The Effectiveness of Low-Precision Floating Arithmetic on Numerical Codes: A Case Study on Power Consumption

Ryuichi Sakamoto, Masaaki Kondo, Kohei Fujita, Tsuyoshi Ichimura, Kengo Nakajima

研究成果: Conference contribution

3 被引用数 (Scopus)

抄録

The low-precision floating point arithmetic that performs computation by reducing numerical accuracy with narrow bit-width is attracting since it can improve the performance of the numerical programs. Small memory footprint, faster computing speed, and energy saving are expected by performing calculation with low precision data. However, there have not been many studies on how low-precision arithmetics affects power and energy consumption of numerical codes. In this study, we investigate the power efficiency improvement by aggressively using low-precision arithmetics for HPC applications. In our evaluations, we analyze power characteristics of the Poisson's equation and the ground motion simulation programs with double precision and single precision floating point arithmetics. We confirm that energy efficiency improves by using low-precision arithmetics but it is heavily influenced by parameters such as data division and the number of OpenMP threads.

本文言語English
ホスト出版物のタイトルProceedings of International Conference on High Performance Computing in Asia-Pacific Region, HPC Asia 2020
出版社Association for Computing Machinery
ページ199-206
ページ数8
ISBN(電子版)9781450372367
DOI
出版ステータスPublished - 2020 1月 15
外部発表はい
イベント2020 International Conference on High Performance Computing in Asia-Pacific Region, HPC Asia 2020 - Fukuoka, Japan
継続期間: 2020 1月 152020 1月 17

出版物シリーズ

名前ACM International Conference Proceeding Series

Conference

Conference2020 International Conference on High Performance Computing in Asia-Pacific Region, HPC Asia 2020
国/地域Japan
CityFukuoka
Period20/1/1520/1/17

ASJC Scopus subject areas

  • ソフトウェア
  • 人間とコンピュータの相互作用
  • コンピュータ ビジョンおよびパターン認識
  • コンピュータ ネットワークおよび通信

フィンガープリント

「The Effectiveness of Low-Precision Floating Arithmetic on Numerical Codes: A Case Study on Power Consumption」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