Due to the COVID-19 pandemic IWOMP 2021 will be completely virtual. All the sessions will be presented live. The start times for each session are shown in US Pacific Standard Time (PST) and European Central Time (CET). All speakers and delegates are required to Register to attend. Instructions for joining the online sessions will be included in the booking confirmation. Speakers are marked in Bold.
Best Paper Award
A Case Study of LLVM-Based Analysis for Optimizing SIMD Code Generation
Authors: Joseph Huber, Weile Wei, Giorgis Georgakoudis, Johannes Doerfert and Oscar Hernandez
Which was the highest ranked paper by the reviewers.
Productivity, performance and portability: towards cross-domain DSL compiler architecture
Prof. Paul Kelly, Imperial College London
Domain-specific languages enable us to automate generation of high-performance code from a high-level abstraction. This talk will show, through a couple of example projects (Firedrake and Devito) that DSLs can deliver productivity, performance, and performance-portability. The key to success is compiler architecture – designing intermediate representations that making optimisations easy and analysis trivial. But the DSL software ecosystem is dysfunctional: DSL compilers (including ours) are typically standalone projects, reliant on support from a narrow developer base. Few, if any, components are shared between DSLs. The talk will conclude with a manifesto for fixing this – building on MLIR to establish community support for code generation tools that underpin multiple front-end DSLs. I will argue that this is in fact the only way we can tackle the complexity involved in achieving high performance for complex applications on diverse hardware.
Biography: Paul Kelly leads the Software Performance Optimisation group at Imperial College London. His research focus is domain-specific program optimisation, leading to close engagement with colleagues in computational science, robotics and computer vision. This talk covers joint work with many such collaborators.
BREAK – 30 mins
Papers Session I: Synchronization and Data
Improving Speculative taskloop in Hardware Transactional Memory
Juan Salamanca and Alexandro Baldassin
Vectorized Barrier and Reduction in LLVM OpenMP Runtime
Outcomes of OpenMP Hackathon: OpenMP Application Experiences with the Offloading Model
Swaroop Pophale, Barbara Chapman, Buu Pham, Charlene Yang, Christopher Daley, Colleen Bertoni, Dhruva Kulkarni, Dhruva Kulkarni, Dossay Oryspayev, Ed D’Azevedo, Helen He, Johannes Doerfert, Keren Zhou, Kiran Ravikumar, Mark Gordon, Mauro Del Ben, Meifeng Lin, Melisa Alkan, Michael Kruse, Oscar Hernandez, P. K. Yeung, Paul Lin, Peng Xu, Tosaporn Sattasathuchana, Vivek Kale, William Huhn and Dhruva Kulkarni