cuda c by example - 1

并行计算大当其道，cuda c, 给了开发者与NVIDIA 通用型GPU设备交互的能力，举2个栗子先了解一下，

1，枚举设备属性代码

int main( void ) {
    cudaDeviceProp  prop;

    int count;
    HANDLE_ERROR( cudaGetDeviceCount( &count ) );
    for (int i=0; i< count; i++) {
        HANDLE_ERROR( cudaGetDeviceProperties( &prop, i ) );
        printf( "   --- General Information for device %d ---\n", i );
        printf( "Name:  %s\n", prop.name );
        printf( "Compute capability:  %d.%d\n", prop.major, prop.minor );
        printf( "Clock rate:  %d\n", prop.clockRate );
        printf( "Device copy overlap:  " );
        if (prop.deviceOverlap)
            printf( "Enabled\n" );
        else
            printf( "Disabled\n");
        printf( "Kernel execution timeout :  " );
        if (prop.kernelExecTimeoutEnabled)
            printf( "Enabled\n" );
        else
            printf( "Disabled\n" );

        printf( "   --- Memory Information for device %d ---\n", i );
        printf( "Total global mem:  %ld\n", prop.totalGlobalMem );
        printf( "Total constant Mem:  %ld\n", prop.totalConstMem );
        printf( "Max mem pitch:  %ld\n", prop.memPitch );
        printf( "Texture Alignment:  %ld\n", prop.textureAlignment );

        printf( "   --- MP Information for device %d ---\n", i );
        printf( "Multiprocessor count:  %d\n",
                    prop.multiProcessorCount );
        printf( "Shared mem per mp:  %ld\n", prop.sharedMemPerBlock );
        printf( "Registers per mp:  %d\n", prop.regsPerBlock );
        printf( "Threads in warp:  %d\n", prop.warpSize );
        printf( "Max threads per block:  %d\n",
                    prop.maxThreadsPerBlock );
        printf( "Max thread dimensions:  (%d, %d, %d)\n",
                    prop.maxThreadsDim[0], prop.maxThreadsDim[1],
                    prop.maxThreadsDim[2] );
        printf( "Max grid dimensions:  (%d, %d, %d)\n",
                    prop.maxGridSize[0], prop.maxGridSize[1],
                    prop.maxGridSize[2] );
        printf( "\n" );
    }
}

结果

marco@marco-System-Product-Name:~/Tests/chapter03$ nvcc -arch sm_60 enum_gpu.cu -o enum_gpu
marco@marco-System-Product-Name:~/Tests/chapter03$ ./enum_gpu 
   --- General Information for device 0 ---
Name:  GeForce GTX 1050 Ti
Compute capability:  6.1
Clock rate:  1392000
Device copy overlap:  Enabled
Kernel execution timeout :  Enabled
   --- Memory Information for device 0 ---
Total global mem:  4233035776
Total constant Mem:  65536
Max mem pitch:  2147483647
Texture Alignment:  512
   --- MP Information for device 0 ---
Multiprocessor count:  6
Shared mem per mp:  49152
Registers per mp:  65536
Threads in warp:  32
Max threads per block:  1024
Max thread dimensions:  (1024, 1024, 64)
Max grid dimensions:  (2147483647, 65535, 65535)

多GPU情况下如何选择合适的GPU设备运行保证性能呢？

int main( void ) {
    cudaDeviceProp  prop;
    int dev;

    HANDLE_ERROR( cudaGetDevice( &dev ) );
    printf( "ID of current CUDA device:  %d\n", dev );

    memset( &prop, 0, sizeof( cudaDeviceProp ) );
    prop.major = 1;
    prop.minor = 3;
    HANDLE_ERROR( cudaChooseDevice( &dev, &prop ) );
    printf( "ID of CUDA device closest to revision 1.3:  %d\n", dev );

    HANDLE_ERROR( cudaSetDevice( dev ) );
}

结果：当然当前只有一个设备满足哈

marco@marco-System-Product-Name:~/Tests/chapter03$ ./set_gpu 
ID of current CUDA device:  0
ID of CUDA device closest to revision 1.3:  0