cudamallocandmemcpy.cu

cuda基本程序：矩阵转置的较优实现等

/*
 * Copyright 1993-2008 NVIDIA Corporation.  All rights reserved.
 *
 * NOTICE TO USER:
 *
 * This source code is subject to NVIDIA ownership rights under U.S. and
 * international Copyright laws.  Users and possessors of this source code
 * are hereby granted a nonexclusive, royalty-free license to use this code
 * in individual and commercial software.
 *
 * NVIDIA MAKES NO REPRESENTATION ABOUT THE SUITABILITY OF THIS SOURCE
 * CODE FOR ANY PURPOSE.  IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR
 * IMPLIED WARRANTY OF ANY KIND.  NVIDIA DISCLAIMS ALL WARRANTIES WITH
 * REGARD TO THIS SOURCE CODE, INCLUDING ALL IMPLIED WARRANTIES OF
 * MERCHANTABILITY, NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE.
 * IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL,
 * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
 * OF USE, DATA OR PROFITS,  WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
 * OR OTHER TORTIOUS ACTION,  ARISING OUT OF OR IN CONNECTION WITH THE USE
 * OR PERFORMANCE OF THIS SOURCE CODE.
 *
 * U.S. Government End Users.   This source code is a "commercial item" as
 * that term is defined at  48 C.F.R. 2.101 (OCT 1995), consisting  of
 * "commercial computer  software"  and "commercial computer software
 * documentation" as such terms are  used in 48 C.F.R. 12.212 (SEPT 1995)
 * and is provided to the U.S. Government only as a commercial end item.
 * Consistent with 48 C.F.R.12.212 and 48 C.F.R. 227.7202-1 through
 * 227.7202-4 (JUNE 1995), all U.S. Government End Users acquire the
 * source code with only those rights set forth herein.
 *
 * Any use of this source code in individual and commercial software must
 * include, in the user documentation and internal comments to the code,
 * the above Disclaimer and U.S. Government End Users Notice.
 */


// includes, system
#include <stdio.h>
#include <assert.h>

// Simple utility function to check for CUDA runtime errors
void checkCUDAError(const char *msg);

///////////////////////////////////////////////////////////////////////////////
// Program main
///////////////////////////////////////////////////////////////////////////////
int main( int argc, char** argv) 
{
    // pointer and dimension for host memory
    int n, dimA;
    float *h_a;

    // pointers for device memory
    float *d_a, *d_b;

    // allocate and initialize host memory
    // Bonus: try using cudaMallocHost in place of malloc
    dimA = 8;
    h_a = (float *) malloc(dimA*sizeof(float));
    for (n=0; n<dimA; n++)
    {
        h_a[n] = (float) n;
    }

    // Part 1 of 5: allocate device memory
    size_t memSize = dimA*sizeof(float);
    cudaMalloc(  );
    cudaMalloc(  );

    // Part 2 of 5: host to device memory copy
    cudaMemcpy(  );

    // Part 3 of 5: device to device memory copy
    cudaMemcpy(  );

    // clear host memory
    for (n=0; n<dimA; n++)
    {
        h_a[n] = 0.f;
    }

    // Part 4 of 5: device to host copy
    cudaMemcpy(  );

    // Check for any CUDA errors
    checkCUDAError("cudaMemcpy calls");

    // verify the data on the host is correct
    for (n=0; n<dimA; n++)
    {
        assert(h_a[n] == (float) n);
    }

    // Part 5 of 5: free device memory pointers d_a and d_b
    cudaFree( );
    cudaFree( );

    // Check for any CUDA errors
    checkCUDAError("cudaFree");

    // free host memory pointer h_a
    // Bonus: be sure to use cudaFreeHost for memory allocated with cudaMallocHost
    free(h_a);

    // If the program makes it this far, then the results are correct and
    // there are no run-time errors.  Good work!
    printf("Correct!\n");

    return 0;
}

void checkCUDAError(const char *msg)
{
    cudaError_t err = cudaGetLastError();
    if( cudaSuccess != err) 
    {
        fprintf(stderr, "Cuda error: %s: %s.\n", msg, cudaGetErrorString( err) );
        exit(-1);
    }                         
}