我编写了一个内核，用于使用约简来计算大约100,000个浮点数组的最小值和最大值（参见下面的代码）。我使用线程块将1024个值的块减少到单个值（在共享内存中），然后在CPU上的块之间进行最终减少。
然后我将其与CPU上的串行计算进行了比较。 CUDA版本需要2.2毫秒，CPU版本需要0.21毫秒。为什么CUDA版本要慢得多？数组大小是否不足以利用并行性，或者我的代码是否以某种方式未优化？
这是Udacity Parallel Programming类练习的一部分。我通过他们的网站运行这个，所以我不知道确切的硬件是什么，但他们声称代码在实际的GPU上运行。
这是CUDA代码：
__global__ void min_max_kernel(const float* const d_logLuminance,
const size_t length,
float* d_min_logLum,
float* d_max_logLum) {
// Shared working memory
extern __shared__ float sh_logLuminance[];
int blockWidth = blockDim.x;
int x = blockDim.x * blockIdx.x + threadIdx.x;
float* min_logLuminance = sh_logLuminance;
float* max_logLuminance = sh_logLuminance + blockWidth;
// Copy this block's chunk of the data to shared memory
// We copy twice so we compute min and max at the same time
if (x < length) {
min_logLuminance[threadIdx.x] = d_logLuminance[x];
max_logLuminance[threadIdx.x] = min_logLuminance[threadIdx.x];
}
else {
// Pad if we're out of range
min_logLuminance[threadIdx.x] = FLT_MAX;
max_logLuminance[threadIdx.x] = -FLT_MAX;
}
__syncthreads();
// Reduce
for (int s = blockWidth/2; s > 0; s /= 2) {
if (threadIdx.x < s) {
if (min_logLuminance[threadIdx.x + s] < min_logLuminance[threadIdx.x]) {
min_logLuminance[threadIdx.x] = min_logLuminance[threadIdx.x + s];
}
if (max_logLuminance[threadIdx.x + s] > max_logLuminance[threadIdx.x]) {
max_logLuminance[threadIdx.x] = max_logLuminance[threadIdx.x + s];
}
}
__syncthreads();
}
// Write to global memory
if (threadIdx.x == 0) {
d_min_logLum[blockIdx.x] = min_logLuminance[0];
d_max_logLum[blockIdx.x] = max_logLuminance[0];
}
}
size_t get_num_blocks(size_t inputLength, size_t threadsPerBlock) {
return inputLength / threadsPerBlock +
((inputLength % threadsPerBlock == 0) ? 0 : 1);
}
/*
* Compute min, max over the data by first reducing on the device, then
* doing the final reducation on the host.
*/
void compute_min_max(const float* const d_logLuminance,
float& min_logLum,
float& max_logLum,
const size_t numRows,
const size_t numCols) {
// Compute min, max
printf("\n=== computing min/max ===\n");
const size_t blockWidth = 1024;
const size_t numPixels = numRows * numCols;
size_t numBlocks = get_num_blocks(numPixels, blockWidth);
printf("Num min/max blocks = %d\n", numBlocks);
float* d_min_logLum;
float* d_max_logLum;
int alloc_size = sizeof(float) * numBlocks;
checkCudaErrors(cudaMalloc(&d_min_logLum, alloc_size));
checkCudaErrors(cudaMalloc(&d_max_logLum, alloc_size));
min_max_kernel<<<numBlocks, blockWidth, sizeof(float) * blockWidth * 2>>>
(d_logLuminance, numPixels, d_min_logLum, d_max_logLum);
float* h_min_logLum = (float*) malloc(alloc_size);
float* h_max_logLum = (float*) malloc(alloc_size);
checkCudaErrors(cudaMemcpy(h_min_logLum, d_min_logLum, alloc_size, cudaMemcpyDeviceToHost));
checkCudaErrors(cudaMemcpy(h_max_logLum, d_max_logLum, alloc_size, cudaMemcpyDeviceToHost));
min_logLum = FLT_MAX;
max_logLum = -FLT_MAX;
// Reduce over the block results
// (would be a bit faster to do it on the GPU, but it's just 96 numbers)
for (int i = 0; i < numBlocks; i++) {
if (h_min_logLum[i] < min_logLum) {
min_logLum = h_min_logLum[i];
}
if (h_max_logLum[i] > max_logLum) {
max_logLum = h_max_logLum[i];
}
}
printf("min_logLum = %.2f\nmax_logLum = %.2f\n", min_logLum, max_logLum);
checkCudaErrors(cudaFree(d_min_logLum));
checkCudaErrors(cudaFree(d_max_logLum));
free(h_min_logLum);
free(h_max_logLum);
}
这是主机版本：
void compute_min_max_on_host(const float* const d_logLuminance, size_t numPixels) {
int alloc_size = sizeof(float) * numPixels;
float* h_logLuminance = (float*) malloc(alloc_size);
checkCudaErrors(cudaMemcpy(h_logLuminance, d_logLuminance, alloc_size, cudaMemcpyDeviceToHost));
float host_min_logLum = FLT_MAX;
float host_max_logLum = -FLT_MAX;
printf("HOST ");
for (int i = 0; i < numPixels; i++) {
if (h_logLuminance[i] < host_min_logLum) {
host_min_logLum = h_logLuminance[i];
}
if (h_logLuminance[i] > host_max_logLum) {
host_max_logLum = h_logLuminance[i];
}
}
printf("host_min_logLum = %.2f\nhost_max_logLum = %.2f\n",
host_min_logLum, host_max_logLum);
free(h_logLuminance);
}