The Sixth Workshop on the LLVM Compiler Infrastructure in HPC (original) (raw)

Agenda

Time (EST) Speaker Title
10:00 Hal Finkel Welcome
10:05 Mehdi Amini Keynote: MLIR: an Agile Infrastructure for Building a Compiler Ecosystem [Slides][Video]
11:15 Coffee Break
11:30 Rahim Mammadli Static Neural Compiler Optimization via Deep Reinforcement Learning [Slides][Video]
12:10 Michael Kruse Autotuning Search Space for Loop Transformations [Slides][Video]
12:50 Dibyendu Das Deep Learning-based Approximate Graph-Coloring Algorithm for Register Allocation [Slides][Video]
1:30 Lunch Break
2:30 Alok Mishra Extending the LLVM/Clang Framework for OpenMP Metadirective Support [Slides][Video]
3:10 Andrew Lamzed-Short Towards Automated Kernel Fusion for the Optimisation of Scientific Applications [Slides]
3:50 Alexis Engelke Robust Practical Binary Optimization at Run-time using LLVM [Slides][Video]
4:30 Coffee Break
4:45 Hal Finkel Really Embedding Domain-Specific Languages into C++ [Video]
5:25 All Presenters Panel Discussion
6:25 Final Discussion
6:30 The End

Abstract

LLVM, winner of the 2012 ACM Software System Award, 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.

In cooperation with:

Held in conjunction with SC20: The International Conference for High Performance Computing, Networking, Storage, and Analysis

Format

This workshop will feature contributed papers and invited talks focusing on recent developments, from both academia and industry, that build on LLVM to advance the state of the art in high-performance computing.

Topics of interest include, but are not limited to:

The workshop will hold a lightning-talk session. Please contribute to making this session both vibrant and informative! An abstract and one-page summary are required for consideration.

Deadlines

Please see the SC20 home page for registration deadlines and other information associated with the parent event. See also the SC20 Program Entry.

Submissions

Please submit papers using the SC20 Submissions system by selecting the "SC20 Workshop: LLVM-HPC2020 Full Papers" form. Papers must be in IEEE conference format (templates are available). Papers should be no more than 12 pages (including references and figures) and must be at least eight pages long. Please also note IEEE's Article-Posting Policy.

To submit a lightning talk, please use the "SC20 Workshop: LLVM-HPC2020 Lightning Talks" form.

Organizers

Program Committee

Name Affiliation
Richard Barton ARM
Sunita Chandrasekaran University of Delaware
Camille Coti University of Paris XIII / University of Oregon
Christian Delozier U.S. Naval Academy
Tobias Grosser ETH Zürich
Jeff Hammond Intel
Torsten Hoefler ETH Zürich
Teresa Johnson Google
Alice Koniges University of Hawaii
Cameron McInally Hewlett Packard Enterprise
Pat McCormick Los Alamos National Laboratory
EJ Park Los Alamos National Laboratory
Nadav Rotem Facebook
Frank Winter Thomas Jefferson National Accelerator Facility
Michael Wong Codeplay

Contact Information

Alexis Perry-Holby (aperry@lanl.gov)