我是 cuda 编程的新手。在我的程序（使用共享内存的矩阵乘法）中，我定义了 block_size=20，当矩阵为 1200*1200 时，该程序适用于双元素，但不适用于浮点元素（当元素为浮点时，它适用于 840*840 矩阵）。我的问题是为什么会发生这种情况，尽管我们知道浮点类型小于双精度？
// Matrices are stored in row-major order:
// M(row, col) = *(M.elements + row * M.stride + col)
#include <stdio.h>
#define BLOCK_SIZE 20
typedef struct {
int width;
int height;
int stride;
float* elements;
} Matrix;
// 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;
}
// Thread block size
// Forward declaration of the matrix multiplication kernel
__global__ void MatMulKernel(const Matrix, const Matrix, Matrix);
// Matrix multiplication - Host code
// Matrix dimensions are assumed to be multiples of BLOCK_SIZE
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;
siz e_t size = A.width * A.height * sizeof(float);
cudaMalloc((void **)&d_A.elements, size);
cudaMemcpy(d_A.elements, A.elements, size,
cudaMemcpyHostToDevice);
Matrix d_B;
d_B.width = d_B.stride = B.width; d_B.height = B.height;
size = B.width * B.height * sizeof(float);
cudaMalloc((void **)&d_B.elements, size);
cudaMemcpy(d_B.elements, B.elements, size,
cudaMemcpyHostToDevice);
// Allocate C in device memory
Matrix d_C;
d_C.width = d_C.stride = C.width; d_C.height = C.height;
size = C.width * C.height * sizeof(float);
cudaMalloc((void **)&d_C.elements, size);
// Invoke kernel
dim3 dimBlock(BLOCK_SIZE,BLOCK_SIZE);
//dim3 dimBlock(C.height, C.width);
//dim3 dimGrid(B.width / dimBlock.x, A.height / dimBlock.y);
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);
// Read C from device memory
cudaMemcpy(C.elements, d_C.elements, size,
cudaMemcpyDeviceToHost);
// Free device memory
cudaFree(d_A.elements);
cudaFree(d_B.elements);
cudaFree(d_C.elements);
}
// 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;
// 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;
// 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 < (A.width / 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);
}
//////////////////////////////////////////////////////////
/// print_matrix function ///////////////////////////
////////////////////////////////////////////////////////
void print_matrix(float *c,int row,int col){
for (int i = 0; i < row; ++i){
for (int j = 0; j < col; ++j)
printf("%f ",c[col*i +j]);
printf("\n\n");
}
}
//////////////////////////////////////////////////////////
/// random_init function ///////////////////////////
////////////////////////////////////////////////////////
void random_init(float *a,int size){
for(int i=0;i<size;i++)
a[i]=rand()%10;
}
////////////////////////////////////////////////////////
int main(void){
//////////////////////////////////////////////////////\|/
cudaEvent_t start,stop;
///////////////////////////////////////////////////////|\
Matrix A,B,C;
A.width=1200;
A.height=1200;/////
B.width=1200;/////
B.height=1200;
C.width=B.width;
C.height=A.height;
size_t size = A.width * A.height * sizeof(float);
A.elements = (float *)malloc(size);
//random_init(A.elements,A.width * A.height );
size = B.width * B.height * sizeof(float);
B.elements= (float *)malloc(size);
//random_init(B.elements,B.width * B.height);
size = C.width * C.height * sizeof(float);
C.elements= (float *)malloc(size);
for(int i=0;i<A.width*A.height;i++)
A.elements[i]=1;
for(int i=0;i<B.width*B.height;i++)
B.elements[i]=1;
printf("matrix A(%d,%d) & matrix B(%d,%d) & matrix C(%d,%d)\n",A.width,A.height,B.width,
B.height,C.width,C.height);
//////////////////////////////////////////////////////\|/
cudaEventCreate(&start);
cudaEventCreate(&stop);
cudaEventRecord(start,0);
///////////////////////////////////////////////////////|\
MatMul(A,B,C);
//////////////////////////////////////////////////////\|/
cudaEventRecord(stop,0);
cudaEventSynchronize(stop);
float elapsedTime;
cudaEventElapsedTime(&elapsedTime,start,stop);
printf("Time to genreat : %3.5f ms\n",elapsedTime);
///////////////////////////////////////////////////////|\
printf("\nC\n");
//print_matrix(C.elements,C.height,C.width);
printf("C[%d]=%f\n",0,C.elements[0]);
printf("C[%d]=%f\n",C.width -1,C.elements[C.width-1]);
printf("C[%d]=%f\n",(C.width * C.height)-1,C.elements[(C.width * C.height)-1]);
getchar();
return(0);
}