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: Elmer who wrote (74991)10/11/1999 12:59:00 PM
From: Tenchusatsu  Read Replies (2) | Respond to of 1576323
 
Elmer, it is important to note that in the test where Coppermine 600EB got 12% improvement in SPECint95_base and 20% in SPECfp95_base over a Katmai 600B, *both* processors were benefitting from the SSE optimizations.

In my opinion, we'd see similar percentages if optimizations weren't used. Coppermine is indeed faster than Katmai clock-for-clock.

Tenchusatsu



To: Elmer who wrote (74991)10/11/1999 1:09:00 PM
From: Tenchusatsu  Respond to of 1576323
 
Elmer, here are the Athlon scores from the AMD foils at MPF:

Athlon 700 (current system)
---------------------------
SPECint95_base: 32
SPECfp95_base: 24

Athlon 700 (enhanced system)
----------------------------
SPECint95_base: 35 to 37.5
SPECfp95_base: 34 to 41

Current system: Production level reference motherboard Rev.
B w/ AMD-750 chipset, PC100 SDRAM, Windows NT 4.0 SP5.
(Motherboard is not commercially available, although I doubt
that makes a difference.)

Enhanced system: "with 266 bus and projected compiler and
prefetch optimizations" I think the "266 bus" implies that
the new Irongate chipset with DDR SDRAM will be used here.

Tenchusatsu