Advanced Micro Devices - Moderated (AMD) Message Board

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : Advanced Micro Devices - Moderated (AMD)

AMD 246.76

-0.5%

Nov 14 9:30 AM EST

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: Ali Chen who wrote (227010)	2/28/2007 3:14:37 PM
From: pgerassi	Read Replies (2) of 275872

Dear Ali: The major issue is that current Opterons are 50% behind Core2 in major, single-thread performance, as per most recent SPEC2006 (66% in INT, and 32% in FP). 20% or even 40% increase in IPC (which IPC do you/they meant BTW?) will not bring AMD any performance crown, with all associated disadvantages in marketplace. I looked and didn't see 66% in SPECint_2006 or 32% in SPECfp_2006. Here are the two comparable I found: spec.org spec.org Both are 3GHz and use Linux and non Intel compilers. Opteron 256 (K8E) with RDDR 3200 and Xeon 5160 with FBDIMM 667. Opteron got 13.3 and Woodcrest got 16.3. That's only a 23% advantage for C2D with most large score differences on cache happy subtests. A 20% IPC increase puts it practically on par and because this is an older K8, the bigger BW of DDR2 5400 or 6400 will help some more. A 40% IPC increase and Woodcrest is well behind. For SPECfp_2006, these are the two I found: spec.org spec.org Both are 3GHz use Linux and non Intel compilers. The Opteron is a older K8E (256) and uses RDDR 400MHz while the Woodcrest uses FBDIMM 667MHz. Opteron got 13.2 and Xeon got 15.8. That is a 20% advantage for C2D. Again the faster RDDR2 will help Opteron K8H some. But a 70% IPC improvement will bury C2D. How could C2D make up a 42% IPC deficit? I didn't even use Sun's Studio autoparallel compiler results which place K8E only 7% behind C2D. At a 70% increase in FP for K8H over K8F, C2D would be a daunting 58% behind. And by the time you equalize TDPmax between the two (including of course the TDPmax of the four FBDIMM controllers and FSB of the NB into Woodcrest and Cloverton), K8H may have a higher clock rate. 2 80W TDPtyp Clovertons run only 2.33GHz and then you add the 30W TDPtyp of the 4 FBDIMM controllers and the FSB to match 2 95W 2.3GHz Barcelonas. Xeon uses a little more power because its standard is lower than Barcelona. With 2 130W TDPtyp 2.66GHz Clovertons and 30W TDPtyp for the FBDIMMs and FSB yield 290W TDPtyp. All we know of is a speculated 2.5GHz 120W TDPmax Barcelona and 2 of them use 240W versus 290W for the Clovertons. Thus Clovertons uses 21% more power at 7% higher clock than Barcelonas. So Barcelona will take the crown when TDPs match. Even without that, it will likely take the crown anyway. Pete

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next