Formerly About Advanced Micro Devices Message Board

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

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: Paul Engel who wrote (37068)	9/16/1998 1:32:00 PM
From: Petz	Read Replies (3) of 1571100

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

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next