December 2020 Newsletter

Events

HPC Asia 2021

Mark your calendar for IXPUG Workshop at HPC Asia 2021 January 22, 2021, an open workshop on high-performance computing applications, systems, and architecture with Intel technologies. This is a half-day workshop with invited talks and contributed papers. The workshop aims to bring together software developers and technology experts to share challenges, experiences and best-practice methods for the optimization of HPC, Machine Learning, and Data Analytics workloads on Intel® Xeon® Scalable processors, Intel® Xeon Phi™ processors, Intel® FPGA, and any related hardware/software platforms. The workshop will cover application performance and scalability challenges at all levels – from intra-node performance up to large-scale compute systems.

HPC Asia is an international conference series on HPC technologies in Asia Pacific region to exchange ideas, research results and case studies related to all issues of high performance computing and related technologies. IXPUG has participated each year since 2018.

SC20

Did you miss IXPUG at SC20? Replay the Exhibitor Forum session organized by IXPUG, Accelerating Code Development with Intel OneAPI on Intel XPUs* Presenters:

• David Martin, Argonne National Laboratory
• Thomas Steinke, Zuse Institute Berlin
• Joe Curley, Intel Corporation
• Colleen Bertoni, Argonne National Laboratory
• Bethany Lusch, Argonne National Laboratory

This session focuses on highlighting and encouraging community activities to prepare for the use of Intel XPUs (GPUs, FPGAs) in large systems. Programming for heterogeneous platforms containing XPUs within the Intel oneAPI programming framework is the central topic. This builds on IXPUG community work in preparing codes for parallelism on Intel CPUs and Xe devices. Researchers, code developers, HPC center staff and industry experts share early experiences with oneAPI on existing and pre-product GPUs. An IXPUG overview, the oneAPI initiative, and oneAPI for Aurora and Science Drivers are discussed.

*All of the SC20 program and exhibitor content will be available via the SC20 Virtual Event Platform for six months, but you must register by or on December 7, 2020 to secure access. Exhibitor Forum content may be accessed for free with Exhibits Only (XO) registration.

IXPUG Annual Conference

The IXPUG Annual Conference 2020, virtually hosted by Texas Advanced Computing Center (TACC), brought together many longstanding IXPUG members and new contributors to our community. Special thanks to this year’s conference Co-Chairs Stephen Harrell (TACC) and Amit Ruhela (TACC) for successfully orchestrating the 4-day virtual event. Although we missed seeing each other in person, it was great to have so much live Q&A and conversation via the Slack channel. If you missed any of the presentations, all of the available slides and recordings have been posted, so feel free to download and view the topics you’re interested in. And share with your colleagues!

Resources

• Tech docs: new tech docs available for #oneAPI, an open, standards-based programming model that makes it easier to embrace #heterogeneous programming. Community feedback and contributions welcomed.
• Article: Now Available – Additional oneAPI Open Source Math Library Interfaces by Pavel Dyakov, Math Algorithm Engineer at Intel Corporation discusses array of opensource interfaces for oneAPI Math Kernel Library expands beyond basic linear algebra with support for random number generators, useful in Monte Carlo simulations, financial forecasting, risk management & cryptography applications.
• Looking for presentations from our past Workshops, Meetings, and BOFs? Check the IXPUG Resources page for a searchable repository of slides and recordings from all of our events.

Webinars and Podcasts

• Podcast: In Pursuit of the Holy Grail: Portable, Performant Programming Dr. Tom Deakin, senior research associate and lecturer in the High-Performance Computing Research Group at the University of Bristol, and Dr. James Brodman, software engineer at Intel, discuss performance portability. As contributors to the Khronos SYCL Working Group, they talk about the exciting growth of the SYCL community and its implementations that now support a variety of hardware architectures, including DPC++ and hipSYCL.
• Podcast: Optimizing HPC Clusters: Meeting the Challenges of Today and Tomorrow As HPC moves far beyond its traditional users to the domains of AI, machine learning, enterprises and the cloud, and heterogeneous programming becomes the norm. Nico Mittenzwey, senior HPC engineer at Megware Computer, and Mike Lee, technical, enterprise and cloud segment marketing manager at Intel, discuss the considerations in optimizing HPC clusters and applications. They discuss Intel MPI Library, the challenges of fragmentation in heterogeneous computing environments, and how a single, common programming model can help address these challenges.
• Podcast: Tuning Applications for Multiple Architecture Senior Principal Engineers at Intel Henry Gabb and Paul Petersen discuss the possibilities enabled by oneAPI…i.e., spend time being creative, not recoding for heterogeneous setups.
• Webinar: Achieve AI Performance from Datacenter to Edge Intel AI product manager Saumya Satish addresses Intel’s holistic approach to AI and Data Science and discusses a set of software tools that enable developments and deployment of machine and deep learning models across XPUs. Wednesday, December 9 | 9:00AM PT

About IXPUG

• IXPUG is an independent users group whose mission is to provide a forum for the free exchange of information that enhances the usability and efficiency of scientific and technical applications running on HPC, AI, and data analytics systems using advanced Intel technologies. IXPUG is administered by representatives of member sites that operate large Intel-based HPC systems.