TY - GEN
T1 - An Analysis of System Balance and Architectural Trends Based on Top500 Supercomputers
AU - Khan, Awais
AU - Sim, Hyogi
AU - Vazhkudai, Sudharshan S.
AU - Butt, Ali R.
AU - Kim, Youngjae
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/1/20
Y1 - 2021/1/20
N2 - Supercomputer design is a complex, multi-dimensional optimization process, wherein several subsystems need to be reconciled to meet a desired figure of merit performance for a portfolio of applications and a budget constraint. However, overall, the HPC community has been gravitating towards ever more Flops, at the expense of many other subsystems. To draw attention to overall system balance, in this paper, we analyze balance ratios and architectural trends in the world's most powerful supercomputers. Specifically, we have collected the performance characteristics of systems between 1993 and 2019 based on the Top500 lists and then analyzed their architectures from diverse system design perspectives. Notably, our analysis studies the performance balance of the machines, across avariety of subsystems such as compute, memory, I/O, interconnect, intra-node connectivity and power. Our analysis reveals that balance ratios of the various subsystems need to be considered carefully alongside the application workload portfolio to provision the subsystem capacity and bandwidth specifications, which can help achieve optimal performance.
AB - Supercomputer design is a complex, multi-dimensional optimization process, wherein several subsystems need to be reconciled to meet a desired figure of merit performance for a portfolio of applications and a budget constraint. However, overall, the HPC community has been gravitating towards ever more Flops, at the expense of many other subsystems. To draw attention to overall system balance, in this paper, we analyze balance ratios and architectural trends in the world's most powerful supercomputers. Specifically, we have collected the performance characteristics of systems between 1993 and 2019 based on the Top500 lists and then analyzed their architectures from diverse system design perspectives. Notably, our analysis studies the performance balance of the machines, across avariety of subsystems such as compute, memory, I/O, interconnect, intra-node connectivity and power. Our analysis reveals that balance ratios of the various subsystems need to be considered carefully alongside the application workload portfolio to provision the subsystem capacity and bandwidth specifications, which can help achieve optimal performance.
KW - Architectural Trends and Performance Balance Ratio
KW - High Performance Computing
KW - Top500 Supercomputers
UR - http://www.scopus.com/inward/record.url?scp=85099884845&partnerID=8YFLogxK
U2 - 10.1145/3432261.3432263
DO - 10.1145/3432261.3432263
M3 - Conference contribution
AN - SCOPUS:85099884845
T3 - ACM International Conference Proceeding Series
SP - 11
EP - 22
BT - Proceedings of International Conference on High Performance Computing in Asia-Pacific Region, HPC Asia 2021
PB - Association for Computing Machinery
T2 - 2021 International Conference on High Performance Computing in Asia-Pacific Region, HPC Asia 2021
Y2 - 20 January 2021 through 22 January 2021
ER -