Petascale general solver for semidefinite programming problems with over two million constraints

Katsuki Fujisawa, Toshio Endo, Yuichiro Yasui, Hitoshi Sato, Naoki Matsuzawa, Satoshi Matsuoka, Hayato Waki

    研究成果: Chapter in Book/Report/Conference proceedingConference contribution

    11 被引用数 (Scopus)

    抄録

    The semi definite programming (SDP) problem is one of the central problems in mathematical optimization. The primal-dual interior-point method (PDIPM) is one of the most powerful algorithms for solving SDP problems, and many research groups have employed it for developing software packages. However, two well-known major bottlenecks, i.e., the generation of the Schur complement matrix (SCM) and its Cholesky factorization, exist in the algorithmic framework of the PDIPM. We have developed a new version of the semi definite programming algorithm parallel version (SDPARA), which is a parallel implementation on multiple CPUs and GPUs for solving extremely large-scale SDP problems with over a million constraints. SDPARA can automatically extract the unique characteristics from an SDP problem and identify the bottleneck. When the generation of the SCM becomes a bottleneck, SDPARA can attain high scalability using a large quantity of CPU cores and some processor affinity and memory interleaving techniques. SDPARA can also perform parallel Cholesky factorization using thousands of GPUs and techniques for overlapping computation and communication if an SDP problem has over two million constraints and Cholesky factorization constitutes a bottleneck. We demonstrate that SDPARA is a high-performance general solver for SDPs in various application fields through numerical experiments conducted on the TSUBAME 2.5 supercomputer, and we solved the largest SDP problem (which has over 2.33 million constraints), thereby creating a new world record. Our implementation also achieved 1.713 PFlops in double precision for large-scale Cholesky factorization using 2,720 CPUs and 4,080 GPUs.

    本文言語英語
    ホスト出版物のタイトルProceedings - IEEE 28th International Parallel and Distributed Processing Symposium, IPDPS 2014
    出版社IEEE Computer Society
    ページ1171-1180
    ページ数10
    ISBN(印刷版)9780769552071
    DOI
    出版ステータス出版済み - 1 1 2014
    イベント28th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2014 - Phoenix, AZ, 米国
    継続期間: 5 19 20145 23 2014

    出版物シリーズ

    名前Proceedings of the International Parallel and Distributed Processing Symposium, IPDPS
    ISSN(印刷版)1530-2075
    ISSN(電子版)2332-1237

    その他

    その他28th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2014
    国/地域米国
    CityPhoenix, AZ
    Period5/19/145/23/14

    All Science Journal Classification (ASJC) codes

    • 計算理論と計算数学
    • 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
    • ソフトウェア

    フィンガープリント

    「Petascale general solver for semidefinite programming problems with over two million constraints」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