Extreme-scale Scientific Software Stack team emits v22.02

Open-source HPC suite now includes 100 full-release products

The Extreme-scale Scientific Software Stack (E4S) project has released version 22.02 of its collection of software packages for developing, deploying and running scientific applications on high-performance compute (HPC) platforms.

E4S is supported by the US Department of Energy (DoE) via the Exascale Computing Project, and is effectively a curated ecosystem of numerical libraries, runtime systems, and tools that are intended to make it easier for the HPC and AI/ML developer communities to deploy them.

With version 22.02, E4S now comprises 100 full-release products, compared with just 24 full and 24 partial-release products for the first version of the collection delivered in October 2018.

The list includes tools such as Catalyst, ParaView, OpenMP, Kokkos, and the Flang Fortran compiler, plus development tools such as HPCToolkit, TAU and PAPI, and mathematical libraries including PETSc and Trilinos.

According to the E4S release notes [PDF], v22.02 includes a subset of the full portfolio of Exascale Computing Project (ECP) Software Technologies (ST) products, but demonstrates a target approach for future delivery of the entire ECP ST software stack.

E4S uses the Spack multi-platform package manager as a meta-build tool to identify and track the software dependencies of all the packages, and products were apparently targeted for inclusion based on Spack package maturity as well as location within the scientific software stack, so not all ECP ST packages were included in this release.

According to E4S project leader Mike Heroux, the project ends up building hundreds of dependencies so that there is a complete software stack available to the end users. Heroux is also a senior scientist at Sandia National Laboratories.

"One kind of minimalist way to think of E4S is that it's a Spack build script, which in fact, it is. Spack is a tool that allows you to define how to build your product, and then it allows you to identify the other products that your product depends upon," Heroux explained in the E4S announcement on the ECP site.

"You can think of E4S as being the final delivery vehicle of hardened and truly robust capabilities that are provided by ECP as reusable libraries and tools."

In future, E4S will increasingly include AI tools and libraries that are needed specifically to apply to scientific problem sets, according to the project team.

The E4S collection is available on GitHub and can be downloaded as a container image in Docker, Singularity, or CharlieCloud format, or via a Spack manifest to install from source.

It is also available as an AWS EC2 image. It supports Arm, x86, and PowerPC processors, plus Nvidia, Intel, and AMD GPUs, and hence includes GPU runtimes including CUDA, NVHPC, ROCm, and oneAPI as well as AI/ML packages such as TensorFlow and PyTorch.

While E4S is open source software published under the MIT License, the packages within the collection each have their own open-source license. ®

Similar topics

TIP US OFF

Send us news


Other stories you might like