ログイン
言語:

WEKO3

  • トップ
  • ランキング
To
lat lon distance
To

Field does not validate



インデックスリンク

インデックスツリー

メールアドレスを入力してください。

WEKO

One fine body…

WEKO

One fine body…

アイテム

  1. 防災科研関係論文

The design of ultra scalable MPI collective communication on the K computer

https://nied-repo.bosai.go.jp/records/6374
https://nied-repo.bosai.go.jp/records/6374
6a8ae682-39e4-41c2-9f20-79a91bca201d
Item type researchmap(1)
公開日 2023-09-20
タイトル
言語 ja
タイトル The design of ultra scalable MPI collective communication on the K computer
タイトル
言語 en
タイトル The design of ultra scalable MPI collective communication on the K computer
言語
言語 eng
著者 Tomoya Adachi

× Tomoya Adachi

ja Tomoya Adachi

en Tomoya Adachi

Search repository
Naoyuki Shida

× Naoyuki Shida

ja Naoyuki Shida

en Naoyuki Shida

Search repository
Kenichi Miura

× Kenichi Miura

ja Kenichi Miura

en Kenichi Miura

Search repository
Shinji Sumimoto

× Shinji Sumimoto

ja Shinji Sumimoto

en Shinji Sumimoto

Search repository
Atsuya Uno

× Atsuya Uno

ja Atsuya Uno

en Atsuya Uno

Search repository
Motoyoshi Kurokawa

× Motoyoshi Kurokawa

ja Motoyoshi Kurokawa

en Motoyoshi Kurokawa

Search repository
Fumiyoshi Shoji

× Fumiyoshi Shoji

ja Fumiyoshi Shoji

en Fumiyoshi Shoji

Search repository
Mitsuo Yokokawa

× Mitsuo Yokokawa

ja Mitsuo Yokokawa

en Mitsuo Yokokawa

Search repository
抄録
内容記述タイプ Other
内容記述 This paper proposes the design of ultra scalable MPI collective communication for the K computer, which consists of 82,944 computing nodes and is the world's first system over 10 PFLOPS. The nodes are connected by a Tofu interconnect that introduces six dimensional mesh/torus topology. Existing MPI libraries, however, perform poorly on such a direct network system since they assume typical cluster environments. Thus, we design collective algorithms optimized for the K computer.On the design of the algorithms, we place importance on collision-freeness for long messages and low latency for short messages. The long-message algorithms use multiple RDMA network interfaces and consist of neighbor communication in order to gain high bandwidth and avoid message collisions. On the other hand, the short-message algorithms are designed to reduce software overhead, which comes from the number of relaying nodes. The evaluation results on up to 55,296 nodes of the K computer show the new implementation outperforms the existing one for long messages by a factor of 4 to 11 times. It also shows the short-message algorithms complement the long-message ones.
言語 en
書誌情報 ja : Computer Science - Research and Development
en : COMPUTER SCIENCE-RESEARCH AND DEVELOPMENT

巻 28, 号 2-3, p. 147-155, 発行日 2012-05-23
出版者
言語 ja
出版者 Springer Science and Business Media LLC
出版者
言語 en
出版者 SPRINGER HEIDELBERG
ISSN
収録物識別子タイプ EISSN
収録物識別子 1865-2042
DOI
関連識別子 10.1007/s00450-012-0211-7
戻る
0
views
See details
Views

Versions

Ver.1 2023-09-20 08:09:38.934031
Show All versions

エクスポート

OAI-PMH
  • OAI-PMH JPCOAR 2.0
  • OAI-PMH JPCOAR 1.0
  • OAI-PMH DublinCore
  • OAI-PMH DDI
Other Formats
  • JSON
  • BIBTEX

Confirm


Powered by WEKO3

Change consent settings


Powered by WEKO3

Change consent settings