it.h

@@ -0,0 +1,48 @@
+/**
+  ******************************************************************************
+  * @file    py32f002b_it.h
+  * @author  MCU Application Team
+  * @brief   This file contains the headers of the interrupt handlers.
+  ******************************************************************************
+  * @attention
+  *
+  * <h2><center>&copy; Copyright (c) Puya Semiconductor Co.
+  * All rights reserved.</center></h2>
+  *
+  * <h2><center>&copy; Copyright (c) 2016 STMicroelectronics.
+  * All rights reserved.</center></h2>
+  *
+  * This software component is licensed by ST under BSD 3-Clause license,
+  * the "License"; You may not use this file except in compliance with the
+  * License. You may obtain a copy of the License at:
+  *                        opensource.org/licenses/BSD-3-Clause
+  *
+  ******************************************************************************
+  */
+
+/* Define to prevent recursive inclusion -------------------------------------*/
+#ifndef __PY32F002B_IT_H
+#define __PY32F002B_IT_H
+
+#ifdef __cplusplus
+ extern "C" {
+#endif 
+
+/* Private includes ----------------------------------------------------------*/
+/* Exported types ------------------------------------------------------------*/
+/* Exported constants --------------------------------------------------------*/
+/* Exported macro ------------------------------------------------------------*/
+/* Exported functions prototypes ---------------------------------------------*/
+void NMI_Handler(void);
+void HardFault_Handler(void);
+void SVC_Handler(void);
+void PendSV_Handler(void);
+void SysTick_Handler(void);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* __PY32F002B_IT_H */
+
+/************************ (C) COPYRIGHT Puya *****END OF FILE******************/

AliBoardExample/Core/Src/gpio.c

@@ -0,0 +1,59 @@
+/**
+  ******************************************************************************
+  * @file    gpio.c
+  * @brief   This file provides code for the configuration
+  *          of all used GPIO pins.
+  ******************************************************************************
+  * @attention
+  *
+  * <h2><center>&copy; Copyright (c) Puya Semiconductor Co.
+  * All rights reserved.</center></h2>
+  *
+  * <h2><center>&copy; Copyright (c) 2016 STMicroelectronics.
+  * All rights reserved.</center></h2>
+  *
+  * This software component is licensed by ST under BSD 3-Clause license,
+  * the "License"; You may not use this file except in compliance with the
+  * License. You may obtain a copy of the License at:
+  *                        opensource.org/licenses/BSD-3-Clause
+  *
+  ******************************************************************************
+  */
+
+/* Includes ------------------------------------------------------------------*/
+#include "gpio.h"
+
+/* Private define ------------------------------------------------------------*/
+/* Private variables ---------------------------------------------------------*/
+/* Private user code ---------------------------------------------------------*/
+/* Private macro -------------------------------------------------------------*/
+/* Private function prototypes -----------------------------------------------*/
+/** Configure pins as
+        * Analog
+        * Input
+        * Output
+        * EVENT_OUT
+        * EXTI
+*/
+void MX_GPIO_Init(void)
+{
+
+  GPIO_InitTypeDef GPIO_InitStruct = {0};
+
+  /* GPIO Ports Clock Enable */
+  __HAL_RCC_GPIOA_CLK_ENABLE();
+
+  /*Configure LED GPIO pin : PA1 PA4 PA5 */
+  GPIO_InitStruct.Pin = GPIO_PIN_1|GPIO_PIN_4|GPIO_PIN_5;
+  GPIO_InitStruct.Mode = GPIO_MODE_OUTPUT_PP;
+  GPIO_InitStruct.Pull = GPIO_NOPULL;
+  GPIO_InitStruct.Speed = GPIO_SPEED_FREQ_LOW;
+  HAL_GPIO_Init(GPIOA, &GPIO_InitStruct);
+  
+  /*Configure KEY GPIO pin : PA3 PA0 */
+  GPIO_InitStruct.Pin = GPIO_PIN_0|GPIO_PIN_3;
+  GPIO_InitStruct.Mode = GPIO_MODE_INPUT;
+  GPIO_InitStruct.Pull = GPIO_PULLUP; 
+  HAL_GPIO_Init(GPIOA, &GPIO_InitStruct);
+}
+/************************ (C) COPYRIGHT Puya *****END OF FILE******************/

AliBoardExample/Core/Src/main.c

@@ -0,0 +1,161 @@
+/**
+  ******************************************************************************
+  * @file    main.c
+  * @author  MCU Application Team
+  * @brief   Main program body
+  ******************************************************************************
+  * @attention
+  *
+  * <h2><center>&copy; Copyright (c) Puya Semiconductor Co.
+  * All rights reserved.</center></h2>
+  *
+  * <h2><center>&copy; Copyright (c) 2016 STMicroelectronics.
+  * All rights reserved.</center></h2>
+  *
+  * This software component is licensed by ST under BSD 3-Clause license,
+  * the "License"; You may not use this file except in compliance with the
+  * License. You may obtain a copy of the License at:
+  *                        opensource.org/licenses/BSD-3-Clause
+  *
+  ******************************************************************************
+  */
+
+/* Includes ------------------------------------------------------------------*/
+#include "main.h"
+#include "gpio.h"
+
+/* Private define ------------------------------------------------------------*/
+/* Private variables ---------------------------------------------------------*/
+uint32_t led_delay = 100;
+/* Private user code ---------------------------------------------------------*/
+/* Private macro -------------------------------------------------------------*/
+/* Private function prototypes -----------------------------------------------*/
+static void APP_SystemClockConfig(void);
+
+/**
+  * @brief  Application Entry Function.
+  * @retval int
+  */
+int main(void)
+{
+  /* Reset of all peripherals, Initializes the Systick. */
+  HAL_Init();
+  
+  /* System clock configuration */
+  APP_SystemClockConfig();
+  
+  MX_GPIO_Init();  
+  
+  /* infinite loop */
+  while (1)
+  {
+    // ïî íàæàòèþ êíîïêè äèîäû ïðîáåãàþò "âíèç"
+    if((GPIOA->IDR & GPIO_PIN_0) == 0)
+    {
+      // ïåðåõîä ñ 2 äèîäà íà 4
+      GPIOA->ODR |= GPIO_LED_2;
+      GPIOA->ODR &= ~GPIO_LED_4;
+      HAL_Delay(led_delay);
+      // ïåðåõîä ñ 4 äèîäà íà 3
+      GPIOA->ODR |= GPIO_LED_4;
+      GPIOA->ODR &= ~GPIO_LED_3;
+      HAL_Delay(led_delay);
+      // ïåðåõîä ñ 3 äèîäà íà 2
+      GPIOA->ODR |= GPIO_LED_3;
+      GPIOA->ODR &= ~GPIO_LED_2;
+      HAL_Delay(led_delay);
+    }
+    // ïî íàæàòèþ êíîïêè äèîäû ïðîáåãàþò "ââåðõ"
+    else if ((GPIOA->IDR & GPIO_PIN_3) == 0)
+    {
+      // ïåðåõîä ñ 4 äèîäà íà 2
+      GPIOA->ODR |= GPIO_LED_4;
+      GPIOA->ODR &= ~GPIO_LED_2;
+      HAL_Delay(led_delay);
+      // ïåðåõîä ñ 2 äèîäà íà 3
+      GPIOA->ODR |= GPIO_LED_2;
+      GPIOA->ODR &= ~GPIO_LED_3;
+      HAL_Delay(led_delay);
+      // ïåðåõîä ñ 3 äèîäà íà 4
+      GPIOA->ODR |= GPIO_LED_3;
+      GPIOA->ODR &= ~GPIO_LED_4;
+      HAL_Delay(led_delay);
+    }
+    else
+    {
