我試圖掃描一個簡單的數組使用CUDA,但它似乎有錯誤的代碼在下面..我試圖找到我做錯了什麼,但我can't.Can任何人都可以請幫我?掃描陣列CUDA
#include <stdio.h>
#include <stdlib.h>
__global__ void prescan(int *g_odata, int *g_idata, int n){
extern __shared__ int temp[];// allocated on invocation
int thid = threadIdx.x;
int offset = 1;
temp[2*thid] = g_idata[2*thid]; // load input into shared memory
temp[2*thid+1] = g_idata[2*thid+1];
for (int d = n>>1; d > 0; d >>= 1){ // build sum in place up the tree
__syncthreads();
if (thid < d){
int ai = offset*(2*thid+1)-1;
int bi = offset*(2*thid+2)-1;
temp[bi] += temp[ai];
}
offset *= 2;
}
if (thid == 0) { temp[n - 1] = 0; } // clear the last element
for (int d = 1; d < n; d *= 2){ // traverse down tree & build scan
offset >>= 1;
__syncthreads();
if (thid < d){
int ai = offset*(2*thid+1)-1;
int bi = offset*(2*thid+2)-1;
int t = temp[ai];
temp[ai] = temp[bi];
temp[bi] += t;
}
}
__syncthreads();
g_odata[2*thid] = temp[2*thid]; // write results to device memory
g_odata[2*thid+1] = temp[2*thid+1];
}
int main(int argc, char *argv[]){
int i;
int *input = 0;
int *output = 0;
int *g_idata = 0;
int *g_odata = 0;
int numblocks = 1;
int radix = 16;
input = (int*)malloc(numblocks*radix*sizeof(int));
output = (int*)malloc(numblocks*radix*sizeof(int));
cudaMalloc((void**)&g_idata, numblocks*radix*sizeof(int));
cudaMalloc((void**)&g_odata, numblocks*radix*sizeof(int));
for(i=0; i<numblocks*radix; i++){
input[i] = 1 + 2*i;
}
for(i=0; i<numblocks*radix; i++){
printf("%d ", input[i]);
}
cudaMemcpy(g_idata, input, numblocks*radix*sizeof(int), cudaMemcpyHostToDevice);
prescan<<<1,8>>>(g_odata, g_idata, numblocks*radix);
cudaThreadSynchronize();
cudaMemcpy(output, g_odata, numblocks*radix*sizeof(int), cudaMemcpyDeviceToHost);
for(i=0; i<numblocks*radix; i++){
printf("%d ", output[i]);
}
free(input);
free(output);
cudaFree(g_idata);
cudaFree(g_odata);
return 0;
}
輸出是這樣的:1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0。I希望有這輸出:1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 0 1 4 9 16 25 36 49 64 81 100 121 144 169 196 225
您正在啓動內核時未指定共享內存大小。它可能不會啓動或運行完成並返回一個錯誤,但是您沒有檢查錯誤,所以您看不到錯誤。我無法理解內核,它可能仍然會被打破,但如果遇到更多的根本性問題,這將浪費每個人的時間去嘗試。 – talonmies 2012-07-08 18:51:35
'prescan <<< 1,8,numblocks * radix * sizeof(int)>>>(g_odata,g_idata,numblocks * radix);' – geek 2012-07-08 20:11:53
這些評論應該是答案。 :) – harrism 2012-07-09 00:45:55