SI
SI
discoversearch

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)
AMD 217.91+0.9%Dec 5 9:30 AM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: stribe30 who wrote (69450)1/30/2002 2:02:31 AM
From: Harvey AllenRead Replies (2) of 275872
 
Some PIV Performance Anamolies being reported.

"A PIV Anamoly
Tim Cole - 1/27/02

--------------------------------------------------------------------------------

I'm seeing some odd results from this Northwood of mine.

It's running at 2.8GHz just fine, but what it's not doing is producing noticeably better results than my older 2GHz willy.

I run SETI 24/7 on everything I have, so I have a good feel for it. I compared the Team Lamb Chop bench score from my old 2GHz chip to that just run on this box at 2.8GHz, and the difference was only 23 minutes (Ed.note: a little more than 10% improvement). This is not at all what I expected from a 40% MHz jump. I get the feeling something is not quite right. All of the chipset drivers are installed, and the board seems to be tweaked as much as possible.

What really raised a flag is I got this 1.8A part running on an i845 board, and while cruising at 2.4GHz it's outperforming the 2.8 box in some areas. Can't put my finger on it yet, but something's wrong. I was just thinking that maybe it looks like this 2.2 is running fine at 2.8, but perhaps it's actually getting hot enough to trigger the throttling diode under load and then it's not running as fast as stock, or something of that nature.

Ed. note: I have been wondering about this ever since I saw the Tom's Hardware benchmarking with an overclocked Northwood. In that case, though, temperature was not an obvious factor.

There's a few other possibilities. Many of these PIV boards allow for asynchronous settings of FSB and memory. Asynchronous modes in the past have led to performance hits, that may be a factor here.

In the case of i850 boards, if RDRAM is being slowed down, that could lead to a possible bottleneck.

In the case of at least video-intense benchmarks, it may just be a matter of a video card bottleneck.

Or it may well be some sort of throttling is going on.

If you are one of the Northwood pioneers, I'd like to hear from you to see whether or not you're running into the same thing in your favorite benchmarks when you crank it up. Please include items like the mobo you're using, the type of RAM, the FSB and memory speeds.

overclockers.com
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext