Since 1987 - Covering the Fastest Computers in the World and the People Who Run Them
Since 1987 - Covering the Fastest Computers in the World and the People Who Run Them
ISC 2022 Program Chair Keren Bergman is the Charles Batchelor Professor at Columbia University where she also directs the Lightwave Research Laboratory. Our exclusive interview with Bergman covers her history with ISC with a focus on the event’s return to Hamburg, Germany, May 29-June 2, as well as her insights into the HPC landscape.
Congratulations on being the 2022 HPCwire Person to Watch as well as ISC 2022 Program Chair! It’s a big year for ISC, with the conference returning to an in-person event after two years of having a digital format. Could you tell us a bit about your history with the conference, and how you see its trajectory as we (hopefully) move toward a post-pandemic world?
Thank you, I am deeply honored! It is indeed a big year – ISC 2022 will be a tremendous opportunity for our HPC community to come together. We have learned over the past two years that technical progress certainly continues, but there is no substitute for in-person interactions. We all sorely miss seeing our friends and colleagues, exchanging new ideas, experiencing HPC advances first hand at the exhibition, connecting over shared meals, and engaging in the numerous networking opportunities.
My personal history with HPC began 25 years ago (hard to believe it’s been that long!) when I was fortunate to become part of a ‘moon shot’ project called HTMT to develop a Petaflops computer with a hybrid technology approach. Led by Thomas Sterling the project involved many HPC luminaries – Peter Kogge, Burton Smith, Larry Bergman, Paul Messina, Guang Gao, and Rick Stevens – making what was at the time a quantum leap in scalable architectures and taking a big bet on emerging ideas including – processing-in-memory, multi-threading, superconducting processors, and optical networking (my part). This is how I got ‘bit’ by the HPC bug. My research has been at the intersection of optics and computing ever since and I’ve been attending HPC conferences including SC and ISC since the early 2000s. Of course, ISC is the oldest and largest international conference on HPC in Europe.
ISC 2022 will be a hybrid conference – primarily in-person, but with digital content. Going forward, I am optimistic about our post-pandemic trajectory. From our two years of all-digital experience, we have learned quite a bit about what works (and what doesn’t), especially the services that most benefit and broaden our HPC community. ISC will continue to produce and develop digital content, in synergy with the in-person experience creating what I believe will be an even more successful conference series in the future.
What are you most looking forward to for ISC 2022? Is there anything new or extra-noteworthy you’d like to highlight in this year’s program? The conference is back in Hamburg after 10 years (last there in 2012). Could you share some of the highlights or special things about this venue and/or city?
We are now truly in the Exascale Era and ISC 2022 will feature some of the most exciting advances driving innovative system architectures, algorithms, programming, and applications. As we aim to define the ‘Road to Zetascale’ the invited program is designed to cover the most pressing challenges in machine learning and data analytics, as well as look into the future and emerging uses of quantum computing. ISC 2022 will be an opportunity for us to fully connect across our global community, as well as to recognize and celebrate numerous advances.
I am especially looking forward to our return to Hamburg. Being from New York City I love Hamburg’s big city vibe, walkable downtown, amazing architecture, and waterfront cafes. Of course, there is the not to be missed Planten und Blomen park – and weather wise our conference timing in late spring is hopefully ideal.
Can you give us a peek into your role as director of the Lightwave Research Laboratory? What is the focus of your work? What problems of silicon photonics do you work on? Would you briefly detail your some of your sponsored research projects? What advances and or breakthroughs in silicon advances should people know about?
My lab explores data movement in the optical domain for scaling computing performance and reducing energy consumption. We are developing a new class of silicon photonic interconnects integrated directly on-chip that are capable of “feeding” and “extracting” ultra-high communications bandwidths from the heterogeneous computing socket to anywhere in the system with extreme energy efficiencies. Our work makes use of 300mm wafer-scale silicon foundry fabrication. This is especially exciting because the research advances can be directly transitioned to commercial applications. Our photonic links build on novel integrated optical ‘comb’ lasers that can produce hundreds of unique wavelength channels with precise, intrinsic spacing. The data is encoded optically on each of the wavelengths to realize petabit-per-second “chip escape” communications while minimizing energy consumption to sub-pico-Joule/bit.
At the system level our work examines new architectural paradigms that can take advantage of photonic communications. With the explosive growth of data analytics applications, HPC system performance is particularly tied to data movement and its associated energy consumption. Our research is focused on disaggregated architecture where the photonic fabric offers a ‘no hop’ flexible high-bandwidth connectivity among compute and memory resources. The adaptable photonic interconnect fabric opens new possibilities in systems designs to meet diverse applications requirements. I am grateful to the funding agencies supporting this research that include multiple programs under ARPA-E, DARPA, DOE, and DOD. We work closely with and get supported by several industry partners.
