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: bacchus_ii who wrote (8592)	9/14/2000 7:59:44 PM
From: Petz	Read Replies (1) \| Respond to of 275872

Gottfried, re:<Any double precision floating-point application is a danger for AMD because SSE2 handle double precision number. Auto-Cad is the most important one I think. If Mustang can do double precision we are safe here.> Actually, the Athlon FPU is double precision and it is superior to the PIII FPU and the P4 FPU. The problem is that the standard x86 instruction set makes it difficult to write floating point code without a lot of redundant, unnecessary loads and stores to memory. SSE2 gets around that problem by defining a new instruction set for double precision floating point. So, if double precision floating point code does a lot of memory access, SSE2 with a poor FPU may be faster than Athlon's fast FPU. I don't think Mustang will have any additions to 3DNow to bring an equivalent capability for improving floating point code efficiency. I don't know if AutoCad is one of the apps that can benefit a lot from SSE2. Petz