CUDA 学习（CUDA实战 第三章）

1. hello_world

1.1 hello_world(CPU)

#include <stdio.h>
int main( void ) {
    printf( "Hello, World!\n" );
    return 0;
}

1.2 hello_world(GPU)

#include <stdio.h>

__global__ void kernel( void ) {
}

int main( void ) {
    kernel<<<1,1>>>();
    printf( "Hello, World!\n" );
    return 0;
}

2. Add 1

#include <stdio.h>

__global__ void add( int a, int b, int *c ) {
    *c = a + b;
}

int main( void ) {
    int c;
    int *dev_c;
    cudaMalloc( (void**)&dev_c, sizeof(int) );

    add<<<1,1>>>( 2, 7, dev_c );

    cudaMemcpy( &c, dev_c, sizeof(int),
                              cudaMemcpyDeviceToHost );
    printf( "2 + 7 = %d\n", c );
    cudaFree( dev_c );

    return 0;
}

输出：

3.设备信息获取

#include <stdio.h>

int main( void ) {
    cudaDeviceProp  prop;

    int count;
    cudaGetDeviceCount( &count ) ;
    for (int i=0; i< count; i++) {
        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" );
    }
}

输出：