Floating point min/max in CUDA slower than CPU version. Why? - performance

Question

I wrote a kernel for computing the min and max values of an array of about 100,000 floats using reduction (see code below). I use thread blocks to reduce chunks of 1024 values to a single value (in shared memory), and then do the final reduction among the blocks on the CPU.
I then compared this with a serial calculation just on the CPU. The CUDA version takes 2.2ms, and the CPU version takes 0.21ms. Why is the CUDA version much slower? Is the array size not large enough to take advantage of the parallelism, or is my code not optimized somehow?
This is part of an exercise in the Udacity Parallel Programming class. I am running this through their web site, so I don't know what the exact hardware is, but they claim the code runs on actual GPUs.
Here is the CUDA code:
__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);
}
And here is the host version:
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);
}

Answer 1

As #talonmies suggests, behavior may be different for larger sizes; 100,000 is really not that much: Much of it fits within the combined overall L1 cache of the cores on a modern CPU; half of it fits in a single core's L2 cache.
Transfer over PCI express takes time; and in your case, double the time it might have, since you don't use pinned memory.
You're not overlapping computation and PCI express I/O (not that it would make much sense for only 100,000 elements)
Your kernel is rather slow, for more than one reason; not the least of which is the extensive use of shared memory, most of which is unnecessary
More generally: Always profile your code using nvvp (or nvprof for getting textual information for further analysis).