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 : Intel Corporation (INTC) -- Ignore unavailable to you. Want to Upgrade?

To: Mary Cluney who wrote (138378)	6/29/2001 9:12:06 AM
From: Dan3	Read Replies (2) \| Respond to of 186894

New P4 Xeon test - The key differences revolve around packaging and dual-CPU support. The standard Pentium 4 is built into a 423-pin package, whereas the Xeon comes wrapped in a 603-pin package. The added pins carry the signals needed for cache coherency between the two CPUs. and summary: Test Analysis In most cases, the performance of the Xeon proved something of a disappointment. For example, the Content Creation Winstone 2001 score was nearly 63% faster on a Pentium 4 1.7GHz system than the Xeon dual CPU rig. We tested and retested, and came up with the same results. We are at a loss to understand why the Tyan system performed so poorly relative to the P4 1.7GHz system. We are investigating this further with Tyan, and will report our findings as soon we understand what's happening. Note that the Pentium 4 only had 256MB of RAM to boot. Even the streaming memory tests ran slower. At first, we thought the CPU wasn't really running at 1.7GHz, but several quick diagnostic checks disabused us of that notion. The one bright spot was Lightwave 6.5 in dual CPU mode. The time to render one frame of the scene was nearly cut in half. To be fair, we were running an early BIOS, and its possible that improvements to the BIOS will improve memory throughput--we've sent his happen before, and the change can often be substantial. What we hope is that there isn't too much overhead being introduced by the 82803AA memory repeater hubs. extremetech.com Hey Paul - more clock throttling?

To: Mary Cluney who wrote (138378)	6/29/2001 9:46:08 AM
From: Tomcat	Read Replies (1) \| Respond to of 186894

Re: I am pretty sure that 1M servers do not equate to 1M processors (more processors than servers) - the ratio is probably much, much higher. Just FYI from my experience, most Intel 4-way servers ship with 1 or 2 processors in them. The same with 8-way servers. The highest volume servers are probably 2-way servers with one processor. I don't know how many of these machines get upgraded with extra processors later. So the ratio is higher, but not much, much higher.

To: Mary Cluney who wrote (138378)	7/2/2001 4:22:59 AM
From: Amy J	Read Replies (2) \| Respond to of 186894

Hi Mary, RE: "I am pretty sure that 1M servers do not equate to 1M processors (more processors than servers) - the ratio is probably much, much higher." I didn't mean to imply it was 1:1. Was just loosely saying, I think there's some good cheer for the eventual future in that there's enough market opp from various sources (this being only one of them), to expect a nice run up et al at some point in the future. Could be easy to lose sight of that in the current stock doldrums. It surprises me there aren't more reports on total server market opp, given the size and the potential impact to INTC. Regards, Amy J