LLVM-GPU 2024: First International Workshop on LLVM for GPUs University Carlos III of Madrid Madrid, Spain, August 27, 2024 |
| Conference website | https://hps.vi4io.org/events/2024/llvm-gpu |
| Abstract registration deadline | May 6, 2024 |
| Submission deadline | May 6, 2024 |
LLVM-GPU: First International Workshop on LLVM for GPUs
Co-hosted at Euro-Par 2024, 30th International European Conference on Parallel and Distributed Computing
August 26-30, 2024, University Carlos III of Madrid, Madrid, Spain
In cooperation with ACM/SIGHPC
Workshop website: https://hps.vi4io.org/events/2024/llvm-gpu
Important dates
- Paper Deadline: May 6, 2024 (AoE)
- Author Notification: June 20 2024
- Workshop camera-ready deadline: July 1, 2024
- Workshop date: Tuesday, 27th August 2024
Workshop details
Euro-Par is the prime European conference covering all aspects of parallel and distributed processing, ranging from theory to practice, from small to the largest parallel and distributed systems and infrastructures, from fundamental computational problems to full-fledged applications, from architecture, compiler, language and interface design and implementation, to tools, support infrastructures, and application performance aspects. Euro-Par’s unique organization into topics provides an excellent forum for focused technical discussion, as well as interaction with a large, broad and diverse audience.
New to Euro-Par workshops, the LLVM-GPU workshop is dedicated to bringing researchers and practitioners who are interested in LLVM for GPUs. Co-located with Euro-Par 2024, this full day workshop will be held on the 27th of August in Madrid, Spain. The proceedings of the workshop will be published in the workshop proceedings volume of Euro-Par 2024 by Springer.
Workshop scope
The LLVM framework is a vast ecosystem that stretches far beyond a "simple" C/C++ compiler. The variety of programming language and toolchain-related parts help to support most programming models for GPUs, including CUDA, HIP, OpenACC, OpenCL, OpenMP, SYCL, and offloading C++ and Fortran native parallelism. In addition, LLVM serves as a vehicle for various languages in which parallelism is a first-class citizen, such as Julia or Chapel. Summarized, LLVM plays a central role in the GPU offloading landscape, and with the creation of the LLVM/Offload subproject, we expect features and collaborations in this space to grow even further and faster. In this workshop, held in conjunction with the Euro-Par 2024 conference, researchers are invited to speak about experiences, extensions, and ideas for GPU usage, especially those related to LLVM. Through this forum, we believe industry and academia can come together and exchange thoughts on the future of (GPU) offloading.
Workshop topics We invite submissions of high-quality, original research results, user reports, and works-in-progress on LLVM for GPUs. Topics of interest for this workshop include (but are not limited to):
- Contributions related to GPU usage with LLVM
- User reports and use-cases and case-studies with LLVM on GPUs
- GPU offloading
- Extensions for GPUs
- Compilers, languages targeting GPUs with LLVM
- GPU runtimes
- Performance evaluation tools and performance studies using LLVM on GPUs
- Lessons learned from leveraging LLVM for GPUs
- Industry papers exploring the use of LLVM for GPUs
Paper submission
Authors are invited to submit unpublished, original work. Accepted papers will appear in the post-conference workshop proceedings in the Springer Lecture Notes in Computer Science (LNCS) series and submitted versions will be available online for the workshop. Submissions of original work are welcomed on work-in-progress, position papers, or mature work. All papers should be submitted via EasyChair at [https://easychair.org/conferences/?conf=europar24-ws-phd-poster-whpc].
All papers should be formatted using Springer single column LNCS style, with formatting information and templates at [https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines].
Publications must be in PDF format and should not exceed 12 pages (including references). Short papers can be accepted and presented at the workshop. However, to be included in the formal Springer proceedings, the minimum length is of 10 pages per paper (including references). Contributions submitted elsewhere or currently under review will not be considered.
Organization
Organizing committee
- Johannes Doerfert (LLNL, USA)
- Anja Gerbes (TU Dresden, Germany)
- Sameer Shende (University of Oregon, USA)
Program Committee
- Sunita Chandrasekaran, U. Delaware, USA
- Jeffrey Vetter, ORNL, USA
- John Linford, NVIDIA, USA
- Markus Velten, TU Dresden, Germany
- Hartwig Anzt, TU Munich, Germany
- Shilei Tian, AMD, USA
- Georgiana Mania, DKRZ, Germany
- William Moses, UIUC, USA
- Ivan Ivanov, Tokyo Tech and RIKEN CCS, Japan
- Johannes De Fine Licht, Next Silicon, Switzerland
- Carlos Eduardo Gonzalo, NVIDIA, Germany
- Jean-Baptiste Besnard, ParaTools, SAS, France
- Hervé Yviquel, UNICAMP, Brazil
- Thomas Schwinge, BayLibre, Germany
- Tom Lin, U. Bristol, UK