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: Scott D. who wrote (19126)	11/15/2000 7:54:43 AM
From: fyodor_	Read Replies (1) \| Respond to of 275872

<Scott: From reading the public documents on the Intel site, it appears that the Pentium 4 gains the ability to operate on two 64-bit (double precision) floats in parallel.> Yes, that's what I gathered from the Developer's Manual as well. I'm just still in shock over the boost that the PIII gets from the Intel compilers. With gcc or MSVC, the Athlon completely and utterly dominates the PIII on double precision code. This is to be expected if you actually look at the properties of the Athlon FPU pipeline (latency and throughput of dp fp instructions are much, much better on the Athlon). I wasn't able to find a detailed description of the SSE2 dp fp instructions (latency and throughput, along with what you can run while a given instruction is executing, another point where the Athlon dominates the PIII). In all likelihood, SSE2 is significantly better than what an Athlon can do. This should give Intel an unsurmountable lead in SPECfp (and in "real" dp floating point performance as well!!), at least until such a time as AMD introduces the Hammer. Although AMD refuses to comment on it now, they have previously stated that the Hammer series would support the dp fp instructions of SSE2. -fyo