------------------------------------------------
[san-tech][02406] US DOD DARPA 新 HPCプロジェクト (OHPC) 公募
標題の OHPCプロジェクトではなく、元プロジェクト UHPC (Ubiquitous High
Performance Computing) の契約が決まりました：
"DARPA Developing ExtremeScale Supercomputer System", August 6, 2010
http://www.darpa.mil/WorkArea/DownloadAsset.aspx?id=1795
※PDFファイル
プロトタイプ (第一フェーズだけの契約だと思います) 4チーム
Intel Corporation,
NVIDIA Corporation,
Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory,
Sandia National Laboratory,
Applications, Benchmarks and Metrics (プロジェクト期間ずっと)
Georgia Institute of Technology
>
>
>
>
スケジュールは 22枚目、全部で 5フェーズ、第 1, 2：1年、第 3：2年....
Development Team
Phase 1: 12 months: 5 - 6 Teams (予算削減？)
Conceptual system designs, including the initial execution model.
Architectural review and analysis
Phase 2: 12 months: 3 - 4 Teams
Updated UHPC Designs, non-UHPC Critical Technologies and Subsystems.
Analysis and initial simulations/emulations of proposed systems.
※以下省略
Applications, Benchmarks, and Metrics Team
Phases 1 - 5: 1 Team
Develop representative challenge applications to drive UHPC designs
Develop benchmarks and metrics for evaluating performance, security, ….
...
いまのところ、プレスリリースは Nvidiaからだけです
"NVIDIA-Led Team Receives $25 Million Contract From DARPA to Develop
High-Performance GPU Computing Systems",
http://pressroom.nvidia.com/easyir/customrel.do?easyirid=A0D622CE9F579F09&version=live&prid=649882&releasejsp=release_157
"A team led by NVIDIA has been awarded a research grant of $25 million
by the Defense Advanced Research Projects Agency (DARPA), the U.S.
Defense Department's research and development arm, to address what
the agency calls a "crisis in computing.""
"The four-year research contract, awarded under DARPA's Ubiquitous
High Performance Computing (UHPC ) program," ...
※フェーズ 1 - 3 (合計 4カ年) がまとめられたのでしょうか？
フェーズ 1 - 3は 4チームでの研究・設計競争、最終の実機検証は 2チーム？
"The team -- which also includes Cray Inc., Oak Ridge National Laboratory
and six top U.S. universities"
Intel、MIT、Sandia各チームもどこかメーカーと組んでいるはずでしょう。
(Intelは MIC (Many Integrated Core) の開発費に回せますね)
"DARPA awards petaflops super challenge squeeze", 9th August 2010
http://www.theregister.co.uk/2010/08/09/darpa_extremescale_awards/
http://www.theregister.co.uk/2010/08/09/darpa_extremescale_awards/page2.html
"The mystery about the DARPA ExtremeScale awards is why SGI was not
among those chosen - perhaps SGI is on the Intel team? In early June,
SGI announced Project Mojo, its own plan to pack a petaflops into
a server rack - and using various kinds of accelerators."
"Project Mojo ? the server rack that packs petaflops", 3rd June 2010
http://www.theregister.co.uk/2010/06/03/sgi_petaflops_cabinet/
"And what about IBM and Hewlett-Packard? Don't they accept ExtremeScale
challenges?" のこりはこの二社になりますね。
Nvidiaと Oak Ridgeでは、一年近い前の記事ですが
"Oak Ridge goes gaga for Nvidia GPUs", 1st October 2009
http://www.theregister.co.uk/2009/10/01/oak_ridge_fermi/
http://www.theregister.co.uk/2009/10/01/oak_ridge_fermi/page2.html
------------------------------------------------
Date: Wed, 22 Sep 2010 03:33:44 +0900
Crayは Intelの UHPCプロジェクトのメンバーでもあります。
"Intel and DARPA Collaborate on $49M Research Effort in Extreme Computing"
August 16, 2010
http://blogs.intel.com/research/2010/08/intel_and_darpa_collaborate_on.php
"Intel's UHPC Principal Investigator, which is DARPA-speak for the
lead researcher, is Shekhar Borkar, an Intel Fellow and currently
the head of the Academic Programs and Research unit at Intel Labs."
... "Our UHPC program will also engage several leading manufacturers
of compute-intensive systems, including SGI, Lockheed Martin, and
Cray to review our work and help guide us to commercially practical,
extreme-scale solutions. Other collaborators include Micron Technology
on advanced memory chip design and Sandia National Laboratories on
future applications development."
------------------------------------------------
[san-tech][02873] NVIDIA GPUDirect等々 (＋Storage と GPU)
Date: Mon, 27 Dec 2010 19:41:05 +0900
時系列が逆になりますが、まずは先月開催された SC10関連：
NVIDIA GPU Computing, SC10
http://www.nvidia.com/object/sc10.html
※SC10オフィシャルサイトへのリンク
NVIDIA GPU Computing Theater, SC10
http://www.nvidia.com/object/sc10_theater.html
※NVIDIA展示ブースでの講演資料 (PDF＋一部 MP4)
例えば、
"GPU Computing: To ExaScale and Beyond"
Bill Dally, NVIDIA Research, November 18, 2010
http://www.nvidia.com/content/PDF/sc_2010/theater/Dally_SC10.pdf
http://www.nvidia.com/content/mp4/sc-2010/theater/dally-sc10.mp4
これについての解説：
"SC10 - Exaスケールスパコンの実現を目指すNVIDIAの「Echelon計画」"
2010/12/24
http://journal.mycom.co.jp/articles/2010/12/24/sc10-nvidia/index.html
------------------------------------------------
2011/06/21
[san-tech][02877] US NCSA Blue Waters I/O Hub and Interconnection Network情報とか
Date: Wed, 29 Dec 2010 20:14:59 +0900
"The UHPC X-Caliber Project"
Arun Rodrigues, Sandia, USA
https://wiki.ncsa.illinois.edu/display/jointlab/Workshop+Program#WorkshopProgram-RodriguesA
https://wiki.ncsa.illinois.edu/download/attachments/17630761/INRIA-UIUC-WS4-arodrigues.pdf
※[san-tech][02527] Re: US DOD DARPA 新 HPCプロジェクト (OHPC) 公募 で
紹介した DARPA UHPC (Ubiquitous High Performance Computing) プロジェクト
Sandiaチーム (すごいメンバー)
0 件のコメント:
コメントを投稿