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: wbmw who wrote (245362)	1/3/2008 12:11:00 AM
From: pgerassi	Read Replies (1) \| Respond to of 275872

Wbmw: Your assertions are to test quad core with predominantly single threaded tasks. Or stuff that fits in cache. As you have shown that you don't know what is desired by HPC folks, your assertions leave much to be desired. More games are going for more AI and PhysX type concurrent threads because that is demanded by gamers. Too bad, Penryn and Conroe are bad at that kind of thing. The unganged dual channel IMC and 128 bit FPUs of K10 help greatly at both of those. Pete

To: wbmw who wrote (245362)	1/3/2008 2:40:23 AM
From: Petz	Read Replies (1) \| Respond to of 275872

You still didn't explain why QX loses to Phenom in UT3. You listed some non-reason strawmen, such as "code optimizations for Phenom." How about this as a reason: UT3 code runs faster on Phenom, by a long shot, clock for clock, than it does on QX9XXX or QX6XXX. The same thing is true for MainConcept H.264 encoding, where a lowly $240 95 watt Phenom 9600 outperforms a $1,000 130 watt QX6700. lostcircuits.com The same is true for F.E.A.R., where $240 Phenom 9600 gets higher frame rates than the $1,000 QX6700. lostcircuits.com Petz