Due to COVID-19, the workshop will be organized as a virtual event using video conferencing, the videos of the presentations will be published on this page.

The LLVM framework is a vast ecosystem surrounding a compiler core which enabled various advances in source-code tools, debuggers, linkers, and a whole host of programming-language and toolchain-related components. Similar to the very successful LLVM-HPC workshop at SuperComputing (SC), we want to provide a forum for LLVM-related discussions and talks from academia and industry at ISC.

The workshop is held in conjunction with the ISC-HPC during the ISC workshop day.

This workshop is powered by LLVM.

The workshop is organized by

• Anja Gerbes (Center for Information Services and High Performance Computing, Technische Universität Dresden, Germany), anja.gerbes@tu-dresden.de
• Dr. Johannes Doerfert (Compiler Technology and Programming Languages, Argonne National Laboratory, USA), jdoerfert@anl.gov
• Dr. Sameer Shende (Performance Research Lab, University of Oregon, USA), sameer@cs.uoregon.edu
• Dr. Jeremy Bennett (Embecosm, United Kingdom), jeremy.bennett@embecosm.com

The YouTube playlist of the whole workshop is available soon.

• 14:00 - 14:30 CEST ¹⁾
  Demo of Multi-image Offloading with OpenMP in LLVM
  Gregory Rodgers – AMD
  

• 14:30 - 15:00 CEST ²⁾
  Fast Linear Programming through Transprecision Computing on Small and Sparse Data
  Tobias Grosser – University of Edinburgh
  

• 15:00 - 15:30 CEST ³⁾
  Tutorial: Writing a Semantic Check for OpenMP in LLVM Flang
  Arnamoy Bhattacharyya – Huawei Canada
  

• 15:30 - 16:00 CEST ⁴⁾
  OpenACC support in Flang/LLVM
  Valentin Clement – ORNL
  

• 16:00 - 16:30 CEST ⁵⁾
  BOLT: LLVM OpenMP over Lightweight Threads for Massive Fine-Grained Parallelism
  Shintaro Iwasaki – ANL
  

• 16:30 - 17:00 CEST ⁶⁾
  LLVM use in the HPE Cray Programming Environment
  Jeff Sandoval – HPE/Cray
  

• 17:00 - 17:30 CEST ⁷⁾
  DPC++ Performance Optimization and Interoperability with OpenMP on Xe GPUs
  Xinmin Tian – Intel
  

• 17:30 - 18:00 CEST ⁸⁾
  C++/Fortran OpenMP Dispatch Variant Design and Implementation for GPUs
  Ernesto Su – Intel
  

• 18:00 - 18:30 CEST ⁹⁾
  C++/OpenMP in LLVM for Users
  Johannes Doerfert – ANL
  

The workshop is integrated into ISC-HPC. We welcome everybody to join the workshop, including:

• Researchers/Engineers from industry and academia working on high-performance computing
• LLVM developers
• Interested domain scientists and computer scientists interested in discussing compiler issues.