The Ninth Annual Workshop on the LLVM Compiler Infrastructure in HPC

Workshop held in conjunction with SC23 - Sunday, November 12, 2023 - Denver, Colorado, USA

SC23Logo Held in conjunction with SC23: The International Conference for High
Performance Computing, Networking, Storage, and Analysis, and in
cooperation with the IEEE Computer Society (IEEE CS) and the Association for Computing Machinery (ACM).

/IEEELogo ACMLogo



Agenda

Time (MST) Speaker Title
9:00 James Brodman and Ryan Kabrick Welcome
9:01 Shilei Tian OpenMP Kernel Language Extensions for Performance Portable GPU Codes
9:31 Sergio Iserte DPU Offloading Programming with the OpenMP API
10:00 Coffee Break
10:30 Nick Brown Fortran performance optimisation and auto-parallelisation by leveraging MLIR-based domain specific abstractions in Flang
11:00 Anton Rydahl Precision and Performance Analysis of C Standard Math Library Functions on GPUs
11:30 Marcin Copik Lightning Talk - Cppless: Productive and Performant Serverless Programming in C++
11:37 Alister Johnson Lightning Talk - Automating Loop Optimization with Code Samples and AST Matching
11:44 Camille Coti Lightning Talk - Just-in-Time Autotuning
11:51 Christopher Taylor Lightning Talk - META: A Toolkit for Template Metaprogramming Performance Analysis
11:58 James Brodman, Sergio Iserte, Nick Brown, Anton Rydahl Panel Discussion
12:28 James Brodman and Ryan Kabrick Closing Remarks
12:30 The End

Overview

LLVM has become an integral part of the software-development ecosystem for optimizing compilers, dynamic-language execution engines, source-code analysis and transformation tools, debuggers and linkers, and a whole host of programming-language and toolchain-related components. Now heavily used in both academia and industry, where it allows for rapid development of production-quality tools, LLVM is increasingly used in work targeted at high-performance computing. Research in, and implementation of, program analysis, compilation, execution, and profiling has clearly benefited from the availability of a high-quality, freely-available infrastructure on which to build. This workshop will focus on recent developments, from both academia and industry, that build on LLVM to advance the state of the art in high-performance computing.

Format

This workshop will feature contributed papers and an invited talk focusing on recent developments that build on LLVM to advance the state of the art in high-performance computing.

Topics of interest include, but are not limited to:

Please note: All particpants (authors, presenters, committee members, and attendees alike) are expected to follow both the LLVM Code of Conduct as well as the relevant SC23 conduct policies.

Deadlines

Please see the SC23 home page for registration deadlines and other information associated with the parent event. Pending the acceptance of the final workshop proceedings, the selected papers will be published by IEEE Xplore.

Submissions

Please submit papers using the SC23 Submissions system by selecting the "SC23 Workshop: LLVM-HPC2023 Full Papers" form. Papers must use the new proceedings templates and the CCS2012 guide (available here), should be no more than 12 pages (including references and figures), and must be at least 6 pages long.

Organizers

Program Committee

Contact Information

Alexis Perry-Holby (aperry@lanl.gov)

Ryan Kabrick (rkabrick@tactcomplabs.com)

James Brodman (james.brodman@intel.com)

Pat McCormick (pat@lanl.gov)