我对 CUDA 上的矩阵乘法很感兴趣。所得乘积矩阵始终为零。我已经阅读了一些示例代码,例如 matrix multiplication in cuda解决了我的问题,但一切都是徒劳的。
除了 0 的不稳定结果外,“Width”(下面的代码)的最大大小甚至不是 512。我无法调试问题所在。也许我们可以在 StackOverflow 上讨论它。
我指的是“编程大规模并行处理器”
#include<cuda.h>
#include<stdio.h>
int main(void) {
void MatrixMultiplication(float *, float *, float *, int);
const int Width = 5;
float M[Width*Width], N[Width*Width], P[Width*Width];
for(int i = 0; i < (Width*Width) ; i++) {
M[i] = 5;
N[i] = 5;
P[i] = 0;
}
MatrixMultiplication(M, N, P, Width);
for(int i = 0; i < (Width*Width) ; i++) {
printf("%d \n", P[i]);
}
int quit;
scanf("%d",&quit);
return 0;
}
//Matrix multiplication kernel - thread specification
__global__ void MatrixMulKernel(float *Md, float *Nd, float *Pd, int Width) {
//2D Thread ID
int tx = threadIdx.x;
int ty = threadIdx.y;
//Pvalue stores the Pd element that is computed by the thread
float Pvalue = 0;
for(int k = 0; k < Width ; ++k) {
float Mdelement = Md[ty*Width + k];
float Ndelement = Nd[k*Width + tx];
Pvalue += (Mdelement*Ndelement);
}
Pd[ty*Width + tx] = Pvalue;
}
void MatrixMultiplication(float *M, float *N, float *P, int Width) {
int size = Width*Width*sizeof(float);
float *Md, *Nd, *Pd;
//Transfer M and N to device memory
cudaMalloc((void**)&Md, size);
cudaMemcpy(Md,M,size,cudaMemcpyHostToDevice);
cudaMalloc((void**)&Nd, size);
cudaMemcpy(Nd,N,size,cudaMemcpyHostToDevice);
//Allocate P on the device
cudaMalloc((void**)&Pd,size);
//Setup the execution configuration
dim3 dimBlock(Width,Width);
dim3 dimGrid(1,1);
//Launch the device computation threads!
MatrixMulKernel<<<dimGrid,dimBlock>>>(Md,Nd,Pd,Width);
//Transfer P from device to host
cudaMemcpy(P,Pd,size,cudaMemcpyDeviceToHost);
//Free device matrices
cudaFree(Md);
cudaFree(Nd);
cudaFree(Pd);
}
最佳答案
在这一点之前你做得很好:
for(int i = 0; i < (Width*Width) ; i++) {
printf("%d \n", P[i]);
}
我将其更改为 %f(因为它是一个 float )并且它们都打印得很好 :)
$ ./test.exe
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
125.000000
关于c - 使用 CUDA 的矩阵乘法,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/5021930/