x264 CPU benchmark - Compare different CPUs encoding the same file

[graysky]

This is sort of the similar to the original meGUI test (http://forum.doom9.org/showthread.php?t=122318) thread I started back in Feb. It's more or less the same thing, except this test uses a minimal number of avisynth plugins (just dgdecode.dll) and encodes a full 720x480 DVD sample. The original test was a 480x480, interlaced sample.

Anyway, Techarp kindly agreed to host the file and results at this (http://www.techarp.com/showarticle.aspx?artno=442&pgno=0) URL.

This version doesn't require meGUI or .net to be installed. It's just avisynth and x264 all driven by a batch file. Have a look and please contribute (just post your results in this thread and I'll get them into the table).

Thanks all!

[legoman666]

can you sort the lists differently? kind of hard to see where you in by speed.

[graysky]

I have it "sorted" by chip and speed sort of... some folks at techarp are working on making it interactive sort of like the vga chart at th.com

[graysky]

As of 20-Sep-2007, we have data on over 100 Intel-based systems and on over 40 AMD-based systems. There are a few trends I picked-up on while browsing through the database. I put them into a single table and color coded them to make them easier to see. If you see a trend I missed, lemme know and I'll add it to the table.

Request: we don't have a single example of a machine that has both WinXP and WinVista on it. If you have a dual-boot setup, it would be cool to see the difference the O/S makes. Another missing trend is a 32-bit O/S vs. the same O/S that's 64-bit.

On to the table:

http://img291.imageshack.us/img291/1554/resultstrendsml9.gif

Yellow: Nearly 1:1 increase by adding an additional processor to a dual-chip MB
Orange: Some operating systems seem to handle x264 more efficiently than others
Red: Insignificant gain by upping the DRAM speed by 50 %
Blue: For the most part, these chips scale in a pretty linear fashion
Green: Tighter/looser memory timings have a pretty insignificant effect
Purple: Keeping the same over-all clock speed using a different combo of multiplier and FSB can give pretty insignificant gains

Again, I only gave this a once-over look; please point out any trends you see that I missed and also don't forgot about the O/S request!

Thanks again to all who contributed!

[Dr.Khron]

Wow, awesome work! A big improvment on the original project, as we are now testing x264 in a more direct manner.

When I get some time, I'll run all my machines and send in the data.

[bourtzovlakas]

Request: we don't have a single example of a machine that has both WinXP and WinVista on it. If you have a dual-boot setup, it would be cool to see the difference the O/S makes. Another missing trend is a 32-bit O/S vs. the same O/S that's 64-bit.


I have XP pro and Vista Ultimate on dual boot...
I will try to run the test and post some results...

[legoman666]

I might be tempted to install xp pro 32bit (am runnign 64bit at the moment) just to see if there is a difference (i suspect not).

[graysky]

legoman666 - that would be cool

[bourtzovlakas]

Here are my results...
http://bourtzovlakas.googlepages.com/x264Benchmarkresults.rar

Vista Ultimate+XP pro on dual boot....
Core 2 Duo 6400(8x266 & 8x400), M/B XFX 680i LT, RAM DDR2-800 4-4-4-12...

Vista is a little bit slower....

[graysky]

cool man... what your mem:cpu always 1:1? what were the mrm core speeds @ 8x266 and 8x400?

[bourtzovlakas]

cool man... what your mem:cpu always 1:1? what were the mrm core speeds @ 8x266 and 8x400?

The memory was always at 800mhz...
2:3 for 8x266(2,13 Ghz) and 1:1 for 8x400(3,2 Ghz)...

[graysky]

Very cool thanks for the results... can I get you to run your WinXP stock @ 1:1 as well? (DRAM 533 MHz)?

[bourtzovlakas]

Very cool thanks for the results... can I get you to run your WinXP stock @ 1:1 as well? (DRAM 533 MHz)?


