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: Paul Engel who wrote (37068)	9/16/1998 2:48:00 AM
From: Elmer	Read Replies (1) \| Respond to of 1571045

re: "Meanwhile, Intel's existing 32-bit processor roadmap will also move forward, with new devices scheduled for introduction up through McKinley's launch and beyond. And in a sign of what's to come on the desktop PC, the company demonstrated a Pentium II running at approximately 800 MHz. " WOW 800mhz!!!! As anyone who has followed Intel's processor demonstrations can remember, it is clear that todays demo is tomorrows product. The first one I remember was a 100mhz 486 demo, which was followed by 100mhz production not too long after. There was a 400mhz Pentium II demo last year and we have already surpassed that with 450mhz PII's now readily available. Hey but don't worry, AMD is now ramping up 350mhz k6's and hope to get to 400mhz (maybe) late this year. Expect the gap between Intel and AMD to continue to widen. Today it is 100mhz, tomorrow ????? EP

To: Paul Engel who wrote (37068)	9/16/1998 1:32:00 PM
From: Petz	Read Replies (3) \| Respond to of 1571045

HA, HA, HA, Katmai is NOT double precision SIMD, its single precision, just like 3DNow! From the Intel developers forum: tomshardware.com Introduction of 8 new 128 bit = 4 x 32 bit wide single precision packed CPU registers, enabling the computation of 4 single precision* FP variables at the same time.* Tom is in error when he states that AMD's implementation is only capable of 2 single precision floating point ops per clock cycle. Perhaps the 3DNow! implementation can only do 4 ops/cycle on multiply-accumulates, but in real calculations, hearly all multiplies are followed by accumulates. From the AMD website: - Execution of up to two 3DNow! instructions per clock - Total of four floating-point calculations (add, subtract, multiply) per clock (Enables potential peak performance of 1.2 Gigaflops at 300MHz vs. potential peak performance of 0.3 gigaflops for 300MHz processors without 3DNow! technology) People are running off-the-shelf K6-2-350 CPU's at 450MHz right now in standard motherboards, not test systems and experiencing 1.8 GFlops of peak floating point performance. A 2 GFlop Intel system will be available in March? Wow, I'm really holding my breath. Petz