CUDA 12.0.0

CUDA (formerly Compute Unified Device Architecture) is a parallel computing platform and programming model created by NVIDIA and implemented by the graphics processing units (GPUs) that they produce. CUDA gives developers access to the virtual instruction set and memory of the parallel computational elements in CUDA GPUs.

Accessing CUDA 12.0.0

To load the module for CUDA 12.0.0 please use this command on the BEAR systems (BlueBEAR and BEAR Cloud VMs):

📋 module load bear-apps/2022b
module load CUDA/12.0.0

BEAR Apps Version

2022b

Architectures

EL8-sapphirerapids

The listed architectures consist of two part: OS-CPU. The OS used is represented by EL and there are several different processor (CPU) types available on BlueBEAR. More information about the processor types on BlueBEAR is available on the BlueBEAR Job Submission page.

More Information

For more information visit the CUDA website.

Required By

This version of CUDA is a direct dependent of: cuDNN/8.8.0.121-CUDA-12.0.0 magma/2.7.1-foss-2022b-CUDA-12.0.0 NCCL/2.16.2-GCCcore-12.2.0-CUDA-12.0.0 PyTorch/2.1.2-foss-2022b-CUDA-12.0.0 PyTorch-Geometric/2.5.0-foss-2022b-PyTorch-2.1.2-CUDA-12.0.0 UCX-CUDA/1.13.1-GCCcore-12.2.0-CUDA-12.0.0

Other Versions

These versions of CUDA are available on the BEAR systems (BlueBEAR and BEAR Cloud VMs). These will be retained in accordance with our Applications Support and Retention Policy.

Last modified on 13th May 2024