• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

First northwood benchmarks!

Remnant2

Senior member
You can find them Here.. It's a chinese site, and like any "leaked" benchmarks, the accuracy of them is highly in doubt. But they look roughly like what they should be.

The sample scales roughly 5% better than clockspeed alone would dictate in the ALU test, and 7% in multimedia. Note that its running on a 845(blah) platform and (in sandra) being compared to the i850 one, so running on equal platforms probably would make those more like 10-15%.
 
wow looks good, beats the 2ghz by a lil... but for the 600 + probable price tag... ill stick to my lil ole 1.4! 😛
 
I've already seen these, and I wasn't impressed. The Northwood in that test is no faster in those benchmarks other than what the 13% increase in clock speed provided.
I seriously doubt the validity of these benchmarks.
 
noj wrote:

"I seriously doubt the validity of these benchmarks."

While the validity of the results is questionable, considering the board is i845 based, I wouldn't be shocked. i845 is the absolute lowest-performing platform possible for P4 right now. Even VIA's murky P4X266 ousts it. Northwood will likely need the benefit of much larger RAM bandwidth than what PC133 can offer.
 
If PC1066 and Northwood are all what they were cracked up to be then single-channel P4X333 may not be able to bring out the true nature of Northwood. I'm excited about the future products of both AMD and Intel. Let the future processor wars begin!
 
Northwood will likely need the benefit of much larger RAM bandwidth than what PC133 can offer.

Exactly. Those people should not have benchmarked that Northwood with SDR memory? Those scores aren't surprising though, aving PC133 doesn't help a bit.

I wouldn't get my hopes up about the performance of Northwood though. I think just about the only thing Northwood will bring is more MHz. It surely will bring more performance with it's .13 technology and 512kb of L2 (maybe), but likely the boost won't be more than 10% (if you compared, for example, a 2GHz Willy and a 2GHz NW).
 


<< I've already seen these, and I wasn't impressed. The Northwood in that test is no faster in those benchmarks other than what the 13% increase in clock speed provided. >>



Noj, note that I specifically said : percent faster than simple scaling alone would dictate. That means I've already removed the percentage gain resulting from the clockspeed increase.

Running on i845, those numbers are pretty respectable -- 512kb of L2 should help insulate the P4 from the memory subsystem better. They're not exactly earthshattering, but Northwood is supposed to be a shrink+more L2, not a whole new design.
 
Back
Top