Silicon Investor (SI) -- The First Internet Community

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) -- Ignore unavailable to you. Want to Upgrade?

To: Ali Chen who wrote (227010)	2/28/2007 2:14:17 PM
From: Tenchusatsu	Read Replies (1) \| Respond to of 275872

Ali, > SPECrates are not visible or sensible to general public I was waiting for someone to mention this. The two problems I have with SPECrate are: a) The results are all over the place. Two similar systems can display widely varying results. b) It's a poor correlation to real-world multithreading and multitasking. At least SPEC (not to be confused with SPECrate) is useful for microarchitectural analysis, especially when it comes to single-threaded IPC. Tenchusatsu

To: Ali Chen who wrote (227010)	2/28/2007 3:14:37 PM
From: pgerassi	Read Replies (2) \| Respond to 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

To: Ali Chen who wrote (227010)	3/1/2007 2:39:14 AM
From: Petz	Read Replies (1) \| Respond to of 275872

re: <<"All I assumed was a 20% increase in IPC">> <John, you are focusing on a narrow range of processor's applications. SPECrates are not visible or sensible to general public, where the bulk of PC sales have been and always will be. 4- or 8-16-way servers bring relatively small volume of CPU sales,> 2 way servers are the lifeblood of the server market and always will be. The numbers on spec.org prove that in CFP2000_rate, Intel will be WAY behind the Barcelona. THEY ONLY HAVE A FREAKIN 19% LEAD WITH FOUR TIMES AS MANY FPU'S -- 114 vs. 96. That's an 8-way score vs. a 4-way score. Xeon doesn't have a prayer of a chance in CFP2000_rate. SPECrates are not visible or sensible to general public, You are correct, hardly any "general public applications" can utilize 4 cores. So whay's your point? CFP2000 rate and CFP2006 rate are designed to utilize modern multiprocessors efficiently. The fact that Intel does so poorly at these benchmarks only points to the fact that when games and graphics software are written to take advantage of 4 processors, Intel CPU's will be choking on their FSB, and AMD processors will not. it is inconsequential to focus on little possible advantages the current Barcelona could theoretically bring. I would estimate that 1/3 of AMD's CPU revenues were from the server market for most of 2006. 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). Single thread performance is totally irrelevant in the server market and the desktop market, what on earth are you talking about? 66% in INT Not even correct. Highest CINT2006 is a dual core C2 Extreme 2.93 GHz that got 18.5. A 2.6 GHz DC Opteron got 12.9. Even with the clock speed advantage and AMD penalized for registered DDR2, it's 43%. 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. In dual socket CINT2006_rate, a 10% increase in IPC over K8 core will give AMD the performance crown with a 2.3 GHz Barcelona vs. a 2.66 GHz Xeon. 4-way (2x 2.8 GHz) CINT2006_rate is already at 51.7 spec.org Derate by 2300/2800 for lower clock speed (though reduction is never that much) -- 42.5 Increase by factor of 1.8 for doubling number of cores -- 76.4 this is more than justifiable -- going from single to dual core on a 4-socket system goes from 46.9 to (93.1, 97.6) on (HP DL585, Sun Blade result, Tyan result, sorry I couldn't find two results with identical hardware, but using a factor of 1.8 instead of 2.0 seems quite pessimistic on my part seeing as AMD's CINT2006_rate numbers scale almost linearly in number of CPU's OK, now add my 10% for L3 cache and the long laundry list of core improvements, and we are up to 84.1. Guess what a pair of the fastest available Clovertown's got in CINT2006_rate? 82.2 Q.E.D. Petz