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: j3pflynn who wrote (240175)	9/10/2007 2:14:13 PM
From: dougSF30	Read Replies (1) \| Respond to of 275872

I fear I've mis-estimated your evenhandedness on this board. Funny, I have no fear that I've mis-estimated your AMD bias on this board. :)

To: j3pflynn who wrote (240175)	9/10/2007 3:03:49 PM
From: eracer	Respond to of 275872

Re: And you don't think that server systems would require just a little more groundwork than being able to bench a Phenom? I sure hope you were being facetious, otherwise, I fear I've mis-estimated your evenhandedness on this board. AMD couldn't get 2GHz Barcelona out in a timely manner for what was supposedly one of their most important product launches ever. Given that, it is difficult to believe AMD is distributing 3GHz Phenom samples ~6 months before launch. Rahul has been somewhat of an AMD partisan in the past. It is not hard to imagine that he would talk up Phenom performance based on AMD's word alone. Since you believe Rahul has a 3GHz Phenom, and you apparently believe Rahul when he says it kicks the crap out of any current AMD or Intel CPU, how much faster do you believe 3GHz Phenom X4 will be on average compared to the current 3GHz Core 2 Extreme QX6850? 10%? 20%? 30%? How about in a 3GHz dual-core comparison? The Anandtech K10 vs. K8 desktop benchmarks did not look that promising for K10. For example, replacing two K8 Opteron CPUs with one K10 CPU for a 16.2% increase in Oblivion performance looks pretty good at first glance. However, AMD two-socket systems often don't perform as well as their single-socket desktop counterparts in single- or dual-threaded benchmarks. An earlier Anandtech review showed that a single 3GHz A64 X2 6000+ was 17.1% faster than a dual 3GHz FX-74 system. So replacing two K8s with one K8 increased performance more than replacing two K8s with one quad-core K10. anandtech.com I do realize K10 performance is likely to scale better than Core 2 as frequency is increased. Hopefully newer steppings or chipsets can improve performance.