How is TFP so fast?

Article View: comp.arch

Article #12391

#12391

From: Andre T. Yew
Date: Thu, 28 Jan 1993 03:04

9 lines
601 bytes

	Can someone say how SGI achieved its 300 MFLOPS/chip
rate in the TFP?  Is it too much to hope that it's
asynchronous (ala micropipelines)?

--Andre

-- 
             Andre Yew andrey@cco.caltech.edu (131.215.139.2)

Technical Details

Message-ID: <1k7igjINNpk6@gap.caltech.edu>

Path: arc1-ca.pugleaf.net!sparky!uunet!think.com!rpi!usc!elroy.jpl.nasa.gov!nntp-server.caltech.edu!andrey

Show Full Headers

Complete Article Headers

Path: arc1-ca.pugleaf.net!sparky!uunet!think.com!rpi!usc!elroy.jpl.nasa.gov!nntp-server.caltech.edu!andrey
From: andrey@cco.caltech.edu (Andre T. Yew)
Newsgroups: comp.arch
Subject: How is TFP so fast?
Date: 28 Jan 1993 03:04:51 GMT
Organization: California Institute of Technology, Pasadena
Lines: 9
Message-ID: <1k7igjINNpk6@gap.caltech.edu>
NNTP-Posting-Host: punisher.caltech.edu