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 (94608)	2/22/2000 3:02:00 PM
From: Epinephrine	Read Replies (1) \| Respond to of 1571935

RE <Operating system support may be more of an issue.> Scumbria, Ouch! I was under the impression that a dual core design would make the separate cores transparent to the OS and handle scheduling and executing instructions between the two cores internally. If a dual core design would actually require special OS support that is indeed a significant obstacle, at least I would think so. Like I said Ouch! Thanks, Epinephrine

To: Scumbria who wrote (94608)	2/22/2000 9:46:00 PM
From: Joe NYC	Read Replies (1) \| Respond to of 1571935

Scumbria, Assuming that the Athlon core is already equipped for multiprocessing, it shouldn't be a very big deal. All that is required is to connect both cores to a coherent L2, and snoop the memory accesses on both sides of the L2. That sounds interesting. Since Mustang is planning to increase the size of L2, it would be kind of used twice. Another thing that might help it rock would be moving Northbridge to the die, unless AMD was considering multiple CPU systems (of dual core chips). Operating system support may be more of an issue. How differently would a dual core, single chip CPU behave from simple dual CPU (from OS standpoint). Shouldn't the CPU configuration be transparent to the OS? Joe