Threaded accurate matrix-matrix multiplications with sparse matrix-vector multiplications

Shuntaro Ichimura, Takahiro Katagiri, Katsuhisa Ozaki, Takeshi Ogita, Toru Nagai

研究成果: Conference contribution

5 被引用数 (Scopus)

抄録

Basic Linear Algebra Subprograms (BLAS) is a frequently used numerical library for linear algebra computations. However, it places little emphasis on computational accuracy, especially with respect to the accuracy assurance of the results. Although some algorithms for ensuring the computational accuracy of BLAS operations have been studied, there is a need for performance evaluation in advanced computer architectures. In this study, we parallelize high-precision matrix-matrix multiplication using thread-level parallelism. In addition, we conduct a performance evaluation from the viewpoints of execution speed and accuracy. We implement a method to convert dense matrices into sparse matrices by exploiting the nature of the target algorithm and adapting sparse-vector multiplication. Results obtained using the FX100 supercomputer system at Nagoya University indicate that (1) implementation with the ELL format achieves 1.43x speedup and (2) a maximum of 38x speedup compared to conventional implementation for dense matrix operations with dgemm.

本文言語English
ホスト出版物のタイトルProceedings - 2018 IEEE 32nd International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2018
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1093-1102
ページ数10
ISBN(印刷版)9781538655559
DOI
出版ステータスPublished - 2018 8月 3
外部発表はい
イベント32nd IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2018 - Vancouver, Canada
継続期間: 2018 5月 212018 5月 25

Other

Other32nd IEEE International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2018
国/地域Canada
CityVancouver
Period18/5/2118/5/25

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ ネットワークおよび通信
  • ハードウェアとアーキテクチャ
  • 情報システムおよび情報管理

フィンガープリント

「Threaded accurate matrix-matrix multiplications with sparse matrix-vector multiplications」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