This commit is contained in:
2025-02-28 12:32:54 +03:00
commit 3fe4b442a4
2259 changed files with 1042663 additions and 0 deletions

View File

@@ -0,0 +1,340 @@
/**
******************************************************************************
* @file py32f002bxx_Start_Kit.c
* @author MCU Application Team
* @brief This file provides set of firmware functions to manage Leds,
* push-button available on Start Kit.
******************************************************************************
* @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 "py32f002bxx_Start_Kit.h"
/**
* @brief PY32F002Bxx STK BSP Driver version number
*/
#define __PY32F002Bxx_STK_BSP_VERSION_MAIN (0x01U) /*!< [31:24] main version */
#define __PY32F002Bxx_STK_BSP_VERSION_SUB1 (0x00U) /*!< [23:16] sub1 version */
#define __PY32F002Bxx_STK_BSP_VERSION_SUB2 (0x00U) /*!< [15:8] sub2 version */
#define __PY32F002Bxx_STK_BSP_VERSION_RC (0x00U) /*!< [7:0] release candidate */
#define __PY32F002Bxx_STK_BSP_VERSION ((__PY32F002Bxx_STK_BSP_VERSION_MAIN << 24) \
|(__PY32F002Bxx_STK_BSP_VERSION_SUB1 << 16) \
|(__PY32F002Bxx_STK_BSP_VERSION_SUB2 << 8 ) \
|(__PY32F002Bxx_STK_BSP_VERSION_RC))
#ifdef HAL_UART_MODULE_ENABLED
UART_HandleTypeDef DebugUartHandle;
#endif
GPIO_TypeDef* LED_PORT[LEDn] = {LED3_GPIO_PORT};
const uint16_t LED_PIN[LEDn] = {LED3_PIN};
GPIO_TypeDef* BUTTON_PORT[BUTTONn] = {USER_BUTTON_GPIO_PORT };
const uint16_t BUTTON_PIN[BUTTONn] = {USER_BUTTON_PIN };
const uint8_t BUTTON_IRQn[BUTTONn] = {USER_BUTTON_EXTI_IRQn };
/** @addtogroup PY32F002Bxx_STK_Exported_Functions
* @{
*/
/**
* @brief This method returns the PY32F002B STK BSP Driver revision.
* @retval version : 0xXYZR (8bits for each decimal, R for RC)
*/
uint32_t BSP_GetVersion(void)
{
return __PY32F002Bxx_STK_BSP_VERSION;
}
/** @addtogroup LED_Functions
* @{
*/
/**
* @brief Configures LED GPIO.
* @param Led Specifies the Led to be configured.
* This parameter can be one of following parameters:
* @arg LED3
* @retval None
*/
void BSP_LED_Init(Led_TypeDef Led)
{
GPIO_InitTypeDef GPIO_InitStruct;
/* Enable the GPIO_LED Clock */
LEDx_GPIO_CLK_ENABLE(Led);
/* Configure the GPIO_LED pin */
GPIO_InitStruct.Pin = LED_PIN[Led];
GPIO_InitStruct.Mode = GPIO_MODE_OUTPUT_PP;
GPIO_InitStruct.Pull = GPIO_NOPULL;
GPIO_InitStruct.Speed = GPIO_SPEED_FREQ_HIGH;
HAL_GPIO_Init(LED_PORT[Led], &GPIO_InitStruct);
HAL_GPIO_WritePin(LED_PORT[Led], LED_PIN[Led], GPIO_PIN_SET);
}
/**
* @brief DeInitialize LED GPIO.
* @param Led Specifies the Led to be deconfigured.
* This parameter can be one of the following values:
* @arg LED3
* @note BSP_LED_DeInit() does not disable the GPIO clock
* @retval None
*/
void BSP_LED_DeInit(Led_TypeDef Led)
{
GPIO_InitTypeDef GPIO_InitStruct;
/* Turn off LED */
HAL_GPIO_WritePin(LED_PORT[Led], LED_PIN[Led], GPIO_PIN_RESET);
/* DeInit the GPIO_LED pin */
GPIO_InitStruct.Pin = LED_PIN[Led];
HAL_GPIO_DeInit(LED_PORT[Led], GPIO_InitStruct.Pin);
}
/**
* @brief Turns selected LED On.
* @param Led Specifies the Led to be set on.
* This parameter can be one of following parameters:
* @arg LED3
* @retval None
*/
void BSP_LED_On(Led_TypeDef Led)
{
HAL_GPIO_WritePin(LED_PORT[Led], LED_PIN[Led], GPIO_PIN_RESET);
}
/**
* @brief Turns selected LED Off.
* @param Led Specifies the Led to be set off.
* This parameter can be one of following parameters:
* @arg LED3
* @retval None
*/
void BSP_LED_Off(Led_TypeDef Led)
{
HAL_GPIO_WritePin(LED_PORT[Led], LED_PIN[Led], GPIO_PIN_SET);
}
/**
* @brief Toggles the selected LED.
* @param Led Specifies the Led to be toggled.
* This parameter can be one of following parameters:
* @arg LED3
* @retval None
*/
void BSP_LED_Toggle(Led_TypeDef Led)
{
HAL_GPIO_TogglePin(LED_PORT[Led], LED_PIN[Led]);
}
/**
* @brief Configures Button GPIO and EXTI Line.
* @param Button: Specifies the Button to be configured.
* This parameter should be: BUTTON_USER
* @param ButtonMode: Specifies Button mode.
* This parameter can be one of following parameters:
* @arg BUTTON_MODE_GPIO: Button will be used as simple IO
* @arg BUTTON_MODE_EXTI: Button will be connected to EXTI line with interrupt
* generation capability
* @retval None
*/
void BSP_PB_Init(Button_TypeDef Button, ButtonMode_TypeDef ButtonMode)
{
GPIO_InitTypeDef gpioinitstruct;
/* Enable the BUTTON Clock */
BUTTONx_GPIO_CLK_ENABLE(Button);
gpioinitstruct.Pin = BUTTON_PIN[Button];
gpioinitstruct.Pull = GPIO_NOPULL;
gpioinitstruct.Speed = GPIO_SPEED_FREQ_MEDIUM;
if(ButtonMode == BUTTON_MODE_GPIO)
{
/* Configure Button pin as input */
gpioinitstruct.Mode = GPIO_MODE_INPUT;
HAL_GPIO_Init(BUTTON_PORT[Button], &gpioinitstruct);
}
if(ButtonMode == BUTTON_MODE_EXTI)
{
/* Configure Button pin as input with External interrupt */
gpioinitstruct.Mode = GPIO_MODE_IT_FALLING;
HAL_GPIO_Init(BUTTON_PORT[Button], &gpioinitstruct);
/* Enable and set Button EXTI Interrupt to the lowest priority */
HAL_NVIC_SetPriority((IRQn_Type)(BUTTON_IRQn[Button]), 0x0F, 0);
HAL_NVIC_EnableIRQ((IRQn_Type)(BUTTON_IRQn[Button]));
}
}
/**
* @brief Push Button DeInit.
* @param Button: Button to be configured
* This parameter should be: BUTTON_USER
* @note PB DeInit does not disable the GPIO clock
* @retval None
*/
void BSP_PB_DeInit(Button_TypeDef Button)
{
GPIO_InitTypeDef gpio_init_structure;
gpio_init_structure.Pin = BUTTON_PIN[Button];
HAL_NVIC_DisableIRQ((IRQn_Type)(BUTTON_IRQn[Button]));
HAL_GPIO_DeInit(BUTTON_PORT[Button], gpio_init_structure.Pin);
}
/**
* @brief Returns the selected Button state.
* @param Button: Specifies the Button to be checked.
* This parameter should be: BUTTON_USER
* @retval Button state.
*/
uint32_t BSP_PB_GetState(Button_TypeDef Button)
{
return HAL_GPIO_ReadPin(BUTTON_PORT[Button], BUTTON_PIN[Button]);
}
#ifdef HAL_UART_MODULE_ENABLED
/**
* @brief DEBUG_USART GPIO Config,Mode Config,115200 8-N-1
* @param None
* @retval None
*/
void BSP_USART_Config(void)
{
GPIO_InitTypeDef GPIO_InitStruct;
DEBUG_USART_CLK_ENABLE();
DebugUartHandle.Instance = DEBUG_USART;
DebugUartHandle.Init.BaudRate = DEBUG_USART_BAUDRATE;
DebugUartHandle.Init.WordLength = UART_WORDLENGTH_8B;
DebugUartHandle.Init.StopBits = UART_STOPBITS_1;
DebugUartHandle.Init.Parity = UART_PARITY_NONE;
DebugUartHandle.Init.HwFlowCtl = UART_HWCONTROL_NONE;
DebugUartHandle.Init.Mode = UART_MODE_TX_RX;
HAL_UART_Init(&DebugUartHandle);
DEBUG_USART_RX_GPIO_CLK_ENABLE();
DEBUG_USART_TX_GPIO_CLK_ENABLE();
/**USART GPIO Configuration
PB4 ------> USART1_TX
PB5 ------> USART1_RX
*/
GPIO_InitStruct.Pin = DEBUG_USART_TX_PIN;
GPIO_InitStruct.Mode = GPIO_MODE_AF_PP;
GPIO_InitStruct.Pull = GPIO_PULLUP;
GPIO_InitStruct.Speed = GPIO_SPEED_FREQ_VERY_HIGH;
GPIO_InitStruct.Alternate = DEBUG_USART_TX_AF;
HAL_GPIO_Init(DEBUG_USART_TX_GPIO_PORT, &GPIO_InitStruct);
GPIO_InitStruct.Pin = DEBUG_USART_RX_PIN;
GPIO_InitStruct.Alternate = DEBUG_USART_RX_AF;
HAL_GPIO_Init(DEBUG_USART_RX_GPIO_PORT, &GPIO_InitStruct);
/* ENABLE NVIC */
HAL_NVIC_SetPriority(DEBUG_USART_IRQ,0,1);
HAL_NVIC_EnableIRQ(DEBUG_USART_IRQ );
}
#if (defined (__CC_ARM)) || (defined (__ARMCC_VERSION) && (__ARMCC_VERSION >= 6010050))
/**
* @brief writes a character to the usart
* @param ch
* *f
* @retval the character
*/
int fputc(int ch, FILE *f)
{
/* Send a byte to USART */
HAL_UART_Transmit(&DebugUartHandle, (uint8_t *)&ch, 1, 1000);
return (ch);
}
/**
* @brief get a character from the usart
* @param *f
* @retval a character
*/
int fgetc(FILE *f)
{
int ch;
HAL_UART_Receive(&DebugUartHandle, (uint8_t *)&ch, 1, 1000);
return (ch);
}
#elif defined(__ICCARM__)
/**
* @brief writes a character to the usart
* @param ch
* *f
* @retval the character
*/
int putchar(int ch)
{
/* Send a byte to USART */
HAL_UART_Transmit(&DebugUartHandle, (uint8_t *)&ch, 1, 1000);
return (ch);
}
#elif defined(__GNUC__)
/**
* @brief writes a character to the usart
* @param ch
* @retval the character
*/
int __io_putchar(int ch)
{
/* Send a byte to USART */
HAL_UART_Transmit(&DebugUartHandle, (uint8_t *)&ch, 1, 1000);
return ch;
}
int _write(int file, char *ptr, int len)
{
int DataIdx;
for (DataIdx=0;DataIdx<len;DataIdx++)
{
__io_putchar(*ptr++);
}
return len;
}
#endif
#endif
/**
* @}
*/
/**
* @}
*/
/**
* @}
*/
/************************ (C) COPYRIGHT Puya *****END OF FILE****/

View File

@@ -0,0 +1,170 @@
/**
******************************************************************************
* @file py32f002bxx_Start_Kit.h
* @author MCU Application Team
* @brief This file provides set of firmware functions to manage Leds,
* push-button available on Start Kit.
******************************************************************************
* @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_START_KIT_H
#define PY32F002B_START_KIT_H
#ifdef __cplusplus
extern "C" {
#endif
/* Includes ------------------------------------------------------------------*/
#include "py32f0xx_hal.h"
/** @addtogroup BSP
* @{
*/
/** @defgroup py32f002b_Start_Kit
* @brief This section contains the exported types, contants and functions
* required to use the Nucleo 32 board.
* @{
*/
/** @defgroup py32f002b_Start_Kit_Exported_Types Exported Types
* @{
*/
typedef enum
{
LED3 = 0,
LED_GREEN = LED3
} Led_TypeDef;
typedef enum
{
BUTTON_USER = 0,
/* Alias */
BUTTON_KEY = BUTTON_USER
} Button_TypeDef;
typedef enum
{
BUTTON_MODE_GPIO = 0,
BUTTON_MODE_EXTI = 1
} ButtonMode_TypeDef;
#define LEDn 1
#define LED3_PIN GPIO_PIN_1
#define LED3_GPIO_PORT GPIOA
#define LED3_GPIO_CLK_ENABLE() __HAL_RCC_GPIOA_CLK_ENABLE()
#define LED3_GPIO_CLK_DISABLE() __HAL_RCC_GPIOA_CLK_DISABLE()
#define LEDx_GPIO_CLK_ENABLE(__INDEX__) do {LED3_GPIO_CLK_ENABLE(); } while(0U)
#define LEDx_GPIO_CLK_DISABLE(__INDEX__) LED3_GPIO_CLK_DISABLE()
#define BUTTONn 1
/**
* @brief User push-button
*/
#define USER_BUTTON_PIN GPIO_PIN_0
#define USER_BUTTON_GPIO_PORT GPIOA
#define USER_BUTTON_GPIO_CLK_ENABLE() __HAL_RCC_GPIOA_CLK_ENABLE()
#define USER_BUTTON_GPIO_CLK_DISABLE() __HAL_RCC_GPIOA_CLK_DISABLE()
#define USER_BUTTON_EXTI_IRQn EXTI0_1_IRQn
/* Aliases */
#define KEY_BUTTON_PIN USER_BUTTON_PIN
#define KEY_BUTTON_GPIO_PORT USER_BUTTON_GPIO_PORT
#define KEY_BUTTON_GPIO_CLK_ENABLE() USER_BUTTON_GPIO_CLK_ENABLE()
#define KEY_BUTTON_GPIO_CLK_DISABLE() USER_BUTTON_GPIO_CLK_DISABLE()
#define KEY_BUTTON_EXTI_IRQn USER_BUTTON_EXTI_IRQn
#define BUTTONx_GPIO_CLK_ENABLE(__INDEX__) do { if((__INDEX__) == 0) USER_BUTTON_GPIO_CLK_ENABLE();} while(0)
#define BUTTONx_GPIO_CLK_DISABLE(__INDEX__) (((__INDEX__) == 0) ? USER_BUTTON_GPIO_CLK_DISABLE() : 0)
#ifdef HAL_UART_MODULE_ENABLED
//debug printf redirect config
#define DEBUG_USART_BAUDRATE 115200
#define DEBUG_USART USART1
#define DEBUG_USART_CLK_ENABLE() do { \
__IO uint32_t tmpreg = 0x00U; \
SET_BIT(RCC->APBENR2, RCC_APBENR2_USART1EN);\
/* Delay after an RCC peripheral clock enabling */ \
tmpreg = READ_BIT(RCC->APBENR2, RCC_APBENR2_USART1EN);\
UNUSED(tmpreg); \
} while(0U)
#define __GPIOB_CLK_ENABLE() do { \
__IO uint32_t tmpreg = 0x00U; \
SET_BIT(RCC->IOPENR, RCC_IOPENR_GPIOBEN);\
/* Delay after an RCC peripheral clock enabling */ \
tmpreg = READ_BIT(RCC->IOPENR, RCC_IOPENR_GPIOBEN);\
UNUSED(tmpreg); \
} while(0U)
#define DEBUG_USART_RX_GPIO_PORT GPIOB
#define DEBUG_USART_RX_GPIO_CLK_ENABLE() __HAL_RCC_GPIOB_CLK_ENABLE()
#define DEBUG_USART_RX_PIN GPIO_PIN_5
#define DEBUG_USART_RX_AF GPIO_AF1_USART1
#define DEBUG_USART_TX_GPIO_PORT GPIOB
#define DEBUG_USART_TX_GPIO_CLK_ENABLE() __HAL_RCC_GPIOB_CLK_ENABLE()
#define DEBUG_USART_TX_PIN GPIO_PIN_4
#define DEBUG_USART_TX_AF GPIO_AF1_USART1
#define DEBUG_USART_IRQHandler USART1_IRQHandler
#define DEBUG_USART_IRQ USART1_IRQn
#endif
/************************************************************/
#ifdef HAL_UART_MODULE_ENABLED
extern UART_HandleTypeDef DebugUartHandle;
#endif
/** @defgroup Functions
* @{
*/
uint32_t BSP_GetVersion(void);
void BSP_LED_Init(Led_TypeDef Led);
void BSP_LED_DeInit(Led_TypeDef Led);
void BSP_LED_On(Led_TypeDef Led);
void BSP_LED_Off(Led_TypeDef Led);
void BSP_LED_Toggle(Led_TypeDef Led);
void BSP_PB_Init(Button_TypeDef Button, ButtonMode_TypeDef ButtonMode);
void BSP_PB_DeInit(Button_TypeDef Button);
uint32_t BSP_PB_GetState(Button_TypeDef Button);
void BSP_USART_Config(void);
#define DEBUG_USART_Config BSP_USART_Config
/**
* @}
*/
/**
* @}
*/
#ifdef __cplusplus
}
#endif
#endif /* PY32F002B_START_KIT_H */
/************************ (C) COPYRIGHT Puya *****END OF FILE****/

