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: semiconeng who wrote (4634)	8/11/2000 6:23:30 PM
From: survivin	Read Replies (1) \| Respond to of 275872

Must've touched your sensitive spot Sorry. I noticed you were so infuriated by my failure to post the "whole" article that you addressed it to mani -- leave him be, he has taken enough flak lately. Btw, I always expect everyone to read the whole article hence the ellipses signifying some content not included in the post. Also, the part I did quote wasn't entirely pro AMD since it included the infamous "IF". Relax semi, your job isn't in jeapordy yet, but I suggest you guys start putting in some quality ot. Those guys in the rear view mirror are getting bigger every day.

To: semiconeng who wrote (4634)	8/11/2000 7:09:15 PM
From: Gopher Broke	Respond to of 275872

Intel said the Itanium and McKinley will run 32- and 64-bit programs seamlessly on the same chip hardware, using a bit switch to send 32-bit instructions to on-chip registers designed to operate in a compatibility mode. Waxman said there is no loss of performance when operating in the native 32-bit mode. I guess Intel aren't sure whether it is a native or a compatibility mode :^) It is not exactly a quantifiable claim is it? "No loss of performance, so it will run 32 bit apps as fast as 64 bit apps"? Unlikely. "No loss of performance when compared with a 386"? Hehe. OK, so we might guess at "no loss when compared with an equivalently clocked PIII", but then it seems Itanics have to be clocked slower than a comparable x86 (ie one produced on a comparable process). I don't think Intel have announced production Itanic clock speeds yet(still at 800 MHz?), but looking at the IA64 roadmap, does the bullet "Significant increase in frequency - beyond GHz" for Madison (.13 shrink of IA64, slated for mid 2002) mean that McKinley is not significantly "beyond GHz"? If so then how will x86 performance of a McKinley 1.2 compare with that of a Sledge 2.0? Or will Intel be using some of that scarce .13 FAB capacity (which they are desperate to use to make Willy competetive) to make McKinley competetive as well? That would definitely be the end of the road for AMD. Better sell off all your shares now guys.

To: semiconeng who wrote (4634)	8/11/2000 7:58:36 PM
From: AK2004	Read Replies (1) \| Respond to of 275872

SemiconEng now, boys, stop fighting. Semi (can I call you that) provides a different point of view and it should be appreciated. Well, I have one of those nasty questions regarding "Intel said the Itanium and McKinley will run 32- and 64-bit programs seamlessly on the same chip hardware, using a bit switch to send 32-bit instructions to on-chip registers designed to operate in a compatibility mode. Waxman said there is no loss of performance when operating in the native 32-bit mode. 1) what does "will run 32- and 64-bit programs seamlessly" mean? I can say the same thing about alpha. 2) "there is no loss of performance" That another one for the history books. No loss in performance as compared to what - itself? Regards -Albert

To: semiconeng who wrote (4634)	8/11/2000 8:54:30 PM
From: milo_morai	Read Replies (1) \| Respond to of 275872

Semicon.. there will be a big difference Itanic@ 800Mhz vs. Sledgehammer @ 2Ghz. Intel still having problems getting Itanic to yield above 800Mhz. Milo

To: semiconeng who wrote (4634)	8/11/2000 9:22:40 PM
From: kash johal	Read Replies (3) \| Respond to of 275872

Semiconeng, I think you raise a good point. It is very unclear to most everyone what the relative performance will be. If we assume that Merced runs at 800Mhz tops with todays Intel 0.18 process it gives us a figure of merit. Merced uses EPIC so IPC is much higher than current x86 approach. Max is around 8 : min say 2x AVG of 4x for typical due to compiler difficulties etc. Thats maybe equivalent to 3.2Ghz 64 bit clocks. If we assume a hammercore - modified Mustang tops out at 1.2Ghz with AMDs current 0.18 process. In a broad brush look -- with dual CMP that gives us 2.4Ghz 64 bit clocks. Now obviously both CPU's will scale as process/design improves. The key is that Sledgehammer may well be 20-30% slower. I can't see it being 2-3x slower. However it will be much cheaper. It will also add the legacy s/w support. It certainly has potential to be a winner in displacing the current Xeon 2/4/8 CPU space and blowing it out of the water. I think AMDs plan has some merit. The S/W is the driving factor as it is usually the most expensive part of the equation when coupled with its attendant support issues. regards, Kash