The IDEAS Productivity project, in partnership with the DOE Computing Facilities of the ALCF, OLCF, and NERSC, and the DOE Exascale Computing Project (ECP), organizes the webinar series on Best Practices for HPC Software Developers.
As part of this series, we offer one-hour webinars on topics in scientific software development and high-performance computing, approximately once a month. The April webinar is titled Facilitating Electronic Structure Calculations on GPU-based Exascale Platforms; and will be presented by Jean-Luc Fattebert (Oak Ridge National Laboratory). The webinar will take place on Wednesday, April 12, 2023, at 1:00 pm ET.
Abstract:
GPUs accelerators offer the prospect of speeding up ab initio molecular dynamics and other large-scale first-principles atomistic simulations. Taking advantage of these devices is, however, not a trivial task given their specificities. Some algorithms struggle, while others thrive with the high level of thread concurrency available on modern GPUs. The PROGRESS and BML libraries, developed within ECP’s Co-design Center for Particle Applications (CoPA) project, allow electronic structure codes to offload their most expensive kernels, with a unified interface for various matrix formats and computer architectures. The webinar will focus on implementations and algorithmic choices made in those libraries, and lessons learned while trying to achieve performance portability on exascale platforms. Specifically, the webinar will discuss eigensolvers and their alternatives, as well as strong scaling in fast time-to-solution in molecular dynamics.
The IDEAS Productivity project, in partnership with the DOE Computing Facilities of the ALCF, OLCF, and NERSC, and the DOE Exascale Computing Project (ECP), organizes the webinar series on Best Practices for HPC Software Developers.
As part of this series, we offer one-hour webinars on topics in scientific software development and high-performance computing, approximately once a month. The May webinar is titled Lessons Learned Developing Performance Portable QMCPACK; and will be presented by Paul Kent (Oak Ridge National Laboratory). The webinar will take place on Wednesday, May 10, 2023, at 1:00 pm ET.
Abstract:
During DOE’s Exascale Computing Project the open source QMCPACK code has been redesigned and reimplemented to run portably and performantly on multiple vendors GPUs as well as CPUs. The QMCPACK code implements Quantum Monte Carlo algorithms to predict the properties of materials with benchmark accuracy. The new implementation has now fully replaced the prior non-portable GPU solution. This webinar will outline some of the design considerations and new algorithms implemented both to run efficiently and to reduce burdens on the developers and maintainers. A key factor has been the adoption of modern development practices, including an extensive test suite. This has accelerated development, improved code quality, and also enabled isolation of problems in the wider HPC software stack, including in compilers and numerical libraries. The webinar will summarize these strategies and other recommendations for HPC application developers and facilities.
The IDEAS Productivity project, in partnership with the DOE Computing Facilities of the ALCF, OLCF, and NERSC, and the DOE Exascale Computing Project (ECP), organizes the webinar series on Best Practices for HPC Software Developers.
As part of this series, we offer one-hour webinars on topics in scientific software development and high-performance computing, approximately once a month. The June webinar is titled The OpenSSF Best Practices Badge Program; and will be presented by Roscoe A. Bartlett (Sandia National Laboratories). The webinar will take place on Wednesday, June 14, 2023, at 1:00 pm ET.
Abstract:
The Linux Foundation’s OpenSSF Best Practices Badge Program represents an impressive collection of the open source community’s knowledge base for creating, maintaining, and sustaining robust, high quality, and (most importantly) secure open source software. At its foundation is a featureful “Badge App” website, which provides a database of projects that document what best practices they have adopted and supporting evidence. This set of best practices (along with the detailed documentation and supporting justifications for each item) also serves as an incremental learning tool and as a foundation for incremental software process and quality improvements efforts. The webinar will provide an overview of this effort and describe some of its surprising benefits. The webinar will also describe how the OpenSSF Best Practices Badge Program can be used to help continue the recent advances in software quality and sustainability efforts in the computational science and engineering community going forward.
The IDEAS Productivity project, in partnership with the DOE Computing Facilities of the ALCF, OLCF, and NERSC, and the DOE Exascale Computing Project (ECP), organizes the webinar series on Best Practices for HPC Software Developers.
As part of this series, we offer one-hour webinars on topics in scientific software development and high-performance computing, approximately once a month. The July webinar is titled Writing Clean Scientific Software; and will be presented by Nick Murphy (Center for Astrophysics, Harvard & Smithsonian). The webinar will take place on Wednesday, July 12, 2023, at 1:00 pm ET.
Abstract:
Most scientists are largely self-taught as programmers. Even many of us who spend most of our time coding have never had formal training in writing software. This webinar is intended for students and scientists who have some experience writing code but who have had to learn mostly on their own. The webinar will describe tips and strategies on how to write readable, reusable, and maintainable code. These tips include writing short functions that do exactly one thing with no effects, and measuring the length of a variable name by the time needed to understand its meaning rather than by number of characters. The webinar will describe strategies for restructuring a complicated function into smaller and more manageable chunks, and provide tips on how to make the best use of comments and error messages. Overall, the webinar will embolden the CS&E community to think of code as communication.
