Similar articles

Abstract: With various exascale systems in different countries planned over the next three to five years, developing application software for such unprecedented computing capabilities and parallel scaling becomes a major challenge. In this study, we start our discussion with the current 125-Pflops Sunway TaihuLight system in China and its related application challenges and solutions. Based on our current experience with Sunway TaihuLight, we provide a projection into the next decade and discuss potential challenges and possible trends we would probably observe in future high performance computing software.

E级超算下应用软件发展的挑战与趋势

[1]Chen Y, Luo T, Liu S, et al., 2014. DaDianNao: a machine-learning supercomputer. 47^th Annual IEEE/ACM Int Symp on Microarchitecture, p.609-622.

[2]Cui Y, Poyraz E, Olsen KB, et al., 2013. Physics-based seismic hazard analysis on peta-scale heterogeneous supercomputers. Int Conf for High Performance Computing, Networking, Storage, and Analysis, p.1-12.

[3]Fang J, Fu H, Zhao W, et al., 2017. SwDNN: a library for accelerating deep learning applications on Sunway TaihuLight. Int Symp on Parallel and Distributed Processing, p.615-624.

[4]Fu H, Liao J, Yang J, et al., 2016. The Sunway TaihuLight supercomputer: system and applications. Sci China Inform Sci, 59(7):072001.

[5]Fu H, He C, Chen B, et al., 2017a. 18.9-PFlops nonlinear earthquake simulation on Sunway TaihuLight: enabling depiction of 18-Hz and 8-meter scenarios. Int Conf for High Performance Computing, Networking, Storage, and Analysis, p.1-12.

[6]Fu H, Liao J, Ding N, et al., 2017b. Redesigning CAM-SE for peta-scale climate modeling performance and ultra-high resolution on Sunway TaihuLight. Int Conf for High Performance Computing, Networking, Storage, and Analysis, p.1-12.

[7]Gan L, Fu H, Luk W, et al., 2013. {Accelerating solvers for global atmospheric equations through mixed-precision data flow engine}. 23^rd Int Conf on Field Programmable Logic and Applications, p.1-6.

[8]Gan L, Fu H, Yang C, et al., 2014. {A highly-efficient and green data flow engine for solving Euler atmospheric equations}. 24^th Int Conf on Field Programmable Logic and Applications, p.1-6.

[9]Palmer T, 2015. Modelling: build imprecise supercomputers. Nature, 526(7571):32-33.

[10]Roten D, Cui Y, Olsen KB, et al., 2016. High-frequency nonlinear earthquake simulations on peta-scale heterogeneous supercomputers. Int Conf for High Performance Computing, Networking, Storage, and Analysis, p.1-12.

[11]Shalf J, Dosanjh S, Morrison J, 2010. Exascale computing technology challenges. In Conf on High Performance Computing for Computational Science, p.1-25.

[12]Shaw DE, Dror RO, Salmon JK, et al., 2009. Millisecond-scale molecular dynamics simulations on Anton. Int Conf on High Performance Computing Networking, Storage, and Analysis, p.1-11.

[13]Shaw DE, Grossman J, Bank JA, et al., 2014. {Anton 2: raising the bar for performance and programmability in a special-purpose molecular dynamics supercomputer}. Int Conf for High Performance Computing, Networking, Storage, and Analysis, p.41-53.

[14]Wells J, Bland B, Nichols J, et al., 2016. Announcing supercomputer summit. Oak Ridge National Lab, Oak Ridge, TN, USA. https://www.osti.gov/servlets/purl/1259664

[15]Yang C, Xue W, Fu H, et al., 2016. 10M-core scalable fully-implicit solver for non-hydrostatic atmospheric dynamics. Int Conf for High Performance Computing, Networking, Storage, and Analysis, p.57-68.