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: Gopher Broke who wrote (96791)	3/4/2000 2:38:00 PM
From: Scumbria	Respond to of 1576163

Gopher, You are obviously confident that branch misprediction occurs less frequently than some people fear. Actually no. The reasons that I am less concerned about branch misprediction in a deep pipeline are: 1. The biggest limiting factor for performance is DRAM latency. Branch misprediction pales by comparison. 2. A deep pipeline will incur more bubbles on branch mispredict than a short pipeline, but each bubble is less expensive. This is due to the higher clock rates (and thus shorter cycle time) of a deep pipeline. All empirical evidence shows that the tradeoffs of a deep pipeline are favorable. Alpha, Athlon, PIII prove this. Short pipelines (PowerPC, Cyrix, K6, etc.) stink. Scumbria