为便利用户寻找 CUDA 安装软件,此处将与 NVIDIA 官网同步更新,并提供便捷的连接。目前最新版本为 CUDA 7.5

- 最新 CUDA 下载,请访问原厂 https://developer.nvidia.com/cuda-downloads
- 旧版 CUDA 下载,请访问原厂 https://developer.nvidia.com/cuda-toolkit-archive

最新 CUDA Toolkit 8.0 简介如下:

1. Pascal Architecture Support

- Out of box performance improvements on Tesla P100, supports GeForce GTX 1080

- Simplify programming using Unified memory on Pascal including support for large datasets, concurrent data access and atomics*

- Optimize Unified Memory performance using new data migration APIs*

- Faster Deep Learning using optimized cuBLAS routines for native FP16 computation

2. Developer Tools

- Quickly identify latent system-level bottlenecks using the new critical path analysis feature

- Improve productivity with up to 2x faster NVCC compilation speed

- Tune OpenACC applications and overall host code using new profiling extensions

3. Libraries

- Accelerate graph analytics algorithms withnvGRAPH

- New cuBLAS matrix multiply optimizations for matrices with sizes smaller than 512 and for batched operation

- Download the CUDA Toolkit 8 RC today; requires membership of the the Accelerated Computing Developer Program

 

其他相关链接

Linux安装手册(英文)

cuFFT Patch(TAR档,122MB),README