我在 Windows 7 x64 上使用 vs2010,在我的大学项目中使用 CUDA 工具包 v4.0。我想实现一个简单的 gpu-vs-cpu 测试,大部分都完成了,但是我的 cuda 测试都没有返回任何结果。我用调试器检查了内存,设备内存包含了我需要的一切,只有内存复制失败。
host_vector<int> addWithCuda(host_vector<int> h_a, host_vector<int> h_b)
{
int size = h_a.size();
host_vector<int> h_c(size);
// Choose which GPU to run on, change this on a multi-GPU system.
cudaError_t cudaStatus = cudaSetDevice(0);
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaSetDevice failed! Do you have a CUDA-capable GPU installed?");
return h_c;
}
else{
// Allocate GPU buffers for three vectors (two input, one output).
// Copy input vectors from host memory to GPU buffers.
device_vector<int> d_c=h_c;
device_vector<int> d_a=h_a;
device_vector<int> d_b=h_b;
int*d_a_ptr = raw_pointer_cast(&d_a[0]);
int*d_b_ptr = raw_pointer_cast(&d_b[0]);
int*d_c_ptr = raw_pointer_cast(&d_c[0]);
int*h_c_ptr = raw_pointer_cast(&h_c[0]);
// Launch a kernel on the GPU with one thread for each element.
addKernel<<<1, size>>>(d_c_ptr, d_a_ptr, d_b_ptr);
// cudaDeviceSynchronize waits for the kernel to finish, and returns
// any errors encountered during the launch.
cudaStatus = cudaDeviceSynchronize();
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaDeviceSynchronize returned error code %d after launching addKernel!\n", cudaStatus);
return h_c;
}
thrust::device_vector<int>::iterator d_it;
thrust::host_vector<int>::iterator h_it;
// Copy output vector from GPU buffer to host memory.
h_c=d_c;
printf("||Debug h_c[0]=%d\td_c[0]=%d\n",h_c[0],d_c[0]);
}
cudaStatus = cudaDeviceReset();
if (cudaStatus != cudaSuccess) {
fprintf(stderr, "cudaDeviceReset failed!");
}
return h_c;
}
注意代码行“h_c=d_c;”。在推力上,这应该将数据从 d_c(设备向量)复制到 h_c(主机向量)。此行不会失败,但也不会正确执行。h_c 一直保持为 0。
我尝试了其他几种方法,例如
thrust::copy(d_c.begin(),d_c.end(),h_c.begin());
或者
cudaMemcpy(h_c_ptr,d_c_ptr,size*sizeof(int),cudaMemcpyDeviceToHost);
甚至
for(int i=0;i < size;++i)h_c[i]=d_c[i];
没有任何效果。我在这里迷路了。
有人有类似的吗?所有帮助表示赞赏。