【NUCLEO-H743ZI】6、FFT计算性能测试

dql2016 · 发表于2023-10-11 22:02

【NUCLEO-H743ZI】6、FFT计算性能测试 [复制链接]

在前面的帖子中完成了DSP库使用环境的搭建，本帖进行数字信号常用的FFT计算测试。

将例子en.stm32cubeh7_v1-11-0\STM32Cube_FW_H7_V1.11.0\Drivers\CMSIS\DSP\Examples\ARM\arm_fft_bin_example中的测试代码加入到DSP测试工程

对例子进行简单修改，只需计算FFT：

修改后的测试代码如下：

#include "arm_math.h"
#include "arm_const_structs.h"

#define TEST_LENGTH_SAMPLES 2048

/* -------------------------------------------------------------------
* External Input and Output buffer Declarations for FFT Bin Example
* ------------------------------------------------------------------- */
extern float32_t testInput_f32_10khz[TEST_LENGTH_SAMPLES];
static float32_t testOutput[TEST_LENGTH_SAMPLES/2];

/* ------------------------------------------------------------------
* Global variables for FFT Bin Example
* ------------------------------------------------------------------- */
uint32_t fftSize = 1024;
uint32_t ifftFlag = 0;
uint32_t doBitReverse = 1;

int32_t fft_test(void)
{
  /* Process the data through the CFFT/CIFFT module */
  arm_cfft_f32(&arm_cfft_sR_f32_len1024, testInput_f32_10khz, ifftFlag, doBitReverse);
}

利用STM32 M7内核自带的DWT模块进行代码执行时间的测量：

测试主函数内容如下：

/* USER CODE BEGIN Header */
/**
  ******************************************************************************
  * [url=home.php?mod=space&uid=1307177]@File[/url] : main.c
  * [url=home.php?mod=space&uid=159083]@brief[/url] : Main program body
  ******************************************************************************
  * [url=home.php?mod=space&uid=1020061]@attention[/url] *
  * Copyright (c) 2023 STMicroelectronics.
  * All rights reserved.
  *
  * This software is licensed under terms that can be found in the LICENSE file
  * in the root directory of this software component.
  * If no LICENSE file comes with this software, it is provided AS-IS.
  *
  ******************************************************************************
  */
/* USER CODE END Header */
/* Includes ------------------------------------------------------------------*/
#include "main.h"
#include "eth.h"
#include "usart.h"
#include "usb_otg.h"
#include "gpio.h"

/* Private includes ----------------------------------------------------------*/
/* USER CODE BEGIN Includes */

/* USER CODE END Includes */

/* Private typedef -----------------------------------------------------------*/
/* USER CODE BEGIN PTD */

/* USER CODE END PTD */

/* Private define ------------------------------------------------------------*/
/* USER CODE BEGIN PD */

/* USER CODE END PD */

/* Private macro -------------------------------------------------------------*/
/* USER CODE BEGIN PM */

/* USER CODE END PM */

/* Private variables ---------------------------------------------------------*/

/* USER CODE BEGIN PV */

/* USER CODE END PV */

/* Private function prototypes -----------------------------------------------*/
void SystemClock_Config(void);
/* USER CODE BEGIN PFP */

/* USER CODE END PFP */

/* Private user code ---------------------------------------------------------*/
/* USER CODE BEGIN 0 */

#include "arm_math.h"

uint32_t dwt_init(void) 
{
    uint32_t c = 0;

    /* Enable TRC */
    CoreDebug->DEMCR &= ~0x01000000;
    CoreDebug->DEMCR |=  0x01000000;

    /* Enable counter */
    DWT->CTRL &= ~0x00000001;
    DWT->CTRL |=  0x00000001;

    /* Reset counter */
    DWT->CYCCNT = 0;

    /* Check if DWT has started */
    c = DWT->CYCCNT;

    /* 2 dummys */
    __ASM volatile ("NOP");
    __ASM volatile ("NOP");

    /* Return difference, if result is zero, DWT has not started */
    return (DWT->CYCCNT - c);
}
  
/* USER CODE END 0 */

/**
  * @brief  The application entry point.
  * @retval int
  */
int main(void)
{
  /* USER CODE BEGIN 1 */

  /* USER CODE END 1 */

  /* Enable I-Cache---------------------------------------------------------*/
  SCB_EnableICache();

  /* Enable D-Cache---------------------------------------------------------*/
  SCB_EnableDCache();

  /* MCU Configuration--------------------------------------------------------*/

  /* Reset of all peripherals, Initializes the Flash interface and the Systick. */
  HAL_Init();

  /* USER CODE BEGIN Init */

  /* USER CODE END Init */

  /* Configure the system clock */
  SystemClock_Config();

  /* USER CODE BEGIN SysInit */

  /* USER CODE END SysInit */

  /* Initialize all configured peripherals */
  MX_GPIO_Init();
  MX_USART3_UART_Init();
  MX_USB_OTG_FS_PCD_Init();
  MX_ETH_Init();
  /* USER CODE BEGIN 2 */
  
    if(dwt_init() == 0)
    {
        printf("dwt init error\r\n");
    }

    extern int32_t fft_test(void);

    uint32_t t1 = DWT->CYCCNT;

    fft_test();
    uint32_t t2 = DWT->CYCCNT;

    uint32_t t = ((t2-t1)*HAL_RCC_GetHCLKFreq() / 1000000);
    
    printf("clk=%dMHz t=%dus\r\n",SystemCoreClock/1000000,t);
  
  /* USER CODE END 2 */

  /* Infinite loop */
  /* USER CODE BEGIN WHILE */
  while (1)
  {
    /* USER CODE END WHILE */

    /* USER CODE BEGIN 3 */

    HAL_GPIO_WritePin (LD1_GPIO_Port, LD1_Pin, GPIO_PIN_RESET);
    HAL_GPIO_WritePin (LD2_GPIO_Port, LD2_Pin, GPIO_PIN_RESET);
    HAL_GPIO_WritePin (LD3_GPIO_Port, LD3_Pin, GPIO_PIN_RESET);
    HAL_Delay(100);
    HAL_GPIO_WritePin (LD1_GPIO_Port, LD1_Pin, GPIO_PIN_SET);
    HAL_GPIO_WritePin (LD2_GPIO_Port, LD2_Pin, GPIO_PIN_SET);
    HAL_GPIO_WritePin (LD3_GPIO_Port, LD3_Pin, GPIO_PIN_SET);
    HAL_Delay(100);
    
  }
  /* USER CODE END 3 */
}

/**
  * @brief System Clock Configuration
  * @retval None
  */
void SystemClock_Config(void)
{
  RCC_OscInitTypeDef RCC_OscInitStruct = {0};
  RCC_ClkInitTypeDef RCC_ClkInitStruct = {0};

  /** Supply configuration update enable
  */
  HAL_PWREx_ConfigSupply(PWR_LDO_SUPPLY);

  /** Configure the main internal regulator output voltage
  */
  __HAL_PWR_VOLTAGESCALING_CONFIG(PWR_REGULATOR_VOLTAGE_SCALE1);

  while(!__HAL_PWR_GET_FLAG(PWR_FLAG_VOSRDY)) {}

  /** Initializes the RCC Oscillators according to the specified parameters
  * in the RCC_OscInitTypeDef structure.
  */
  RCC_OscInitStruct.OscillatorType = RCC_OSCILLATORTYPE_HSI48|RCC_OSCILLATORTYPE_HSI;
  RCC_OscInitStruct.HSIState = RCC_HSI_DIV1;
  RCC_OscInitStruct.HSICalibrationValue = RCC_HSICALIBRATION_DEFAULT;
  RCC_OscInitStruct.HSI48State = RCC_HSI48_ON;
  RCC_OscInitStruct.PLL.PLLState = RCC_PLL_ON;
  RCC_OscInitStruct.PLL.PLLSource = RCC_PLLSOURCE_HSI;
  RCC_OscInitStruct.PLL.PLLM = 4;
  RCC_OscInitStruct.PLL.PLLN = 50;
  RCC_OscInitStruct.PLL.PLLP = 2;
  RCC_OscInitStruct.PLL.PLLQ = 4;
  RCC_OscInitStruct.PLL.PLLR = 2;
  RCC_OscInitStruct.PLL.PLLRGE = RCC_PLL1VCIRANGE_3;
  RCC_OscInitStruct.PLL.PLLVCOSEL = RCC_PLL1VCOWIDE;
  RCC_OscInitStruct.PLL.PLLFRACN = 0;
  if (HAL_RCC_OscConfig(&RCC_OscInitStruct) != HAL_OK)
  {
    Error_Handler();
  }

