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: Steve Porter who wrote (40388)	10/30/1998 2:51:00 AM
From: Petz	Respond to of 1574446

Steve, re:<Add to this the fact that there is no way (for at least another 2 years) that AMD will get a speciic K7 optimization (k8, etc.) module into leading compilers...> K7 should perform well with Pentium II optimizations. Specifically, the latencies on the K7's two FPU's are slightly less than the Pentium II (4 cycles vs. 5). The throughput of the floating point add/sub is identical (1 cycle) but the throughput of the multiplier is superior (1 cycle vs. two). So a compiler that can take advantage of reduced timing dependencies of the K7 FPU would be an advantage, but in general a K7 FPU just looks like a faster Pentium II FPU (faster latency and higher throughput), unlike the K6 which had faster latency and lower throughput. The deep instruction queue of the K7 should allow more instructions to be started in parallel to fill the execution units. Petz