Editor’s Choice

• @HPCpodcast: Silicon Photonics – Columbia Prof. Keren Bergman on the Why, How and When of a Technology that Could Transform HPC

  

  Silicon photonics has the potential to transform HPC: it’s a dual-threat interconnect technology that could – if and when it is wrestled into commercial, cost-effective form – move data within chips and systems much faster than conventional, copper-based interconnects while also delivering far greater energy efficiency. Venture-backed start-ups and established tech companies (HPC, NVIDIA, AMD and Intel, to name four) have mounted significant R&D efforts.  In this episode of the @HPCpodcast, Shahin and Doug spoke with a leading silicon photonics expert, Keren Bergmen, Columbia University’s Charles Batchelor Professor of Electrical Engineering, Faculty Director of the Columbia Nano Initiative, and Principal [READ MORE…]

• Azure, AMD and the Power of Cloud-based HPC for Sustainability R&D Projects

  

  [SPONSORED GUEST ARTICLE]  Sustainability – both in the way it operates and in its support for the development of sustainable technologies and products – is a theme that permeates the Microsoft Azure public cloud platform and its end-user community. Azure, in combination with advanced and ultra-efficient CPUs from AMD and other HPC-class technologies, is a hothouse for sustainability R&D projects ranging from electric vehicles to wind turbine design. Before we look in detail at an example of those projects, let’s start with Azure’s operational efficiencies….

• Frontier Pushes Boundaries: 86% of Nodes Engaged on Reactor Simulation Runs

  

  Details have trickled out of the Oak Ridge Leadership Computing Facility (OLCF) indicating progress in preparing Frontier, the exascale-class supercomputer ranked the world’s most powerful system, for full user operations. Earlier this week, the Exascale Computing Project released an article on its web site entitled “Predicting the Future of Fission Power” discussing the ExaSMR (Exa for exascale; SMR for small modular reactors) toolkit for running nuclear reactor design simulations on Frontier. Toward the end of the article, we learn that ExaSMR performed simulations on 8,192 of Frontier’s 9,472 nodes, involving more than 250 billion neutron histories per iteration, according to [READ MORE…]

• Conventional Wisdom Watch: Matsuoka & Co. Take on 12 Myths of HPC

  

  A group of HPC thinkers, including the estimable Satoshi Matsuoka of the RIKEN Center for Computational Science in Japan, have come together to challenge common lines of thought they say have become, to varying degrees, accepted wisdom in HPC. In a paper entitled “Myths and Legends of High-Performance Computing” appearing this week on the Arvix site, Matsuoka and four colleagues (three from the RIKEN Center – see author list below) offer opinions and analysis on such issues as quantum replacing classical HPC, the zettascale timeline, disaggregated computing, domain-specific languages (DSLs) vs. Fortran and cloud subsuming HPC, among other topics. “We [READ MORE…]

• SC22: CXL3.0, the Future of HPC Interconnects and Frontier vs. Fugaku

  

  HPC luminary Jack Dongarra’s fascinating comments at SC22 on the low efficiency of leadership-class supercomputers highlighted by the latest High Performance Conjugate Gradients (HPCG) benchmark results will, I believe, influence the next generation of supercomputer architectures to optimize for sparse matrix computations. The upcoming technology that will help address this problem is CXL. Next generation architectures will use CXL3.0 switches to connect processing nodes, pooled memory and I/O resources into very large, coherent fabrics within a rack, and use Ethernet between racks. I call this a “Petalith” architecture (explanation below), and I think CXL will play a significant and growing [READ MORE…]