Re: Playstation 2 has as much FPU power as Merced?

Article View: comp.arch

Article #23423

#23423

From: Andy Glew
Date: Thu, 04 Mar 1999 00:00

9 lines
1405 bytes

> I'd not be amazed if it actually achieved that - what they seem to be
> claiming is one-tick-throughput matrix-vector multiply, which is
> probably achievable. Essentially it's a 300MHz geometry accelerator.

Prediction: within 5 years, a single instruction that performs a 4-vector
by 4x4-matrix multiply, of 32 bit FP numbers, will be as common as
vector FP and integer (MMX, KNI, 3DNow) are now.

Probably less than 5 years, but I want to have a bit of slack.

Technical Details

Message-ID: <36DF4F87.FFDEFF0C@cs.wisc.edu>

Path: arc1-ca.pugleaf.net!unknown!not-for-mail

References: <7bjr4a$cq2$1@nnrp1.dejanews.com> <36DDB3AB.378F5C87@igs.net> <7bkjm8$72f$1@news.ox.ac.uk>

Show Full Headers

Complete Article Headers

X-Google-Language: ENGLISH,ASCII-7-bit
X-Google-Thread: 110292,e8b7abf312c36c04
X-Google-Attributes: gid110292,public
X-Google-Thread: 1024aa,e8b7abf312c36c04
X-Google-Attributes: gid1024aa,public
X-Google-Thread: 105ad2,e8b7abf312c36c04
X-Google-Attributes: gid105ad2,public
X-Google-Thread: 102b75,e8b7abf312c36c04
X-Google-Attributes: gid102b75,public
From: Andy Glew <glew@cs.wisc.edu>
Subject: Re: Playstation 2 has as much FPU power as Merced?
Date: 1999/03/04
Message-ID: <36DF4F87.FFDEFF0C@cs.wisc.edu>
X-Deja-AN: 451410177
Content-Transfer-Encoding: 7bit
References: <7bjr4a$cq2$1@nnrp1.dejanews.com> <36DDB3AB.378F5C87@igs.net> <7bkjm8$72f$1@news.ox.ac.uk>
To: Thomas Womack <mert0236@sable.ox.ac.uk>
X-Accept-Language: en
Content-Type: text/plain; charset=us-ascii
Organization: U Wisc CS (& Intel)
Mime-Version: 1.0
Newsgroups: comp.arch,intel.etc,comp.games.development.industry,comp.sys.intel

Reply to Parent Message