Schedule:
This two-day tutorial will run July 26-27, 12:00pm-3:25pm ET.
Abstract:
A majority of HPC system users use scripting languages such as Python to prototype their computations, coordinate their large executions, and analyze the data resulting from their computations. Python is great for these many uses, but it frequently falls short when significantly scaling up the amount of data and computation, as required to fully leverage HPC system resources. In this tutorial, we show how example computations such as heat diffusion, k-mer counting, file processing, and distributed maps can be written to efficiently leverage distributed computing resources in the Chapel, UPC++, and Fortran parallel programming models. This tutorial should be accessible to users with little-to-no parallel programming experience, and everyone is welcome. A partial differential equation problem will be shown in all three programming models along with performance and scaling results on big machines. Attendees will be shown how to compile and run these programming examples, and provided opportunities to experiment with different parameters and code alternatives while being able to ask questions and share their own observations. Come join us to learn about some productive and performant parallel programming models!
Current OLCF users with access to Frontier will be able to access a reservation on Frontier to work the examples. Current NERSC users will be able to use Perlmutter. Training accounts on Perlmutter are available for participants who do not have access to either Frontier or are not NERSC users. The examples will also be available in a Docker container and a cloud-based virtual desktop environment for access by any attendee.
Keywords:
- Basic and introductory topics for expanding broader engagement
- Software engineering for portable performance and scalability
- Parallel programming methods, models, languages and environments
- Clusters and distributed systems
The IDEAS Productivity project, in partnership with the DOE Computing Facilities of the ALCF, OLCF, and NERSC, and the DOE Exascale Computing Project (ECP), organizes the webinar series on Best Practices for HPC Software Developers.
As part of this series, we offer one-hour webinars on topics in scientific software development and high-performance computing, approximately once a month. The August webinar is titled Infrastructure for High-Fidelity Testing in HPC Facilities; and will be presented by Ryan Prout (Oak Ridge National Laboratory). The webinar will take place on Wednesday, August 9, 2023, at 1:00 pm ET.
Abstract:
The Exascale Computing Project (ECP) is investing heavily in software for exascale systems, as can be seen in the many tools, libraries and software components within ECP. In order to boost software integration across computing facilities, ECP has developed infrastructure and tools for high-fidelity testing. This infrastructure is made accessible to ECP software technology developers to provide a trusted and efficient testing environment that employs continuous integration (CI). At the core of the ECP-enabled testing infrastructure is the Jacamar CI tool. This tool allows us to link multi-tenant HPC systems to Gitlab CI workflows. This webinar will provide an overview of the ECP testing infrastructure, discuss what this could look like post-ECP, and how it could benefit other HPC facilities.
2023 HDF5 User Group Meeting (HUG23)
Registration is now open for the 2023 HDF5 User Group (HUG) Meeting being held August 16-18, 2023 at Scott Laboratory on The Ohio State University campus. This year is special, as we are celebrating 25 years of HDF5. The meeting will consist of over 25 presentations from community members, keynote speakers, lunch talks, a group dinner out, and a full day of tutorials.
Complete information, including information on the conference’s hotel room block, daily schedules, and more can be found on the conference website.
2023 HDF5 User Group Meeting (HUG23)
Registration is now open for the 2023 HDF5 User Group (HUG) Meeting being held August 16-18, 2023 at Scott Laboratory on The Ohio State University campus. This year is special, as we are celebrating 25 years of HDF5. The meeting will consist of over 25 presentations from community members, keynote speakers, lunch talks, a group dinner out, and a full day of tutorials.
Complete information, including information on the conference’s hotel room block, daily schedules, and more can be found on the conference website.
2023 HDF5 User Group Meeting (HUG23)
Registration is now open for the 2023 HDF5 User Group (HUG) Meeting being held August 16-18, 2023 at Scott Laboratory on The Ohio State University campus. This year is special, as we are celebrating 25 years of HDF5. The meeting will consist of over 25 presentations from community members, keynote speakers, lunch talks, a group dinner out, and a full day of tutorials.
Complete information, including information on the conference’s hotel room block, daily schedules, and more can be found on the conference website.
The ECP SOLLVE project, which is working to evolve OpenMP for exascale computing, invites you to participate in a new series of monthly telecons that will occur on the last Friday of every month. The next call in the series will take place on Friday, December 1st, between 11:00 am and 12:00 pm ET.
We are organizing these monthly calls so that ECP application teams may share their OpenMP experiences with the community and bring any related issues or concerns to the attention of the compiler developers and OpenMP language committee members. Application developers may treat them as office hours on all topics related to OpenMP. We expect that representatives of vendors will attend on a regular basis. Please note that attendance is open to ECP and the broader HPC community, and therefore participants should not share confidential and/or proprietary information.
Our goal is to enable application teams to be more productive using OpenMP and help make your codes portable across different vendor compilers and systems. The telecons will be conducted via Zoom. In order to receive the Zoom coordinates for the call, please fill out the following form or click “Tickets” above. Note, you will only be required to fill this form out once to receive the invite to the monthly series.
For the agenda and previous telecons’ materials please check
https://www.openmp.org/events/ecp-sollve-openmp-monthly-teleconference/