Programming at Exascale: Challenges and Innovations

TL;DR

This paper reviews the challenges and recent innovations in programming for Exascale supercomputers, which are a thousand times faster than Petascale systems, requiring new hardware and software solutions.

Contribution

It provides a comprehensive survey of the programming challenges and recent developments in models and systems for Exascale supercomputers.

Findings

Identification of key programming challenges at Exascale.

Survey of recent innovations in programming models and systems.

Highlighting the need for new software and hardware solutions.

Abstract

Supercomputers become faster as hardware and software technologies continue to evolve. Current supercomputers are capable of 1015 floating point operations per second (FLOPS) that called Petascale system. The High Performance Computer (HPC) community is Looking forward to the system with capability of 1018 (FLOPS) that is called Exascale. Having a system to thousand times faster than the previous one produces challenges to the high performance computer (HPC) community. These challenges require innovation in software and hardware. In this paper, the challenges posed for programming at Exascale systems are reviewed and the developments in the main programming models and systems are surveyed.