NVIDIA CUDA 11.3
NVIDIA has announced our newest release of the CUDA toolkit and development environment, consisting of GPU-accelerated libraries, debugging and optimization tools, a C/C++ compiler, and a runtime library to build and deploy your application on major architectures including NVIDIA Ampere, x86, Arm server processors, and POWER.
CUDA 11.3 features are focused on enhancing the programming model and performance of your GPU-accelerated applications.
New features include:
- CUDA programming model enhancements
- CUDA graph enhancements
- Stream-Ordered Memory Allocator enhancements
- Language support for CUDA
- C++ support enhancements
- Python support via preview release on GitHub
- Compiler enhancements
CUDA is ideal for diverse workloads from high performance computing, data science analytics, and AI applications. With that, we are expanding the market opportunity with Python in data science and AI applications.
CUDA Python is a preview release providing Cython/Python wrappers for CUDA driver and runtime APIs. Python developers will be able to leverage massively parallel GPU computing to achieve faster results and accuracy.
Learn more about CUDA Python.
For more information, read these new posts: