• Welcome to Overclockers Forums! Join us to reply in threads, receive reduced ads, and to customize your site experience!

A thought

Overclockers is supported by our readers. When you click a link to make a purchase, we may earn a commission. Learn More.
Can you/Did yuo run tests with REAL applications and see what happens? Would "real" applications show the same behavior with changing the ID?

(your picture is blocked at my office so I cant see your response - host the images here if you would be so kind)

Haven't figured out how to host an image through overclockers yet. The picture I posted is from my excel chart showing Aida results and how MASSIVELY they change. I'm not done testing just benchmarks yet and haven't gotten to "real world applications" or games yet (they will be forthcoming). So far I've seen huge differences with Aida even to the point of when I name the Vendor string "Bubba Hotepp" I get the message "the benchmark is not optimized for your CPU". Meaning it's optimizing code dependant on which vendor string or model number it detects and NOT by which optimization flags it detects in the CPUID. That IMHO makes it completely unreliable. I'm seeing suspicious results in PCMark 7, 3DMark06, 3DMark 11, Passmark PT7 among others. IF they aren't doing the same thing as Aida (which I suspect is a result of being coded using Intels compiler and/or libraries) then even the fact that the results are changing as much as they are regardless of the reason make them unreliable as a comparison of CPU performance.
 
Well one thing is pretty clear and that is I don't want me n0 "Bubba-Hotepp" model cpu since they really underperform.

Looks interesting. Remember the little man almost always loses. :bang head


Haven't figured out how to host an image through overclockers yet. The picture I posted is from my excel chart showing Aida results and how MASSIVELY they change. I'm not done testing just benchmarks yet and haven't gotten to "real world applications" or games yet (they will be forthcoming). So far I've seen huge differences with Aida even to the point of when I name the Vendor string "Bubba Hotepp" I get the message "the benchmark is not optimized for your CPU". Meaning it's optimizing code dependant on which vendor string or model number it detects and NOT by which optimization flags it detects in the CPUID. That IMHO makes it completely unreliable. I'm seeing suspicious results in PCMark 7, 3DMark06, 3DMark 11, Passmark PT7 among others. IF they aren't doing the same thing as Aida (which I suspect is a result of being coded using Intels compiler and/or libraries) then even the fact that the results are changing as much as they are regardless of the reason make them unreliable as a comparison of CPU performance.
 
Looks like i ain't going to be taking much notice of CPU reviews on AIDA :) Not that i take any notice of such things anyway....

Frakk, I couldn't have said it all better myself.

To all of those talking about "synthetic" benchmarks I only have one response to that.



Hardware and all settings are exactly the same only thing changed was CPUID Vendor ID string (i.e. from via via via to genuineintel, authenticamd etc) and CPU model/family #.
 
Here's some interesting info from the latest MaximumPC that just came in the mail today. First (directed at all of you "AMD should quit" belly achers), it looks like AMD is teaming up with ARM for a future heterogeneous multi-core processor. The plan as it goes now is that there will be a Cortex-A5 core built in to take over security tasks and some other small tasks. Doesn't sound like AMD is "throwing in the towel" to me. (you can read the column on page 9)

Second, they took the 2008 Dream Machine and rebuilt it using an FX-8150, CHV, and 7970 (for $1500 not including the reused case) as a "compliment" to the 2012 Dream Machine which is a Xeon E5-2687W (8 core 16 thread $1900 CPU), 64GB DDR3, quad 690 $14,482 PC. While it gets "crushed" by the dream machine (I would hope so for that money) it doesn't do too bad vs their zero point system (3930K build). He ends with
So am I surprised or appalled that a $1500 Bulldozer build can't beat a rig that costs a thousand dollars more? Nope. Instead, I'm happy that I built what I set out build: a kick-butt (edited for the forum) gaming rig that looks amazing and peforms well for the price, and a chance for the case from one of our old Dream Machines to live again.
 
Back