• 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.

strange sandra score (dhrystone benchmark)

E

erector16

Senior member
i've been running my P4-2.4b at 2.7ghz on my p4pe. the other day i decided to benchmark the cpu to see how it fared against the competition. to my surprise, the dhrystone benchmark score i received was extremely low compared to comparable cpus. the score showed a dhrystone of 3015 MIPS. this is about half of what it should be (based upon looking at scores of other p4s). the wheatstone score is right where i'd expect it to be at around 1456/3370 MFLOPS (beating a p4-2.66). i thought maybe this was a side effect of overclocking so i put the cpu speed down to the default 2.4ghz. again, the dhrystone score was about half of what it should be (compared to the reference p4-2.4b score). the weird thing is that when i first put this system together i wasn't seeing this problem. the scores looked completely normal. to make things even stranger, if i were to reboot my system say 3 times, i'd get at least 1 time where the score would look how it's supposed to. in other words, this is not 100% reproducable. is anyone else seeing strange behavior like this? i guess it could just be a sandra bug, but this is really bothering me. i typically don't worry too much about benchmarks, but this is too much of a performance gap to simply overlook. any comments/suggestions would be greatly appreciated!
 
the newer sandra gets ~ the worse it gets.

i wouldnt worry about it ~ run something else and forget about sandra
 
that's what i'm thinking... i just ran cpubench and the dhrystone was very respectable. i still kinda want to know why it's screwing up tho. i don't know why that's the only benchmark that's not reproducable.
 
whats screwing it up is how NEW sandra is calculating your score.

forget it ~ sandra cpu/media scores are meaningless ~ mhz is mhz.
 
It's just a crappy benchmark method. I get variability of ~4-5 hundred mips just by running it at different times, even though I have none other programs running in the background.
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top