PCMark05 Tweaking Thread

[bob80]

But software ramdisk aren't allowed....

[saint19]

Sorry guys for ''copy'' all the tweaks, but this willl help me a lot to do something good in the gigabyte competition. Hope find someones from my side and share with all of you.

[Sweet]

Originally Posted by saint19

Sorry guys for ''copy'' all the tweaks, but this willl help me a lot to do something good in the gigabyte competition. Hope find someones from my side and share with all of you.

No problem saint, this is for all, buuuutttt if you win something, you share with me

[Hondacity]

and me! lol

[Christian Ney]

Originally Posted by Hondacity

and me! lol

Spam...

You don't even bench PCMark05

[Hondacity]

hahahhaha

after this 3d comp, i'll be trying my hands on some raid for some 2d points

[K404]

I'm still not a PCMark05 guy, but I had an SSD to test so I started playing a little and the info in this thread has helped some of my scores quite a lot

Thankyou!

[saint19]

Lol, sweet in near to me ( at least in same continent) but hondacity is different.

Well, I need bench 1st to know if i can win something.

[I.M.O.G.]

Originally Posted by S_A_V

I don't have direct comparison with more than 4 cores with exact the same settings.
Just found PCMark04 results with FX-4100 @ 6918 MHz and FX-8120 @ 6782 MHz:
4-core: 49.3 web page rendering, 317 fps WMV - http://hwbot.org/submission/2231053_
8-core: 55.2 web page rendering, 362 fps WMV - http://hwbot.org/submission/2240067_
Don't look at Overall score, FX-4100 result was done with wrong Grammar Check.

Windows was updated with AMD Bulldozer Performance Updates:
Windows6.1-KB2592546-x64.msu
Windows6.1-KB2645594-x64.msu
Windows6.1-KB2646060-v3-x64.msu


Do you use WMV settings suggested in PCMark05 Tweaking Thread?
I mean this: "Force NumThreads"=dword:00000002
Try playing with other values

Thanks.

I did set the registry value for the number of threads on fx-8120.

This was hard set to 8 threads (just look at audio/video):
http://hwbot.org/submission/2246975_...20_39611_marks

This was hard set to 4 threads (just look at audio/video):
http://hwbot.org/submission/2259791_...20_42727_marks

The 8 threaded score was better, but I believe that was the result of Vista over Win7 and I was running higher clocks on the 8 threaded submission (I spent more time on it, and higher clocks were easier on that motherboard). That isn't a good comparison because many settings as well as the OS was different.

I don't personally have any direct comparisons with similar settings either, but from running the bench a few dozen times on the fx-8120, it seemed to me that scaling stopped more or less at 4 cores.

That said, I don't believe the encoder actually supports splitting out more than 4 threads (reference here: http://www.microsoft.com/windows/win...dsettings.aspx - that isn't talking about wmencoder9, but even a newer version). Seeing as how it is doing a video and audio encode at the same time though, I suppose the video encode should be able to use 4 threads itself, and perhaps the audio can use several of its own... I don't know.

Looking at scores however, the best 2600k scores are done with only 4 cores active and no HT. This tells me that its likely scaling stops at beyond 4 cores again.

Not sure, just my inferences from my own benching and looking around.

[pro]

its funny how time changes things, 18-24 months ago most of these were considered cheats,

now its all gravy,

im very happy that this benchmark is progressing..

a tweak applied by one man is a cheat, a cheat applied by everyone is a tweak