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: Tenchusatsu who wrote (95650)	2/28/2000 1:55:00 PM
From: Scumbria	Read Replies (2) \| Respond to of 1573364

Ten, even though Willamette has fewer integer units than Athlon (actually, it's more complicated than that), it will be able to execute more instructions per main clock than Athlon. I don't see how you arrived at that conclusion. The ability to forward results at mid cycle will improve throughput for the specific case where a simple arithmetic instruction is stalled waiting for results from another simple arithmetic instruction. The fact is that this isn't an extremely common case. The ALU only handles logical ops, shifts, and 32 bit adds. It does not handle multiplies or divides. Also, compilers will insert non-dependent instructions between dependencies wherever possible to avoid such stalls. I'm sure that the fast ALU provides some performance benefit, but probably not a huge amount. Scumbria