Breaking News
News & Analysis

ISSCC: China eyes petaflops, IBM hits 5 GHz

2/22/2011 00:30 AM EST
9 comments
NO RATINGS
Page 1 / 3 Next >
More Related Links
View Comments: Oldest First | Newest First | Threaded View
krisi
User Rank
CEO
re: ISSCC: China eyes petaflops, IBM hits 5 GHz
krisi   2/22/2011 12:38:30 AM
NO RATINGS
18% of speed improvements by moving from 65nm to 45nm process node? That must be disappointing. Will we ever see 10 GHz processors? Kris

selinz
User Rank
CEO
re: ISSCC: China eyes petaflops, IBM hits 5 GHz
selinz   2/22/2011 7:30:33 PM
NO RATINGS
Mmm. I look at going from 4.4 to 5.2 as an impressive jump. Particularly with approximately the same power...

jederrick
User Rank
Rookie
re: ISSCC: China eyes petaflops, IBM hits 5 GHz
jederrick   2/22/2011 7:32:19 PM
NO RATINGS
Actually it is good to see an edging up on the frequency. The move to an out-of-order design (40% improvement) is a key advancement along with an increase of 18% in frequency. I would expect the frequency might edge up a little more over time with the same basic design, but the "step" function of 40% for OOE is the kicker.. I actually know something about both projects, ex-IBMer and ex-MIPS executive..

krisi
User Rank
CEO
re: ISSCC: China eyes petaflops, IBM hits 5 GHz
krisi   2/22/2011 9:02:07 PM
NO RATINGS
thank you Joel, sounds that 40% improvement due to out-of-order design is more important than 18% due to faster process. Can someone explain how out-o-order works? dr Kris

rick merritt
User Rank
Blogger
re: ISSCC: China eyes petaflops, IBM hits 5 GHz
rick merritt   2/22/2011 10:43:54 PM
NO RATINGS
Just to clarify, I believe it is 40% overall performance benefit from a combo of all technqiues used including out-of-order pipeline, 18% freq incrrease and etc.

rpcy
User Rank
Rookie
re: ISSCC: China eyes petaflops, IBM hits 5 GHz
rpcy   2/24/2011 2:05:20 PM
NO RATINGS
I strongly suspect Rick is right. Out of order techniques don't yield 40% perf improvements across the board, all by themselves. 20 - 25%, maybe. How well the compiler understands the new, complex microarch is another strong factor. After that you have cache design, bus design, policies on TLB usage, provisions for coherence, and how aggressive you were on lots of other things.

docdivakar
User Rank
Manager
re: ISSCC: China eyes petaflops, IBM hits 5 GHz
docdivakar   2/28/2011 11:09:15 PM
NO RATINGS
@RickMerrit: thanks for the writeup, didn't see you at the Computer History Museum for the 40th Anniversary of Spice event (most ISSCC attendees made it there!). I wonder why IBM isn't using their Power7 platform to push the clock speeds instead of the z196. The Power6 older generation was already clocking at 4.5GHz whereas Power7 had already reached 5.0GHz (8-core version?). The Power7 also has a L3 cache of 32Mb max. MP Divakar

Flash Poll
Radio
LATEST ARCHIVED BROADCAST
Join our online Radio Show on Friday 11th July starting at 2:00pm Eastern, when EETimes editor of all things fun and interesting, Max Maxfield, and embedded systems expert, Jack Ganssle, will debate as to just what is, and is not, and embedded system.
Like Us on Facebook

Datasheets.com Parts Search

185 million searchable parts
(please enter a part number or hit search to begin)
EE Times on Twitter
EE Times Twitter Feed
Top Comments of the Week