cuda 查看gpu性能

mian.cu

#include <stdio.h>



#define CHECK(call)                                   \
do                                                    \
{                                                     \
    const cudaError_t error_code = call;              \
    if (error_code != cudaSuccess)                    \
    {                                                 \
        printf("CUDA Error:\n");                      \
        printf("    File:       %s\n", __FILE__);     \
        printf("    Line:       %d\n", __LINE__);     \
        printf("    Error code: %d\n", error_code);   \
        printf("    Error text: %s\n",                \
            cudaGetErrorString(error_code));          \
        exit(1);                                      \
    }                                                 \
} while (0)



int main(int argc, char *argv[])
{
    int device_id = 0;
    if (argc > 1) device_id = atoi(argv[1]);
    CHECK(cudaSetDevice(device_id));

    cudaDeviceProp prop;
    CHECK(cudaGetDeviceProperties(&prop, device_id));

    printf("Device id:                                 %d\n",
        device_id);
    printf("Device name:                               %s\n",
        prop.name);
    printf("Compute capability:                        %d.%d\n",
        prop.major, prop.minor);
    printf("Amount of global memory:                   %g GB\n",
        prop.totalGlobalMem / (1024.0 * 1024 * 1024));
    printf("Amount of constant memory:                 %g KB\n",
        prop.totalConstMem  / 1024.0);
    printf("Maximum grid size:                         %d %d %d\n",
        prop.maxGridSize[0], 
        prop.maxGridSize[1], prop.maxGridSize[2]);
    printf("Maximum block size:                        %d %d %d\n",
        prop.maxThreadsDim[0], prop.maxThreadsDim[1], 
        prop.maxThreadsDim[2]);
    printf("Number of SMs:                             %d\n",
        prop.multiProcessorCount);
    printf("Maximum amount of shared memory per block: %g KB\n",
        prop.sharedMemPerBlock / 1024.0);
    printf("Maximum amount of shared memory per SM:    %g KB\n",
        prop.sharedMemPerMultiprocessor / 1024.0);
    printf("Maximum number of registers per block:     %d K\n",
        prop.regsPerBlock / 1024);
    printf("Maximum number of registers per SM:        %d K\n",
        prop.regsPerMultiprocessor / 1024);
    printf("Maximum number of threads per block:       %d\n",
        prop.maxThreadsPerBlock);
    printf("Maximum number of threads per SM:          %d\n",
        prop.maxThreadsPerMultiProcessor);

    return 0;
}

 欢迎star我的github

https://github.com/Alexjqw/cuda-learning