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: Haim Barad who wrote (74987)	10/11/1999 12:37:00 PM
From: Goutam	Read Replies (2) \| Respond to of 1576274

Haim, re:< Most applications will query for processor type and use a processor specific code (if desired).> Thanks for a very interesting info. But, my earlier post was in reply to spec scores + prefetch inst. Does your statement also hold true for the presumably new compiled spec_code, used by Intel to calculate the new PIII's SpecInt95_base and SpecFP95_base? TIA Goutama

To: Haim Barad who wrote (74987)	10/11/1999 12:40:00 PM
From: vince doran	Read Replies (1) \| Respond to of 1576274

Haim Barad: If it should prove true that the prefetch operation yielded very large performance improvements for both Athlon and CUmine, and assuming both processors could use the same opcode for that particular operation, would it make sense for MS to incorporate that particular optimization into its compiler, thus allowing the generic compiler to optimize for both players? Or would the lack of SSE support in some chips prevent such a generic application? Thanks, Vince