From large scale problems such as understanding the structure of the universe and simulating weather, to the nano scale required in designing pharmaceuticals, high performance computing enables many areas of modern science and engineering. Both simulation and the rapidly expanding field of data science are driving the HPC community towards its next milestone: exascale. An exascale computing facility is one that is capable of performing 10^18 floating point operations per second; this will be likely be in production by 2025 and will afford new insights and enable scientific discoveries that hitherto have been unreachable.
While the potential system architectures are still evolving, one can safely assume that they will be largely based on complex arrangements of processing units, likely with much greater heterogeneity than we are used to today, with similarly complex deep memory hierarchies. On the software side the tools, libraries and runtimes will have to adapt to this environment, supporting millions of threads of execution and addressing concerns around reliability and the scalability of I/O systems that will likely have to move on from the now-standard POSIX model. The challenge of designing and implementing applications that will efficiently use these platforms involves developers from all levels of the software stack: applications, libraries, programming models, and system software.
The aim of this special issue is to bring together developers from many different application fields and levels in the software stack to present work on the problems encountered and progress made on the road to exascale.
Topics of interest include but are not limited to:
enabling and optimising applications for exascale in any area;
developing and enhancing algorithms for exascale systems;
aiding the exploitation of massively parallel systems through tools, e.g. performance analysis, debugging, development environments;
programming models and libraries for exascale;
exascale runtimes and system software;
evaluating best practice in HPC concerning large-scale facilities and application execution;
novel uses of current generation and future exascale systems;
new hardware technologies and their exploitation to solve exascale challenges.
Research and/or experience that brings together current theory and practice is particularly welcome.
The authors should prepare their manuscript following the formatting guidelines at Guide for Authors online: https://www.elsevier.com/journals/journal-of-parallel-and-distributed-computing/0743-7315/guide-for-authors
The authors should select article tpye name of \”SI: Parallelism for Big Data\” while submitting their paper.
Submission due date: July 31, 2018,
Final decision due: March 29, 2019,
Expected publication: June 2019
Rupert Nash, The University of Edinburgh,
Nick Brown, The University of Edinburgh
Lorna Smith, The University of Edinburgh
Juan F R Herrera, The University of Edinburgh
Mark Bull, The University of Edinburgh
Stefano Markidis, KTH Royal Institute of Technology,