Here it is...
XP pro
CPU 8x266
RAM @533 with 4-3-3-8

---------- RUN1PASS1.LOG
encoded 1749 frames, 60.54 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 61.07 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 61.57 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 61.64 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 61.71 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 15.12 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 15.13 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 15.11 fps, 1826.39 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 15.13 fps, 1825.85 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 15.10 fps, 1826.38 kb/s

[graysky]

Cool man, thanks... trend is consistent with my results (+50 % RAM speed = slight gain in TET). Your result is 0.4 % faster.

[Episodio1]

I loved the new comparative chart. So I'd like to contribute with more data: same CPU + different RAM timings. :)

AMD 64 X2 5600+
WinXP PRO 32b
CHIPSET: NVIDIA MCP61 rev. A1
core speed: 2.8 Ghz
14 x 200 Mhz

RAM: DDR2 2048 Mb -- 533 Mhz
4 / 4 / 4 / 12

(before it was: 4 / 6 / 6 / 18 @ 533 Mhz)


---------- RUN1PASS1.LOG
...

---------- RUN5PASS2.LOG


Gain: more than 1 fps in 1st pass. ^_^

Judging from the "+50% speed RAM = slight gain" would it be better to reduce RAM speed (Mhz) to be able to reduce CAS/RAS timings? It looks like low timings give more speedup.

EDIT:

RAM timings: 3 - 3 - 3 - 9 @ 400 Mhz



---------- RUN1PASS1.LOG
encoded 1749 frames, 69.96 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 70.18 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 70.05 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 70.05 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 70.18 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 17.95 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 17.95 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 17.93 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 17.92 fps, 1826.37 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 17.94 fps, 1826.38 kb/s


Gain: 0.2 - 0.5fps faster than 4-6-6-18 @ 533 Mhz

[graysky]

Thanks for the new data. I'll warn you about comparing raw fps values though. The change bought you about 1.6 % gain in total encoding time, which in this case is 2.0 seconds faster. If you extend it out to a 2-1/2 hour source, it should shave off 243 sec or about 4 min from the 4-1/4 hours.

Thanks for the data... it might help some who are debating the cost of lower latency RAM (say 5-5-5-15 vs. 4-4-4-12) vs. small gain in performance. I'll add your data to the trends table also.

[lucassp]

what tools do I need to do the tests under linux (...ubuntu)??

[graysky]

Sorry dude, avisynth is a windows app and you'll need some sort of frame server. For it to be a fair comparison, I think everyone needs to use the same one.

[lucassp]

ok, but in your table there is a linux comparison...and I want to know how can I do it so I can use it for my own tests, not only for this comparison. thank you!

[graysky]

Sure thing... have a look at this (http://forums.hexus.net/showpost.php?p=1218938&postcount=73).

[TalenHead]

Hi graysky,
Here's one more for your test EDIT sorry graysky fixed now

Pentium M740 Dothan 133X13 1729 Mhz, i915PM/GM, 3-3-3-8 @ 199.5 XP Pro SP2
Dell Inspiron 6000

---------- RUN1PASS1.LOG
encoded 1749 frames, 20.61 fps, 1854.10 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 21.38 fps, 1854.10 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 22.06 fps, 1854.10 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 21.53 fps, 1854.10 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 21.95 fps, 1854.10 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 5.34 fps, 1825.89 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 5.39 fps, 1825.89 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 5.22 fps, 1825.89 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 5.20 fps, 1825.89 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 5.38 fps, 1825.89 kb/s

[Adub]

Core 2 Duo L7500, Merom, 8x199.5, GM965, 5-5-5-15@332.5 MHz, Windows XP SP2

---------- RUN1PASS1.LOG
encoded 1749 frames, 46.08 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 46.99 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 47.19 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 47.03 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 47.31 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 11.38 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 11.36 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 11.44 fps, 1826.38 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 11.45 fps, 1826.38 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 11.30 fps, 1826.37 kb/s

[graysky]