+      // âûêëþ÷åíèå âñåõ äèîäîâ
+      HAL_GPIO_WritePin(GPIOA, GPIO_LED_2|GPIO_LED_3|GPIO_LED_4, GPIO_PIN_SET);
+    }
+  }
+}
+
+/**
+  * @brief  System clock configuration function
+  * @param  None
+  * @retval None
+  */
+static void APP_SystemClockConfig(void)
+{
+  RCC_OscInitTypeDef RCC_OscInitStruct = {0};
+  RCC_ClkInitTypeDef RCC_ClkInitStruct = {0};
+
+  /* Oscillator configuration */
+  RCC_OscInitStruct.OscillatorType = RCC_OSCILLATORTYPE_HSE | RCC_OSCILLATORTYPE_HSI | RCC_OSCILLATORTYPE_LSI | RCC_OSCILLATORTYPE_LSE; /* Select oscillator HSE, HSI, LSI, LSE */
+  RCC_OscInitStruct.HSIState = RCC_HSI_ON;                           /* Enable HSI */
+  RCC_OscInitStruct.HSIDiv = RCC_HSI_DIV1;                           /* HSI 1 frequency division */
+  RCC_OscInitStruct.HSICalibrationValue = RCC_HSICALIBRATION_24MHz;  /* Configure HSI clock 24MHz */
+  RCC_OscInitStruct.HSEState = RCC_HSE_BYPASS_DISABLE;               /* Close HSE bypass */
+  RCC_OscInitStruct.LSIState = RCC_LSI_OFF;                          /* Close LSI */
+  /*RCC_OscInitStruct.LSICalibrationValue = RCC_LSICALIBRATION_32768Hz;*/
+  RCC_OscInitStruct.LSEState = RCC_LSE_OFF;                          /* Close LSE */
+  /*RCC_OscInitStruct.LSEDriver = RCC_LSEDRIVE_MEDIUM;*/
+  /* Configure oscillator */
+  if (HAL_RCC_OscConfig(&RCC_OscInitStruct) != HAL_OK)
+  {
+    APP_ErrorHandler();
+  }
+
+  /* Clock source configuration */
+  RCC_ClkInitStruct.ClockType = RCC_CLOCKTYPE_HCLK | RCC_CLOCKTYPE_SYSCLK | RCC_CLOCKTYPE_PCLK1; /* Choose to configure clock HCLK, SYSCLK, PCLK1 */
+  RCC_ClkInitStruct.SYSCLKSource = RCC_SYSCLKSOURCE_HSISYS; /* Select HSISYS as the system clock */
+  RCC_ClkInitStruct.AHBCLKDivider = RCC_SYSCLK_DIV1;        /* AHB clock 1 division */
+  RCC_ClkInitStruct.APB1CLKDivider = RCC_HCLK_DIV1;         /* APB clock 1 division */
+  /* Configure clock source */
+  if (HAL_RCC_ClockConfig(&RCC_ClkInitStruct, FLASH_LATENCY_0) != HAL_OK)
+  {
+    APP_ErrorHandler();
+  }
+}
+
+/**
+  * @brief  Error executing function.
+  * @param  None
+  * @retval None
+  */
+void APP_ErrorHandler(void)
+{
+  while (1)
+  {
+  }
+}
+
+#ifdef  USE_FULL_ASSERT
+/**
+  * @brief  Reports the name of the source file and the source line number
+  *         where the assert_param error has occurred.
+  * @param  file: pointer to the source file name
+  * @param  line: assert_param error line source number
+  * @retval None
+  */
+void assert_failed(uint8_t *file, uint32_t line)
+{
+  /* Users can add their own printing information as needed,
+     for example: printf("Wrong parameters value: file %s on line %d\r\n", file, line) */
+  /* Infinite loop */
+  while (1)
+  {
+  }
+}
+#endif /* USE_FULL_ASSERT */
+
+/************************ (C) COPYRIGHT Puya *****END OF FILE******************/

