...
Several scientific applications are already able to offload computations to the MI250X, many others are in the process of being ported to AMD GPUs. Here is a list of the main ones and their current status.
| Name | Support status | Module on Setonix |
|---|---|---|
| Amber | Supported | |
| Gromacs | Supported | |
| LAMMPS | Supported | |
| NAMD | Supported | |
| NekRS | Supported | |
| PyTorch | Supported | |
| ROMS | Not supported | |
| Tensorflow | Supported | |
| VASP | Porting in progress, no ETA |
Table 1. List of popular applications
...
Popular numerical routines and functions have been implemented by AMD to run on their GPU hardware. All of the following are available when loading the ROCm module.
| Name | Description |
|---|---|
| rocFFT | Fast Furier Transform. Documentation pages (external site). |
| rocBLAS | rocBLAS is the AMD library for Basic Linear Algebra Subprograms (BLAS) on the ROCm platform. Documentation pages (external site). |
| rocSOLVER | rocSOLVER is a work-in-progress implementation of a subset of LAPACK functionality on the ROCm platform. Documentation pages (external site). |
Each of the above libraries has an equivalent HIP wrapper that enables compilation on both ROCm and NVIDIA platforms.
A complete list of available libraries can be found on this page (external site).
AMD ROCm installations
The main ROCm installation is rocm/5.0.2 provided by HPE Cray. In addition Pawsey staff installed rocm/5.4.3 from source using ROCm-from-source. It is an experimental installation and users might encounter compilation or linking errors. You are encouraged to explore it during development and to report any issues. For production jobs, however, we currently recommend sticking to rocm/5.0.2.
Submitting Jobs
Accounting
...