Hi graysky,
Here's one more for your test

Pentium M740 Dothan 133X13 1729 Mhz, i915PM/GM, 3-3-3-8 @ 199.5 XP Pro SP2
Dell Inspiron 6000
---------- RUN5PASS1.LOG
encoded 1749 frames, 21.95 fps, 1854.10 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 5.34 fps, 1825.89 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 5.39 fps, 1825.89 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 5.22 fps, 1825.89 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 5.20 fps, 1825.89 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 5.38 fps, 1825.89 kb/s

Dude, is this the log in its entirety? If so something is majority wrong. I think you may have left out part of the log :)

[graysky]

@Merlin777 - cool, thanks!

[Adub]

Core 2 Duo E6600, Conroe, 9x335, P965/G965, 2Gb 3-3-3-12@335, XP SP2


---------- RUN1PASS1.LOG
encoded 1749 frames, 84.16 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 84.87 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 84.80 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 84.67 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 84.61 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 20.95 fps, 1826.38 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 21.10 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 21.08 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 21.08 fps, 1826.38 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 20.97 fps, 1826.38 kb/s

[Dark Shikari]

---------- RUN1PASS1.LOG
encoded 1749 frames, 48.82 fps, 1850.94 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 49.77 fps, 1850.94 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 49.84 fps, 1850.94 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 49.59 fps, 1850.94 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 49.38 fps, 1850.94 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 12.35 fps, 1829.03 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 12.51 fps, 1829.11 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 12.47 fps, 1829.29 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 12.46 fps, 1829.52 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 12.47 fps, 1829.45 kb/s

Core 2 Duo T7200, Merom, 12x166, 5-5-5-15@333, XP SP2, i945PM chipset

[graysky]

Cool, thanks all. Table updated and will update on the main page soon.

[dansus]

Well i would like to test it, but nothing happens after giving the test a name. Im running it as C:/work2 and have avisynth 2.5.7.

what am i doing wrong and can i still get the old test files?

[graysky]

...did you copy the dll from C:\work2\Initial setup to C:\Program Files\AviSynth 2.5\plugins ? I'll bet that's your problem.

[Inventive Software]

Hey hey! Ran the test on my Dell Inspiron 1501 with an AMD Turion X2 TL-50 at 1.6 GHz. Here's the benchmark:


---------- RUN1PASS1.LOG
encoded 1749 frames, 42.30 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 42.85 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 42.87 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 42.86 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 42.84 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 10.07 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 10.12 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 10.12 fps, 1826.38 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 10.11 fps, 1826.38 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 10.12 fps, 1826.38 kb/s


EDIT: CPU speeds: 200 MHz Bus Speed, 8x multiplier. Memory speeds: DDR2 533 MHz, 4-4-4-12

[graysky]

Thanks for the result, can you provide the following:

Chipset of MB
Speed at which your DDR2-533 is running
O/S you're running

CPUZ (http://www.cpuid.com/cpuz.php) should give you the first two, and you should know the o/s yourself :)

[Inventive Software]

OS is Windows XP MCE 2005, with Rollup 2 and all the recent security updates. Speed of DDR2-533 changes with CPU activity, but whilst running the benchmark, twas at stock speeds, i.e 266 MHz, but doubled because that's what DDR does? Chipset is an ATI Xpress 200 (RS480).

[red_rage]

Core 2 Duo E6400

Chipset : Intel P965/G965, 9 x 266,

DDR2 speed : 5-5-5-15 333 MHZ

OS : Windows XP SP2

Test Results


---------- RUN1PASS1.LOG
encoded 1749 frames, 59.69 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 59.85 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 59.79 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 59.82 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 59.88 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 14.53 fps, 1826.38 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 14.55 fps, 1826.38 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 14.55 fps, 1826.38 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 14.59 fps, 1826.38 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 14.37 fps, 1826.37 kb/s

[graysky]

@red_rage: thanks for the result.. just one question, your fsb is 266 but your dram is 333?

[red_rage]

Err i just pasted the max frequency of one of my Dram i.e 333 Mhz. What do I have to see exactly?

[graysky]

Can you post the output of cpuz's htm feature?

[dansus]

...did you copy the dll from C:\work2\Initial setup to C:\Program Files\AviSynth 2.5\plugins ? I'll bet that's your problem.

Yes i did.


:confused:

[graysky]

@red_rage: can you post the output from cpuz's html dump?
@dansus: what happens if your drag-and-drop the avs file into your mediaplayer? It should give an error pointing to a specific line in the script.

[TalenHead]

Hi Graysky,
I am aware this is more of a cpu test but I ran the test on my laptop only difference was the HD and OS. for vista it's a 60gig 5400rmp
xp pro has a 100gig 7200rpm hd.

Cheers Gerry



Pentium M740 Dothan 133X13 1729 Mhz, i915PM/GM, 3-3-3-8 @ 199.5 Vista Ultimate
Dell Inspiron 6000

---------- RUN1PASS1.LOG
encoded 1749 frames, 20.79 fps, 1854.10 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 21.39 fps, 1854.10 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 21.05 fps, 1854.10 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 20.85 fps, 1854.10 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 20.64 fps, 1854.10 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 5.26 fps, 1825.89 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 5.20 fps, 1825.89 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 5.12 fps, 1825.89 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 5.07 fps, 1825.89 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 5.15 fps, 1825.89 kb/s

[dansus]

@dansus: what happens if your drag-and-drop the avs file into your mediaplayer? It should give an error pointing to a specific line in the script.

mpeg2source: unable to load D2V file "C:\work2\test\test-480p.d2v
(C:\work2\work2\test\test-480p.avs, line1)

Im guessing the double work2 folder is the problem.

[dansus]

C2Q Q6600 G0 - 386x9

Intel P35 - Abit IP35 Pro

Geil DDR2 800: 5-5-5-15 1:1

OS : Windows XP SP2

Test Results


---------- RUN1PASS1.LOG
encoded 1749 frames, 174.62 fps, 1850.94 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 174.90 fps, 1850.94 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 174.36 fps, 1850.94 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 174.34 fps, 1850.94 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 174.36 fps, 1850.94 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 46.10 fps, 1829.11 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 46.01 fps, 1829.01 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 45.88 fps, 1829.40 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 45.86 fps, 1829.34 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 46.16 fps, 1829.48 kb/s

:p

[graysky]

mpeg2source: unable to load D2V file "C:\work2\test\test-480p.d2v
(C:\work2\work2\test\test-480p.avs, line1)

Im guessing the double work2 folder is the problem.

First off, thanks for the data. Yeah, it was the doubled dirs/avisynth is really picky :)

What is your RAM frequency (CPUZ>memory tab)?

[dansus]

300 Mhz 1:1

[graysky]

dansus: so it's 9x386 but you're running the mem @ 300 which is 1:1? 1:1 would be 386, not 300. I don't know of a board that'll allow you to drop the mem below the CPU. Can you post a screenshot of the output of an htm or txt dump from within CPUZ?

[dansus]

dansus: so it's 9x386 but you're running the mem @ 300 which is 1:1? 1:1 would be 386, not 300. I don't know of a board that'll allow you to drop the mem below the CPU. Can you post a screenshot of the output of an htm or txt dump from within CPUZ?

oops sorry, its 386 OC'ed

300 is my default setting.

[graysky]

OK... so is the RAM speed also 386?

[dansus]

Sorry, im a bit confused.

The ram is DDR2 800, so i guess its 400 stock and the extclock is 386x9. What else do you need?

--

[graysky]

Well, your RAM is DDR2-800 but you can run it at various multipliers from 772 in your case up to... whatever it'll clock up to.

I'm guess you're running 1:1 though. Just run CPU-Z and look at the memory tab.

