From: tcmay@netcom.com (Timothy C. May) (by way of tcmay@netcom.com (Timothy C. May))
To: cypherpunks@toad.com
Message Hash: a071ce48a8a2f12efb496d1ee31d7531d1f4ae49b6d4afca8da5800be945910a
Message ID: <199407030643.XAA16053@netcom.netcom.com>
Reply To: N/A
UTC Datetime: 1994-07-03 06:43:40 UTC
Raw Date: Sat, 2 Jul 94 23:43:40 PDT
From: tcmay@netcom.com (Timothy C. May) (by way of tcmay@netcom.com (Timothy C. May))
Date: Sat, 2 Jul 94 23:43:40 PDT
To: cypherpunks@toad.com
Subject: NSA and CSS Computer Resources
Message-ID: <199407030643.XAA16053@netcom.netcom.com>
MIME-Version: 1.0
Content-Type: text/plain
Earlier I mentioned the list of supercomputer installations that Gunter
Ahrendt maintains and I included a few (dated) excerpts. Well, tonight I
found a new version posted.
I'm only including the top handful of sites.
Not reported are installations in non-U.S. intelligence agencies, such as
Chobetsu, SDECE, Mossad, BND, etc. They probably don't have Crays,
Connection Machines, or Paragons.
I'll also edit the intro material a bit. The sites are ranked in order of
what I'd call "Cray equivalents," where the Cray Y-MP/1 is rated at 1. For
example, the top-ranked site has the estimated equivalent of 380 Cray
Y-MP/1s.
--Tim May
From: gunter@yarrow.wt.uwa.edu.au (Gunter Ahrendt)
Newsgroups: comp.sys.super
Subject: JUL-1994 List of the world's most powerful computing sites
Date: 3 Jul 94 01:37:07 GMT
Organization: The University of Western Australia
Message-ID: <gunter.773199427@yarrow>
03-JUL-1994 List of the world's most powerful computing sites
=============================================================
(available by fingering me, joining my mailing list or in comp.sys.super)
....
Ratings are ratios to a Cray Y-MP/1 based on NASA NPB BT Size A
benchmark reports. Figures prefixed '~' denote approximations usually
based on comparable programs, figures suffixed '?' denote relative guesses
based on Intel iPSC/860 peak Gflops ratios.
The current minimum performance for inclusion is a benchmarked rating
of 4 BT, or 10.56 Gflops peak for unbenchmarked systems.
...
1) 380.82 - (27-JUN-1994) [NAL]
National Aerospace Lab,Chofu-shi,Tokyo,Japan,
nahirose@asuka.aerospace-lab.go.jp
1) NAL NWT 2/140 ~357 (5.1 @ 2 cpus)
2) Intel Paragon-336 18.38 (7 @ 128 cpus)
3) Fujitsu VP2600/10 ~ 5.44
2) 196.1 - (APR-1994) [CSS]
Central Security Service,National Security Agency Headquarters,Fort
George G Meade,Maryland,US,postmaster@dockmaster.ncsc.mil
1) TMC CM-5/512 44.8 (2.8 @ 32 cpus)
2) Cray C916-1024 35.52 = 2.22 * 16 cpus
3) Cray C916-1024 35.52 = 2.22 * 16 cpus
4) Cray C916-1024 35.52 = 2.22 * 16 cpus
5) Cray Y-MP/8E-256 8 = 1 * 8 cpus
6) Cray Y-MP/8E-256 8 = 1 * 8 cpus
7) Cray Y-MP/8E-256 8 = 1 * 8 cpus
8) Cray Y-MP/8E-256 8 = 1 * 8 cpus
9) Cray M98-4096 ~ 7.01
10) Cray 3/2-64 [-4Q96] 5.73?
11) NSA SMPP-2/2M [+4Q96] 7407.05?