Where do you see HPC headed? What trends – and in particular emerging trends – are you particularly excited or concerned about?
In the HPC community we are always driving toward the very top performance (by definition!). Not surprisingly we are the first to encounter the most critical challenges. This happened with energy consumption – 2022 is already the 10th anniversary of the ‘Green 500’ – while other computing platforms are just catching up. This trend is strongly accelerated by the growth in AI/ML applications, heterogeneous computing and the convergence of HPC and Data Centers. I am seeing a major shift toward embracing new technologies that help drive performance forward while reducing energy consumption. In my own area of photonics, commercial enterprises are beginning to include photonic interconnect technologies on their roadmaps. I cannot think of anything more exciting than to see research transform future systems.
Outside of the professional sphere, what can you tell us about yourself – family stories, unique hobbies, favorite places, etc.? Is there anything about you your colleagues might be surprised to learn?
I love sports of all kinds. In my youth I played soccer, but with injured knees I stick to running, biking, tennis, and skiing. I was born in Israel, and my first name ‘Keren’ is Hebrew for ‘a ray of light’ – so I like to think that my parents sort of foreshadowed my career.
Bergman is one of 12 HPCwire People to Watch for 2022. You can read the interviews with the other honorees at this link.
Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!
HPCwire is pleased to present our interview with SC22 General Chair Candace Culhane, program/project director at Los Alamos National Lab and an HPCwire 2022 Person to Watch. In this exclusive Q&A, Culhane covers her Read more…
The lack of large-scale energy storage bottlenecks many sources of renewable energy, such as sunlight-reliant solar power and unpredictable wind power. Researchers from Lawrence Livermore National Laboratory (LLNL) are w Read more…
A supermassive black hole called Sagittarius A* (yes, the asterisk is part of it!) sits at the center of the Milky Way. Now, for the first time, we can see it. The resulting direct image of Sagittarius A*, revealed this Read more…
Quantum computers are coming down the pike, and hardware makers warned of a potential security crisis looming with such superfast systems able to break encryption within a matter of seconds. To counter that, companies Read more…
Intel has shared more details on a new interconnect that is the foundation of the company’s long-term plan for x86, Arm and RISC-V architectures to co-exist in a single chip package. The semiconductor company is taking a modular approach to chip design with the option for customers to cram computing blocks such as CPUs, GPUs and AI accelerators inside a single chip package. Read more…
This post was contributed by Pankaj Vats, PhD, and Timothy Harkins, PhD, from NVIDIA Parabricks.
Advances in Next Generation Sequencing (NGS) technologies over the last decade have led to many novel discoveries in cancer genomics1,2,3. Read more…
Intel is extending its roadmap for infrastructure processors through 2026, the company said at its Vision conference being held in Grapevine, Texas. The company's IPUs (infrastructure processing units) are megachips that are designed to improve datacenter efficiency by offloading functions such as networking control, storage management and security that were traditionally... Read more…
HPCwire is pleased to present our interview with SC22 General Chair Candace Culhane, program/project director at Los Alamos National Lab and an HPCwire 2022 Per Read more…
A supermassive black hole called Sagittarius A* (yes, the asterisk is part of it!) sits at the center of the Milky Way. Now, for the first time, we can see it. Read more…
Intel has shared more details on a new interconnect that is the foundation of the company’s long-term plan for x86, Arm and RISC-V architectures to co-exist in a single chip package. The semiconductor company is taking a modular approach to chip design with the option for customers to cram computing blocks such as CPUs, GPUs and AI accelerators inside a single chip package. Read more…
Intel is extending its roadmap for infrastructure processors through 2026, the company said at its Vision conference being held in Grapevine, Texas. The company's IPUs (infrastructure processing units) are megachips that are designed to improve datacenter efficiency by offloading functions such as networking control, storage management and security that were traditionally... Read more…
Installation has begun on the Aurora supercomputer, Rick Stevens (associate director of Argonne National Laboratory) revealed today during the Intel Vision event keynote taking place in Dallas, Texas, and online. Joining Intel exec Raja Koduri on stage, Stevens confirmed that the Aurora build is underway – a major development for a system that is projected to deliver more... Read more…
At the hybrid Intel Vision event today, Intel’s Habana Labs team launched two major new products: Gaudi2, the second generation of the Gaudi deep learning training processor; and Greco, the successor to the Goya deep learning inference processor. Intel says that the processors offer significant speedups relative to their predecessors and the... Read more…
IBM today issued an extensive and detailed expansion of its Quantum Roadmap that calls for developing a new 1386-qubit processor – Kookaburra – built from modularly scaled chips, and delivering a 4,158-qubit POC system built using three connected Kookaburra processors by 2025. Kookaburra (Australian Kingfisher) is a new architecture... Read more…
