Date/Time
Date(s) - 05/27/2026
12:00 PM - 1:00 PM
Add to Google Calendar or iCal/Outlook Calendar
Speaker
Murali Emani is a computer scientist at Argonne Leadership Computing Facility (ALCF) at Argonne National Laboratory.
Abstract
Scientific applications are increasingly adopting Artificial Intelligence (AI) techniques to advance science. There exist specialized hardware accelerators designed to run AI applications efficiently. With a wide diversity in the hardware architectures and software stacks of these systems, it is challenging to understand the differences between these accelerators, their capabilities, programming approaches, and how they perform, particularly for scientific applications. In this tutorial, we will cover an overview of the AI accelerators deployed at ALCF: SambaNova, Cerebras, Groq, and Tenstorrent systems, along with the architectural features and details of their software stacks. Through hands-on exercises, attendees will gain practical experience in refactoring code and running models on these systems, focusing on use cases of pre-training and fine-tuning open-source Large Language Models (LLMs) and deploying AI inference solutions relevant to scientific contexts. Additionally, the sessions will cover the low-level HPC software stack of these accelerators using simple HPC kernels. The tutorial will provide the attendees with an understanding of the key capabilities of emerging AI accelerators and their performance implications for scientific applications.
Biography
Murali Emani is a computer scientist at Argonne Leadership Computing Facility (ALCF) at Argonne National Laboratory. He co-leads the ALCF AI Testbed effort to help evaluate the performance of novel AI accelerators and port scientific machine learning applications. He is also the co-founder of the MLPerf HPC working group. His research interests are scalable machine learning, emerging HPC/AI architectures, parallel programming models, and performance optimization. Previously, he was a postdoctoral research staff member at Lawrence Livermore National Laboratory. He obtained his PhD from the Institute for Computing Systems Architecture at the School of Informatics, University of Edinburgh. Murali has published in top conferences, including PACT, PLDI, CGO, and SC, and has three granted patents. He was involved with the publication on GenSLM that won the ACM Gordon Bell Prize for High Performance Computing at SC22. Murali was also a co-chair of MLPerf HPC group with MLCommons.