3) 146.41 - (10-JUN-1994) [LANL]
Los Alamos National Labs,Los Alamos,New Mexico,US,iaa@lanl.gov
1) TMC CM-5/1056-32 [-4Q94] 92.4 (2.8 @ 32 cpus)
2) Cray T3D SC128-8/3-64 15 (12 @ 128 cpus + 1 * 3 cpus)
3) Cray Y-MP/8-128 8 = 1 * 8 cpus
4) Cray Y-MP/8-128 8 = 1 * 8 cpus
5) Cray Y-MP/8-64 8 = 1 * 8 cpus
6) Cray Y-MP/8-32 8 = 1 * 8 cpus
7) Cray M98-2048 ~ 7.01
8) TMC CM-5/1056-128 [+4Q94] 92.4 (2.8 @ 32 cpus)
4) 142.08 - (10-JUN-1994) [NSA]
National Security Agency,Dallas,Texas,US,postmaster@dockmaster.ncsc.mil
1) Cray C916-512 35.52 = 2.22 * 16 cpus
2) Cray C916-512 35.52 = 2.22 * 16 cpus
3) Cray C916-512 35.52 = 2.22 * 16 cpus
4) Cray C916-512 35.52 = 2.22 * 16 cpus
5) Cray C916-1024 [+2Q95] 35.52 = 2.22 * 16 cpus
6) Cray C916-1024 [+2Q95] 35.52 = 2.22 * 16 cpus
7) Cray C916-1024 [+2Q95] 35.52 = 2.22 * 16 cpus
8) Cray C916-512 [+2Q95] 35.52 = 2.22 * 16 cpus
5) 112.97 - (16-JUN-1994) [CRI]
Cray Research Computer Network,Eagan,Minnesota,US,root@cray.com
1) Cray C916-256 35.52 = 2.22 * 16 cpus
2) Cray T3D 256 24 (12 @ 128 cpus)
3) Cray Y-MP/8E-128 8 = 1 * 8 cpus
4) Cray Y-MP/8D-128 8 = 1 * 8 cpus
5) Cray Y-MP/8D-64 8 = 1 * 8 cpus
6) Cray Y-MP/8D-32 8 = 1 * 8 cpus
7) Cray M98-4096 ~ 7.01
8) Cray Y-MP8I/6-64 6 = 1 * 6 cpus
9) Cray C92A-128 4.44 = 2.22 * 2 cpus
10) Cray Y-MP/4E-64 4 = 1 * 4 cpus
11) Cray T91 [+1Q95] 4.44?
12) Cray T3D 1024A [+4Q96] 204.8 ?
13) Cray T932 [+4Q96] 142.08?
14) Cray T3D 1024B [+4Q99] 640 ?
6) 106 - (20-MAY-1994) [SANDIA]
Sandia National Labs,Albuquerque,New Mexico,US,arbreck@sandia.gov
1) Intel Paragon-1840 98 (7 @ 128 cpus)
2) Cray Y-MP/8-64 8 = 1 * 8 cpus
7) 104.38 - (29-JUN-1994) [MSCI]
Minnesota Supercomputer Center,Minneapolis,Minnesota,US,consult@msc.edu
1) TMC CM-5/896VU 78.4 (2.8 @ 32 cpus)
2) Cray C916/9-512 19.98 = 2.22 * 9 cpus
3) Cray T3D 64 [-4Q94] 6
4) Cray T3D 128 [+4Q94] 12
8) 98.4 - (02-JUN-1994) [ATP]
Angstrom Technology Partnership,Tsukuba,Japan,sato@jrcat.or.jp
1) Fujitsu VPP500/32 76.8 (4.8 @ 2 cpus)
2) TMC CM-5E/128 21.6 (5.4 @ 32 cpus)
9) 83.52 - (17-JUN-1994) [PSC]
Pittsburgh Supercomputing Center,Pittsburgh,Pennsylvania,US,
remarks@psc.edu
1) Cray T3D 512 48 (12 @ 128 cpus)
2) Cray C916-512 35.52 = 2.22 * 16 cpus
10) 82.4 - (10-JUN-1994) [CALTECH]
Caltech,Pasadena,California,US,goss@delilah.ccsf.caltech.edu
1) Intel Paragon-555 30.35 (7 @ 128 cpus)
2) Intel Touchstone Delta-513 ~28.05 (7 @ 128 cpus)
3) Cray T3D 256 24 (12 @ 128 cpus)
11) 81.55 - (21-JUN-1994) [LLNL]
Lawrence Livermore National Labs,Livermore,California,US,
seager@llnl.gov
1) Cray C916-256 35.52 = 2.22 * 16 cpus
2) Meiko CS-2/256-512VU [-4Q96] ~ 24 (1.5 @ 16 cpus)
3) Cray Y-MP/8-128 8 = 1 * 8 cpus
4) Cray Y-MP/8-64 8 = 1 * 8 cpus
5) Cray 2S/8-128 6.03?
6) Cray T3D SC128-8/3-64 [+3Q94] 15 (12 @ 128+1 * 3 cpus)
7) Meiko CS-2/1280-2560VU [+4Q96] ~120 (1.5 @ 16 cpus)
12) 77.31 - (07-APR-1994) [TSUKUBA]
Uni of Tsukuba,Ibaraki,Japan,root@ume.cc.tsukuba.ac.jp
1) Fujitsu VPP500/30 72 (4.8 @ 2 cpus)
2) Tsukuba QCDPAX-480 5.31?
3) Tsukuba CP-PACS/1024 [+3Q96] 113.68?
13) 75.44 - (25-JUN-1994) [NAS]
NAS,NASA Ames Research Center,Mountain View,California,US,
jet@nas.nasa.gov
1) Cray C916-1024 35.52 = 2.22 * 16 cpus
2) Cray C98-128 17.76 = 2.22 * 8 cpus
3) TMC CM-5/128VU-32/256 11.2 (2.8 @ 32 cpus)
4) Intel Paragon-204 11.16 (7 @ 128 cpus)
5) IBM 9076 SP2/160 [+3Q94] ~63.8 (3.19 @ 8 cpus)
Return to July 1994
Return to “tcmay@netcom.com (Timothy C. May) (by way of tcmay@netcom.com (Timothy C. May))”