mcastle@mcs213e.cs.umr.edu (Mike Castle {Nexus}) (03/26/91)
Was listening to National Public Radio earlier, and they had a little piece
on computers. They mentioned some sort of tests run at Los Alamos something
or the other. They said the fastest machine ran there was one made by
Thinking Machines, Corporation, and turned in a result of 5 BILLION computations
per second.
Now, since the news show is not all that technically knowledgable, I assumed he
meant 5000 MIPS , as opposed to 5000 different computations.
Does anyone have any more information on this?? What test were run? What
machine is it?? How much is it? When can I get one? ;->
Rather dumbfounded by these results,
--
Mike Castle (Nexus) S087891@UMRVMA.UMR.EDU (preferred) | XEDIT: Emacs
mcastle@mcs213k.cs.umr.edu (unix mail-YEACH!)| on a REAL
Life is like a clock: You can work constantly, and be right | operating
all the time, or not work at all, and be right twice a day. | system. :->eijkhout@s41.csrd.uiuc.edu (Victor Eijkhout) (03/26/91)
mcastle@mcs213e.cs.umr.edu (Mike Castle {Nexus}) writes: >Was listening to National Public Radio earlier, and they had a little piece >on computers. They mentioned some sort of tests run at Los Alamos something >or the other. They said the fastest machine ran there was one made by >Thinking Machines, Corporation, and turned in a result of 5 BILLION computations >per second. Thinking Machines in Boston make the Connection Machine, which is (they claim) a 64K processor machine. However, every processor is a bit-processor, and there are 16 of those on a single custom chip, so it is closer to the truth to say it's a 4K processor machine, with a 12-dimensional hypercube architecture. And their latest model has a floating point accelerator per node so you have 4K fp chips. Now, if you take an 'algorithm' that has hardly any communication (vector plus vector, or so) 5Gflop is easy to believe. I seem to remember from a few years back that they can do inner products at 20Gflop, and slightly less trivial algorithms such as a Conjugate Gradient method at 5Gflop. (flop is floating point op per sec.). Victor.
abennett@athena.mit.edu (Andrew Bennett) (03/27/91)
In article <1991Mar26.015138.28898@csrd.uiuc.edu>, eijkhout@s41.csrd.uiuc.edu (Victor Eijkhout) writes: |> |> Thinking Machines in Boston make the Connection Machine, |> which is (they claim) a 64K processor machine. |> However, every processor is a bit-processor, and there are |> 16 of those on a single custom chip, so it is closer to |> the truth to say it's a 4K processor machine, with a 12-dimensional |> hypercube architecture. And their latest model has |> a floating point accelerator per node so you have 4K |> fp chips. Now, if you take an 'algorithm' that has hardly |> any communication (vector plus vector, or so) |> 5Gflop is easy to believe. I seem to remember from |> a few years back that they can do inner products |> at 20Gflop, and slightly less trivial algorithms such |> as a Conjugate Gradient method at 5Gflop. (flop is |> floating point op per sec.). |> |> Victor. Also, you can only use a Connection Machine (CM) on a limited (but important) class of problems; those that can use fine-grain parallelism. i.e. if you can break your simulation into lots & lots of little routines (fluid flow and finite element analysis are the classic examples), then the CM is perfect for you. If, on the other hand, your job is a complex series of calculations on a limited number of loops (physics has lots of these kind of problems), then the CM won't be very useful to you. An interesting fact about the Los Alamos tests: There were three tests run on the supercomputers, but thinking Machines only competed in one of them. It's kind of like Edwin Moses (the hurdler), entering the Decathalon and then only competing in the hurdles part. Hardly indicative of his overall abilities... Hedge your bets, buy a CM _and_ a Cray! -Drew -- Andrew Bennett MIT Network Services abennett@mit.edu MIT Room 11-124H abennett%athena@mitvma.bitnet 77 Massachusetts Ave. Phone: (617) 253-7174 Cambridge, MA 02139 <Standard disclaimers apply> "In the Morning, Laughing Happy Fish Heads, In the Evening, Floating in the Soup!"
rdippold@cancun.qualcomm.com (Ron Dippold) (03/27/91)
In article <2480@umriscc.isc.umr.edu> mcastle@mcs213e.cs.umr.edu (Mike Castle {Nexus}) writes: >Was listening to National Public Radio earlier, and they had a little piece >on computers. They mentioned some sort of tests run at Los Alamos something >or the other. They said the fastest machine ran there was one made by >Thinking Machines, Corporation, and turned in a result of 5 BILLION computations >per second. > >Now, since the news show is not all that technically knowledgable, I assumed he >meant 5000 MIPS , as opposed to 5000 different computations. > >Does anyone have any more information on this?? What test were run? What >machine is it?? How much is it? When can I get one? ;-> > >Rather dumbfounded by these results, They are likely talking about the Connection Machine, a massively parallel computer that uses up to 65536 processors running simultaneously. That number doesn't sound unreasonable. And they probably did mean MIPS... To give you an idea, the Cray III is specced to run at 16 Gigaflops, last I heard of it.
tighe@convex.com (Mike Tighe) (03/27/91)
In article <2480@umriscc.isc.umr.edu> mcastle@mcs213e.cs.umr.edu (Mike Castle {Nexus}) writes: > They said the fastest machine ran there was one made by Thinking Machines, > Corporation, and turned in a result of 5 BILLION computations per second. > Does anyone have any more information on this?? What test were run? What > machine is it?? How much is it? When can I get one? ;-> What I think you heard was an announcement that the CM-2 is the new world record holder for the Linpack benchmark. It clocked in at around 5.2 GFLOPS. The date of the announcement on the newswire was Mar 21. The announcement state that for further info you should contact: CONTACT: Martha Keeley of Thinking Machines Corporation, 617-234-5502 or Maura FitzGerald of Cunningham Communication Inc. for Thinking Machines Corporation, 617-494-8202. -- ------------------------------------------------------------- Mike Tighe, Internet: tighe@convex.com, Voice: (214) 497-4206 -------------------------------------------------------------