  /** Initializes the CPU, AHB and APB buses clocks
  */
  RCC_ClkInitStruct.ClockType = RCC_CLOCKTYPE_HCLK|RCC_CLOCKTYPE_SYSCLK
                              |RCC_CLOCKTYPE_PCLK1|RCC_CLOCKTYPE_PCLK2
                              |RCC_CLOCKTYPE_D3PCLK1|RCC_CLOCKTYPE_D1PCLK1;
  RCC_ClkInitStruct.SYSCLKSource = RCC_SYSCLKSOURCE_PLLCLK;
  RCC_ClkInitStruct.SYSCLKDivider = RCC_SYSCLK_DIV1;
  RCC_ClkInitStruct.AHBCLKDivider = RCC_HCLK_DIV2;
  RCC_ClkInitStruct.APB3CLKDivider = RCC_APB3_DIV2;
  RCC_ClkInitStruct.APB1CLKDivider = RCC_APB1_DIV2;
  RCC_ClkInitStruct.APB2CLKDivider = RCC_APB2_DIV2;
  RCC_ClkInitStruct.APB4CLKDivider = RCC_APB4_DIV2;

  if (HAL_RCC_ClockConfig(&RCC_ClkInitStruct, FLASH_LATENCY_2) != HAL_OK)
  {
    Error_Handler();
  }
}

/* USER CODE BEGIN 4 */

/* USER CODE END 4 */

/**
  * @brief  This function is executed in case of error occurrence.
  * @retval None
  */
void Error_Handler(void)
{
  /* USER CODE BEGIN Error_Handler_Debug */
  /* User can add his own implementation to report the HAL error return state */
  __disable_irq();
  while (1)
  {
  }
  /* USER CODE END Error_Handler_Debug */
}

#ifdef  USE_FULL_ASSERT
/**
  * @brief  Reports the name of the source file and the source line number
  *         where the assert_param error has occurred.
  * @param  file: pointer to the source file name
  * @param  line: assert_param error line source number
  * @retval None
  */
void assert_failed(uint8_t *file, uint32_t line)
{
  /* USER CODE BEGIN 6 */
  /* User can add his own implementation to report the file name and line number,
     ex: printf("Wrong parameters value: file %s on line %d\r\n", file, line) */
  /* USER CODE END 6 */
}
#endif /* USE_FULL_ASSERT */

FFT测试主要使用的是arm_cfft_f32函数，它主要对输入数据进行FFT处理，第二个参数为输入数组，必须是复数，即用数组的连续两个元素分别作为一个复数点的实部与虚部。

优化等级选择速度最快：

测试结果如下：

计算2048点cFFT跟F4对比，差距十分明显：

stm32h743_test.rar (35.44 MB, 下载次数: 3)

damiaa · 发表于2023-10-12 09:08

好板，st的板子里面这块板子最受欢迎，比stm32mp1xxx还受欢迎，受欢迎成度高。

dql2016 · 发表于2023-10-12 18:44

damiaa 发表于 2023-10-12 09:08 好板，st的板子里面这块板子最受欢迎，比stm32mp1xxx还受欢迎，受欢迎成度高。

是呀，新版本是stlinkv3的，这个是b2

【NUCLEO-H743ZI】6、FFT计算性能测试 [复制链接]

最新回复

点评

测评达人