Re: COMP: Physics and computation: two papers

Max More (maxmore@primenet.com)
Wed, 18 Dec 1996 11:46:37 -0700 (MST)


At 04:23 PM 12/18/96 +1000, Mitch wrote:
>
>(iii) While I'm talking about computers, a comment on Intel's
>announcement that it's built a teraflop (trillion operations per second)
>computer (http://www.intel.com/pressroom/archive/releases/cn121796.htm):
>wasn't this achieved by a computer in Japan earlier in 1996?

According to what I read, no. The previous record was about a third of that
speed. As reported in the Advances section of Extropy #17, the record as of
April of this year was a mere 281 gigaflops. It may have gone a bit higher
between then and the Intel announcement. I believe the news story I read
said the Japanese record was around 360 gigaflops.

The completed Intel machine (made entirely from Pentium Pro microprocessors)
will be several times faster than the announced result. A 10-teraflops
machine is expected by 2001. The ASCI folks reckon we may ahve a
500-teraflops machine by 2005. If fast hardware was all that was needed,
according to Moravec we should have uploading in just a few years. But of
course that's the *easy* part.

Max

Max More, Ph.D.
more@extropy.org
http://www.primenet.com/~maxmore
President, Extropy Institute, Editor, Extropy
info-exi@extropy.org, http://www.extropy.org
(310) 398-0375