ISSCC08: 45 nm Cell is 115mm²consumes less than 20 watts

[ADEX]

Do you have a source to support that? Is it at 3.2 GHz?

All I find are estimates of about 80 W at 4 GHz and 1.2 V, like this one. They are all based on this ancient graph from the 2005 ISSC presentation of the 221 mm2 Cell prototype.

The 110W figure is from IBM, I first heard it at a conference a couple of years back.
but a more official source is here (pg 14):

http://www.power.org/resources/devcorner/cellcorner/hpcspe.pdf

It was originally estimated to run at 60W at 0.9v. The actual chip used 1.1v due to SRAM stability problems which, when solved at 65nm gave a big power usage drop.

 

[Crossbar]

The 110W figure is from IBM, I first heard it at a conference a couple of years back.
but a more official source is here (pg 14):

http://www.power.org/resources/devcorner/cellcorner/hpcspe.pdf

It was originally estimated to run at 60W at 0.9v. The actual chip used 1.1v due to SRAM stability problems which, when solved at 65nm gave a big power usage drop.

Thanks that makes the 20 W statement very dubious, indeed. Still 35-40 W is not bad either.

@FutureCTO, I cannot make head or tail from "2 port 512 data bit controller", what are you talking about?

 

[The Seventh Taylor]

Can anybody tell the die size of the 65nm RSX? I've only been able to find some sporadic figures about the 90nm RSX (varying from 230 to 258 mm2).

Also, has anybody seen any die shots of either RSX? I could find a picture of a related GPU but not precisely RSX.