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: Scumbria who wrote (66985)	7/30/1999 5:33:00 PM
From: grok	Respond to of 1575273

RE: <Joey, Suppose that Intel built an SSE version of SPEC which gave them a 50% boost. AMD will be able to do the same thing with 3DNow! and jump back into a huge lead. This kind of trickery will not work for Intel. Scumbria> But where will AMD get the compiler? Currently they use Intel's optimized compiler for Spec.

To: Scumbria who wrote (66985)	7/30/1999 5:42:00 PM
From: Joey Smith	Read Replies (1) \| Respond to of 1575273

re:Suppose that Intel built an SSE version of SPEC which gave them a 50% boost. AMD will be able to do the same thing with 3DNow! and jump back into a huge lead. This kind of trickery will not work for Intel. Problem for AMD is that SSE is widely accepted and quickly becoming the industry standard for software developers (and i'm not just talking about games). Athlon better provide support for SSE pronto! Will hurt them as they try to target the commercial sector. joey

To: Scumbria who wrote (66985)	7/30/1999 11:11:00 PM
From: Elmer	Read Replies (1) \| Respond to of 1575273

Re: "Suppose that Intel built an SSE version of SPEC which gave them a 50% boost. AMD will be able to do the same thing with 3DNow! and jump back into a huge lead. This kind of trickery will not work for Intel." That point has been tossed around before. I am no expert in this area but I thought the conclusion was that the 3DNOW instructions in the K7 would not offer better performance then the already optimized K7 FPU. As a matter of fact, Intel's use of the SIMD registers was widely speculated on for a possible means for Intel to match the K7 FPU performance. Why the surprise now? This is not a smoke and mirrors benchmark thing if the optimizing compilers support it. EP