c - OpenCL : Querying max clock frequency of a mobile GPU always returns a lesser value

Question

为了了解 Mali T760 GPU 的最大时钟频率，我使用了以下代码片段:

// Get device max clock frequency
cl_uint max_clock_freq;
err_num = clGetDeviceInfo(cl_devices[device_idx], CL_DEVICE_MAX_CLOCK_FREQUENCY, sizeof(max_clock_freq), &max_clock_freq, NULL);
check_cl_error(err_num, "clGetDeviceInfo: Getting device max clock frequency");
printf("CL_DEVICE_MAX_CLOCK_FREQUENCY: %d MHz\n", max_clock_freq);

此处提供完整源代码:https://github.com/sivagnanamn/opencl-device-info

查询结果显示 CL_DEVICE_MAX_CLOCK_FREQUENCY: 99 MHz 而规范中报告的时钟频率为 600MHz (src: https://www.notebookcheck.net/ARM-Mali-T760-MP4.148383.0.html )

为什么规范中报告的实际时钟频率与 OpenCL 查询的时钟频率之间存在差异？

编辑 1:

这是用于查询支持 OpenCl 的 GPU 设备的最大时钟频率的代码的最小版本。

#include <stdio.h>
#include <stdlib.h>

#ifdef __APPLE__
  #include <OpenCL/opencl.h>
#else
  #include <CL/cl.h>
#endif

void check_cl_error(cl_int err_num, char* msg) {
  if(err_num != CL_SUCCESS) {
    printf("[Error] OpenCL error code: %d in %s \n", err_num, msg);
    exit(EXIT_FAILURE);
  }
}

int main(void) {

  cl_int err_num;
  char str_buffer[1024];
  cl_uint num_platforms_available;

  // Get the number of OpenCL capable platforms available
  err_num = clGetPlatformIDs(0, NULL, &num_platforms_available);

  // Exit if no OpenCL capable platform found
  if(num_platforms_available == 0){
    printf("No OpenCL capable platforms found ! \n");
    return EXIT_FAILURE;
  }

  // Create a list for storing the platform id's
  cl_platform_id cl_platforms[num_platforms_available];

  err_num = clGetPlatformIDs(num_platforms_available, cl_platforms, NULL);
  check_cl_error(err_num, "clGetPlatformIDs: Getting available platform id's");

  // Get attributes of each platform available
  for(int platform_idx = 0; platform_idx < num_platforms_available; platform_idx++) {

    // Get the number of OpenCL supported device available in this platform
    cl_uint num_devices_available;
    err_num = clGetDeviceIDs(cl_platforms[platform_idx], CL_DEVICE_TYPE_ALL, 0, NULL, &num_devices_available);
    check_cl_error(err_num, "clGetDeviceIDs: Get number of OpenCL supported devices available");

    cl_device_id cl_devices[num_devices_available];
    err_num = clGetDeviceIDs(cl_platforms[platform_idx], CL_DEVICE_TYPE_ALL, num_devices_available, cl_devices, NULL);
    check_cl_error(err_num, "clGetDeviceIDs: Getting available OpenCL capable device id's");

    // Get attributes of each device
    for(int device_idx = 0; device_idx < num_devices_available; device_idx++) {

      // Get device max clock frequency
      cl_uint max_clock_freq;
      err_num = clGetDeviceInfo(cl_devices[device_idx], CL_DEVICE_MAX_CLOCK_FREQUENCY, sizeof(max_clock_freq), &max_clock_freq, NULL);
      check_cl_error(err_num, "clGetDeviceInfo: Getting device max clock frequency");
      printf("[Platform %d] [Device %d] CL_DEVICE_MAX_CLOCK_FREQUENCY: %d MHz\n", platform_idx, device_idx, max_clock_freq);
    }
  }

  return 0;
}

我在使用 Mali T760 GPU 的 ASUS TinkerBoard 上执行后得到的输出是

[Platform 0] [Device 0] CL_DEVICE_MAX_CLOCK_FREQUENCY: 99 MHz

根据 OpenCL 文档，没有比例因子。查询应返回以 MHz 为单位的频率 ( https://www.khronos.org/registry/OpenCL/sdk/1.2/docs/man/xhtml/clGetDeviceInfo.html )

OpenCL 文档摘录:CL_DEVICE_MAX_CLOCK_FREQUENCY - cl_uint - 设备的最大配置时钟频率(以 MHz 为单位)。

然而，在 PC GPU 上运行相同的代码(在 NVIDIA 和 Intel GPU 上测试)会返回符合规范的预期时钟频率。

Answer 1

出于电源/热管理目的，CPU/GPU 时钟速度通常会受到限制。您的 GPU 可能处于低功耗模式。但是，如果您以编程方式更改电源模式，请注意不要超出电路板配置的规范。有时，这些开发板没有为最大时钟速率配备足够的散热器。