Multi-Threaded Super-Pi Contest

Hahaha!

I'm sorry--I was just getting the bugs worked out. I found out that the 512M requires 64 bit and over 2GB of ram, so I thought that would limit who could do it--so I went with the 256M. If I hadn't seen that, I would have kept it at 512M! I hope you understand...

Actually yeah once I did the 256mb I was surprised it wasn't nearly as stressful as the 512mb was. I had to take my overclock down to 3.6ghz for the 512mb to get through the test all the way.

Jet please update teh scoreboard....just wait until the i7 users come then it will get fun :P

Yeah I7's are gonna kill everybody in these kind of multithreaded benches.
 
I suggest you include version #s in the ranking list. Or you can request that only v0.4.3 or v0.4.4 be used. (v0.4.4 will be coming out in a couple of days)

This benchmark is an evolving program. It'll be updated over time to utilize new hardware features (such as SSE, AVX, etc...).

So speeds may or may not be consistent between versions. (AMD K10 is gonna get a boost with v0.4.4.)


Enjoy ;)

Are you affiliated with the program at all? Both your posts have been really informed...

Post 16 has my updated 32m. I tweaked a little more and got 16.482. You put me in first place anyway even with the times not correct LOL.

Do you want to include 512M as well? Since you mentioned it taxes your processor a whole lot more, it might be useful as another tier--though you still have the lower overclock for 256M. You decide.
 
Last edited:
Do you want to include 512M as well? Since you mentioned it taxes your processor a whole lot more, it might be useful as another tier--though you still have the lower overclock for 256M. You decide.

Sure-

512m.png
 

Ouch you were waiting for quite a while there!


I think I could get the higher overclock on the 512 if I had kept my geminII cooler on there. But right now I'm only running a stock HSF from a 955, the one with copper base and 4 heat pipes. It's not as good, testing the 512 even at 3.6ghz my temps did reach 70c for a few brief seconds on the CPU! Toasty!

Edit- I don't want to cheat, so you can say my 256m test was 3.825 ghz because thats what it was. I used a windows based overclocking tool so it didn't show up as being the 3.8ghz overclock because it was set to 3.6ghz in the bios. After testing the 512m at 3.6, I was simply too lazy to reboot and change biose settings for the 256 test LOL. Also in the 256 and 512 tests you have my CPU as a 520, it's a 550 as you have it correct in the 32m test.
 
Last edited:
Ouch you were waiting for quite a while there!


I think I could get the higher overclock on the 256 and 512 if I had kept my geminII cooler on there. But right now I'm only running a stock HSF from a 955, the one with copper base and 4 heat pipes. It's not as good, testing the 512 even at 3.6ghz my temps did reach 70c for a few brief seconds on the CPU! Toasty!

Yep--this test actually scales really well with quad cores--I have half the cores you do and 70% of the speed per core ;)
 
Are you affiliated with the program at all? Both your posts have been really informed...



Do you want to include 512M as well? Since you mentioned it taxes your processor a whole lot more, it might be useful as another tier--though you still have the lower overclock for 256M. You decide.


lol... I was never trying to hide myself... :D


EDIT:

And Yes... i7s will burn this bench...

Here's the current publicized world records: (These are NOT mine. Don't add them to the list.)
W5590_256%20million.jpg

W5590_512%20million.jpg



EDIT 2:

Since you're including the time needed to write the digits to disk... A ram drive might be able to shave off a few seconds. :D
 
Last edited:
Back
Top