The Fourth Workshop on the LLVM Compiler Infrastructure in HPC

Workshop held in conjunction with SC17 - Monday, November 13, 2017 - Denver, Colorado, USA


Time Speaker Title
9:00 Hal Finkel Welcome
9:15 Vikram Adve Keynote: Heterogeneous Parallel Virtual Machine and Parallelism in LLVM
10:00 Coffee Break
10:30 Paul Osmialowski How The Flang FrontendWorks - Introduction to the interior of the Open-Source Fortran frontend for LLVM
11:00 Lingda Li Benchmarking and Evaluating Unified Memory for OpenMP GPU Offloading
11:30 Michael Haidl PACXXv2 + RV -- An LLVM-based Portable High-Performance Programming Model
12:00 George Stelle OpenMPIR
12:30 N/A Lunch
2:00 Ronny Tschueter An LLVM Instrumentation Plug-in for Score-P
2:30 Diptorup Deb QUARC: An Optimized DSL Framework using LLVM
3:00 Coffee Break
3:30 Gheorghe-Teodor Bercea Implementing Implicit OpenMP Data Sharing on GPUs
4:00 Toshio Endo Applying Temporal Blocking with a Directive-based Approach
4:30 Xinmin Tian LLVM Compiler Implementation for Explicit Parallelization and SIMD Vectorization
Lightning Talks:
5:00 Sunita Chandrasekaran OpenMP 4.5 Validation and Verification Suite
5:07 Hashim Sharif Developing an OpenMP Runtime for UVM-Capable GPUs
5:14 Tobias Grosser Improved Loop Distribution in LLVM using Polyhedral Dependences
5:21 Keyur Joshi Implementation of a Cache Miss Calculator in LLVM/Polly
5:30 The End


Join us at the LLVM in HPC BoF: Tuesday, Nov. 14th, 12:15-1:15pm, in room 601.

Flang Meetup!

Join us at the Flang Meetup: Wednesday, Nov. 15th, 6:30-7:30pm at the Curtis Hotel in the Hopscotch room (3rd floor). 1405 Curtis, St.


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 SC17: The International Conference for High Performance Computing, Networking, Storage and Analysis


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:

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


Please see the SC17 home page for registration deadlines and other information associated with the parent event.


We are using EasyChair to manage submissions. Please submit papers to llvmhpc2017. The ACM SIG Proceedings Templates should be used. Papers should be no more than 12 pages (including references and figures). Please also note the ACM Author Rights policy.


The proceedings will be archived in both the ACM Digital Library and IEEE Xplore through SIGHPC. Lightning-talk summaries will not be included in the proceedings.


Program Committee

Name Affiliation
Andrew TrickApple
Cameron McInallyCray
Chandler CarruthGoogle
Erik SchnetterPerimeter Institute for Theoretical Physics
Frank WinterThomas Jefferson National Accelerator Facility
Gary FunckIntrepid Technology
James BrodmanIntel
Jeff HammondIntel
Jim CownieIntel
Keno FischerJulia Computing, Inc.
Michael WongCodeplay
Nadav RotemFacebook
Pat McCormickLos Alamos National Laboratory
Ralf KarrenbergNVIDIA
Sameer ShendeUniversity of Oregon
Tobias GrosserETH Zürich
Torsten HoeflerETH Zürich

Contact Information

Hal Finkel (