NHR PerfLab Seminar: Why matrix processing? (December 9, online)
Topic: Why matrix processing?
Speaker: Dr. José Moreira, IBM
Date and time: Tuesday, December 9, 2025, at 2:00 p.m. CET
Online via Zoom: https://go-nhr.de/perflab-seminar
Abstract:
It took vector processing approximately 30 years to move from the domain of supercomputers to mainstream computing. In comparison, matrix processing hit the ground running and has arguably been mainstream since inception. Today, matrix processing units are pervasive in modern CPUs and GPUs, as well as in special-purpose processors. In this talk, we will review the principles of matrix processing and discuss its inherent advantage over scalar and vector processing. We will also discuss different approaches to implementing matrix processing units at the instruction-set architecture and micro-architecture level, and the applications and relevance of matrix processing in both AI/ML and more traditional HPC applications. We will also go over some of the challenges and limitations of matrix processing and argue that modern processing elements must offer a balance of scalar, vector, and matrix processing.
Short bio:
José E. Moreira is a Distinguished Research Staff Member at the IBM Thomas J. Watson Research Center. He received a B.S. degree in physics and B.S. and M.S. degrees in electrical engineering from the University of Sao Paulo. He received a Ph.D. degree in electrical engineering from the University of Illinois at Urbana-Champaign. Since joining IBM in 1995, Dr. Moreira has worked on a variety of high-performance systems, including two ASCI systems (Blue Pacific and White) and the Blue Gene/L supercomputer, for which he was the System Software architect. Dr. Moreira has been responsible for various architectural and micro-architectural innovations in the three most recent generations of POWER processors. He conceived the POWER10 matrix unit, the first of its kind in a commercial processor. Dr. Moreira is a Fellow of the IEEE (Institute of Electrical and Electronics Engineers) and a Distinguished Scientist of the ACM (Association for Computing Machinery). He currently serves as Chair of the Vector Special Interest Group and Chair of the Integrated Matrix Extension Task Group of RISC-V International.
For a list of past and upcoming NHR PerfLab seminar events, please see: https://hpc.fau.de/research/nhr-perflab-seminar-series/