View File

@@ -0,0 +1,314 @@
/**
******************************************************************************
* @file py32f002bxx_ll_Start_Kit.c
* @author MCU Application Team
* @brief This file provides set of firmware functions to manage Leds,
* push-button available on Start Kit.
******************************************************************************
* @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 "py32f002bxx_ll_Start_Kit.h"
/**
* @brief PY32F002Bxx STK BSP Driver version number
*/
#define __PY32F002Bxx_STK_BSP_VERSION_MAIN (0x00U) /*!< [31:24] main version */
#define __PY32F002Bxx_STK_BSP_VERSION_SUB1 (0x00U) /*!< [23:16] sub1 version */
#define __PY32F002Bxx_STK_BSP_VERSION_SUB2 (0x01U) /*!< [15:8] sub2 version */
#define __PY32F002Bxx_STK_BSP_VERSION_RC (0x00U) /*!< [7:0] release candidate */
#define __PY32F002Bxx_STK_BSP_VERSION ((__PY32F002Bxx_STK_BSP_VERSION_MAIN << 24) \
|(__PY32F002Bxx_STK_BSP_VERSION_SUB1 << 16) \
|(__PY32F002Bxx_STK_BSP_VERSION_SUB2 << 8 ) \
|(__PY32F002Bxx_STK_BSP_VERSION_RC))
GPIO_TypeDef* LED_PORT[LEDn] = {LED3_GPIO_PORT};
const uint16_t LED_PIN[LEDn] = {LED3_PIN};
GPIO_TypeDef* BUTTON_PORT[BUTTONn] = {USER_BUTTON_GPIO_PORT };
const uint16_t BUTTON_PIN[BUTTONn] = {USER_BUTTON_PIN };
const uint8_t BUTTON_IRQn[BUTTONn] = {USER_BUTTON_EXTI_IRQn };
const uint32_t BUTTON_EXTI_LINE[BUTTONn] = {USER_BUTTON_EXTI_LINE };
/** @addtogroup PY32F002Bxx_STK_Exported_Functions
* @{
*/
/**
* @brief This method returns the PY32F002B STK BSP Driver revision.
* @retval version : 0xXYZR (8bits for each decimal, R for RC)
*/
uint32_t BSP_GetVersion(void)
{
return __PY32F002Bxx_STK_BSP_VERSION;
}
/** @addtogroup LED_Functions
* @{
*/
/**
* @brief Configures LED GPIO.
* @param Led Specifies the Led to be configured.
* This parameter can be one of following parameters:
* @arg LED3
* @retval None
*/
void BSP_LED_Init(Led_TypeDef Led)
{
/* Enable the GPIO_LED Clock */
LEDx_GPIO_CLK_ENABLE(Led);
/* Configure the GPIO_LED pin */
LL_GPIO_SetPinMode(LED_PORT[Led], LED_PIN[Led], LL_GPIO_MODE_OUTPUT);
/* LL_GPIO_SetPinOutputType(LED_PORT[Led], LED_PIN[Led], LL_GPIO_OUTPUT_PUSHPULL); */
/* LL_GPIO_SetPinSpeed(LED_PORT[Led], LED_PIN[Led], LL_GPIO_SPEED_FREQ_LOW); */
/* LL_GPIO_SetPinPull(LED_PORT[Led], LED_PIN[Led], LL_GPIO_PULL_NO); */
LL_GPIO_SetOutputPin(LED_PORT[Led], LED_PIN[Led]);
}
/**
* @brief DeInitialize LED GPIO.
* @param Led Specifies the Led to be deconfigured.
* This parameter can be one of the following values:
* @arg LED3
* @note BSP_LED_DeInit() does not disable the GPIO clock
* @retval None
*/
void BSP_LED_DeInit(Led_TypeDef Led)
{
/* Turn off LED */
LL_GPIO_ResetOutputPin(LED_PORT[Led], LED_PIN[Led]);
/* DeInit the GPIO_LED pin */
LL_GPIO_SetPinMode(LED_PORT[Led], LED_PIN[Led], LL_GPIO_MODE_ANALOG);
/* LL_GPIO_SetPinOutputType(LED_PORT[Led], LED_PIN[Led], LL_GPIO_OUTPUT_PUSHPULL); */
/* LL_GPIO_SetPinSpeed(LED_PORT[Led], LED_PIN[Led], LL_GPIO_SPEED_FREQ_LOW); */
