SI
SI
discoversearch

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 (40331)10/29/1998 3:15:00 PM
From: Tenchusatsu  Read Replies (1) | Respond to of 1573540
 
<Certainly the x86 architecture was a brilliant concept. The farsighted architects at Intel recognized that no program would ever be larger than 64K, and 640K would be the maximum amount of memory necessary for any computer. The entire x86 instruction set was a stroke of far-sighted genius as well.>

You know, it's amazing that about five or six years ago, people were predicting the downfall of x86 and CISC as PowerPC, with its nice and clean RISC architecture, takes over the world. No one counted on Intel to push CISC so far. In that sense, the superscalar Pentium was a milestone in carrying the aging x86 architecture into a new realm of performance.

Now it seems that implementing the x86 architecture in a CISC-to-RISC style is elementary as AMD, IDT, Rise, and Transmeta are all following the same trail that Intel blazed with Pentium and Pentium Pro. So, Scumbria, it's kind of strange that you would ridicule the short-sightedness of the x86 architecture knowing that these days, it's a moot point.

Tenchusatsu



To: Scumbria who wrote (40331)10/29/1998 10:01:00 PM
From: Paul Engel  Read Replies (2) | Respond to of 1573540
 
Scumbria - Re: "The entire x86 instruction set was a stroke of far-sighted genius as well. "

Other than small embedded controllers, x86 CPUs are the highest selling in history - by a long shot.

I guess the instruction set was just fine.

Lsst I heard, nobody ever came up with an algorithm that couldn't work on x86 instructions.

By the way, Scumbria - Intel had nothing to do with the 640K limit on the first IBM machines. That was IBM's DESIGN DECISION- they chose to use the memory above 640K for the graphics adapters and BIOS.

I suppose you think UNIX was a kludge as well - since it was written as a 16 bit OS to begin with.

Paul