我正在尝试熟悉CUDA编程，并且感到非常有趣。我目前正在查看this处理矩阵乘法的PDF，其中包括使用和不使用共享内存的方法。两个版本的完整代码可以在here找到。这段代码几乎与CUDA矩阵乘法示例中的代码完全相同。虽然非共享内存版本具有在任何矩阵大小下运行的能力，而不受块大小的限制，但共享内存版本必须处理块大小的倍数的矩阵（我将其设置为4，默认值最初为16）。
PDF末尾建议的问题之一是更改共享内存版本，使其也能处理非块大小的倍数的矩阵。我认为这将是一个简单的索引检查，就像非共享版本中一样：
int row = blockIdx.y * blockDim.y + threadIdx.y;
int col = blockIdx.x * blockDim.x + threadIdx.x;
if(row > A.height || col > B.width) return;
但这并不起作用。这是完整的代码，减去了主方法（有点混乱，抱歉），我对其进行了一些修改：
void MatMul(const Matrix A, const Matrix B, Matrix C) {
// Load A and B to device memory
Matrix d_A;
d_A.width = d_A.stride = A.width;
d_A.height = A.height;
size_t size = A.width * A.height * sizeof(float);
cudaError_t err = cudaMalloc(&d_A.elements, size);
printf("CUDA malloc A: %s\n",cudaGetErrorString(err));
err = cudaMemcpy(d_A.elements, A.elements, size, cudaMemcpyHostToDevice);
printf("Copy A to device: %s\n",cudaGetErrorString(err));
Matrix d_B;
d_B.width = d_B.stride = B.width;
d_B.height = B.height;
size = B.width * B.height * sizeof(float);
err = cudaMalloc(&d_B.elements, size);
printf("CUDA malloc B: %s\n",cudaGetErrorString(err));
err = cudaMemcpy(d_B.elements, B.elements, size, cudaMemcpyHostToDevice);
printf("Copy B to device: %s\n",cudaGetErrorString(err));
Matrix d_C;
d_C.width = d_C.stride = C.width;
d_C.height = C.height;
size = C.width * C.height * sizeof(float);
err = cudaMalloc(&d_C.elements, size);
printf("CUDA malloc C: %s\n",cudaGetErrorString(err));
dim3 dimBlock(BLOCK_SIZE, BLOCK_SIZE);
dim3 dimGrid((B.width + dimBlock.x - 1) / dimBlock.x, (A.height + dimBlock.y-1) / dimBlock.y);
MatMulKernel<<<dimGrid, dimBlock>>>(d_A, d_B, d_C);
err = cudaThreadSynchronize();
printf("Run kernel: %s\n", cudaGetErrorString(err));
// Read C from device memory
err = cudaMemcpy(C.elements, d_C.elements, size, cudaMemcpyDeviceToHost);
printf("Copy C off of device: %s\n",cudaGetErrorString(err));
// Free device memory
cudaFree(d_A.elements);
cudaFree(d_B.elements);
cudaFree(d_C.elements);
}
// Get a matrix element
__device__ float GetElement(const Matrix A, int row, int col) {
return A.elements[row * A.stride + col];
}
// Set a matrix element
__device__ void SetElement(Matrix A, int row, int col, float value) {
A.elements[row * A.stride + col] = value;
}
// Get the BLOCK_SIZExBLOCK_SIZE sub-matrix Asub of A that is
// located col sub-matrices to the right and row sub-matrices down
// from the upper-left corner of A
__device__ Matrix GetSubMatrix(Matrix A, int row, int col) {
Matrix Asub;
Asub.width = BLOCK_SIZE;
Asub.height = BLOCK_SIZE;
Asub.stride = A.stride;
Asub.elements = &A.elements[A.stride * BLOCK_SIZE * row + BLOCK_SIZE * col];
return Asub;
}
// Matrix multiplication kernel called by MatMul()
__global__ void MatMulKernel(Matrix A, Matrix B, Matrix C) {
// Block row and column
int blockRow = blockIdx.y;
int blockCol = blockIdx.x;
int rowTest = blockIdx.y * blockDim.y + threadIdx.y;
int colTest = blockIdx.x * blockDim.x + threadIdx.x;
if (rowTest>A.height || colTest>B.width)
return;
// Each thread block computes one sub-matrix Csub of C
Matrix Csub = GetSubMatrix(C, blockRow, blockCol);
// Each thread computes one element of Csub
// by accumulating results into Cvalue
float Cvalue = 0.0;
// Thread row and column within Csub
int row = threadIdx.y;
int col = threadIdx.x;
// Loop over all the sub-matrices of A and B that are
// required to compute Csub
// Multiply each pair of sub-matrices together
// and accumulate the results
for (int m = 0; m < (BLOCK_SIZE + A.width - 1)/BLOCK_SIZE; ++m) {
// Get sub-matrix Asub of A
Matrix Asub = GetSubMatrix(A, blockRow, m);
// Get sub-matrix Bsub of B
Matrix Bsub = GetSubMatrix(B, m, blockCol);
// Shared memory used to store Asub and Bsub respectively
__shared__ float As[BLOCK_SIZE][BLOCK_SIZE];
__shared__ float Bs[BLOCK_SIZE][BLOCK_SIZE];
// Load Asub and Bsub from device memory to shared memory
// Each thread loads one element of each sub-matrix
As[row][col] = GetElement(Asub, row, col);
Bs[row][col] = GetElement(Bsub, row, col);
// Synchronize to make sure the sub-matrices are loaded
// before starting the computation
__syncthreads();
// Multiply Asub and Bsub together
for (int e = 0; e < BLOCK_SIZE; ++e)
{
Cvalue += As[row][e] * Bs[e][col];
}
// Synchronize to make sure that the preceding
// computation is done before loading two new
// sub-matrices of A and B in the next iteration
__syncthreads();
}
// Write Csub to device memory
// Each thread writes one element
SetElement(Csub, row, col, Cvalue);
}
我所做的显著更改：我在
MatMulKernel中添加了一个检查，检查当前线程是否试图处理不存在的C位置。这似乎不起作用。虽然它确实改变了结果，但是这些更改似乎没有任何模式，除了后面（更高的x或y值）的条目似乎更受影响（我得到了更多的非整数结果）。我还更改了给定的dimGrid计算方法和MatMulKernel中m的循环条件（之前只是将width或height除以块大小，这似乎是错误的）。即使是我找到的解决方案指南也似乎表明它应该只是一个简单的索引检查，所以我认为我缺少了一些非常基本的东西。