There are two significant challenges when programming for today’s GPU-accelerated supercomputers: 1). Different platforms consist of accelerators from different vendors, 2). Compute nodes often feature multiple accelerators. Given the trend of very fat compute nodes, it is more important than ever to make effective use of the increased acceleration potential. It is also highly desirable that application programmers can use a single programming approach to target the architectural components of a single compute node and across different supercomputing platforms. Therefore, the focus of this workshop is on the use of high-level programming methods that can exploit the maximum compute capability out of such systems. Historically, the favored portable approaches were OpenMP offloading and OpenACC, both based on directives. Today, we recognize the evolution of other options to adapt to heterogeneity and, starting in 2021, we extended the workshop scope to include use of Fortran/C++ standard language parallelism, SYCL, DPC++, Kokkos, RAJA, Chapel as well as task-based and data-centric models like Regent, Legion, OmpSs among several alternatives that can provide scalable as well as portable solutions without compromising on performance. A programmer’s expectation from the software community is to deliver solutions that would allow maintenance of a single code base whenever possible, thus avoiding duplicate effort across programming models and architectures.
The 12th WACCPD workshop will highlight the improvements over the state of art through accepted papers and prompt discussion through keynotes and panels. The workshop aims to showcase all aspects of accelerator programming for heterogeneous systems such as innovative high-level language or library approaches, lessons learned while using directives or other portable approaches to migrate scientific legacy code to modern systems, and compilation and runtime scheduling techniques.
This year we further extend the scope of the workshop to share methods and case studies demonstrating programmability across emerging architectures including ML/AI chips and quantum computing architectures including QPUs.
In the past eleven years of this workshop, WACCPD has been one of the major forums at the Supercomputing Conference to bring together programming model users, developers, and the tools community to share knowledge and experiences to tackle emerging complex parallel computing systems.
Topics of interest for workshop submissions include (but are not limited to)
- Programming Models and Frameworks
- Advanced programming models for heterogeneous computing
- High-Level and Task-Based approaches for productivity
- Meta-programming and JIT compilation
- AI-Assisted and ML-Supported programming
- Performance, Portability, Verification, and Optimization
- Performance, portability, and optimization across architectures
- Automatic and compiler driven kernel optimization
- Performance tuning and scalability for large-scale applications
- Tools for debugging, profiling, and performance analysis
- Quantum, FPGA, and other emerging accelerator technologies
- Hybrid classical-quantum programming models for heterogeneous HPC
- Data flow, data flow inspired, synthesized (FPGA), and other programming models
- Performance portability challenges for integration of emerging programming frameworks (e.g. quantum)
- Leveraging task-based offloading models for quantum algorithms
- AI/ML/LLM workloads in HPC
- Accelerating ML/AI workloads using directive based programming models
- Mixed-precision and reduced precision techniques for scientific and AI applications
- Integration of AI accelerators (e.g. TPUs) with traditional HPC environments
- Data driven approaches to optimize time-evolution models in heterogeneous systems
- Applications and case studies
- Real-world case studies demonstrating performance and/or portability
- Domain-specific optimizations for scientific applications
- Comparative studies of programming models (e.g. CUDA vs HIP vs SYCL)
- Case studies on optimizing legacy codes for modern heterogeneous architectures
Workshop Important Deadlines
- Paper Submission Deadline: 28 of July, 2025, AOE
- Author Notification: August 29, 2025
- Camera Ready Deadline: September 29, 2025
Best Paper Award
The Best Paper Award will be selected on the basis of explicit recommendations of the reviewers and their scoring towards the paper’s originality and quality. In order to be considered for the Best Paper Award, the authors must submit an Artifact Description appendix according to the reproducibility initiative of the SC25 technical papers.
Paper Proceedings
WACCPD papers will be peer-reviewed and selected for presentation at the workshop. The full papers presented will be published in the SC25 Workshop Proceedings.
Paper Submission Guidelines
- WACCPD 2025 features two submission types:
- Full paper
- Submissions between 8 to 12 two-column pages (U.S. letter – 8.5″ x 11″), excluding the bibliography
- 15+5min talk (15 minute presentation + 5 minute Q&A)
- Lightning talk
- Submissions up to 5 to 8 two-column pages (U.S. letter – 8.5″ x 11″), excluding the bibliography
- 5+5min talk (5 minute presentation + 5 minute Q&A)
- Full paper
- Papers should be submitted electronically via the SC25 Submission Page.
- Submissions should use the ACM proceedings template, two-column, US letter. Latex users, please use the “sigconf” option. Word authors can use the “Interim Layout”.
- Templates can be accessed in https://www.acm.org/publications/proceedings-template
- Page limits does not include appendix pages for describing data artifacts and reproducibility actions as outlined in the reproducibility initiative of this workshop.
- Submitted papers should not have appeared in or be under consideration for a different workshop, conference or journal.
- In submitting the paper, the authors acknowledge that at least one author of an accepted submission will register for and attend the workshop.
- Reproducibility files should be uploaded to Linklings with the submission.
Reproducibility
WACCPD supports SC25’s reproducibility initiative. WACCPD is not requiring reproducibility information, however, strongly encourages submitters to provide artifact appendices in form of an Artifact Description (AD) and eventually artifacts that can complete an Artifact Evaluation (AE).
Authors should follow the instructions on SC25’s reproducibility initiative. Similar to SC25’s reproducibility process, AD/AE appendices will be automatically-generated from an AD/AE appendix form provided on the WACCPD submission page. Authors are encouraged to familiarize themselves early with the AD/AE appendix requirements on the SC25 web page and the WACCPD’s submission form.
Submission
To submit your paper or extended abstract visit: https://submissions.supercomputing.org