Stack Overflow
Stack Overflow

Questions tagged [npp]

NPP is the abbreviation of NVIDIA Performance Primitives. It is a free GPU accelerated signal and image processing library that utilizes NVIDIA CUDA enabled GPUs to accelerate processing. NPP is authored and maintained by NVIDIA Corporation. It ships along with the free CUDA Toolkit by NVIDIA.

57 questions
2
votes
3 answers

How can I convert Npp8u * to CUdeviceptr

I am new to cuda driver Api interface but I think that CUdeviceptr looks like a handle parameter.So I confused about the convertion between CUdeviceptr and npp8u *. Npp8u * src; ...... unsigned char temp; temp = src; CUdeviceptr…
user2968731
  • 117
  • 1
  • 9
2
votes
1 answer

CUDA NPP - image reduction - find sum/average of all image pixels

I have an 8-bit unsigned char image, which is grayscale (values between 0-255), and I want to use the NPP CUDA library documentation, which provides some functions such as nppiSum_8u64s_C1R, to find the sum and average over all the pixels. But, I…
Eagle
  • 1,187
  • 5
  • 22
  • 40
2
votes
2 answers

OpenCV GPU Primitives

Are the OpenCV primitives based on the CUDA Nvidia Performance Primitives (NPP)?. By primitives I mean the same ones implemented in the NPP library, for example: boxFilter, Mirror, Convolution... I would like to know about this issue as I'm…
pQB
  • 3,077
  • 3
  • 23
  • 49
1
vote
0 answers

nppiFilterGaussBorder_8u_C1R oSrcSize and oSrcOffset parameters

I would like to run nppiFilterGaussBorder_8u_C1R just on a part of an image. The documentation says the following: pSrc: Source-Image Pointer. oSrcSize: Source image width and height in pixels relative to pSrc. oSrcOffset: The pixel offset that…
Broothy
  • 659
  • 5
  • 20
1
vote
1 answer

How should I correctly use the gaussian filter function in CUDA Npp library?

I am trying to use the Npp library in CUDA for Gaussian filtering of images. The function I am using is nppiFilterGauss_8u_C1R. However, my code always fails to return the correct result. The image returned is either pure black or pure grey, or some…
Yanqi Huo
  • 11
  • 1
1
vote
1 answer

Does NPP support overlapping streams?

I'm trying to perform multiple async 2D convolutions on a single image with multiple filters using NVIDIA's NPP library method nppiFilterBorder_32f_C1R_Ctx. However, even after creating multiple streams and assigning them to NPPI's method, the…
Gustavo Stahl
  • 101
  • 1
  • 7
1
vote
1 answer

how to decide the step size(row size ) for YUV420(I420) image when convert YUV420 to BGR with NVIDIA NPP library

I am a newer to cuda and its image,signal processing library :NPP ,now I am trying to convert YUV420 to BGR ,use this function: NppStatus nppiYUV420ToBGR_8u_P3C3R(const Npp8u * const pSrc[3], int rSrcStep[3], Npp8u * pDst, int nDstStep, NppiSize…
wangz
  • 45
  • 9
1
vote
1 answer

Inconsistent results for nppi and cv::cvtColor

When I run nppi and cv::cvtColor for color conversion, I get different results. // *data_ptr = 1, 1, 1, 1 cv::Mat image1(1, 2, CV_8UC2, data_ptr, 2*2); cv::Mat image2; cv::cvtColor(image1, image2, cv::COLOR_YUV2RGB_UYVY); NppiSize nppSize{2,…
t9UhoI
  • 21
  • 2
1
vote
1 answer

How can I properly use nppiYUV422ToRGB_8u_C2C3R()?

I am trying to convert a YUV422 image into RGB image using CPU and GPU. [On CPU] I tried using cv::cvtColor() as shown below: cv::cvtColor(mat_UYVY, mat_bgr, cv::COLOR_YUV2BGR_UYVY); And it works fine. See the picture attached here. (I removed the…
Jumogehn
  • 1,102
  • 3
  • 11
  • 29
1
vote
1 answer

CUDA NPP min-max returns wrong output

I'm using the following code to test the CUDA NPP min-max function. #include #include #include #include #include #include #include #include #include #include…
user3329035
  • 93
  • 7
1
vote
0 answers

NPP function returns nppiFilterRow_8u_C1R CUDA KERNEL execution error

I am using nvidia nsight application to rotate and blur images. I am using the NPP libraries for the same, The oDeviceDst gets filled the data from the output of function rotate, which is working fine.The code is shown below: Also note that the…
Kunal Khosla
  • 11
  • 4
1
vote
1 answer

Cuda Bounding Box with NPP LabelMarkers

I am trying to find bounding boxes for my input data using cuda libraries. I start off with a data set that has noise (and possibly some zeroed out cells) with areas of data that are much higher than the noise. First I apply a gaussian blur to my…
AAG
  • 235
  • 1
  • 11
1
vote
1 answer

Nvidia NPP static link on windows

Is there no static linking option for windows for nvidia's performance primitives libraries? The guide for npp recommends static linking, and shows how for linux, but not windows. http://docs.nvidia.com/cuda/npp/index.html
Jonathan Olson
  • 1,166
  • 9
  • 19
1
vote
1 answer

NPP: Overlapping computation and data transfer

CUDA allows to overlap computation and data transfer using cuMemcpy async functions and streams. But is it possible with NPP(Performance Primitives)? A little background. I am trying to utilize GPU using NPP image resize functions (in our case it is…
Artur Ispiriants
  • 108
  • 1
  • 7
1
vote
1 answer

cuda-memcheck report nppiFilterGauss_8u_C1R out of bounds

I want to use nppiFilterGauss_8u_C1R, but when I use cuda-memcheck,it always report out of bounds,here is my sourcecode: Npp8u* p1 = NULL; Npp8u* p2 = NULL; unsigned char* p3 = NULL; unsigned char* p4 = NULL; int step1 = 0; int step2 = 0; NppiSize…
langyu
  • 68
  • 1
  • 7
1
2
3 4