Program for Workshops and Tutorials is available here. Please visit the respective webpage of a workshop/tutorial for its detailed schedule.
Abstract
Sustainability is the most important problem. But it won't happen without Steps 1, 2, and 3. I will identify them and explain why.
Speaker
Yale's short bio:
Yale Patt is a teacher at The University of Texas at Austin and the
Virginia Cockrell Centennial Endowed Chair in the Cockrell School of
Engineering. He enjoys teaching the required freshman Intro to Computing
course, using his motivated bottom-up approach every other Fall semester.
His research in aggressive branch prediction and out-of-order execution has
changed the basic structure of microprocessors. He earned obligatory degrees
from reputable universities a long time ago. More information is available
on his website for those who want it.
For Symposium and Workshops & Tutorials Participants.
Moderator:
Dejan S. Milojicic (HPE)
Panelists:
Wen-Mei Hwu (NVIDIA),
Norm Jouppi (Google),
Hironori Kasahara (Waseda University),
Yale Patt (University of Texas at Austin),
Guri Sohi (University of Wisconsin-Madison),
and Carole-Jean Wu (Meta)
Dejan S. Milojicic is an HPE Fellow and VP at Hewlett Packard Labs, Milpitas, CA [1998-present]. Previously, he worked at the OSF Research Institute, Cambridge, MA [1994-1998] and Institute "Mihajlo Pupin", Belgrade, Serbia [1983-1991]. He received his Ph.D. from the University of Kaiserslautern, Germany (1993); and his MSc/BSc from Belgrade University, Serbia (1983/86). Dejan has over 280 papers, 2 books, and 96 granted and 67 pending patents. Dejan is an IEEE Fellow (2010), ACM Distinguished Engineer (2008), and HKN and USENIX member. Dejan was on 10 Ph.D. thesis committees, and he mentored over 80 interns. Dejan was president of the IEEE Computer Society (2014), editor-in-chief of IEEE Computing Now and Distributed Systems Online and he has served on many editorial boards and TPCs.
Wen-Mei W. Hwu is a Senior Distinguished Research Scientist and Senior Director of Research at NVIDIA. He is also a Professor Emeritus at the University of Illinois at Urbana-Champaign after 34 years of service. His research is in parallel architecture, algorithms, and infrastructure software for data intensive and computational intelligence applications. He received the ACM/IEEE Eckert-Mauchly Award, ACM SigArch Maurice Wilkes Award, the ACM Grace Murray Hopper Award, the IEEE Computer Society Charles Babbage Award, the ISCA Influential Paper Award, the MICRO Test-of-Time Award, the IEEE Computer Society B. R. Rau Award, and the CGO Test-of-Time Award. He is a Fellow of IEEE and ACM.
Norm P. Jouppi is a Google Fellow. Norm received his Ph.D. in electrical engineering from Stanford University in 1984. While at Stanford he was one of the principal architects and designers of the MIPS microprocessor. Before joining Google in 2013 Norm was known for his innovations in computer memory systems and was the principal architect and lead designer of several microprocessors. He has been the tech lead for Google's Tensor Processing Units (TPUs) since their inception in 2013. He is a Fellow of the ACM, IEEE, and AAAS, and a member of the National Academy of Engineering. He has received multiple awards, including the ACM/IEEE Eckert-Mauchly Award and Seymour Cray Computer Engineering Award.
Hironori Kasahara is a professor in the CSE department, a director at Advanced Multicore Research Institute, an ex-SEVP at Waseda University, an IEEE Life Fellow, a member of the Engineering Academy of Japan and the Science Council of Japan, and a chair of JST "SPRING" Ph.D. fostering program and IEEE Fran Allen Medal. He was the 2018 IEEE Computer Society President. His research interests include co-designing architecture and compilers, parallelizing-optimizing data locality, and power-reducing compilers for HPC to real-time embedded systems. He participated in developing three Top 1 Supercomputers, NWT based on his OSCAR architecture, Earth Simulator, and K.
Yale Patt is a teacher at The University of Texas at Austin and the Virginia Cockrell Centennial Endowed Chair in the Cockrell School of Engineering. He enjoys teaching the required freshman Intro to Computing course, using his motivated bottom-up approach every other Fall semester. His research in aggressive branch prediction and out-of-order execution has changed the basic structure of microprocessors. He earned obligatory degrees from reputable universities a long time ago. More information is available on his website for those who want it.
Guri Sohi has been at the University of Wisconsin-Madison since 1985 where he currently is a Vilas Research Professor. Over the past four decades he has worked on the design of high-performance processors and computer systems and results from his research can be found in almost every high-end microprocessor in the market today. He has worked with an outstanding group of graduate students who have gone on to make their own impact in the field of computer architecture. His work has received a variety of recognitions within the university, nationally, as well as internationally.
Carole-Jean Wu is a Director of AI Research at Meta, leading the Systems and Machine Learning Research team. She is a founding member and a Vice President of MLCommons ? a non-profit organization that aims to accelerate machine learning innovations for everyone. Dr. Wu's expertise sits at the intersection of computer architecture and machine learning with a focus on performance, energy efficiency and sustainability. She is passionate about pathfinding and tackling system challenges to enable efficient, scalable, and environmentally-sustainable AI technologies. Her work has been recognized with several IEEE Micro Top Picks and ACM/IEEE Best Paper Awards. She is in the Hall of Fame of ISCA, HPCA, IISWC, and serves on the study committee of the National Academies. She earned her M.A. and Ph.D. from Princeton University and B.Sc. from Cornell University.
