I’m working on an image processing project and I decided to use streams.
I created a stream and then I used nppSetStream.
I invoked the function nppiThreshold_LTValGTVal_32f_C1R but 2 stream are used when the function is executed.
Here there’s a code example:
#include <npp.h>
#include <cuda_runtime.h>
#include <cuda_profiler_api.h>
int main(void) {
int srcWidth = 1344;
int srcHeight = 1344;
int paddStride = 0;
float* srcArrayDevice;
float* srcArrayDevice2;
unsigned char* dstArrayDevice;
int status = cudaMalloc((void**)&srcArrayDevice, srcWidth * srcHeight * 4);
status = cudaMalloc((void**)&srcArrayDevice2, srcWidth * srcHeight * 4);
status = cudaMalloc((void**)&dstArrayDevice, srcWidth * srcHeight );
cudaStream_t testStream;
cudaStreamCreateWithFlags(&testStream, cudaStreamNonBlocking);
nppSetStream(testStream);
NppiSize roiSize = { srcWidth,srcHeight };
//status = cudaMemcpyAsync(srcArrayDevice, &srcArrayHost, srcWidth*srcHeight*4, cudaMemcpyHostToDevice, testStream);
int yRect = 100;
int xRect = 60;
float thrL = 50;
float thrH = 1500;
NppiSize sz = { 200, 400 };
for (int i = 0; i < 10; i++) {
int status3 = nppiThreshold_LTValGTVal_32f_C1R(srcArrayDevice + (srcWidth*yRect + xRect)
, srcWidth * 4
, srcArrayDevice2 + (srcWidth*yRect + xRect)
, srcWidth * 4
, sz
, thrL
, thrL
, thrH
, thrH);
}
int length = (srcWidth + paddStride)*srcHeight;
int status6 = nppiScale_32f8u_C1R(srcArrayDevice, srcWidth * 4, dstArrayDevice + paddStride, srcWidth + paddStride, roiSize, 0, 65535);
//int status7 = cudaMemcpyAsync(dstPinPtr, dstTest, length, cudaMemcpyDeviceToHost, testStream);
cudaFree(srcArrayDevice);
cudaFree(srcArrayDevice2);
cudaFree(dstArrayDevice);
cudaStreamDestroy(testStream);
cudaProfilerStop();
return 0;
}
This what I got from the Nvidia Visual Profiler: https://drive.google.com/file/d/0Bwm_zbskOasVWmpldFhBZ0VwSTg/view?usp=sharing
Why there are 2 streams?
I noticed that this behaviour is dependant from the size of the image, if width and height are set to 1500 the result is this:
https://drive.google.com/file/d/0Bwm_zbskOasVc3Qxdk9uZ3hTelU/view?usp=sharing
Is this a bug or am I missing somewthing?