• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

Strange benchmark behaviour

scoobysnack

scoobysnack

scoobysnack

Associate
Joined
5 Jan 2004
Posts
53
Location
Lymington,Hants.
Hi
Have just replaced an Opteron144 which i ran at 2.475ghz(275*9) with a A64 3800+ single core which i'm running at 2.65ghz(265*10) as i thought it would be usefully quicker but when i ran the benchmarks i use (Aquamark3) i get much lower cpu scores (circa 50% drop). Any ideas as to why this might be?
I know it's quite an old benchmark program but i have a record of scores with it so i can compare any changes i make. The 3800+ runs a bit cooler so i might be able to go a bit further but i don't understand these scores. :confused:
M/b is a socket939 Abit AV8-3rd eye if it helps.

Hope someone has some ideas

SS
 
welshtom said:
yes they do a venice 3800 :confused:
Click to expand...

Oooh... never knew that... never heard of one :eek:

Anyway, looking around I see the 3800+ Venice has a 512KB L2 Cache, whereas your Opteron 144 has a 1MB L2 Cache. So the Opteron has twice as much L2 Cache as the 3800+ which will have an impact on performance.

This is most likely the reason for your "strange" bench behaviour. :)

SiriusB
 
it shouldnt be a 50% drop thats far 2 big a gap the difference in cache in real time is about 200mhz slower so they should really be getting around the very same score
 
Thanks for the replies so far. Any other ideas?

Is it anything to do with Aquamark3 being fairly old and maybe not entirely accurate with the latest cpu's?

SS
 
scoobysnack said:
Thanks for the replies so far. Any other ideas?

Is it anything to do with Aquamark3 being fairly old and maybe not entirely accurate with the latest cpu's?

SS
Click to expand...
Tried any other benchies, e.g. PCMark0x or 3DMark0x?
 
hp7909 said:
Tried any other benchies, e.g. PCMark0x or 3DMark0x?
Click to expand...
Would have to put old chip back in to run benchmarks and then swap chips and run again - too much hassle!
Also have now sold old chip on flea-bay.
SS
 
You must log in or register to reply here.
Back
Top Bottom