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 (94216)	2/19/2000 2:02:00 AM
From: Tenchusatsu	Read Replies (1) \| Respond to of 1570819

Scumbria, <CPU architects tend to be notoriously dense about pipelines.> You're not the first one to make this assertion. On the other hand, it's not like higher frequencies just come for free, even when the pipeline is longer. Wouldn't there be higher power requirements corresponding to higher speeds? And these days, power is increasingly becoming a concern. I have no idea how much power Willamette consumes. But if Intel plans on having a Willamette-derivative (Northwood) enter the mobile market, I can't imagine the power requirements being astronomical. Tenchusatsu

To: Scumbria who wrote (94216)	2/19/2000 2:42:00 AM
From: dumbmoney	Read Replies (1) \| Respond to of 1570819

Intel did the right thing with Willamette, and they will be the performance champions next year. No other CPU will match the integer performance of Willamette. Really? Not even the 800Mhz Itanium (or as I like to call it, the Itanic)??? The FP performance might not be too shabby either, when using the new instructions. Intel may finally erase the ignominy of low SPECfp scores.

To: Scumbria who wrote (94216)	2/19/2000 5:43:00 AM
From: Gopher Broke	Read Replies (1) \| Respond to of 1570819

Scumbria, <<No other CPU will match the integer performance of Willamette>> No doubt Willamette will run faster when the pipe is full, but the performance is so much more dependent upon successful branch prediction that I think we may see some strange anomalies introduced by the higher pipe latency. Compiler optimizations will play an even more important role in keeping the pipe primed, and how will pre-Willamette optimized code perform? One thing's for sure - the benchmarks will be interesting.