/* LL_GPIO_SetPinPull(LED_PORT[Led], LED_PIN[Led], LL_GPIO_PULL_NO); */
}
/**
* @brief Turns selected LED On.
* @param Led Specifies the Led to be set on.
* This parameter can be one of following parameters:
* @arg LED3
* @retval None
*/
void BSP_LED_On(Led_TypeDef Led)
{
LL_GPIO_ResetOutputPin(LED_PORT[Led], LED_PIN[Led]);
}
/**
* @brief Turns selected LED Off.
* @param Led Specifies the Led to be set off.
* This parameter can be one of following parameters:
* @arg LED3
* @retval None
*/
void BSP_LED_Off(Led_TypeDef Led)
{
LL_GPIO_SetOutputPin(LED_PORT[Led], LED_PIN[Led]);
}
/**
* @brief Toggles the selected LED.
* @param Led Specifies the Led to be toggled.
* This parameter can be one of following parameters:
* @arg LED3
* @retval None
*/
void BSP_LED_Toggle(Led_TypeDef Led)
{
LL_GPIO_TogglePin(LED_PORT[Led], LED_PIN[Led]);
}
/**
* @brief Configures Button GPIO and EXTI Line.
* @param Button: Specifies the Button to be configured.
* This parameter should be: BUTTON_USER
* @param ButtonMode: Specifies Button mode.
* This parameter can be one of following parameters:
* @arg BUTTON_MODE_GPIO: Button will be used as simple IO
* @arg BUTTON_MODE_EXTI: Button will be connected to EXTI line with interrupt
* generation capability
* @retval None
*/
void BSP_PB_Init(Button_TypeDef Button, ButtonMode_TypeDef ButtonMode)
{
/* Enable the BUTTON Clock */
BUTTONx_GPIO_CLK_ENABLE(Button);
/* Configure GPIO for BUTTON */
LL_GPIO_SetPinMode(BUTTON_PORT[Button], BUTTON_PIN[Button], LL_GPIO_MODE_INPUT);
LL_GPIO_SetPinPull(BUTTON_PORT[Button], BUTTON_PIN[Button], LL_GPIO_PULL_NO);
/* LL_GPIO_SetPinSpeed(BUTTON_PORT[Button], BUTTON_PIN[Button], LL_GPIO_SPEED_FREQ_HIGH); */
if(ButtonMode == BUTTON_MODE_EXTI)
{
/* Configure Button pin as input with External interrupt */
LL_EXTI_EnableIT(BUTTON_EXTI_LINE[Button]);
LL_EXTI_EnableFallingTrig(BUTTON_EXTI_LINE[Button]);
/* Enable and set Button EXTI Interrupt to the lowest priority */
NVIC_SetPriority((IRQn_Type)(BUTTON_IRQn[Button]), 0x0F);
NVIC_EnableIRQ((IRQn_Type)(BUTTON_IRQn[Button]));
}
}
/**
* @brief Push Button DeInit.
* @param Button: Button to be configured
* This parameter should be: BUTTON_USER
* @note PB DeInit does not disable the GPIO clock
* @retval None
*/
void BSP_PB_DeInit(Button_TypeDef Button)
{
NVIC_DisableIRQ((IRQn_Type)(BUTTON_IRQn[Button]));
LL_GPIO_SetPinMode(BUTTON_PORT[Button], BUTTON_PIN[Button], LL_GPIO_MODE_ANALOG);
/* LL_GPIO_SetPinSpeed(BUTTON_PORT[Button], BUTTON_PIN[Button], LL_GPIO_SPEED_FREQ_LOW); */
/* LL_GPIO_SetPinPull(BUTTON_PORT[Button], BUTTON_PIN[Button], LL_GPIO_PULL_NO); */
/* LL_GPIO_SetAFPin_8_15(BUTTON_PORT[Button], BUTTON_PIN[Button], LL_GPIO_AF_0); */
}
/**
* @brief Returns the selected Button state.
* @param Button: Specifies the Button to be checked.
* This parameter should be: BUTTON_USER
* @retval Button state.
*/
uint32_t BSP_PB_GetState(Button_TypeDef Button)
{
return LL_GPIO_IsInputPinSet(BUTTON_PORT[Button], BUTTON_PIN[Button]);