AliBoardExample/Core/Src/py32f002b_hal_msp.c

@@ -0,0 +1,43 @@
+/**
+  ******************************************************************************
+  * @file    py32f002b_hal_msp.c
+  * @author  MCU Application Team
+  * @brief   This file provides code for the MSP Initialization
+  *          and de-Initialization codes.
+  ******************************************************************************
+  * @attention
+  *
+  * <h2><center>&copy; Copyright (c) Puya Semiconductor Co.
+  * All rights reserved.</center></h2>
+  *
+  * <h2><center>&copy; Copyright (c) 2016 STMicroelectronics.
+  * All rights reserved.</center></h2>
+  *
+  * This software component is licensed by ST under BSD 3-Clause license,
+  * the "License"; You may not use this file except in compliance with the
+  * License. You may obtain a copy of the License at:
+  *                        opensource.org/licenses/BSD-3-Clause
+  *
+  ******************************************************************************
+  */
+
+/* Includes ------------------------------------------------------------------*/
+#include "main.h"
+
+/* Private typedef -----------------------------------------------------------*/
+/* Private define ------------------------------------------------------------*/
+/* Private macro -------------------------------------------------------------*/
+/* Private variables ---------------------------------------------------------*/
+/* Private function prototypes -----------------------------------------------*/
+/* External functions --------------------------------------------------------*/
+
+/**
+  * @brief Initialize global MSP.
+  */
+void HAL_MspInit(void)
+{
+  __HAL_RCC_SYSCFG_CLK_ENABLE();
+  __HAL_RCC_PWR_CLK_ENABLE();
+}
+
+/************************ (C) COPYRIGHT Puya *****END OF FILE******************/

AliBoardExample/Core/Src/py32f002b_it.c

@@ -0,0 +1,85 @@
+/**
+  ******************************************************************************
+  * @file    py32f002b_it.c
+  * @author  MCU Application Team
+  * @brief   Interrupt Service Routines.
+  ******************************************************************************
+  * @attention
+  *
+  * <h2><center>&copy; Copyright (c) Puya Semiconductor Co.
+  * All rights reserved.</center></h2>
+  *
+  * <h2><center>&copy; Copyright (c) 2016 STMicroelectronics.
+  * All rights reserved.</center></h2>
+  *
+  * This software component is licensed by ST under BSD 3-Clause license,
+  * the "License"; You may not use this file except in compliance with the
+  * License. You may obtain a copy of the License at:
+  *                        opensource.org/licenses/BSD-3-Clause
+  *
+  ******************************************************************************
+  */
+
+/* Includes ------------------------------------------------------------------*/
+#include "main.h"
+#include "py32f002b_it.h"
+
+/* Private includes ----------------------------------------------------------*/
+/* Private typedef -----------------------------------------------------------*/
+/* Private define ------------------------------------------------------------*/
+/* Private macro -------------------------------------------------------------*/
+/* Private variables ---------------------------------------------------------*/
+/* Private function prototypes -----------------------------------------------*/
+/* Private user code ---------------------------------------------------------*/
+/* External variables --------------------------------------------------------*/
+
+/******************************************************************************/
+/*          Cortex-M0+ Processor Interruption and Exception Handlers          */
+/******************************************************************************/
+/**
+  * @brief This function handles Non maskable interrupt.
+  */
+void NMI_Handler(void)
+{
+}
+
+/**
+  * @brief This function handles Hard fault interrupt.
+  */
+void HardFault_Handler(void)
+{
+  while (1)
+  {
+  }
+}
+
+/**
+  * @brief This function handles System service call via SWI instruction.
+  */
+void SVC_Handler(void)
+{
+}
+
+/**
+  * @brief This function handles Pendable request for system service.
+  */
+void PendSV_Handler(void)
+{
+}
+
+/**
+  * @brief This function handles System tick timer.
+  */
+void SysTick_Handler(void)
+{
+  HAL_IncTick();
+}
+
+/******************************************************************************/
+/* PY32F002B Peripheral Interrupt Handlers                                     */
+/* Add here the Interrupt Handlers for the used peripherals.                  */
+/* For the available peripheral interrupt handler names,                      */
+/* please refer to the startup file.                                          */
+/******************************************************************************/
+
+/************************ (C) COPYRIGHT Puya *****END OF FILE******************/

