cuDNN
The NVIDIA CUDA Deep Neural Network library (cuDNN) isa GPU-accelerated library of primitives for deep neural networks.
https://developer.nvidia.com/cudnn
Available modules
The overview below shows which cuDNN installations are available per target architecture in the HPCC module system, ordered based on software version (new to old).
To start using cuDNN, load one of these modules using a module load command like:
1 | |
(This data was automatically generated on Thu, 15 May 2025 at 12:00:14 EDT)
| neoverse_v1 | generic | zen2 | zen3 | zen4 | haswell | skylake_avx512 | |
|---|---|---|---|---|---|---|---|
| Grace Nodes | everywhere (except Grace nodes) | amd20 | amd22 | amd24 | intel16 | intel18,amd20-v100,amd21,intel21 | |
| cuDNN/8.9.7.29-CUDA-12.4.0 | - | x | - | - | - | - | - |
| cuDNN/8.9.7.29-CUDA-12.3.0 | - | x | - | - | - | - | - |
| cuDNN/8.9.2.26-CUDA-12.1.1 | - | - | - | x | x | - | x |
| cuDNN/8.4.1.50-CUDA-11.7.0 | - | x | - | - | - | x | - |