Spla¶

Support tier: 3

Read information about support tiers.

Installed versions¶

Resource	Version
Dardel-GPU/cpe23.12	1.5.5
Dardel/cpe23.12	1.5.5
Dardel/cpe24.11	1.6.1

Read information about how to load this software in your environment by searching for Lmod module.

General information¶

Specialised Parallel Linear Algebra (SPLA) provides specialised functions for linear algebra computations with a C++ and C interface, which are inspired by requirements in computational material science codes. SPLA provides functions for distributed matrix multiplications with specific matrix distributions, which cannot be used directly with a ScaLAPACK interface. All computations can optionally utilise GPUs through CUDA or ROCm, where matrices can be located either in host or device memory. For more information see the SPLA homepage.

How to use¶

You can check available SPLA modules using

ml spider spla

For example, load the module for the SPLA library 1.5.5 with GPU backend

ml PDC/<version>
ml spla/1.5.5-cpeGNU-23.12-gpu

To see what environment variables are set when loading the module

ml show spla/1.5.5-cpeGNU-23.12-gpu