AliBoardExample/Core/Src/system_py32f002b.c

@@ -0,0 +1,162 @@
+/**
+  ******************************************************************************
+  * @file    system_py32f002b.c
+  * @author  MCU Application Team
+  * @Version V1.0.0
+  * @Date    2020-10-19
+  * @brief   CMSIS Cortex-M0+ Device Peripheral Access Layer System Source File.
+  ******************************************************************************
+  * @attention
+  *
+  * <h2><center>&copy; Copyright (c) Puya Semiconductor Co.
+  * All rights reserved.</center></h2>
+  *
+  * <h2><center>&copy; Copyright (c) 2016 STMicroelectronics.
+  * All rights reserved.</center></h2>
+  *
+  * This software component is licensed by ST under BSD 3-Clause license,
+  * the "License"; You may not use this file except in compliance with the
+  * License. You may obtain a copy of the License at:
+  *                        opensource.org/licenses/BSD-3-Clause
+  *
+  ******************************************************************************
+  */
+
+#include "py32f0xx.h"
+
+#if !defined  (HSE_VALUE)
+#define HSE_VALUE    24000000U    /*!< Value of the External oscillator in Hz */
+#endif /* HSE_VALUE */
+
+#if !defined  (HSI_VALUE)
+#define HSI_VALUE  24000000U   /*!< Value of the Internal oscillator in Hz*/
+#endif /* HSI_VALUE */
+
+#if !defined  (LSI_VALUE)
+#define LSI_VALUE   32768U      /*!< Value of LSI in Hz*/
+#endif /* LSI_VALUE */
+
+#if !defined  (LSE_VALUE)
+#define LSE_VALUE  32768U      /*!< Value of LSE in Hz*/
+#endif /* LSE_VALUE */
+
+
+/************************* Miscellaneous Configuration ************************/
+/*!< Uncomment the following line if you need to relocate your vector Table in
+     Internal SRAM. */
+/* #define FORBID_VECT_TAB_MIGRATION */
+/* #define VECT_TAB_SRAM */
+#define VECT_TAB_OFFSET  0x00 /*!< Vector Table base offset field.
+                                   This value must be a multiple of 0x100. */
+/******************************************************************************/
+/*----------------------------------------------------------------------------
+  Clock Variable definitions
+ *----------------------------------------------------------------------------*/
+/* This variable is updated in three ways:
+    1) by calling CMSIS function SystemCoreClockUpdate()
+    2) by calling HAL API function HAL_RCC_GetHCLKFreq()
+    3) each time HAL_RCC_ClockConfig() is called to configure the system clock frequency
+       Note: If you use this function to configure the system clock; then there
+             is no need to call the 2 first functions listed above, since SystemCoreClock
+             variable is updated automatically.
+*/
+uint32_t SystemCoreClock = HSI_VALUE;
+
+const uint32_t AHBPrescTable[16] = {0, 0, 0, 0, 0, 0, 0, 0, 1, 2, 3, 4, 6, 7, 8, 9};
+const uint32_t APBPrescTable[8] =  {0, 0, 0, 0, 1, 2, 3, 4};
+#if defined(RCC_HSI48M_SUPPORT)
+const uint32_t HSIFreqTable[8] = {0U, 0U, 0U, 0U, 24000000U, 48000000U, 0U, 0U};
+#else
+const uint32_t HSIFreqTable[8] = {0U, 0U, 0U, 0U, 24000000U, 0U, 0U, 0U};
+#endif
+
+/* Private function prototypes -----------------------------------------------*/
+#ifndef SWD_DELAY
+static void DelayTime(uint32_t mdelay);
+#endif /* SWD_DELAY */
+
+/**
+ * @brief  Clock functions.
+ * @param  none
+ * @return none
+ */
+void SystemCoreClockUpdate(void)             /* Get Core Clock Frequency      */
+{
+  uint32_t tmp;
+  uint32_t hsidiv;
+  uint32_t hsifs;
+
+  /* Get SYSCLK source -------------------------------------------------------*/
+  switch (RCC->CFGR & RCC_CFGR_SWS)
+  {
+  case RCC_CFGR_SWS_0:  /* HSE used as system clock */
+    SystemCoreClock = HSE_VALUE;
+    break;
+
+  case (RCC_CFGR_SWS_1 | RCC_CFGR_SWS_0):  /* LSI used as system clock */
+    SystemCoreClock = LSI_VALUE;
+    break;
+#if defined(RCC_LSE_SUPPORT)
