更新:我发现了这个错误。由于我之前贴的代码很复杂,所以我把它们简化了,只有在出现问题的时候才保留部分。
if (number >= dim * num_points)
return;
但实际上,我只有num_points,我想使用num_points线程,所以正确的方法应该是
if (number >= num_points)
return;
谢谢大家的帮助。
我正在将一些 C++ 代码从 CPU 重写到 GPU。代码粘贴在下面。对不起,它很长,因为我认为通过这种方式更容易检测到问题。
在代码中,对于每个线程我都需要一些矩阵格式的中间结果,所以我为这些中间结果分配了设备内存,比如d_dir2、d_R、d_Stick、d_PStick。结果结果不是我预期的,所以为了调试,我尝试用这种方式输出一些中间结果R:
如果(k == 0) { 结果[tmp_int1 + i * dim + j] = R[tmp_int1 + i * dim + j]; }
后来在 C++ 中,我打印结果。但是,我发现结果每次都给出不同的值。有时它给出正确答案 R,有时给出 PStick 的值,有时是 R 和 PStick 的组合,有时是 R 和 0 的组合(结果一开始就初始化为 0)。
我很困惑是什么导致了这个问题。任何想法?非常感谢 :)
__global__ void stickvote(const int dim, const int num_points, const int gridx, float Sigma, float* input, float* dir2, float* R, float* Stick, float* PStick, float* results) {
float threshold = 4 * Sigma;
float c = (- 16 * log(0.1f) * (sqrt(Sigma) - 1)) / 3.1415926f / 3.1415926f;
int row = blockIdx.y * blockDim.y + threadIdx.y;
int col = blockIdx.x * blockDim.x + threadIdx.x;
int number = row * BLOCK_SIZE * gridx + col;
if (number >= dim * num_points) //// The bug is here!
return;
}
extern "C" void KernelStickVote(int dim, int num_points, float Sigma, float* input, float* results) {
const int totalpoints = num_points;
const int totalpoints_input = (dim + 1)* (dim + 1) * num_points;
const int totalpoints_output = dim * dim * num_points;
size_t size_input = totalpoints_input * sizeof(float);
size_t size_output = totalpoints_output * sizeof(float);
float* d_input;
cutilSafeCall(cudaMalloc((void**)&d_input, size_input));
float* d_result;
cutilSafeCall(cudaMalloc((void**)&d_result, size_output));
// used to save dir, and calculate dir * dir'
float* d_dir2;
cutilSafeCall(cudaMalloc((void**)&d_dir2, dim * num_points * sizeof(float)));
// used to save R: dim * dim * N
float* d_R;
cutilSafeCall(cudaMalloc((void**)&d_R, size_output));
// used to save Stick: dim * dim * N
float* d_Stick;
cutilSafeCall(cudaMalloc((void**)&d_Stick, size_output));
// used to save Stick: dim * dim * N
float* d_PStick;
cutilSafeCall(cudaMalloc((void**)&d_PStick, size_output));
// Copy input data from host to device
cudaMemcpy(d_input, input, size_input, cudaMemcpyHostToDevice);
int totalblock = (totalpoints % BLOCKPOINTS==0 ? totalpoints/BLOCKPOINTS : (int(totalpoints/BLOCKPOINTS) + 1));
int gridx = (65535 < totalblock ? 65535 : totalblock);
int gridy = (totalblock % gridx == 0 ? totalblock/gridx : (int(totalblock/gridx)+1) );
dim3 dimBlock(BLOCK_SIZE, BLOCK_SIZE);
dim3 dimGrid(gridx, gridy);
stickvote<<<dimGrid, dimBlock>>>(dim, num_points, gridx, Sigma, d_input, d_dir2, d_R, d_Stick, d_PStick, d_result);
cudaMemcpy(results, d_result, size_output, cudaMemcpyDeviceToHost);
cudaFree(d_input);
cudaFree(d_result);
cudaFree(d_dir2);
cudaFree(d_R);
cudaFree(d_Stick);
cudaFree(d_PStick);
}