}
/**
* @brief DEBUG_USART GPIO Config,Mode Config,115200 8-N-1
* @param None
* @retval None
*/
void BSP_USART_Config(void)
{
DEBUG_USART_CLK_ENABLE();
/* USART Init */
LL_USART_SetBaudRate(DEBUG_USART, SystemCoreClock, LL_USART_OVERSAMPLING_16, DEBUG_USART_BAUDRATE);
LL_USART_SetDataWidth(DEBUG_USART, LL_USART_DATAWIDTH_8B);
LL_USART_SetStopBitsLength(DEBUG_USART, LL_USART_STOPBITS_1);
LL_USART_SetParity(DEBUG_USART, LL_USART_PARITY_NONE);
LL_USART_SetHWFlowCtrl(DEBUG_USART, LL_USART_HWCONTROL_NONE);
LL_USART_SetTransferDirection(DEBUG_USART, LL_USART_DIRECTION_TX_RX);
LL_USART_Enable(DEBUG_USART);
LL_USART_ClearFlag_TC(DEBUG_USART);
/**USART GPIO Configuration
PB4 ------> USART1_TX
PB5 ------> USART1_RX
*/
DEBUG_USART_RX_GPIO_CLK_ENABLE();
DEBUG_USART_TX_GPIO_CLK_ENABLE();
LL_GPIO_SetPinMode(DEBUG_USART_TX_GPIO_PORT, DEBUG_USART_TX_PIN, LL_GPIO_MODE_ALTERNATE);
LL_GPIO_SetPinSpeed(DEBUG_USART_TX_GPIO_PORT, DEBUG_USART_TX_PIN, LL_GPIO_SPEED_FREQ_VERY_HIGH);
LL_GPIO_SetPinPull(DEBUG_USART_TX_GPIO_PORT, DEBUG_USART_TX_PIN, LL_GPIO_PULL_UP);
LL_GPIO_SetAFPin_0_7(DEBUG_USART_TX_GPIO_PORT, DEBUG_USART_TX_PIN, DEBUG_USART_TX_AF);
LL_GPIO_SetPinMode(DEBUG_USART_RX_GPIO_PORT, DEBUG_USART_RX_PIN, LL_GPIO_MODE_ALTERNATE);
LL_GPIO_SetPinSpeed(DEBUG_USART_RX_GPIO_PORT, DEBUG_USART_RX_PIN, LL_GPIO_SPEED_FREQ_VERY_HIGH);
LL_GPIO_SetPinPull(DEBUG_USART_RX_GPIO_PORT, DEBUG_USART_RX_PIN, LL_GPIO_PULL_UP);
LL_GPIO_SetAFPin_0_7(DEBUG_USART_RX_GPIO_PORT, DEBUG_USART_RX_PIN, DEBUG_USART_RX_AF);
}
#if (defined (__CC_ARM)) || (defined (__ARMCC_VERSION) && (__ARMCC_VERSION >= 6010050))
/**
* @brief writes a character to the usart
* @param ch
* *f
* @retval the character
*/
int fputc(int ch, FILE *f)
{
/* Send a byte to USART */
LL_USART_TransmitData8(DEBUG_USART, ch);
while (!LL_USART_IsActiveFlag_TC(DEBUG_USART));
LL_USART_ClearFlag_TC(DEBUG_USART);
return (ch);
}
/**
* @brief get a character from the usart
* @param *f
* @retval a character
*/
int fgetc(FILE *f)
{
int ch;
while (!LL_USART_IsActiveFlag_RXNE(DEBUG_USART));
ch = LL_USART_ReceiveData8(DEBUG_USART);
return (ch);
}
#elif defined(__ICCARM__)
/**
* @brief writes a character to the usart
* @param ch
* *f
* @retval the character
*/
int putchar(int ch)
{
/* Send a byte to USART */
LL_USART_TransmitData8(DEBUG_USART, ch);
while (!LL_USART_IsActiveFlag_TC(DEBUG_USART));
LL_USART_ClearFlag_TC(DEBUG_USART);
return (ch);
}
#elif defined(__GNUC__)
/**
* @brief writes a character to the usart
* @param ch
* @retval the character
*/
int __io_putchar(int ch)
{
/* Send a byte to USART */
LL_USART_TransmitData8(DEBUG_USART, ch);
while (!LL_USART_IsActiveFlag_TC(DEBUG_USART));
LL_USART_ClearFlag_TC(DEBUG_USART);
return ch;
}
int _write(int file, char *ptr, int len)
{
int DataIdx;
for (DataIdx=0;DataIdx<len;DataIdx++)
{
__io_putchar(*ptr++);
}
return len;
}
#endif
/**
* @}
*/
/************************ (C) COPYRIGHT Puya *****END OF FILE****/

