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.

Technology Stocks : Advanced Micro Devices - Moderated (AMD) -- Ignore unavailable to you. Want to Upgrade?

To: graphicsguru who wrote (239515)	8/29/2007 9:13:47 AM
From: combjelly	Read Replies (3) \| Respond to of 275872

"Now we know why CSI is taking so long. " True. The thing that puzzles me is this is a lot of effort for what is in essence a corner case.

To: graphicsguru who wrote (239515)	8/29/2007 12:38:01 PM
From: Tenchusatsu	Read Replies (2) \| Respond to of 275872

GG, > Now we know why CSI is taking so long. This unwinding mechanism sounds scary to me in its complexity. It's a big risk. On the other hand, Intel has done more complex things in the past, and gotten them to work. The P4 replay mechanism, for example. I find it impressive that there were no fdiv-like recalls on it. I'm not 100% sure about what this "unwinding mechanism" is, but if it refers to cacheline conflicts, I know why it's complex. Basically, Intel intends to make CSI scalable beyond four sockets. Too bad even four socket servers are declining thanks to multi-core. Tenchusatsu