One of the hard realities is that the hardware continues to evolve very rapidly with diverse memory subsystems or cores with different ISAs or accelerators of varied types. The HPC community is in constant need for sophisticated software tools and techniques to port legacy code to these emerging platforms. Maintaining a single code base yet achieving performance portable solution continues to pose a daunting task. Directive-based programming models such as OpenACC, OpenMP tackle this issue by offering scientists a high-level approach to accelerate scientific applications and develop performance portable solutions. This enables accelerators to be first-class citizens for HPC!
To address the rapid pace of hardware evolution, developers continue to explore and add richer features to the various (parallel) programming standards. Domain scientists continue to explore the programming and tools space while preparing themselves for future Exascale systems.
This workshop aims to solicit papers that explore innovative language features – their implementations, compilation & runtime scheduling techniques, performance optimization strategies, autotuning tools exploring the optimization space and so on.
WACCPD has been one of the major forums for bringing together the users, developers and tools community to share their knowledge and experiences of using directives and similar approaches to program emerging complex systems.
Compiler and Runtime support for current and emerging architectures
Language-based extensions
Memory management using directives
Performance evaluation and lessons learnt
Auto-tuning and optimization strategies
Programming experience porting applications in any domain
Extensions to and shortcomings of current accelerator directives APIs
Hybrid heterogeneous or many-core programming with accelerator directives with other models (i.e. OpenMP, MPI, OpenSHMEM)
Scientific libraries interoperability with accelerator directives
Experiences in implementing compilers for accelerator directives on newer architectures
Low level communication APIs or runtimes that support accelerator directives
Asynchronous execution and scheduling (heterogeneous tasks)
Power / energy studies
Static analysis and verification tools
Modeling and performance analysis tools
Benchmarks and validation suites
Nov 14
2016
Conference Date
Draft paper submission deadline
Registration deadline
2022-11-13 United States Dallas
2022 Workshop on Accelerator Programming Using Directives2017-11-13 United States
Fourth Workshop on Accelerator Programming Using Directives2015-11-16 United States
Workshop on Accelerator Programming Using Directives2014-11-17 United States
Workshop on Accelerator Programming using Directives
Submit Comment