将阵列从RAM复制到GPU并从GPU复制到RAM

Question

我试图在我的一个项目中介绍一些CUDA优化。但我认为我在这里做错了什么。我想实现一个简单的矩阵向量乘法（result = matrix * vector）。但是当我想将结果复制回主机时，会发生错误（cudaErrorLaunchFailure）。我的内核中是否有错误（matrixVectorMultiplicationKernel），或者我错误地调用cudaMemcpy？我发现这种错误状态没有有用的文档。我认为这完全破坏了GPU的状态，因为我不能在第一次出现之后再次出现此错误的情况下调用任何CUDA内核。

编辑＃1：更新的代码，遵循leftaroundabout的建议。

// code 
... 
Eigen::MatrixXf matrix(M, N); // matrix.data() usually should return a float array 
Eigen::VectorXf vector(N); // same here for vector.data() 
Eigen::VectorXf result(M); 
... // fill matrix and vector 
float* matrixOnDevice = copyMatrixToDevice(matrix.data(), matrix.rows(), matrix.cols()); 
matrixVectorMultiplication(matrixOnDevice, vector.data(), result.data(), matrix.rows(), cm.cols()); 
... // clean up 

// helper functions 
float* copyMatrixToDevice(const float* matrix, int mRows, int mCols) 
{ 
    float* matrixOnDevice; 
    const int length = mRows*mCols; 
    const int size = length * sizeof(float); 
    handleCUDAError(cudaMalloc((void**)&matrixOnDevice, size)); 
    handleCUDAError(cudaMemcpy(matrixOnDevice, matrix, size, cudaMemcpyHostToDevice)); 
    return matrixOnDevice; 
} 

void matrixVectorMultiplication(const float* matrixOnDevice, const float* vector, float* result, int mRows, int mCols) 
{ 
    const int vectorSize = mCols*sizeof(float); 
    const int resultSize = mRows*sizeof(float); 
    const int matrixLength = mRows*mCols; 
    float* deviceVector; 
    float* deviceResult; 
    handleCUDAError(cudaMalloc((void**)&deviceVector, vectorSize)); 
    handleCUDAError(cudaMalloc((void**)&deviceResult, resultSize)); 
    handleCUDAError(cudaMemset(deviceResult, 0, resultSize)); 
    handleCUDAError(cudaMemcpy(deviceVector, vector, vectorSize, cudaMemcpyHostToDevice)); 
    int threadsPerBlock = 256; 
    int blocksPerGrid = (mRows + threadsPerBlock - 1)/threadsPerBlock; 
    matrixVectorMultiplicationKernel<<<blocksPerGrid, threadsPerBlock>>>(matrixOnDevice, vector, result, mRows, mCols, matrixLength); 
    // --- no errors yet --- 
    handleCUDAError(cudaMemcpy(result, deviceResult, resultSize, cudaMemcpyDeviceToHost)); // cudaErrorLaunchFailure 
    handleCUDAError(cudaFree(deviceVector)); // cudaErrorLaunchFailure 
    handleCUDAError(cudaFree(deviceResult)); // cudaErrorLaunchFailure 
} 

__global__ void matrixVectorMultiplicationKernel(const float* matrix, const float* vector, float* result, int mRows, int mCols, int length) 
{ 
    int row = blockDim.x * blockIdx.x + threadIdx.x; 
    if(row < mRows) 
    { 
    for(int col = 0, mIdx = row*mCols; col < mCols; col++, mIdx++) 
     result[row] += matrix[mIdx] * vector[col]; 
    } 
} 

Answer 1

你的问题是void copyMatrixToDevice(..., float* matrixOnDevice, ...)按值取这个指针，即它不能“输出”设备矩阵。你可以用void copyMatrixToDevice(..., float** matrixOnDevice, ...)做到这一点，通过

copyMatrixToDevice(matrix.data(), &matrixOnDevice, matrix.rows(), matrix.cols()); 

称为有与matrixVectorMultiplicationresult同样的问题。

从长远来看，在C++中，您应该在所有这些环节中放置合适的类抽象层。