View File

@@ -0,0 +1,170 @@
/**
******************************************************************************
* @file py32f002bxx_ll_Start_Kit.h
* @author MCU Application Team
* @brief This file provides set of firmware functions to manage Leds,
* push-button available on Start Kit.
******************************************************************************
* @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 __PY32F002Bxx_LL_START_KIT_H
#define __PY32F002Bxx_LL_START_KIT_H
#ifdef __cplusplus
extern "C" {
#endif
/* Includes ------------------------------------------------------------------*/
#include <stdio.h>
#include "py32f002b_ll_rcc.h"
#include "py32f002b_ll_bus.h"
#include "py32f002b_ll_system.h"
#include "py32f002b_ll_exti.h"
#include "py32f002b_ll_cortex.h"
#include "py32f002b_ll_utils.h"
#include "py32f002b_ll_pwr.h"
#include "py32f002b_ll_gpio.h"
#include "py32f002b_ll_usart.h"
/** @addtogroup BSP
* @{
*/
/** @defgroup py32f002bxx_Start_Kit
* @brief This section contains the exported types, contants and functions
* required to use the Nucleo 32 board.
* @{
*/
/** @defgroup py32f002bxx_Start_Kit_Exported_Types Exported Types
* @{
*/
typedef enum
{
LED3 = 0,
LED_GREEN = LED3
} Led_TypeDef;
typedef enum
{
BUTTON_USER = 0,
/* Alias */
BUTTON_KEY = BUTTON_USER
} Button_TypeDef;
typedef enum
{
BUTTON_MODE_GPIO = 0,
BUTTON_MODE_EXTI = 1
} ButtonMode_TypeDef;
#define LEDn 1
#define LED3_PIN LL_GPIO_PIN_1
#define LED3_GPIO_PORT GPIOA
#define LED3_GPIO_CLK_ENABLE() LL_IOP_GRP1_EnableClock(LL_IOP_GRP1_PERIPH_GPIOA)
#define LED3_GPIO_CLK_DISABLE() LL_IOP_GRP1_DisableClock(LL_IOP_GRP1_PERIPH_GPIOA)
#define LEDx_GPIO_CLK_ENABLE(__INDEX__) do {LED3_GPIO_CLK_ENABLE(); } while(0U)
#define LEDx_GPIO_CLK_DISABLE(__INDEX__) LED3_GPIO_CLK_DISABLE())
#define BUTTONn 1
/**
* @brief User push-button
*/
#define USER_BUTTON_PIN LL_GPIO_PIN_0
#define USER_BUTTON_GPIO_PORT GPIOA
#define USER_BUTTON_GPIO_CLK_ENABLE() LL_IOP_GRP1_EnableClock(LL_IOP_GRP1_PERIPH_GPIOA)
#define USER_BUTTON_GPIO_CLK_DISABLE() LL_IOP_GRP1_DisableClock(LL_IOP_GRP1_PERIPH_GPIOA)
#define USER_BUTTON_EXTI_IRQn EXTI0_1_IRQn
#define USER_BUTTON_EXTI_LINE LL_EXTI_LINE_0
#define USER_BUTTON_EXTI_LINE_ENABLE() LL_EXTI_EnableIT(USER_BUTTON_EXTI_LINE)
#define USER_BUTTON_EXTI_FALLING_TRIG_ENABLE() LL_EXTI_EnableFallingTrig(USER_BUTTON_EXTI_LINE)
#define USER_BUTTON_IRQHANDLER EXTI0_1_IRQHandler
/* Aliases */
#define KEY_BUTTON_PIN USER_BUTTON_PIN
#define KEY_BUTTON_GPIO_PORT USER_BUTTON_GPIO_PORT
