Remembering Kent Farrell Smith
Kent Farrell Smith, a Kahlert School of Computing emeritus faculty member and former department chair, passed away on September 12, 2025.
Born and raised on the shores of Bear Lake in Fish Haven, Idaho, Kent moved to Utah to study electrical engineering at Utah State University. He first came to the University of Utah as a PhD student with an interest in early computers. His interest in computer science provided the opportunity for involvement with early computer research, working towards the innovation of integrated circuit design. Following his PhD, Kent served as a professor and researcher at the University of Utah for both the computer science and electrical engineering departments.
Kent collaborated with innovators behind such landmarks as the first video game, Pong; the first artificial heart; the first artificial eye implant; military innovations such as the Gatling gun; and CMOS, still used today in a majority of electronics. Kent remained active in circuit design and defense contracts for the remainder of his life, while also remaining actively involved in his church and the lives of his children, grandchildren, and great-grandchildren.
His viewing will take place on Thursday, September 18, 2025, followed by a celebration of Kent’s life on Friday, September 19, 2025.
https://www.memorialutah.com/obituaries/kent-smith
Distinguished Colloquium - Daniel Kroening
Thursday, September 11, 2025
Kennecott Mechanical Engineering Building (MEK)
Room 3550
5:15pm - lecture
AI Accelerators 1010
Abstract
LLMs are arguably among the largest technology investments since the moon landing, and rely on custom hardware accelerators both for training and inference.
The talk will cover accelerating LLM transformer architectures using the combination of a compiler and a systolic compute array. The key enabler to achieving meaningful performance using the systolic compute array are deep program analyses of the model architecture in the Neuron Compiler. I will briefly report on our effort to build a verified (using Lean) compiler from XLA/HLO to the Trainium ISA.
BIO
Daniel Kroening is a Senior Principal Applied Scientist at Amazon, where he works on the correctness of the Neuron Compiler for distributed training and inference. Prior to joining Amazon, he worked as a Professor of Computer Science at the University of Oxford and is the co-founder of Diffblue Ltd., a University spinout that develops Al that targets code and code-like artefacts. He wrote the CBMC (for C), JBMC (for Java) and EBMC (for SystemVerilog) model checkers; CBMC is the engine of Kani (for verifying unsafe Rust).
He has received the Semiconductor Research Corporation (SRC) Inventor Recognition Award, an IBM Faculty Award, a Microsoft Research SEIF Award, the Wolfson Research Merit Award, and the Rance Cleaveland Test-of-Time tool award. He serves on the CAV steering committee and was co-chair of FLOC 2018, EiC of Springer FMSD, and is co-author of the textbooks on Decision Procedures and Model Checking.
