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: Elmer who wrote (72704)	2/27/2002 10:15:55 PM
From: ptanner	Read Replies (1) \| Respond to of 275872

EP, re: Infoworld SMT benchmarks I agree the results look very impressive. From the description of how they tested it sounded like it was off the shelf software? No specific rewrite/recompile? I would imagine most server applications have already been optimized for SMP operations so were amenable to the benefits of SMT? Pardon any mixup in terms. No servers in this office or my "formal" education. -PT

To: Elmer who wrote (72704)	2/27/2002 10:31:09 PM
From: Dan3	Read Replies (1) \| Respond to of 275872

Re; This is HUUUUUUUUUUGGGGGGEEEEEEEEE!!!!!!!!! Well, yes and no. It's one benchmark, and it happened to be a benchmark on which P4 was awful to begin with, so it had a lot of room for improvement. They stated that 2GHZ Northwood was only 34% faster than 1GHZ PIII in the benchmarks - even worse than usual for P4. Server benchmarks run with a limited number of sessions often don't do much more than exchange cache contents across a network. It's interesting how quickly the difference between SMT and non/SMT went away as the number of sessions increased.