Fwd: Towards GPU-accelerated automated reasoning- RuleML webinar (this Friday)

Imagine systems powered by reasoning capability much faster and much greater
than humans can ever be able to verify/process
 webinar below not for the faint hearted

---------- Forwarded message ---------
From: Tomáš Kliegr <tomas.kliegr@vse.cz>
Date: Tue, Nov 12, 2024 at 12:14 PM
Subject: Towards GPU-accelerated automated reasoning- RuleML webinar (this
Friday)
To: semantic-web@w3c.org <semantic-web@w3c.org>


This is a talk/webinar announcement. The upcoming RuleML webinar will host
a speaker on an ILP topic which might be of interest to some on the
ilp-news mailing list.

Title: "Towards GPU-accelerated automated reasoning"

Date and time: November 15  (Friday), starting at 10 am CET

Speaker: Martin Berger <https://martinfriedrichberger.net/> (University of
Sussex, UK & Montanarius Ltd).

Abstract: Graphics Processing Units (GPUs) are the work-horses of
high-performance computing. The acceleration they provide to applications
compatible with their programming paradigm can surpass CPU performance by
several orders of magnitude, as notably evidenced by the advancements in
deep learning. A significant spectrum of applications, especially within
automated reasoning—like SAT/SMT solvers—has yet to reap the benefits of
GPU acceleration.  In this talk, we discuss recent work that successfully
implemented program synthesis on GPUs and used it to accelerate learning of
logical specifications from examples.  We conclude by mapping out a
research programme to move more formal verification workloads to GPUs.

Speaker's bio: Martin Berger did his PhD in formal models for distributed
systems at Imperial College. He's currently an associate professor in the
Department of Informatics at the University of Sussex.  He's also working
as a verification consultant for the microprocessor industry and is one of
the maintainers of the official RISC-V instruction set architecture (
https://github.com/riscv/sail-riscv).  His research interests include logic
and verification, typing systems, process calculus, meta-programming, and
JIT compilers.

Webinar connection information: ZOOM
https://bit.ly/kegseminar20241115

The talk is hybrid. It will also be given in person as part of the Knowledge
Engineering Group <https://kizi.vse.cz/english/seminars-keg/> seminar at
VSE Prague.

-----------------
Tomas Kliegr
Organizer of the RuleML webinar
<https://github.com/RuleML/ruleml-website/blob/master/talks/README.md>