With a strong reliance on research software projects in both industry and for scientific simulations, research software sustainability is increasingly becoming a major point of contention. A necessary but nonsufficient aspect of software sustainability is Continuous Integration and Benchmarking (CI/CB/Cx). In this talk, we will showcase the Cx practices of the Ginkgo numerical linear algebra framework, which was designed with unit testing, good software design techniques as well as Cx practices as centerpieces. Because of HPC software constraints, access to HPC clusters for both CI and CB are essential to ensure correctness. We will show our configurable solution for running Cx on HPC clusters implemented thanks to a custom GitLab runner, a...
The source separation technology developed by Audionamix requires a significant amount of computatio...
International audienceSupport teams of high-performance computing (HPC) systems often find themselve...
The aim of this project was to encapsulate the needs of computational science applications. Performa...
Ginkgo is a production-ready sparse linear algebra library for high performance computing on GPU-cen...
Presentation in the context of the HiRSE seminar series on 28 April 2022. Abstract: Continuous Inte...
An important aspect in the design of a numerical software ecosystem is software sustainability and t...
© ACM, YYYY. This is the author's version of the work "Anzt, H., Cojean, T., Flegar, G., Göbel, F., ...
Presentation by Terry Cojean at the "Bridging the Gap from HPC Software Engineering to Academic Rese...
This artifact archives the repository used for our paper on implementing batched iterative solvers f...
With discrete Intel GPUs entering the high-performance computing landscape, there is an urgent need ...
Abstract: Many different numerical algorithms contain the solution of lin-ear equation systems as a ...
We introduce HPCx- the UK's new National HPC Service- which aims to deliver a world-class servi...
GPUs are getting more and more important in scientific computing, slowly growing from peripheral acc...
Ensuring longevity and maintainability of modern software applications is mandatory for a proper ret...
Nowadays, HPC, Grid and Cloud systems are evolving very rapidly. However, the development of infrast...
The source separation technology developed by Audionamix requires a significant amount of computatio...
International audienceSupport teams of high-performance computing (HPC) systems often find themselve...
The aim of this project was to encapsulate the needs of computational science applications. Performa...
Ginkgo is a production-ready sparse linear algebra library for high performance computing on GPU-cen...
Presentation in the context of the HiRSE seminar series on 28 April 2022. Abstract: Continuous Inte...
An important aspect in the design of a numerical software ecosystem is software sustainability and t...
© ACM, YYYY. This is the author's version of the work "Anzt, H., Cojean, T., Flegar, G., Göbel, F., ...
Presentation by Terry Cojean at the "Bridging the Gap from HPC Software Engineering to Academic Rese...
This artifact archives the repository used for our paper on implementing batched iterative solvers f...
With discrete Intel GPUs entering the high-performance computing landscape, there is an urgent need ...
Abstract: Many different numerical algorithms contain the solution of lin-ear equation systems as a ...
We introduce HPCx- the UK's new National HPC Service- which aims to deliver a world-class servi...
GPUs are getting more and more important in scientific computing, slowly growing from peripheral acc...
Ensuring longevity and maintainability of modern software applications is mandatory for a proper ret...
Nowadays, HPC, Grid and Cloud systems are evolving very rapidly. However, the development of infrast...
The source separation technology developed by Audionamix requires a significant amount of computatio...
International audienceSupport teams of high-performance computing (HPC) systems often find themselve...
The aim of this project was to encapsulate the needs of computational science applications. Performa...