cudafunc.cu

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

#define w 8000

//设备端代码
__global__ void vectorAdd(const float *A, const float *B, float *C, int numElements)  
{  
  int i = blockDim.x * blockIdx.x + threadIdx.x;
    if (i < numElements)
    {
        C[i] = A[i] * B[i];
    }
}  


__global__ void DotMulVet(const float* A,const float* B,float* C,int N)
{    
    int index = blockIdx.x*blockDim.x+threadIdx.x;    
    const int offset = gridDim.x * blockDim.x;
 
 
    while (index < N)
    {
        C[index] = A[index] * B[index];
        index += offset;
    }
}





//主机端代码
extern "C" int func() // 注意这里定义形式  
{
  // Error code to check return values for CUDA calls
    cudaError_t err = cudaSuccess;

    // Print the vector length to be used, and compute its size
    int numElements = 512;
    size_t size = numElements * sizeof(float);
    printf("[Vector addition of %d elements]\n", numElements);

    // Allocate the host input vector A
    float *h_A = (float *)malloc(size);

    // Allocate the host input vector B
    float *h_B = (float *)malloc(size);

    // Allocate the host output vector C
    float *h_C = (float *)malloc(size);

    // Verify that allocations succeeded
    if (h_A == NULL || h_B == NULL || h_C == NULL)
    {
        fprintf(stderr, "Failed to allocate host vectors!\n");
        exit(EXIT_FAILURE);
    }

    printf("Index    h_A       h_B\n");
    // Initialize the host input vectors
    for (int i = 0; i < numElements; ++i)
    {
        h_A[i] = rand()/(float)RAND_MAX;
        h_B[i] = rand()/(float)RAND_MAX;
    	//printf("Index %d: %f  %f\n",i,h_A[i],h_B[i]);
    }
    printf("\n");

    // Allocate the device input vector A
    float *d_A = NULL;
    err = cudaMalloc((void **)&d_A, size);//分配一维的线性存储空间

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to allocate device vector A (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Allocate the device input vector B
    float *d_B = NULL;
    err = cudaMalloc((void **)&d_B, size);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to allocate device vector B (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Allocate the device output vector C
    float *d_C = NULL;
    err = cudaMalloc((void **)&d_C, size);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to allocate device vector C (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Copy the host input vectors A and B in host memory to the device input vectors in
    // device memory
    printf("Copy input data from the host memory to the CUDA device\n");
    err = cudaMemcpy(d_A, h_A, size, cudaMemcpyHostToDevice);//将一维线性存储器的数据从主机端传输到设备端

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to copy vector A from host to device (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    err = cudaMemcpy(d_B, h_B, size, cudaMemcpyHostToDevice);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to copy vector B from host to device (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Launch the Vector Add CUDA Kernel
    int threadsPerBlock = 256;
    int blocksPerGrid =(numElements + threadsPerBlock - 1) / threadsPerBlock;
    printf("CUDA kernel launch with %d blocks of %d threads\n", blocksPerGrid, threadsPerBlock);
    DotMulVet<<<blocksPerGrid, threadsPerBlock>>>(d_A, d_B, d_C, numElements);
    err = cudaGetLastError();

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to launch vectorAdd kernel (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Copy the device result vector in device memory to the host result vector
    // in host memory.
    printf("Copy output data from the CUDA device to the host memory\n");
    err = cudaMemcpy(h_C, d_C, size, cudaMemcpyDeviceToHost);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to copy vector C from device to host (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Verify that the result vector is correct
    for (int i = 0; i < 5; ++i)
    {
        if (fabs(h_A[i] * h_B[i] - h_C[i]) > 1e-5)
        {
            fprintf(stderr, "Result verification failed at element %d!\n", i);
            exit(EXIT_FAILURE);
        }
    }

    printf("Test PASSED\n\n");

    printf("vectorAdd_Result:\n");
    for(int i=0;i<5;i++)
      printf("Index %d: %f\n",i,h_C[i]);
    printf("\n");
    // Free device global memory
    err = cudaFree(d_A);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to free device vector A (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    err = cudaFree(d_B);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to free device vector B (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    err = cudaFree(d_C);

    if (err != cudaSuccess)
    {
        fprintf(stderr, "Failed to free device vector C (error code %s)!\n", cudaGetErrorString(err));
        exit(EXIT_FAILURE);
    }

    // Free host memory
    free(h_A);
    free(h_B);
    free(h_C);

    printf("Done\n");
    return 0;
}

struct Matrix
{
    int width;
    int height;
    float *elements;
};


__device__ float getElement(Matrix *A, int row, int col)
{
        return A->elements[row * A->width + col];
}

__device__ void setElement(Matrix *A, int row, int col, float value)
{
        A->elements[row * A->width + col] = value;
}

__global__ void matMulKernel(Matrix *A, Matrix *B, Matrix *C)
{
        float Cvalue = 0.0;
        int row = threadIdx.y + blockIdx.y * blockDim.y;
        int col = threadIdx.x + blockIdx.x * blockDim.x;
        
        for (int i = 0; i < A->width; ++i)
        {
                Cvalue += getElement(A, row, i) * getElement(B, i, col);
        }
        setElement(C, row, col, Cvalue);
}

extern "C" int testmatMul() {
     int width = w;
    int height = w;

    Matrix *A, *B, *C;

    cudaMallocManaged((void**)&A, sizeof(Matrix));
    cudaMallocManaged((void**)&B, sizeof(Matrix));
    cudaMallocManaged((void**)&C, sizeof(Matrix));

    int nBytes = width * height * sizeof(float);

    cudaMallocManaged((void**)&A->elements, nBytes);
    cudaMallocManaged((void**)&B->elements, nBytes);
    cudaMallocManaged((void**)&C->elements, nBytes);

    A->height = height;
    A->width = width;
    B->height = height;
    B->width = width;
    C->height = height;
    C->width = width;

    for (int i = 0; i < width * height; ++i)
    {
        A->elements[i] = 1.0;
        B->elements[i] = 2.0;
    }

    dim3 blockSize(32, 32);
    dim3 gridSize((width + blockSize.x - 1) / blockSize.x,
        (height + blockSize.y - 1) / blockSize.y);

/*
    struct timeval t1,t2;
    gettimeofday(&t1,NULL);
    double timeuse;
*/
    matMulKernel << < gridSize, blockSize >> >(A, B, C);

    cudaDeviceSynchronize();

/*
    gettimeofday(&t2,NULL);
    timeuse = t2.tv_sec - t1.tv_sec + (t2.tv_usec - t1.tv_usec)/1000000.0;
    printf("Use Time:%fs\n", timeuse);
*/
}