+  case RCC_CFGR_SWS_2:  /* LSE used as system clock */
+    SystemCoreClock = LSE_VALUE;
+    break;
+#endif /* RCC_LSE_SUPPORT */
+  case 0x00000000U:  /* HSI used as system clock */
+  default:                /* HSI used as system clock */
+    hsifs = ((READ_BIT(RCC->ICSCR, RCC_ICSCR_HSI_FS)) >> RCC_ICSCR_HSI_FS_Pos);
+    hsidiv = (1UL << ((READ_BIT(RCC->CR, RCC_CR_HSIDIV)) >> RCC_CR_HSIDIV_Pos));
+    SystemCoreClock = (HSIFreqTable[hsifs] / hsidiv);
+    break;
+  }
+  /* Compute HCLK clock frequency --------------------------------------------*/
+  /* Get HCLK prescaler */
+  tmp = AHBPrescTable[((RCC->CFGR & RCC_CFGR_HPRE) >> RCC_CFGR_HPRE_Pos)];
+  /* HCLK clock frequency */
+  SystemCoreClock >>= tmp;
+}
+
+/**
+ * @brief  Setup the microcontroller system.
+ *         Initialize the System.
+ * @param  none
+ * @return none
+ */
+void SystemInit(void)
+{
+  /*Set the HSI clock to 24MHz by default*/
+  RCC->ICSCR = (RCC->ICSCR & 0xFFFF0000) | (*(uint32_t *)(0x1FFF0100));
+
+  /*Set the LSI clock to 32.768KHz by default*/
+  RCC->ICSCR = (RCC->ICSCR & 0xFE00FFFF) | ((*(uint32_t *)(0x1FFF0144)) << RCC_ICSCR_LSI_TRIM_Pos);
+
+  /* Configure the Vector Table location add offset address ------------------*/
+#ifdef VECT_TAB_SRAM
+  SCB->VTOR = SRAM_BASE | VECT_TAB_OFFSET; /* Vector Table Relocation in Internal SRAM */
+#else
+  SCB->VTOR = FLASH_BASE | VECT_TAB_OFFSET; /* Vector Table Relocation in Internal FLASH */
+#endif /* VECT_TAB_SRAM */
+
+#ifndef SWD_DELAY
+  /* When the SWD pin is reused for other functions, this function is used to solve the 
+  problem of not being able to update the code. */
+  DelayTime(100);
+#endif /* SWD_DELAY */
+}
+
+#ifndef SWD_DELAY
+/**
+  * @brief  This function provides delay (in milliseconds) based on CPU cycles method.
+  * @param  mdelay: specifies the delay time length, in milliseconds.
+  * @retval None
+  */
+static void DelayTime(uint32_t mdelay)
+{
+  __IO uint32_t Delay = mdelay * (24000000U / 8U / 1000U);
+  do
+  {
+    __NOP();
+  }
+  while (Delay --);
+}
+#endif /* SWD_DELAY */
+/************************ (C) COPYRIGHT Puya *****END OF FILE******************/

AliBoardExample/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        
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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        
+ */

AliBoardExample/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        
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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        
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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        
+ */

AliBoardExample/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        
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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        
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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        
+ */

AliBoardExample/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    
+ */

AliBoardExample/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       
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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        
+ */

AliBoardExample/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        
+ */

AliBoardExample/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        
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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    
+ */

AliBoardExample/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
+};

AliBoardExample/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        
+ */

AliBoardExample/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    
+ */

AliBoardExample/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        
+ */