Accelerated Computing Toolkit
The NVIDIA Accelerated Computing Toolkit is a suite of tools, libraries, middleware solutions and more for developing applications with breakthrough levels of performance. Combined with the performance of GPUs, the toolkit helps developers start immediately accelerating applications on NVIDIA’s embedded, PC, workstation, server, and cloud datacenter platforms.
CUDA Toolkit
A comprehensive development environment for C and C++ developers building GPU-accelerated applications. Includes a compiler, math libraries, and tools for debugging and performance optimization. Learn more>
DownloadPGI Community Edition
Fortran, C and C++ compilers with OpenACC, a performance-portable directives-based programming model for parallel computing on CPUs and GPUs. Also supports CUDA Fortran and OpenMP. Learn more>
DownloadDeep Learning Toolkit
A software suite for data scientists to train and deploy next generation deep neural networks quickly and efficiently. Includes GPU-accelerated libraries for deep learning applications. Learn more>
DownloadSoftware Components
GPU-Accelerated Libraries
- Algebraic Multi-Grid (AMGx)
- Deep Neural Network (cuDNN)
- Fast Fourier Transforms (cuFFT)
- Basic Linear Algebra Subroutines (cuBLAS)
- Sparse Matrix Routines (cuSPARSE)
- Dense and Sparse Direct Solvers (cuSOLVER)
- Random Number Generation (cuRAND)
- GPU Rest Engine (GRE)
- Deep Learning Inference Engine (TensorRT)
- Image & Video Processing Primitives (NPP)
- Graph Analytics library (nvGRAPH)
- IndeX Framework (IndeX)
- NVIDIA Video Codec Libraries
- Templated Parallel Algorithms & Data Structures (Thrust)
- CUDA Math Library
Language Solutions
- OpenACC Compiler Directives
- PGI Fortran Compiler (pgfortran)
- PGI C++ Compiler (pgc++)
- NVIDIA CUDA C/C++ Compiler (NVCC)
Development Tools
Web Services
- NVIDIA Image Compute Engine (ICE)
- NVIDIA GPU REST Engine (GRE)