[0gg]

Dual Xeon Quad Core E5330ES 2.13 @ 2.66 by BSEL
4x1 Go RAM PC5400 DDR667 FBDIMM
FSB : 8x333
OS = Vista ultimate 64 bits

Used ram = 1,22 GB


---------- RUN1PASS1.LOG
encoded 1749 frames, 129.12 fps, 1849.61 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 130.61 fps, 1849.61 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 129.40 fps, 1849.61 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 132.00 fps, 1849.61 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 132.79 fps, 1849.61 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 66.19 fps, 1834.86 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 66.87 fps, 1834.89 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 67.15 fps, 1834.86 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 67.35 fps, 1834.86 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 66.55 fps, 1834.22 kb/s

[graysky]

Dual Xeon Quad Core E5330ES 2.13 @ 2.66 by BSEL
4x1 Go RAM PC5400 DDR667 FBDIMM
FSB : 8x333
OS = Vista ultimate 64 bits

Wow dude, pretty quick result. I have two questions for ya:

1) What are you mem timings?
2) Can you run it again @ stock settings?

Thanks!

[0gg]

1) What are you mem timings?
2) Can you run it again @ stock settings?

1. 5 5 5 12 (FB DIMM, ECC ...)
2. no : it is a hardware modifiction on pin mod
3. i will do it again on 2xE5440 @ 2.4 + 8x1 Go with XP 64b

[graysky]

Updated the Intel table. It now contains several Yorkfield ES chips including:

Xeon E5330 (Dual board)
Q9550
Q9350

[0gg]

Dual Xeon Quad Core E5340ES 2.4
8x1 Go RAM PC5400 DDR667 FBDIMM 4 4 4 12 (266 Mhz)
FSB : 9x266
OS = XP Pro 64 bits

---------- RUN1PASS1.LOG
encoded 1749 frames, 115.88 fps, 1849.61 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 119.84 fps, 1849.61 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 116.97 fps, 1849.61 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 119.59 fps, 1849.61 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 116.48 fps, 1849.61 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 60.28 fps, 1834.86 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 60.70 fps, 1834.22 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 60.31 fps, 1834.90 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 60.64 fps, 1834.86 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 60.50 fps, 1834.22 kb/s

[graysky]

@ogg - thanks again for the data. A question. Isn't the E5340's stock speed 2.33 GHz w/ a 333 MHz FSB? See this (http://techreport.com/discussions.x/13036) article for the reference.

[0gg]

Isn't the E5340's stock speed 2.33 GHz w/ a 333 MHz FSB?
My Xeon E5340 is ES, but all E5340 have their FSB 266

Xeon E5345 is 2.33GHz w/ a 333 MHz FSB

In fact :
- 53x0 = 266
- 53x5 = 333

With 53x0 you can modify pin mod to o/c by hardware in order to have a better Vcore and a 333 FSB, without much more heat
And then with Systool, you're able to put a maximum of 373 FSB
... 9x373 = 3357 Mhz

The best Xeon is X5350 running @ 2,66 FSB66
By BSEL modification = 3330 Mhz and then with systool = 3730 Mhz.... but power supply 700 W must have !

++

[graysky]

Updated the tables with another 45 nm chip: the QX9650 -- both at stock levels and @ overclocked to 4.2 GHz! With it, and the others (Xeon E5330 (Dual board), Q9550, and Q9350) there is now data on 4 different 45 nm chips.

One thing that I found striking about these new chips is that they are only marginally faster than their 65 nm counterparts when encoding x264 (about 5-6 % faster with all other factors being equal or close to equal). Have a look at the general trends table for the Kentsfield vs. Yorkfield comparison at the official host (http://www.techarp.com/showarticle.aspx?artno=442&pgno=0).

[Bigmango]

C2D E6400, Conroe, 8x400, 4-4-4-12, Asus P5B-Deluxe

Vista x64.

