CUDA 11 has a wealth of features – from platform system software to everything you need to get started and develop GPU-accelerated applications. Here is an overview of the key software features in this release.
- Support for the NVIDIA Ampere GPU architecture, including the new NVIDIA A100 GPU for accelerated scaling and shrinking of AI and HPC data centers; multi-GPU systems with NVSwitch architecture, such as the DGX A100 and HGX A100.
- Multi-instance GPU (MIG) partitioning capabilities that are particularly beneficial to cloud service providers (CSPs) to improve GPU utilization.
- New third-generation tensor cores that accelerate mixed-precision, matrix computing for different data types, including TF32 and Bfloat16.
- Programming and APIs for task graphs, asynchronous data movement, fine-grained synchronization, and secondary cache-resident control.
- Performance optimizations for linear algebra, FFT, and matrix multiplication in the CUDA library.
- Updates to the Nsight product family of tools for tracing, profiling, and debugging CUDA applications.
- Full support for all major CPU architectures, including x86_64, Arm64 server, and POWER architectures.
The installation process on the Jetson platform is also quite simple. Copy the following code into your terminal then execute.
- wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/sbsa/cuda-ubuntu1804.pin
- sudo mv cuda-ubuntu1804.pin /etc/apt/preferences.d/cuda-repository-pin-600
- wget http://developer.download.nvidia.com/compute/cuda/11.0.2/local_installers/cuda-repo-ubuntu1804-11-0-local_11.0.2-450.51.05-1_arm64.deb
- sudo dpkg -i cuda-repo-ubuntu1804-11-0-local_11.0.2-450.51.05-1_arm64.deb
- sudo apt-key add /var/cuda-repo-ubuntu1804-11-0-local/7fa2af80.pub
- sudo apt-get update
- sudo apt-get -y install cuda
After installation, run command
dpkg -l | grep cuda
Then you’ll see CUDA 11 is installed.