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.

Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?

To: Scumbria who wrote (93417)	2/15/2000 11:45:00 PM
From: Jim McMannis	Read Replies (1) \| Respond to of 1570894

RE:"The Willamette demo is starting to look like a big sham. Where did the 3.0 GHz number come from? In the old days, Intel was very honest with their product announcements, and AMD was always in question. The roles seem to have reversed. AMD is becoming the trusted company, and Intel appears desperate." The 3 Ghz integer number came from Anand and was immediately embraced by PB, Ten and EP...of course... Jim

To: Scumbria who wrote (93417)	2/15/2000 11:52:00 PM
From: Elmer	Read Replies (1) \| Respond to of 1570894

Re: "In the old days, Intel was very honest with their product announcements, and AMD was always in question. The roles seem to have reversed. AMD is becoming the trusted company, and Intel appears desperate." You're the one who is desperate Scumbria and I am embarrassed on your behalf. EP

To: Scumbria who wrote (93417)	2/15/2000 11:59:00 PM
From: Saturn V	Read Replies (1) \| Respond to of 1570894

Scumbria, Ref Where did the 3.0 GHz number come from? Process Boy posted a link to a prelim. version of Willamette Programers Manual. developer.intel.com Intel is still playing its cards close to its vest, and disclosing precious little. No disclosures about numbers of integer units, floating point units, instruction execution time etc. But it does disclose the following architectural aspects: A. The Integer Unit runs at 2x the processor clock. B. The presence of a trace cache to improve performance on branches. C. Describes the new SIMD instructions, and new Cache Control Instructions. I have not studies them in detail, except to note that SIMD has been extended to double precision operands ( a painful omission on Pentium III). I feel that the performance may be even higher than we think, and Intel will not disclose these details until late Q2. Some AMD faithful still appear to be in denial.

To: Scumbria who wrote (93417)	2/16/2000
From: kapkan4u	Read Replies (3) \| Respond to of 1570894

1.5GHz core, 3GHz ALUs numbers seem to be solid. I spoke to one of the Willamette designers about that. There are rumors swirling around that it was a specially cooled part built with the experimental 0.13 process. Kap

To: Scumbria who wrote (93417)	2/16/2000 1:44:00 AM
From: Charles R	Read Replies (1) \| Respond to of 1570894

Scumbria, <The Willamette demo is starting to look like a big sham.> Sham is too strong a word but so far it looks to me like Wilamette is still a 1.5G/750M processor being touted a 1.5G processor. <Where did the 3.0 GHz number come from? > I am interested in this too. <In the old days, Intel was very honest with their product announcements, and AMD was always in question. The roles seem to have reversed. AMD is becoming the trusted company, and Intel appears desperate.> As much as the MHz numbers sound confusing, I don't see much desperation on Intel's part here. Clearly 20-stage pipeline is nothing to sneeze at. MHz sells and Intel will advertize the Integer MHz - most probably in 2001. Chuck