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: Ali Chen who wrote (54670)	4/7/1999 9:14:00 PM
From: RDM	Read Replies (2) \| Respond to of 1576479

I would personally be surprised if the K7 were more than 20% faster than the Pentium III of the same same clock and cache size without compiler optimization. However, I expect the K7 to get to 20 higher clock than the Pentium III relatively quickly giving a 40% advantage particularly for FPU benchmarks.

To: Ali Chen who wrote (54670)	4/7/1999 10:09:00 PM
From: Tenchusatsu	Read Replies (1) \| Respond to of 1576479

<Don't you think that the Mustang-K7 (tm Allen Kim) can do significantly better only on the software specifically optimized for K7?> Here's what Microprocessor Report says: Like Intel's P6, the K7 decodes three x86 instructions per cycle. Unlike the P6, and more like the K6, the K7's decoders are generalized and completely symmetric. ... The symmetry and generality of the K7's decoders may have limited benefit for code compiled for the P6, since such code trys to avoid instructions that run afoul of the P6's decoders. But a lot of software is still compiled for 486s and Pentiums, which should be no problem for the K7. All I can say is that it remains to be seen whether code can be (or even will be) specifically compiled for the K7. Judging that the software and driver support for 3DNow is pretty weak, I'm not going to hold my breath and wait for software specifically optimized for the K7. Tenchusatsu