nppiFilterGaussBorder_8u_C1R oSrcSize and oSrcOffset parameters

Accelerated Computing GPU-Accelerated Libraries
2

based on your SO posting, and according to my testing, you will get expected output if you pass the actual original image dimensions for oSrcSize. Here is my example:

$ cat t18.cu
#include <npp.h>
#include <nppi.h>
#include <iostream>
const int sz = 32;
int main() {
    Npp8u* src_img = new Npp8u[sz*sz];
    for (int i = 0; i < sz*sz; i++) src_img[i] = (i&1)?80:40;
    Npp8u* cudaMem = nppsMalloc_8u(sz * sz);
    Npp8u* cudaMemDst = nppsMalloc_8u(sz * sz);

    if(cudaMem == nullptr)
    {
        throw std::runtime_error("Error malloc");
    }
    cudaMemcpy(cudaMem, src_img, sz*sz, cudaMemcpyHostToDevice);
    if(cudaMemDst == nullptr)
    {
        throw std::runtime_error("Error malloc dst");
    }
    cudaMemset(cudaMemDst, 0, sz*sz);
    NppiPoint const blurTopLeft{16, 16};       //inclusive
    NppiPoint const blurBottomRight{sz, sz}; //exclusive

    //Source image width and height in pixels relative to pSrc.
//    NppiSize const oSrcSize{sz - blurTopLeft.x, sz - blurTopLeft.y};
    NppiSize const oSrcSize{sz, sz};
    NppiSize const oSizeROI{blurBottomRight.x - blurTopLeft.x, blurBottomRight.y - blurTopLeft.y};

    auto const nppiError{nppiFilterGaussBorder_8u_C1R(
        cudaMem + blurTopLeft.y * sz + blurTopLeft.x,
        sz,            // pitch
        oSrcSize,       // source image width and height in pixels relative to pSrc.
        blurTopLeft,    // aka. oSrcOffset: The pixel offset that pSrc points to relative to the origin of the source image.
        cudaMemDst + blurTopLeft.y * sz + blurTopLeft.x,
        sz,            // dst pitch
        oSizeROI,
        NPP_MASK_SIZE_3_X_3,
        NPP_BORDER_REPLICATE
    )};

    if(nppiError != 0)
    {
        // We get NPP_OUT_OFF_RANGE_ERROR
        std::cerr << "nppiFilterGaussBorder_8u_C1R failed: " << nppiError << std::endl;
    }
    else
    {
        cudaMemcpy(src_img, cudaMemDst, sz*sz, cudaMemcpyDeviceToHost);
        for (int i = 0; i< sz; i++){
          for (int j = 0; j < sz; j++)
            std::cout << (int)(src_img[i*sz+j]) << " ";
          std::cout << std::endl;}
    }
    nppsFree(cudaMem);
    nppsFree(cudaMemDst);
}
$ nvcc -o t18 t18.cu -lnpps -lnppif
$ compute-sanitizer ./t18
========= COMPUTE-SANITIZER
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 61 58 61 58 61 58 61 58 61 58 61 58 61 58 61 69
========= ERROR SUMMARY: 0 errors
$

No, I don’t have answers for all the questions that engenders. I have found NPP parameter handling to be inscrutable at times. You’re welcome to file a bug to request doc clarification.

1 Like