Reinventing HPC

Conference Keynote Ponders Post-Exascale Era

Hamburg, Germany, February 06, 2024We are pleased to announce that Katherine (Kathy) Yelick, who holds the position of Vice Chancellor for Research and is the Robert S. Pepper Distinguished Professor of Electrical Engineering and Computer Sciences at the University of California, Berkeley, will be delivering the ISC 2024 opening keynote talk on Monday, May 13.

In the keynote titled "Beyond Exascale Computing," Yelick will address the challenges and opportunities of post-exascale computing for the scientific community. With the first exascale systems now online, a clearer picture of what will be needed in the future has become more apparent.  But as the requirements of more powerful simulations and data analytics grow, the limits of chip technologies, along with the promise of AI and the evolving computing marketplace, are creating unique challenges for the years ahead.

To set the stage for her talk, Yelick will present the findings of the US National Academies report that reviewed the hardware and software technologies that are likely to be relevant in this new era of HPC. Notably, the report also considered the changing industrial and geopolitical landscape driving some of these technologies. To round out her presentation, Yelick will also offer some of her thoughts about how the research community will have to adapt to this new environment.

A highly respected individual in the HPC research community, Yelick is also a Senior Faculty Scientist at Lawrence Berkeley National Laboratory. Her research is in high performance computing, programming systems, parallel algorithms, and computational genomics. She is well known for her work in Partitioned Global Address Space languages, including co-inventing the Unified Parallel C (UPC) and Titanium languages. She has worked on interdisciplinary teams developing scientific applications ranging from simulations of chemistry, fusion, and blood flow in the heart to analysis problems in phylogenetics and genome assembly. She currently leads the ExaBiome project on Exascale Solutions for Microbiome Analysis, part of the Department of Energy's Exascale Computing Project.

Yelick was the Director of the National Energy Research Scientific Computing Center (NERSC) from 2008 to 2012 and led the Computing Sciences Area at Berkeley Lab from 2010 through 2019, where she oversaw NERSC, the Energy Sciences Network (ESnet), and the Computational Research Division of scientists and engineers in applied math, computer science, data science, and computational science. She earned her Ph.D. in Electrical Engineering and Computer Science from MIT and has been a professor at UC Berkeley since 1991 with a joint research appointment at Berkeley Lab since 1996.

In keeping with the post-exascale theme, Wednesday’s keynote is on “Reinventing HPC with Specialized Architectures and New Applications Workflows.” Rosa M. Badia from the Barcelona Supercomputing Center and John Shalf from Lawrence Berkeley National Laboratory will delve more deeply into the architectures and application workflows required to support these increasingly powerful systems. In particular, they will outline the utility of architectural specialization and the new mathematical models and algorithmic approaches needed to support it. As a result of these changes, application workflows will become increasingly complex, incorporating data analytics, AI, and traditional modeling and simulation. Badia and Shalf will devote particular attention to the role of AI and how it can be leveraged to provide new capabilities for post-exascale HPC.

We encourage the HPC community to come together at ISC 2024 for this year's conference. It's a critical event for us to collectively rethink how we can create HPC systems that provide cost-effective and practical computing performance for scientific and technical computing. Registration for the event will open towards the end of this month.

Join ISC High Performance 2024 in #Reinventing HPC

ISC 2024 returns to the Congress Center Hamburg. Since its inception in 1986, it has been acknowledged as the world’s oldest and Europe’s must-attend event for HPC, machine learning, and high-performance data analytics professionals. The exhibition will showcase the latest developments in high performance computing, covering all significant advancements in system design, programming models, applications, machine learning, quantum computing, and emerging technologies.


Nages Sieslack

Go back