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: wanna_bmw who wrote (150816)	12/3/2001 4:35:10 PM
From: Joe NYC	Read Replies (1) \| Respond to of 186894

wbmw, They'll put the benchmarks up on big banners and wave them around both forums and claim how poor the performance of the Pentium 4 really is - and how Intel should be condemned for calling their chip 2GHz. Personally, I don't see the usefulness in an application that is so far removed from real life that it had to be pain-stakingly engineered to do what it was designed to do. I don't think there is much disagreement that P4 perform poorly on code that is not in the trace cache, well on the code that is in trace cache. I agree that this type of test is not that useful for real life, since it is totally synthetic. But if the decoder is in fact half speed and Kap can prove it with software test, the test would be worthwhile, and anybody interested in PC technology should welcome it. I have no idea how I would go about what Kap is trying to do, but some insight can be gained timing some code with with trace cache ON / OFF - if it can be turned off, which would simulate some of what the routine would do. Joe

To: wanna_bmw who wrote (150816)	12/3/2001 4:37:23 PM
From: Charles Gryba	Read Replies (1) \| Respond to of 186894

wbmw, I will agree with the way you phrased your argument unless this benchmark shows any resemblance to the real-life apps that we run. I want to see if the front-end of the P4 is responsible for the dismal performance that it displays when running our apps which are very branch-intensive. I have run the bench on a bunch of different P3's. I am waiting for the results from the P4. I 've sent the benchmark to the person who's using it. It won't be long now. Here are the P3 results: Coppermine 550 28 seconds Coppermine 1Ghz 18 seconds Dual Tualatin 1.26Ghz 13 seconds Tomorrow I should have MP and XP results as well as P4 results. C