For Symposium and Workshops & Tutorials Participants.
participants with “Workshops & Tutorials Ofnly Registration” needs an extra reception ticket for each to attend the reception.
Abstract
The idealisms of Seymour Cray have long served as our guiding principles. His famous analogy questioning the use of "two strong oxen or 1024 chickens" perfectly encapsulated an era of architectural divergence, where powerful vector systems for HPC stood in stark contrast to the nascent, massively parallel machines for symbolic AI. For decades, these two worlds – numerical simulation and symbolic inference – traveled along separate roads.Today, however, that schism has seemingly vanished with the tectonic shift to modern deep neural networks and the universal adoption of massively parallel processing. We now know the answer to Cray's question is "both," as modern systems like Fugaku and El Capitan leverage the synergy of powerful cores and vast parallelism to achieve astounding performance. Still, a new fear has emerged: that the commercial tsunami of AI will create a new divergence, optimizing architectures for the enterprise while leaving scientific computing behind. This talk will argue this is a myth, and that a deeper convergence is not only possible but essential.
By embracing an "applications-first" co-design philosophy, we can harness AI-centric hardware for traditional science. We will explore cutting-edge techniques like the Ozaki Scheme, which emulates high-precision numerics on low-precision tensor cores, and discuss the critical importance of system-level resilience and interconnects – honoring Cray's wisdom that "anyone can build a fast CPU. The trick is to build a fast system.Looking forward, however, we may even embrace a future of managed, radical divergence through purpose-built heterogeneous architectures. The programmability challenge this presents seems insurmountable, yet the solution may come from AI itself, with intelligent compilers translating standard programs for these novel systems on the fly. This frees architects to explore truly innovative designs, ensuring the future is a bright, symbiotic partnership between HPC and AI that continues the legacy of daring innovation left to us by Seymour Cray.
Satoshi Matsuoka's short bio: Satoshi Matsuoka has been the director of RIKEN Center for Computational Science (R-CCS) since 2018. He is responsible for developing the supercomputer Fugaku which has become the fastest supercomputer in the world in all four major supercomputer rankings in 2020 and 2021 (Top500, HPCG, HPL-AI, Graph500), along with multitudes of ongoing cutting edge HPC research being conducted, including investigating Post-Moore era computing, especially the future Fugaku NEXT supercomputer. He was the leader of the TSUBAME series of supercomputers that had also received many international acclaims, at the Institute of Science Tokyo (formerly known as the Tokyo Institute of Technology), where he still holds a professor position, to continue his research activities in HPC as well as scalable Big Data and AI. Other accolades include the Fellow positions in societies/conferences ACM, ISC, JSSST (Japan Society for Software Science and Technology) and IPSJ (Information Processing Society of Japan); the ACM Gordon Bell Prizes in 2011 & 2021; the IEEE-CS Sidney Fernbach Award in 2014 as well as the IEEE-CS Computer Society Seymour Cray Computer Engineering Award in 2022, both being the highest awards in the field of HPC, and the only individual to receive both awards; one of the HPCwire 35 Legends by the HPC wire in 2024; the Technical Papers Chair and the Program Chair for ACM/IEEE Supercomputing 2009 and 2013 (SC09 and SC13) respectively as well as many other conference chairs, and the ACM Gordon Bell Prize selection committee chair in 2018. His longtime contribution for the computer science research was commended with the Medal of Honor with Purple ribbon by his Majesty Emperor of Japan in 2022.
Abstract
Great innovation thrives on unexpected connections. This talk shares the journey of a unique partnership between Ethiopian and US researchers, which advanced hardware security through novel privacy-enhanced microarchitectures. By crossing geographic, disciplinary, and cultural boundaries, our team was challenged to step out of its comfort zone, sparking fresh creativity and expanding the scope of innovative solutions in data privacy. Join us to discover how embracing unfamiliar perspectives can propel advances in zero-trust systems and help shape the future of architectural innovation.
Speaker
Fitsum's short bio:
Fitsum Assamnew Andargie is an Assistant Professor and current Chair of Computer Engineering at the School of Electrical and Computer Engineering, Addis Ababa University. He also serves as an Adjunct Assistant Research Scientist in the Computer Science and Engineering Department at the University of Michigan. His research interests focus on accelerating graph applications using software and hardware co-design, and developing privacy-enhanced hardware computational infrastructures, particularly supporting artificial intelligence applications in healthcare. Born in Addis Ababa and raised in Jimma, Ethiopia, he completed his Bachelor's and Master's degrees in Electrical and Computer Engineering at Addis Ababa University. He earned his doctorate in Computer Engineering from Addis Ababa University, collaborating closely with the University of Toronto and the University of Michigan.
Todd's short bio: Todd Austin is the S. Jack Hu Collegiate Professor of Electrical Engineering and Computer Science at the University of Michigan and Director of the Computer Engineering Lab. His research spans computer architecture, secure system design, verification, and performance analysis. Previously, he directed C-FAR, a multi-university SRC/DARPA-funded computer engineering research center. Before academia, he was a Senior Computer Architect at Intel. He created the SimpleScalar Tool Set and co-authored Structured Computer Architecture, 6th Ed. He also co-founded Agita Labs and InTempo Design. He is an IEEE Fellow, and he has received the ACM Maurice Wilkes and IEEE Ramakrishna Rau awards. He earned his PhD from the University of Wisconsin.