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: Joe NYC who wrote (98319)	7/22/2003 12:14:06 PM
From: Dan3	Respond to of 275872

Re: Intel will change the code name to Phoenix. But, as they say in Arizona, its dry heat. (which makes me I wonder about Tejas). It doesn't look like there is a Bangor on P4 roadmap. LOL!!! No Anchorage, either!

To: Joe NYC who wrote (98319)	7/22/2003 1:04:03 PM
From: Joe NYC	Read Replies (1) \| Respond to of 275872

xbitlabs has a review of Asus SKN8X + Opteron 144. Not very flattering. They use DDR-333 Registered, whild AMD Zone used DDR-400 Registered. There are some significant difference in results, and in what was tested. I would like to see a full fledged review by Anand, Aces or Lost Circuits, who I think are the best at benchmarking and interpreting results (but Chris Tom of AMD Zone and xbit labs are getting better). I would like to know the difference between DDR-333 and DDR-400 (of course Registered, since this is Opteron, hopefully both at the same Cas 2.5). I think the fastest available memory on both Opteron/A64 and P3 will help highlight the advantage AMD64 chips have in latency. It is weird that Opteron is crippled this way, in that it cannot use the currently fastest memory on the market. Think of it this way. Suppose Opteron and P4 are people who go to work, which involves getting to the bus stop, waiting for the bus and than taking the bus. Suppose both are in a hurry, so they run (the same distance). Opteron is a faster runner and makes it to the bus stop in minutes, P4 makes it there in 10 minutes. They both take a bus. Suppose they both take a bus that takes 20 minutes. So it took Opteron 25 minutes, and P4 30 minutes, or 20% longer. Now suppose they take a faster bus that takes only 10 minutes. So Opteron total is 15 vs. P4 total of 20, which is 25% longer than Opteron. As is, Opteron takes the bus that takes 20 minutes to get to the destination vs. P4 bus that takes 10 minutes, and the fact that Opteron runs faster (has better latency) is completely lost by ths slow bus (slower memory). Anyway, the brightest side of Opteron is game performance (which confirms what nVidia rep said, that Opteron is the best game machine). 2 GHz CPU will most likely extend the lead, and if there is a dual channel Athlon 64 with DDR-400 Cas-2, I dont think anything will be able to touch it in games. Well, we never know, but Tom Pabst may again become an AMD enthusiast. (He always cheers for the CPU that can achieve highest Quake frame rate). Finally, on single vs. dual channel Opteron (which xbit labs tested), some results show no difference, some show differences of up to 15% (SPECViewPerf), while games are somewhere in between. Joe