IXPUG SC26 BOF

 

IXPUG Birds-of-a-Feather

IXPUG Birds-of-a-Feather


Title : Navigating Complexity: Achieving Performance Portability in the Evolving Landscape of Heterogeneous HPC Systems

Location: Room W185abc, McCormick Place, 2301 S Martin Luther King Dr, Chicago, IL 60616

Date: Wednesday, 18 November 2026  12:15pm - 1:15pm CST

Registration: The workshop is held in conjunction with SC26 in Chicago. To attend IXPUG BoF, you must register for SC. More information is on the SC26 Website.

SC Page link:

https://sc26.supercomputing.org/program/birds-of-a-feather/

and

https://sc26.conference-program.com/presentation/?id=bof103&sess=sess397

Event Description:

As AI techniques are increasingly integrated into traditional HPC codes, the community anticipates even greater system diversity in the years ahead. This trend underscores the urgent need for programming models and abstractions that support efficient development across a variety of distributed architectures and application domains. Application developers and computational scientists face growing challenges due to differences in hardware designs, parallelization strategies, interconnect schemes, hardware primitives, and architectural features, all of which complicate the task of creating portable and efficient software capable of running across diverse machines and HPC sites.

This BoF will delve into current approaches, state-of-the-art techniques, and emerging best practices for programming heterogeneous and novel architectures. The objective is to identify common principles and methodologies that enable sustainable and portable development across systems, sites, and scientific applications. The session will highlight real-world experiences from developers using modern programming frameworks such as Kokkos, RAJA, SYCL, and oneAPI, as well as from application developers who have benchmarked performance across a wide variety of systems.

Through invited talks by researchers from HPC centers and developers of widely-used programming abstractions, this BoF aims to provide a rich forum for exchanging practical insights and technical expertise. Participants— including researchers, application developers, HPC facility staff, and industry stakeholders—will be encouraged to engage with the speakers and each other to explore effective strategies for dealing with heterogeneous computing environments and the increasingly varied nature of today’s workloads.

BoF Agenda:  

Session Leader:  David Martin, Energy Sciences Network (ESnet), Lawrence Berkeley National Laboratory

12:15 p.m. Introductions - Dr. Amit Ruhela, Texas Advanced Computing Center
12:20 p.m. Panelist Presentations
    12:20 - 12:27 p.m. Panelist 1
    12:27 - 12:34 p.m. Panelist 2
    12:34 - 12:41 p.m. Panelist 3
    12:41 - 12:48 p.m. Panelist 4
12:50 - 1:15 p.m Open Discussion and Q&A
 

Panelists:

Panelist 1 : Cristina Beldica, Intel Corporation

Cristina Beldica 02 lrg web sq

 

Cristina Beldica is a Senior Director at Intel, leading the organization responsible for software products that accelerate HPC and AI workloads, including oneMKL, oneTBB, OpenMP, and other critical technologies for parallel computing. Previously, she led Intel's communication software portfolio, including Intel MPI, oneCCL, Intel SHMEM, and OFI/libfabric. With more than 30 years of leadership experience in high-performance computing, distributed systems, and performance-critical software, Dr. Beldica has overseen the development and deployment of software for some of the world's most advanced computing systems, including the Aurora Exascale supercomputer at Argonne National Laboratory. Prior to joining Intel, she served as Associate Director at the National Center for Supercomputing Applications (NCSA) and co-Principal Investigator for Blue Waters, a $500+ million leadership class computing system. She conducted independent research and contributed to numerous scientific initiatives spanning materials science, cosmology, and dark energy, with a strong focus on enabling computational science through advanced computing technologies.

 

 

Panelist 2 : Neil Mehta, Lawrence Berkeley National Laboratory (LBNL)

 

Neil Mehta is a computational chemist with experience in molecular dynamics and kinetic Monte Carlo methods. He has served as an HPC performance engineer, optimizing molecular dynamics codes. Neil has been a co-lead for the NESAP Pathfinding and NESAP for NERSC-10 projects. NERSC Science Acceleration Program (NESAP) is a collaborative activity where NERSC works with the DOE science teams to enable these multi-area science teams from across the country to productively use cutting-edge high-performance computing resources. As co-lead, Neil Mehta provides management guidance to liaisons and teams to set goals that benefit both, NERSC's institutional and resource knowledge while helping science teams achieve goals

 

 

Panelist 2 : Peter A Dinda, Northwestern University

 

Peter Dinda is a professor in the CS Department at Northwestern University and also holds an appointment in the ECE Department. He headed the Computer Engineering and Systems division for five years within the previous EECS Department. He holds a B.S. in electrical and computer engineering from the University of Wisconsin and a Ph.D. in computer science from Carnegie Mellon University. He works in experimental computer systems, particularly parallel and distributed systems, and has authored over 140 scientific papers, authored or is a major contributor to several large publicly available codebases, and holds five patents. His research currently involves virtualization and operating systems for distributed and parallel computing, programming languages for parallel computing, privacy in IoT environments, and empathic systems for bridging individual user satisfaction and systems-level decision-making. He is a Fellow of the IEEE. You can find out more about him at pdinda.org

 

 

Panelist 4: Dr. Mathias Puetz and Ilan Tayari, NextSilicon

 

Dr. Mathias Puetz is Director of Technical Pre-Sales at NextSilicon, where he identifies new market areas for Maverick and helps customers reach the full potential of the technology.

He brings 30 years of experience across academic research and industry. His career began at IBM in 2001 as a software consultant and benchmarker, followed by technical and management roles at Cray, HPE and ParTec in HPC benchmarking, solution engineering and technical pre-sales, giving him broad expertise in computing and networking technologies.

Mathias holds a Dr. rer. nat. in theoretical physics from the University of Mainz, conducted his doctoral research at the Max Planck Institute for Polymer Research, and spent nearly two years as a postdoctoral researcher at Sandia National Laboratories.

He sees himself as an enabler: making things more efficient and unlocking applications that were not possible before

     
     

 

Ilan Tayari is co-founder and vice president of architecture at NextSilicon. He oversees NextSilicon’s research and architecture teams, and also leads all aspects of design and delivery. His teams are responsible for perfecting the system and algorithms that lie at the core of NextSilicon’s technology. Ilan is an accomplished engineer and architect, and brings 20+ years of experience leading the design and development of drivers, compilers, firmware, and software.

Before NextSilicon, Ilan was a senior staff engineer (software) at Mellanox Technologies, where he led the design and development of drivers and software for a high-throughput unicast and multicast router and cryptographic-offload NIC. Before Mellanox, Ilan was a distinguished architect at Integrity Project (acquired by Mellanox Technologies) and held positions at Nocturnus Systems and Cogniview Systems.

Ilan earned a BS in physics and computer science from the Hebrew University of Jerusalem, and is the author of multiple patents.

 

Session Organizers:

    Amit Ruhela, Texas Advanced Computing Center (TACC)
    David Martin, Energy Sciences Network (ESnet), Lawrence Berkeley National Laboratory
    Hatem Ltaief, King Abdullah University of Science & Technology
    Clay Hughes, Sandia National Laboratories
    Toshihiro Hanawa, University of Tokyo    
    Steffen Christgau. ZIB    
    Nalini Kumar, Intel Corporation

Contact: Please contact This email address is being protected from spambots. You need JavaScript enabled to view it. with any general questions.