#define KEY_BUTTON_GPIO_CLK_ENABLE() USER_BUTTON_GPIO_CLK_ENABLE()
#define KEY_BUTTON_GPIO_CLK_DISABLE() USER_BUTTON_GPIO_CLK_DISABLE()
#define KEY_BUTTON_EXTI_IRQn USER_BUTTON_EXTI_IRQn
#define BUTTONx_GPIO_CLK_ENABLE(__INDEX__) do { if((__INDEX__) == 0) USER_BUTTON_GPIO_CLK_ENABLE();} while(0)
#define BUTTONx_GPIO_CLK_DISABLE(__INDEX__) (((__INDEX__) == 0) ? USER_BUTTON_GPIO_CLK_DISABLE() : 0)
//debug printf redirect config
#define DEBUG_USART_BAUDRATE 115200
#define DEBUG_USART USART1
#define DEBUG_USART_CLK_ENABLE() LL_APB1_GRP2_EnableClock(LL_APB1_GRP2_PERIPH_USART1)
#define __GPIOA_CLK_ENABLE() do { \
__IO uint32_t tmpreg = 0x00U; \
SET_BIT(RCC->IOPENR, RCC_IOPENR_GPIOAEN);\
/* Delay after an RCC peripheral clock enabling */ \
tmpreg = READ_BIT(RCC->IOPENR, RCC_IOPENR_GPIOAEN);\
UNUSED(tmpreg); \
} while(0U)
#define DEBUG_USART_RX_GPIO_PORT GPIOB
#define DEBUG_USART_RX_GPIO_CLK_ENABLE() LL_IOP_GRP1_EnableClock(LL_IOP_GRP1_PERIPH_GPIOB)
#define DEBUG_USART_RX_PIN LL_GPIO_PIN_5
#define DEBUG_USART_RX_AF LL_GPIO_AF_1
#define DEBUG_USART_TX_GPIO_PORT GPIOB
#define DEBUG_USART_TX_GPIO_CLK_ENABLE() LL_IOP_GRP1_EnableClock(LL_IOP_GRP1_PERIPH_GPIOB)
#define DEBUG_USART_TX_PIN LL_GPIO_PIN_4
#define DEBUG_USART_TX_AF LL_GPIO_AF_1
#define DEBUG_USART_IRQHandler USART1_IRQHandler
#define DEBUG_USART_IRQ USART1_IRQn
/************************************************************/
/** @defgroup Functions
* @{
*/
uint32_t BSP_GetVersion(void);
void BSP_LED_Init(Led_TypeDef Led);
void BSP_LED_DeInit(Led_TypeDef Led);
void BSP_LED_On(Led_TypeDef Led);
void BSP_LED_Off(Led_TypeDef Led);
void BSP_LED_Toggle(Led_TypeDef Led);
void BSP_PB_Init(Button_TypeDef Button, ButtonMode_TypeDef ButtonMode);
void BSP_PB_DeInit(Button_TypeDef Button);
uint32_t BSP_PB_GetState(Button_TypeDef Button);
void BSP_USART_Config(void);
/**
* @}
*/
/**
* @}
*/
#ifdef __cplusplus
}
#endif
#endif /* PY32F002Bxx_LL_START_KIT_H */
/************************ (C) COPYRIGHT Puya *****END OF FILE****/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

File diff suppressed because it is too large Load Diff

View File

@@ -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
};

View File

@@ -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
*/

View File

@@ -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
*/

View File

@@ -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
*/

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

Some files were not shown because too many files have changed in this diff Show More