mirror of https://github.com/NVIDIA/cuda-samples.git synced 2025-04-04 07:21:33 +01:00

History

Rob Armstrong 96901090bc nvJPEG: Modify write_images function to return void instead of int

- Changed return type from int to void
- Removed EXIT_FAILURE return in error case (unchecked)
- Removed control reaches end of non-void function

2025-02-12 11:49:35 -08:00

.vscode

add and update samples for CUDA 11.6

2022-01-13 11:35:24 +05:30

images

add and update samples for CUDA 11.6

2022-01-13 11:35:24 +05:30

CMakeLists.txt

Add missing build targets to general samples

2025-02-08 13:04:26 -05:00

nvJPEG.cpp

nvJPEG: Modify write_images function to return void instead of int

2025-02-12 11:49:35 -08:00

README.md

Remove README references to PPC processors (no longer supported)

2024-12-18 10:54:37 -08:00

nvJPEG - NVJPEG simple

Description

A CUDA Sample that demonstrates single and batched decoding of jpeg images using NVJPEG Library.

Key Concepts

Image Decoding, NVJPEG Library

Supported SM Architectures

Supported OSes

Linux, Windows, QNX

Supported CPU Architecture

x86_64, aarch64

CUDA APIs involved

cudaHostAlloc, cudaStreamCreateWithFlags, cudaStreamDestroy, cudaFree, cudaEventSynchronize, cudaEventRecord, cudaFreeHost, cudaStreamSynchronize, cudaMalloc, cudaEventElapsedTime, cudaGetDeviceProperties, cudaEventCreate

Dependencies needed to build/run

NVJPEG

Prerequisites

Download and install the CUDA Toolkit 12.5 for your corresponding platform. Make sure the dependencies mentioned in Dependencies section above are installed.