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
1
vote
1 answer

Cuda, two streams created by a NPP function

I'm working on an image processing project with Cuda 7.5 and a GeForce GTX 650 Ti. I decided to use 2 stream, one where I apply the algorithms responsible to enhance the image and another stream where I apply an independent algorithm from the rest…
Sanzo
  • 11
  • 5
1
vote
1 answer

cuda opencv undefined reference to `nppiConvert_16u8u_C4R`

I am trying to run a opencv based simple rgb to gray scale script and run it through cuda. The header for the C++ script that does the computation links the following api from opencv: #include …
goofd
  • 2,028
  • 2
  • 21
  • 33
1
vote
1 answer

NPP graph cut for non-integer edge capacities

The nppiGraphcut_32s8u function works on 32 bit signed integer edge capacities. In the grabCut example included with the CUDA 6.5 toolkit, they simply cast Npp32f to Npp32s. For example, from GrabcutUtil.cu in the grabcutNPP example folder: //…
samarth.robo
  • 61
  • 7
1
vote
1 answer

Performance drop in nppiCopyConstBorder_8u_C1R

I have a performance drop using the nppiCopyConstBorder_8u_C1R function in two different architectures (GTX480 and GTX TITAN) involving also different CUDA version (v5.0 and v5.5 respectively). In the first case (GTX480 and CUDA 5.0) the execution…
pQB
  • 3,077
  • 3
  • 23
  • 49
1
vote
1 answer

CUDA NPP - unknown error upon GPU error check

I am trying to sum all the pixels in an image, and get the average of all pixels using the CUDA NPP library. My image is an 8-bit unsigned char grayscale image of dimension w256 x h1024. I have tried to follow all the required rules of declaring…
Eagle
  • 1,187
  • 5
  • 22
  • 40
1
vote
1 answer

CUDA NPP image dot product having cudaErrorUnknown

The function nppiDotProd_8u64f_C1R causes a cudaErrorUnknown. I'm able to compile and run properly boxFilterNPP and histEqualizationNPP so I assume my system is healthy. I'm running with a GTX470 (compute capability 2.0), CUDA 5.5 and VS2012 x64 on…
Simon
  • 13
  • 2
1
vote
1 answer

CUDA_npp_LIBRARY error with cmake 2.8 and CUDA v 5.5

I am trying to build a solution in Visual Studio 2010 and to do so had to setup cmake 2.8, opencv and CUDA v5.5 for supporting files. While doing a cmake build I get the following error. CMake Error: The following variables are used in this…
serendipity
  • 852
  • 13
  • 32
0
votes
1 answer

Cuda NPP Filter Median functions

Was wondering if any one more versed in how to call this NPP cuda function could tell me where the mistake is occurring? #define gpuErrchk(ans) gpuAssert((ans), __FILE__, __LINE__) inline int gpuAssert(cudaError_t code, const char *file, int…
Batmanslow23
  • 1
  • 1
0
votes
0 answers

Scale AVFrame by AV_PIX_FMT_CUDA format on GPU memory using FFMPEG

I've even tried the av_hwframe_transfer_data, transferring the hardware-decoded frame to RAM and got another frame format AV_PIX_FMT_NV12 but still the sws_scale can't resize it, saying the hardware pixel format is not supported. the funny part is,…
hameed abbasi
  • 3
  • 1
  • 4
0
votes
3 answers

Convert NV12 to BGR by NVIDIA Performance Primitives

I'm trying to convert NV12 image to BGR by npp, but in the final array i have zeroes. int lumaStepBytes, chromaStepBytes; int rgbStepBytes; auto dpNV12LumaFrame = nppiMalloc_8u_C1(dec.GetWidth(), dec.GetHeight(), &lumaStepBytes); auto…
Павел Бодак
  • 11
  • 3
0
votes
1 answer

cuda nppiResize() for RGB images

nVidia Cuda nppiResize_32f_C1R works OK on grayscale 1 x 32f, but nppiResize_32f_C3R returns garbage. Clearly, a work around would be to call this routine 3 times by first de-interleaving the data as planar R, G, B, but I was expecting to be able to…
plettplett
  • 9
  • 2
0
votes
1 answer

NPP image cross correlation producing no valid results

I'm trying to implement an image displacement method using the NPP cross correlation library. I have tried creating a simple solution by generating a couple of simple images in memory, outputting either Npp8u or Npp32f arrays. However the cross…
Andy C
  • 65
  • 1
  • 6
0
votes
1 answer

How to calculate image rotation shift for NPP?

ippiGetRotateTransform and nppiRotate both take x and y shift parameters but I am unsure how they work. IPP and NPP both rotate around (0, 0) then shift the result. This example shows using ippiGetRotateShift to rotate around the center, but does…
plswork04
  • 589
  • 6
  • 11
0
votes
1 answer

Static wrapper for Cuda NPP library

I faced a problem trying to create static wrapper for some of NPP icc functions, to call them from cGo (Golang) environment. I'm able to create and compile (C language) executable, with provided static NPP libraries, and it works well. Then I…
Eugene FILIN
  • 1
0
votes
1 answer

How to determine Source-Image Line Step for frame?

I have a YUV422 frame (more specifically UYVY format). How can I determine the Source Image Line step because its needed parameter for conversion in function: NppStatus nppiYUV422ToRGB_8u_P3C3R(const Npp8u* const pSrc[3], int rSrcStep[3], Npp8u*…
Robert Šandor
  • 101
  • 11
1 2
3
4