President Joe Biden today issued an Executive Order and a National Security Memorandum boosting the national focus on quantum information sciences (QIS), including quantum computing and cybersecurity concerns. There is currently a global race heating up to leverage QIS for economic and security purposes. The U.S., China, Europe, Japan, the U.K., and many others have mounted well-funded, expanding efforts... Read more…
Getting a glimpse into Nvidia’s R&D has become a regular feature of the spring GTC conference with Bill Dally, chief scientist and senior vice president of research, providing an overview of Nvidia’s R&D organization and a few details on current priorities. This year, Dally focused mostly on AI tools that Nvidia is both developing and using in-house to improve... Read more…
Intel has shared more details on a new interconnect that is the foundation of the company’s long-term plan for x86, Arm and RISC-V architectures to co-exist in a single chip package. The semiconductor company is taking a modular approach to chip design with the option for customers to cram computing blocks such as CPUs, GPUs and AI accelerators inside a single chip package. Read more…
Fresh off its rebrand last October, Meta (née Facebook) is putting muscle behind its vision of a metaversal future with a massive new AI supercomputer called the AI Research SuperCluster (RSC). Meta says that RSC will be used to help build new AI models, develop augmented reality tools, seamlessly analyze multimedia data and more. The supercomputer’s... Read more…
AMD/Xilinx has released an improved version of its VCK5000 AI inferencing card along with a series of competitive benchmarks aimed directly at Nvidia’s GPU line. AMD says the new VCK5000 has 3x better performance than earlier versions and delivers 2x TCO over Nvidia T4. AMD also showed favorable benchmarks against several Nvidia GPUs, claiming its VCK5000 achieved... Read more…
IBM today announced it will deploy its first quantum computer in Canada, putting Canada on a short list of countries that will have access to an IBM Quantum Sys Read more…
Just about a month ago, Pfizer scored its second huge win of the pandemic when the U.S. Food and Drug Administration issued another emergency use authorization Read more…
The battle for datacenter dominance keeps getting hotter. Today, Nvidia kicked off its spring GTC event with new silicon, new software and a new supercomputer. Speaking from a virtual environment in the Nvidia Omniverse 3D collaboration and simulation platform, CEO Jensen Huang introduced the new Hopper GPU architecture and the H100 GPU... Read more…
PsiQuantum, founded in 2016 by four researchers with roots at Bristol University, Stanford University, and York University, is one of a few quantum computing startups that’s kept a moderately low PR profile. (That’s if you disregard the roughly $700 million in funding it has attracted.) The main reason is PsiQuantum has eschewed the clamorous public chase for... Read more…
GPU-maker Nvidia is continuing to try to keep its proposed acquisition of British chip IP vendor Arm Ltd. alive, despite continuing concerns from several governments around the world. In its latest action, Nvidia filed a 29-page response to the U.K. government to point out a list of potential benefits of the proposed $40 billion deal. Read more…
MLCommons today released its latest MLPerf inferencing results, with another strong showing by Nvidia accelerators inside a diverse array of systems. Roughly fo Read more…
Quantum computing pioneer D-Wave today announced plans to go public via a SPAC (special purpose acquisition company) mechanism. D-Wave will merge with DPCM Capital in a transaction expected to produce $340 million in cash and result in a roughly $1.6 billion initial market valuation. The deal is expected to be completed in the second quarter of 2022 and the new company will be traded on the New York Stock... Read more…
Intel held its 2022 investor meeting yesterday, covering everything from the imminent Sapphire Rapids CPUs to the hotly anticipated (and delayed) Ponte Vecchio GPUs. But somewhat buried in its summary of the meeting was a new namedrop: “Falcon Shores,” described as “a new architecture that will bring x86 and Xe GPU together into a single socket.” The reveal was... Read more…
A new industry consortium aims to establish a die-to-die interconnect standard – Universal Chiplet Interconnect Express (UCIe) – in support of an open chipl Read more…
The rapid adoption of Julia, the open source, high level programing language with roots at MIT, shows no sign of slowing according to data from Julialang.org. I Read more…
Nvidia has announced that it has acquired Excelero. The high-performance block storage provider, founded in 2014, will have its technology integrated into Nvidia’s enterprise software stack. Nvidia is not disclosing the value of the deal. Excelero’s core product, Excelero NVMesh, offers software-defined block storage via networked NVMe SSDs. NVMesh operates through... Read more…
Google CEO Sundar Pichai spoke for only one minute and 42 seconds about the company’s latest TPU v4 Tensor Processing Units during his keynote at the Google I Read more…
© 2022 HPCwire. All Rights Reserved. A Tabor Communications Publication
HPCwire is a registered trademark of Tabor Communications, Inc. Use of this site is governed by our Terms of Use and Privacy Policy.
Reproduction in whole or in part in any form or medium without express written permission of Tabor Communications, Inc. is prohibited.