Affordable Access

Access to the full text

EXA2PRO : A Framework for High Development Productivity on Heterogeneous Computing Systems

Authors
  • Papadopoulos, Lazaros
  • Soudris, Dimitrios
  • Kessler, Christoph
  • Ernstsson, August
  • Ahlqvist, Johan
  • Vasilas, Nikos
  • Papadopoulos, Athanasios I
  • Seferlis, Panos
  • Prouveur, Charles
  • Haefele, Matthieu
  • Thibault, Samuel
  • Salamanis, Athanasios
  • Ioakimidis, Theodoros
  • Kehagias, Dionysios
Publication Date
Jan 01, 2022
Identifiers
DOI: 10.1109/TPDS.2021.3104257
OAI: oai:DiVA.org:liu-180719
Source
DiVA - Academic Archive On-line
Keywords
Language
English
License
Green
External links

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 programming framework 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. The EXA2PRO framework was evaluated using four HPC applications from different domains. By applying the EXA2PRO framework, the applications were automatically deployed and evaluated on a variety of computing architectures, enabling developers to obtain performance results on accelerators, test scalability on MPI clusters and productively investigate the degree by which each application can efficiently use different types of hardware resources. / <p>Funding Agencies|European Unions Horizon 2020 research and innovation programme [801015]; National Infrastructures for Research and Technology S.A. (GRNET) [SNIC 2020/13-113, SNIC 2016/5-6]; PRACE (Piz-Daint) [pr114]</p>

Report this publication

Statistics

Seen <100 times