|
|
|
TH-1: China’s first petaflop supercomputer |
| Xuejun YANG,Xiangke LIAO,Weixia XU,Junqiang SONG,Qingfeng HU,Jinshu SU,Liquan XIAO,Kai LU,Qiang DOU,Juping JIANG,Canqun YANG, |
| School of Computer Science,
National University of Defense Technology, Changsha 410073, China; |
|
|
|
|
Abstract In recent years, heterogeneous systems and cooperative computing have become popular research directions in the field of high performance computing. With fast scaling of the size of high performance computer systems, problems such as power consumption and reliability come to the forefront. The aim of high performance computing has thus shifted from merely seeking peak performance to comprehensively pursuing high efficiency, which takes into consideration many factors including performance, cost, power, reliability and so on. A heterogeneous computing system consisting of general-purpose CPU(s) and special-purpose accelerator(s) features high performance, lower power consumption and low cost, etc. Hence, it has already become the mainstream in the field of high performance computing. However, such systems still face many challenges and problems, for example, programmability and reliability. In this paper, we firstly analyze the main challenges facing heterogeneous computing systems. Then, we introduce the architecture of the first petaflop computing system in China, the Tianhe-1 (TH-1) heterogeneous system, including its hardware/software interface and interconnect network. During development of the TH-1 system, several challenges were encountered; research into the solutions of these challenges is subsequently presented.
|
| Keywords
heterogeneous systems
cooperative computing
Tianhe-1(TH-1) system
load balancing
programming models
low power consumption
fault tolerance
|
|
Issue Date: 05 December 2010
|
|
|
Yang X, Yan X, Xing Z, et al. A 64-bit stream processor architecture for scientificapplications. In: Proceedings of 34th AnnualInternational Symposium on Computer Architecture. 2007, 210–219
|
|
Barker K J, Davis K, Hoisie A, et al. Entering the petaflop era: the architecture and performance of Roadrunner. In: Proceedings of 2008 ACM/IEEE Conference onSupercomputing. 2008, 1–11
|
|
www.clearspeed.com/docs/resources/
|
|
Kirk D. Nvidia cuda software and gpu parallel computing architecture. In: Proceedings of 6th International Symposiumon Memory Management. 2007, 103–104
doi: 10.1145/1296907.1296909
|
|
ati.amd.com/technology/streamcomputing/AMDBrook-plus.pdf
|
|
s08.idav.ucdavis.edu/munshi-opencl.pdf
|
|
www.green500.org
|
|
Semeraro G, Magklis G, Balasubramonian R, et al. Energy-efficient processordesign using multiple clock domains with dynamic voltage and frequencyscaling. In: Proceedings of 8th InternationalSymposium on High-Performance Computer Architecture. 2002, 29–42
|
|
Luk C, Hong S, Kim H. Qilin: exploiting parallelism on heterogeneousmultiprocessors with adaptive mapping. In: Proceedings of 42nd Annual IEEE/ACM International Symposium on Microarchitecture. 2009, 45–55
doi: 10.1145/1669112.1669121
|
|
Dimitrov M, Mantor M, Zhou H. Understanding software approachesfor GPGPU reliability. In: Proceedings of 2nd Workshop on General Purpose Processing on Graphics ProcessingUnits. 2009, 94–104
doi: 10.1145/1513895.1513907
|
|
Oh N, Shirvani P, McCluskey E J. Error detection by duplicatedinstruction in super-scalar processors. IEEE Transactions on Reliability, 2002, 51(1): 63–75
doi: 10.1109/24.994913
|
|
Norman A N, Choi S, Lin C. Compiler-generated staggered checkpointing. In: Proceedings of 7th ACM Workshop on Languages,Compilers, and Runtime Support for Scalable Systems. 2004, 1–8
doi: 10.1145/1066650.1066663
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
