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: Maxwell who wrote (37413)	9/24/1998 1:28:00 PM
From: Paul Engel	Respond to of 1572171

Maxwell - Re: ". "You will not be disappointed", Atiq said." He should have said - ". "You will not be disappointed like you were for the past year and a half. " Or "This time it will be different - we hope". Paul

To: Maxwell who wrote (37413)	9/24/1998 1:50:00 PM
From: Paul Engel	Read Replies (1) \| Respond to of 1572171

Maxwell - Re: " The K7 will fix that and AMD will once again regain the leadership as the fastest CPU in the world. " Here's an interesting thought. The K7 will use DEC's Alpha chip set (EV6 ?) for the K7. Guess who is making these chip sets for DEC/Compaq ? That's right - INTEL ! Would you want your flag ship product to be dependent upon chip sets made by your fiercest rival? Paul

To: Maxwell who wrote (37413)	9/24/1998 7:42:00 PM
From: Elmer	Read Replies (2) \| Respond to of 1572171

Re: "The K7 will fix that and AMD will once again regain the leadership as the fastest CPU in the world. " For your information Hypster, AMD has never held that position, not even close. The K7 won't change that either. With all the mass desertions by AMD design engineers it will be a miracle if the K7 ever shows up in 1H99. EP

To: Maxwell who wrote (37413)	9/24/1998 10:14:00 PM
From: Ali Chen	Read Replies (2) \| Respond to of 1572171

Maxwell, <K6-2 and topped PII in 3D performance but still trailing under Winstone and NT benchmark. The K7 will fix that and AMD will once again regain the leadership as the fastest CPU in the world.> I think you need to be more accurate here. First, it could be fastest CPU for WINDOWS computing only. However, this is not quite simple to outperform current x86 engines. As you probably know, all the x86 code shrinks eventually to something like [MOV EAX, blah-blah], that's it. The whole sophistication of x86 compilers ends up in a MOV to basically 3 and half registers: any programmer's fantasy of attempted parallelism ends up in a MOV to EAX. Period. If all the ideas get grounded into this enormous sequential dependency, then there is not much you can do to increase CPU performance on typical x86 codes. Therefore, I would not expect a tremendous breakthrough relative to Pentium-II core on clock-by-clock basis. The frequency scalability may be a different story. Since MHz sells, so it be. The battle will continue. Intelopers will not go away overnight, unfortunately. Regards, - Ali