后E级系统编程模型的构想

翟季冬; 陈文光

doi:10.1631/FITEE.1800442

Your Location：

Home >

Browse articles >

后E级系统编程模型的构想

后E级超算专辑 | Updated：2022-05-19

- 后E级系统编程模型的构想
- A vision of post-exascale programming
- 信息与电子工程前沿（英文） 2018年19卷第10期页码：1261-1266
- Affiliations：
  
  Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China
- Author bio：
  
  Ji-dong ZHAI, E-mail: zhaijidong@tsinghua.edu.cn
  [ "Wen-guang CHEN, E-mail: cwg@tsinghua.edu.cn" ]
- Funds：
  
  Project supported by the National Key Technology R & D Program of China (No. 2016YFB0200100)
- DOI：10.1631/FITEE.1800442
  中图分类号： TP311
- 收稿：2018-07-21，
  
  修回：2018-10-15，
  
  纸质出版：2018-10
- Accepted：
Scan QR Code
翟季冬, 陈文光. 后E级系统编程模型的构想[J]. 信息与电子工程前沿（英文）, 2018,19(10):1261-1266.

Ji-dong ZHAI, Wen-guang CHEN. A vision of post-exascale programming[J]. Frontiers of Information Technology & Electronic Engineering, 2018, 19(10): 1261-1266.
翟季冬, 陈文光. 后E级系统编程模型的构想[J]. 信息与电子工程前沿（英文）, 2018,19(10):1261-1266. DOI： 10.1631/FITEE.1800442.

Ji-dong ZHAI, Wen-guang CHEN. A vision of post-exascale programming[J]. Frontiers of Information Technology & Electronic Engineering, 2018, 19(10): 1261-1266. DOI： 10.1631/FITEE.1800442.

摘要

E级高性能计算系统已经研制很长时间，可以在未来几年投入使用。现在是时候考虑未来的后E级高性能计算系统。后E级系统存在许多主要挑战，例如处理器体系结构、编程模型、存储架构和互连网络。讨论了后E级系统编程模型面临的3个重要挑战：异构性、并行性和容错性。基于我们当前在大规模系统上编程的经验，针对这些挑战，提出一些可能的解决方案。然而，未来需要更多研究工作以应对这些挑战。

Abstract

Exascale systems have been under development for quite some time and will be available for use in a few years. It is time to think about future post-exascale systems. There are many main challenges with regard to future post-exascale systems

such as processor architecture

programming

storage

and interconnect. In this study

we discuss three significant programming challenges for future post-exascale systems: heterogeneity

parallelism

and fault tolerance. Based on our experience of programming on current large-scale systems

we propose several potential solutions for these challenges. Nevertheless

more research efforts are needed to solve these problems.

关键词

Keywords

references

A Bahmani , , , F Mueller . . Scalable performance analysis of exascale MPI programs through signature-based clustering algorithms . . 28 th ACM Int Conf on Supercomputing , , 2014 . . p.155 - - 164 . . DOI: 10.1145/2597652.2597676 http://doi.org/10.1145/2597652.2597676 . .

P Balaji , , , M Snir , , , A Amer , , , 等 . . Exascale MPI . . 2013 . . https://www.exascaleproject.org/project/exascalempi/ https://www.exascaleproject.org/project/exascalempi/ , , [Accessed on Sept. 10, 2018] . .

W Bland , , , P Du , , , A Bouteiller , , , 等 . . A checkpointon-failure protocol for algorithm-based recovery in standard MPI . . European Conf on Parallel Processing , , 2012 . . p.477 - - 488 . . DOI: 10.1007/978-3-642-32820-6_48 http://doi.org/10.1007/978-3-642-32820-6_48 . .

W Bland , , , A Bouteiller , , , T Herault , , , 等 . . Post-failure recovery of MPI communication capability: design and rationale . . Int J High Perform Comput Appl , , 2013 . . 27 ( ( 3 ): ): 244 - - 254 . . DOI: 10.1177/1094342013488238 http://doi.org/10.1177/1094342013488238 . .

A Bouteiller , , , F Cappello , , , T Herault , , , 等 . . MPICHV2: a fault tolerant MPI for volatile nodes based on pessimistic sender based message logging . . ACM/IEEE Conf on Supercomputing , , 2003 . . p.1 - - 17 . . DOI: 10.1145/1048935.1050176 http://doi.org/10.1145/1048935.1050176 . .

F Cappello . . Fault tolerance in petascale/exascale systems: current knowledge, challenges, and research opportunities . . Int J High Perform Comput Appl , , 2009 . . 23 ( ( 3 ): ): 212 - - 226 . . DOI: 10.1177/1094342009106189 http://doi.org/10.1177/1094342009106189 . .

Z Chen . . Online-ABFT: an online algorithm based fault tolerance scheme for soft error detection in iterative methods . . ACM SIGPLAN Not , , 2013 . . 48 ( ( 8 ): ): 167 - - 176 . . DOI: 10.1145/2442516.2442533 http://doi.org/10.1145/2442516.2442533 . .

L Dagum , , , R Menon . . OpenMP: an industry standard API for shared-memory programming . . IEEE Comput Sci Eng , , 1998 . . 5 ( ( 1 ): ): 46 - - 55 . . DOI: 10.1109/99.660313 http://doi.org/10.1109/99.660313 . .

J Dean , , , S Ghemawat . . MapReduce: simplified data processing on large clusters . . Commun ACM , , 2008 . . 51 ( ( 1 ): ): 107 - - 113 . . DOI: 10.1145/1327452.1327492 http://doi.org/10.1145/1327452.1327492 . .

X Dong , , , N Muralimanohar , , , N Jouppi , , , 等 . . Leveraging 3D PCRAM technologies to reduce checkpoint overhead for future exascale systems . . Int Conf on High Performance Computing Networking, Storage, and Analysis , , 2009 . . p.1 - - 12 . . DOI: 10.1145/1654059.1654117 http://doi.org/10.1145/1654059.1654117 . .

H Fu , , , J Liao , , , J Yang , , , 等 . . The Sunway Taihulight supercomputer: system and applications . . Sci Chin Inform Sci , , 2016 . . 59 ( ( 7 ): ): 072001 DOI: 10.1007/s11432-016-5588-7 http://doi.org/10.1007/s11432-016-5588-7 . .

W Gropp . . MPI at exascale: challenges for data structures and algorithms . . In: Ropo M, Westerholm J, Dongarra J (Eds.), Recent Advances in Parallel Virtual Machine and Message Passing Interface. Springer Berlin Heidelberg , , 2009 . . DOI: 10.1007/978-3-642-03770-2_3 http://doi.org/10.1007/978-3-642-03770-2_3 . .

KH Huang , , , JA Abraham . . Algorithm-based fault tolerance for matrix operations . . IEEE Trans Comput , , 1984 . . C-33 ( ( 6 ): ): 518 - - 528 . . DOI: 10.1109/TC.1984.1676475 http://doi.org/10.1109/TC.1984.1676475 . .

J Jeffers , , , J Reinders . . Intel Xeon Phi Coprocessor High Performance Programming , , : : San Francisco, USA Morgan Kaufmann Publishers Inc. , , 2013 . . .

S Lee , , , JS Vetter . . Early evaluation of directive-based GPU programming models for productive exascale computing . . Int Conf on High Performance Computing, Networking, Storage, and Analysis , , 2012 . . p.1 - - 11 . . DOI: 10.1109/SC.2012.51 http://doi.org/10.1109/SC.2012.51 . .

H Lin , , , X Tang , , , B Yu , , , 等 . . Scalable graph traversal on Sunway Taihulight with ten million cores . . Int Parallel and Distributed Processing Symp , , 2017 . . p.635 - - 645 . . DOI: 10.1109/IPDPS.2017.53 http://doi.org/10.1109/IPDPS.2017.53 . .

A Munshi . . The OpenCL specification . . 21 st IEEE Hot Chips Symp , , 2009 . . p.1 - - 314 . . DOI: 10.1109/HOTCHIPS.2009.7478342 http://doi.org/10.1109/HOTCHIPS.2009.7478342 . .

J Ragan-Kelley , , , A Adams . . Halide . . 2012 . . http://halide-lang.org http://halide-lang.org , , [Accessed on Sept. 10, 2018] . .

J Ragan-Kelley , , , C Barnes , , , A Adams , , , 等 . . Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines . . ACM SIGPLAN Not , , 2013 . . 48 ( ( 6 ): ): 519 - - 530 . . DOI: 10.1145/2499370.2462176 http://doi.org/10.1145/2499370.2462176 . .

B Schroeder , , , G Gibson . . A large-scale study of failures in high-performance computing systems . . IEEE Trans Depend Sec Comput , , 2010 . . 7 ( ( 4 ): ): 337 - - 350 . . DOI: 10.1109/TDSC.2009.4 http://doi.org/10.1109/TDSC.2009.4 . .

JE Stone , , , D Gohara , , , G Shi . . OpenCL: a parallel programming standard for heterogeneous computing systems . . Comput Sci Eng , , 2010 . . 12 ( ( 3 ): ): 66 - - 73 . . DOI: 10.1109/MCSE.2010.69 http://doi.org/10.1109/MCSE.2010.69 . .

X Tang , , , J Zhai , , , B Yu , , , 等 . . Self-checkpoint: an in-memory checkpoint method using less space and its practice on fault-tolerant HPL . . 22 nd ACM SIGPLAN Symp on Principles and Practice of Parallel Programming , , 2017 . . p.401 - - 413 . . DOI: 10.1145/3155284.3018745 http://doi.org/10.1145/3155284.3018745 . .

X Tang , , , J Zhai , , , X Qian , , , 等 . . VSensor: leveraging fixed-workload snippets of programs for performance variance detection . . 23 rd ACM SIGPLAN Symp on Principles and Practice of Parallel Programming , , 2018 . . p.124 - - 136 . . DOI: 10.1145/3200691.3178497 http://doi.org/10.1145/3200691.3178497 . .

JS Vetter , , , R Glassbrook , , , J Dongarra , , , 等 . . Keeneland: bringing heterogeneous GPU computing to the computational science community . . Comput Sci Eng , , 2011 . . 13 ( ( 5 ): ): 90 - - 95 . . DOI: 10.1109/MCSE.2011.83 http://doi.org/10.1109/MCSE.2011.83 . .

RS Xin , , , JE Gonzalez , , , MJ Franklin , , , 等 . . GraphX: a resilient distributed graph system on Spark . . 1 st Int Workshop on Graph Data Management Experiences and Systems , , 2013 . . p.1 - - 6 . . DOI: 10.1145/2484425.2484427 http://doi.org/10.1145/2484425.2484427 . .

E Yao , , , R Wang , , , M Chen , , , 等 . . A case study of designing efficient algorithm-based fault tolerant application for exascale parallelism . . 26 th Int Parallel and Distributed Processing Symp , , 2012 . . p.438 - - 448 . . DOI: 10.1109/IPDPS.2012.48 http://doi.org/10.1109/IPDPS.2012.48 . .

X Zhu , , , W Chen , , , W Zheng , , , 等 . . Gemini: a computation-centric distributed graph processing system . . 12 th USENIX Symp on Operating Systems Design and Implementation , , 2016 . . p.301 - - 316 . . . .

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

PASS: a simple, efficient parallelism-aware solid state drive I/O scheduler