EXA2PRO: Enhancing Programmability and boosting Performance Portability for Exascale Computing Systems
Only 128 seats left
Wednesday, June 30, 2021 3:00 PM to 4:00 PM · 1 hr. (Africa/Abidjan)
Exascale Systems
Information
Contributors:
Abstract:
Programming upcoming exascale computing systems is expected to be a major challenge. New programming models are required to improve programmability, by hiding the complexity of these systems from application developers. The EXA2PRO EU H2020 FETHPC project develops a programming framework that aims at improving developers' productivity for applications that target heterogeneous computing systems. It is based on advanced programming models and abstractions that encapsulate low-level platform-specific optimizations and it is supported by a runtime that handles application deployment on heterogeneous nodes. It supports a wide variety of platforms and accelerators (CPU, GPU, FPGA-based Data-Flow Engines), allowing developers to efficiently exploit heterogeneous computing systems, thus enabling more HPC applications to reach exascale computing systems. Its main advantage is the fact that it enables the evaluation of applications across a wide variety of architectures and backends (CPU sequential, OpenMP, OpenCL, CUDA, StarPU-MPI, MaxJ for Data-Flow Engines) in a way convenient to application developers, who may be not familiar with these complex programming models: As soon as the EXA2PRO API is applied to applications, the evaluation is performed automatically. The EXA2PRO framework was evaluated using several HPC applications from different domains. By applying the EXA2PRO framework, the applications were automatically deployed and evaluated on a variety of underlying computing systems, including accelerators and MPI clusters, enabling developers to obtain performance results, test scalability and reach interesting conclusions.Visit the Project Website
- Dimitrios Soudris (National Technical University of Athens)
- Lazaros Papadopoulos (National Technical University of Athens)
Abstract:
Programming upcoming exascale computing systems is expected to be a major challenge. New programming models are required to improve programmability, by hiding the complexity of these systems from application developers. The EXA2PRO EU H2020 FETHPC project develops a programming framework that aims at improving developers' productivity for applications that target heterogeneous computing systems. It is based on advanced programming models and abstractions that encapsulate low-level platform-specific optimizations and it is supported by a runtime that handles application deployment on heterogeneous nodes. It supports a wide variety of platforms and accelerators (CPU, GPU, FPGA-based Data-Flow Engines), allowing developers to efficiently exploit heterogeneous computing systems, thus enabling more HPC applications to reach exascale computing systems. Its main advantage is the fact that it enables the evaluation of applications across a wide variety of architectures and backends (CPU sequential, OpenMP, OpenCL, CUDA, StarPU-MPI, MaxJ for Data-Flow Engines) in a way convenient to application developers, who may be not familiar with these complex programming models: As soon as the EXA2PRO API is applied to applications, the evaluation is performed automatically. The EXA2PRO framework was evaluated using several HPC applications from different domains. By applying the EXA2PRO framework, the applications were automatically deployed and evaluated on a variety of underlying computing systems, including accelerators and MPI clusters, enabling developers to obtain performance results, test scalability and reach interesting conclusions.Visit the Project Website
