Sujet : Re: 44GB SRAM on a single chip
De : mitchalsup (at) *nospam* aol.com (MitchAlsup1)
Groupes : comp.archDate : 13. Mar 2024, 22:37:06
Autres entêtes
Organisation : Rocksolid Light
Message-ID : <96a1b5625acdfa0c8ac3ca3b813ca84f@www.novabbs.org>
References : 1 2
User-Agent : Rocksolid Light
Michael S wrote:
On Wed, 13 Mar 2024 19:51:34 GMT
scott@slp53.sl.home (Scott Lurndal) wrote:
Viz. earlier discussions related to memory speeds,
here's a single chip (wafer-sized) with just under
a million cores and 44GB of SRAM. Four trillion
transistors. 21PB/s memory bandwidth. 23kW.
https://www.theregister.com/2024/03/13/cerebras_claims_to_have_revived/
You were talking about 1ns latency then. The latency on "chip" like that, corner to corner, would be measured in
microseconds, at best. Quite possibly, over 10 usec.
A MECL 3 chip could deliver 1 ns latency and 1 ns edge speed
in a 16-pin DIP.
An ECL 10K gate with 1,000 gates with 0.5ns gates inside still took 4-5ns
simply to go from input pin on one side of the package to an output pin
on the other side with no logic being performed !! This is not a gate
speed problem, but a wire delay problem.