Dr Miren Radia, Research Software Engineer at Research Computing Services, presents his work on numerical relativity software during the AMReX session at the High Performance Software Foundation conference held in Chicago in May this year.

#HPC #NumericalRelativity #AMReX #ResearchSoftware

https://www.youtube.com/watch?v=PDUpokvDCEM

Numerical Relativity with AMReX - Miren Radia, University of Cambridge

YouTube

We posted a new #preprint: "#AMReX and #pyAMReX: Looking Beyond ECP" by Andrew Myers, Weiqun Zhang, Ann Almgren, Thierry Antoun, John Bell, Axel Huebl, and Alexander Sinn.

https://arxiv.org/abs/2403.12179

#HPC #Simulation #GPU #ML #Python #CXX

AMReX and pyAMReX: Looking Beyond ECP

AMReX is a software framework for the development of block-structured mesh applications with adaptive mesh refinement (AMR). AMReX was initially developed and supported by the AMReX Co-Design Center as part of the U.S. DOE Exascale Computing Project, and is continuing to grow post-ECP. In addition to adding new functionality and performance improvements to the core AMReX framework, we have also developed a Python binding, pyAMReX, that provides a bridge between AMReX-based application codes and the data science ecosystem. pyAMReX provides zero-copy application GPU data access for AI/ML, in situ analysis and application coupling, and enables rapid, massively parallel prototyping. In this paper we review the overall functionality of AMReX and pyAMReX, focusing on new developments, new functionality, and optimizations of key operations. We also summarize capabilities of ECP projects that used AMReX and provide an overview of new, non-ECP applications.

arXiv.org
Once in a blue moon I can work for a hot evening on binary hackery - like this for #AMReX πŸŽ‰πŸ˜
https://github.com/AMReX-Codes/amrex/pull/3735
Add `ParticleIDWrapper::make_invalid()` by ax3l Β· Pull Request #3735 Β· AMReX-Codes/amrex

Summary A cheaper way to swap validity sign on particle ids, as needed to select and track particles from one kernel to another (e.g., boundary condition treatment, re-emission physics, scraping of...

GitHub
The #LBNL #AMReX team will be hosting an AMReX tutorial in the #NERSC Performance Portability Series on March 14. (Free registration is required.)
https://www.nersc.gov/users/training/events/2024/performance-portability-series-amrex-mar2024/
Performance Portability for Next-Generation Heterogeneous Systems, Feb 26, 2024

This performance portability overview session, presented by Tom Deakins of University of Bristol is part of the Performance Portability training series. 

NERSC

We have big news!

Today, we announced that #WarpX and #AMReX intent to join an open foundation for High Performance Software (#HPSF). With this step, we acknowledge & foster our tremendously valuable international scientific contributor and scientific user base, elevating project governance to the same, international, open level.
https://www.linuxfoundation.org/press/linux-foundation-announces-intent-to-form-high-performance-software-foundation-hpsf

1/2

Linux Foundation Announces Intent to Form the High Performance Software Foundation

Foundation aims to build, promote, and advance a portable core software stack for high performance computing.

I'm getting some practice in with the #amrex AMR-Wind LES code this week in preparation for some DOE AWAKEN runs. Here's a bird's eye view of winds for three turbines in a row. You can see the wakes get progressively stronger as you move from left to right