Performance prediction of large-scale parallell system and application using macro-level simulation

Ryutaro Susukita, Yasunori Kimura, Hisashige Ando, Hidemi Komatsu, Mutsumi Aoyagi, Motoyoshi Kurokawa, Hiroaki Honda, Kazuaki J. Murakami, Yuichi Inadomi, Hidetomo Shibamura, Koji Inoue, Shuji Yamamura, Shigeru Ishizuki, Yunqing Yu

研究成果: 書籍/レポート タイプへの寄稿会議への寄与

28 被引用数 (Scopus)

抄録

To predict application performance on an HPC system is an important technology for designing the computing system and developing applications. However, accurate prediction is a challenge, particularly, in the case of a future coming system with higher performance. In this paper, we present a new method for predicting application performance on HPC systems. This method combines modeling of sequential performance on a single processor and macro-level simulations of applications for parallel performance on the entire system. In the simulation, the execution flow is traced but kernel computations are omitted for reducing the execution time. Validation on a real terascale system showed that the predicted and measured performance agreed within 10% to 20 %. We employed the method in designing a hypothetical petascale system of 32768 SIMD-extended processor cores. For predicting application performance on the petascale system, the macro-level simulation required several hours.

本文言語英語
ホスト出版物のタイトル2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2008
DOI
出版ステータス出版済み - 2008
イベント2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2008 - Austin, TX, 米国
継続期間: 11月 15 200811月 21 2008

出版物シリーズ

名前2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2008

その他

その他2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2008
国/地域米国
CityAustin, TX
Period11/15/0811/21/08

!!!All Science Journal Classification (ASJC) codes

  • コンピュータ ネットワークおよび通信
  • ソフトウェア

フィンガープリント

「Performance prediction of large-scale parallell system and application using macro-level simulation」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル