OpenMP: Advanced Task-Based, Device and Compiler Programming

19th International Workshop on OpenMP, IWOMP 2023, Bristol, UK, September 13¿15, 2023, Proceedings
Herausgegeben:McIntosh-Smith, Simon; Klemm, Michael; de Supinski, Bronis R.; Deakin, Tom; Klinkenberg, Jannis

• Broschiertes Buch

Produktbeschreibung

This book constitutes the proceedings of the 19th International Workshop on OpenMP, IWOMP 2023, held in Bristol, UK, during September 13-15, 2023.
The 15 full papers presented in this book were carefully reviewed and selected from 20 submissions. The papers are divided into the following topical sections: OpenMP and AI; tasking extensions; OpenMP offload experiences; beyond explicit GPU support; and OpenMP infrastructure and evaluation.

Produktdetails

• Lecture Notes in Computer Science 14114
• Verlag: Springer / Springer Nature Switzerland / Springer, Berlin
• Artikelnr. des Verlages: 978-3-031-40743-7
• 1st ed. 2023
• Seitenzahl: 252
• Erscheinungstermin: 8. August 2023
• Englisch
• Abmessung: 235mm x 155mm x 14mm
• Gewicht: 388g
• ISBN-13: 9783031407437
• ISBN-10: 3031407431
• Artikelnr.: 68362962

Inhaltsangabe

OpenMP and AI: Advising OpenMP Parallelization via a Graph-Based Approach with Transformers.- Towards Effective Language Model Application in High-Performance Computing.- OpenMP Advisor: A Compiler Tool for Heterogeneous Architectures.- Tasking Extensions: Introducing Moldable Task in OpenMP.- Suspending OpenMP Tasks on Asynchronous Events: Extending the Taskwait Construct.- How to Efficiently Parallelize Irregular DOACROSS Loops Using Fine-Grained Granularity and OpenMP Tasks? The mcf Case.- OpenMP Offload Experiences: The Kokkos OpenMPTarget Backend: Implementation and Lessons Learned.- Fine-Grained Parallelism on GPUs Using OpenMP Target Offloading.- Improving a Multigrid Poisson Solver with Peer-to-Peer Communication and Task Dependencies.- Beyond Explicit GPU Support: Multipurpose Cacheing to accelerate OpenMP Target Regions on FPGAs.- GeneralizingHierarchical Parallelism.- Exploring the Limits of Generic Code Execution on GPUs via Direct (OpenMP) Offload.- OpenMP Infrastructure and Evaluation: Improving Simulations of Task-Based Applications on Complex NUMA Architectures.- Experimental Characterization of OpenMP Offloading Memory Operations and Unified Shared Memory Support.- OpenMP Reverse Offloading Using Shared Memory Remote Procedure Calls.