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: captainfreedom who wrote (227130)	3/1/2007 2:07:44 PM
From: j3pflynn	Read Replies (1) \| Respond to of 275872

captainfreedom - Perhaps. But how does it scale? How much will they have to bump up the clock to gain 10% performance?

To: captainfreedom who wrote (227130)	3/1/2007 5:04:44 PM
From: Petz	Read Replies (1) \| Respond to of 275872

It would take at least a 12.5% Clovertown clock jump to make up a 10% shortfall in SPECint. Both results on same IBM hardware, 8G RAM, 1066 FSB, submitted February 27, 2007, 1 Xeon Clovertown, 4 cores SPECint2006 2.133 GHz 13.8 SPECint2006 2.400 GHz 15.2 Clock speed delta: +12.5% SPECint2006 delta: +10.1% For some reason, IBM hasn't published 2.533 GHz yet, let alone the 3 GHz some here are expecting "any day now." But SPECint2006 scores on the dual core 3 GHz Xeon 5160 are not encouraging. Xeon 5160 has exactly the same L2 cache available to a single core as the Clovertown, 4MB. Apple got 16.6 and Fujitsu got 16.9 for SPECint2006. These are only 9% and 11% higher than the IBM 2.4 GHz score above, despite a 25% jump in clock frequency. Based on those results, Intel will need a >3.33 GHz Clovertown to match the 2.3 GHz Barcelona. Petz