---------- RUN1PASS1.LOG
encoded 1749 frames, 82.82 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 84.38 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 85.40 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 86.03 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 85.55 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 20.84 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 20.93 fps, 1826.38 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 20.98 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 20.97 fps, 1826.37 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 21.24 fps, 1826.37 kb/s


It looks like compared to the results on XP 32bit, the first pass is about 4 fps slower and the 2nd pass about 1 fps slower on vista x64. It would be interesting to compare this with a 64bit build of x264.

[maxisvk]

My notebook Acer Aspire 5920G
Cpu: Intel(R) Core(TM)2 Duo CPU T7300 @ 2.00GHz (200x10), MMX, SSE, SSE2, SSE3, SSSE3, EM64T, 2 x 32 KBytes , 2 x 32 KBytes , 4096 KBytes
Chipset: Intel GM965 rev. C0
Memory: 2 X DDR2, PC2-5300 (333 MHz), 1024 MBytes, Hyundai Electronics 5-5-5-15 @ 333Mhz


---------- RUN1PASS1.LOG
encoded 1749 frames, 55.55 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 55.61 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 54.76 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 54.42 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 55.36 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 13.63 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 13.62 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 13.49 fps, 1826.21 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 13.48 fps, 1826.38 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 13.46 fps, 1826.37 kb/s

;)

[Limit]

CPU: Brisbane-G2 4400+ (11.5x200)
Chipset: AMD 790FX
Mem: 2x DDR2, PC2-8000 (500MHz), 2048MBytes, 5-5-5-15 @383Mhz

---------- RUN1PASS1.LOG
encoded 1749 frames, 61.64 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 61.64 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 61.60 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 61.67 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 61.67 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 14.61 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 14.62 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 14.60 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 14.60 fps, 1826.37 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 14.60 fps, 1826.38 kb/s


CPU: <some as above> (11.5x250)
Chipset: <some as above>
Mem: <some as above> @ 479MHz

---------- RUN1PASS1.LOG
encoded 1749 frames, 77.57 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 77.46 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 77.52 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 77.57 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 77.52 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 18.46 fps, 1826.21 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 18.56 fps, 1826.38 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 18.54 fps, 1826.38 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 18.53 fps, 1826.38 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 18.49 fps, 1826.27 kb/s

CPU: <some as above> (11.5x264)
Chipset: <some as above>
Mem: <some as above> @ 506MHz

---------- RUN1PASS1.LOG
encoded 1749 frames, 82.00 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 82.06 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 82.19 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 82.49 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 82.61 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 19.59 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 19.59 fps, 1826.38 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 19.58 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 19.58 fps, 1826.38 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 19.58 fps, 1826.38 kb/s

[Konrad Klar]

Poor results of Core2Duo E6320 7x350:

---------- RUN1PASS1.LOG
encoded 1749 frames, 58.21 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 58.45 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 58.57 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 58.30 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 58.03 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 16.11 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 16.15 fps, 1826.38 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 16.18 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 16.04 fps, 1826.37 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 16.09 fps, 1826.38 kb/s
P965. 4GB of DDR2, running at 700MHz 4-4-4-12 [2T]

My conclusion: 4MB of L2 cache (against 2MB in E6300/E6400) does not help at all in x264.

[graysky]

Thanks for the data guys. Will update the table soon.

[dansus]

Ok, im up to speed now.

C2Q Q6600 G0 - 455x8

Intel P35 - Abit IP35 Pro

Geil DDR2 6400: 5-5-5-15 1:1

Ram @ 455mhz

OS : Windows XP SP3

Test Results


---------- RUN1PASS1.LOG
encoded 1749 frames, 195.01 fps, 1850.51 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 195.70 fps, 1850.51 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 194.33 fps, 1850.51 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 193.99 fps, 1850.51 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 193.99 fps, 1850.51 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 51.75 fps, 1829.56 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 51.80 fps, 1829.56 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 51.94 fps, 1829.56 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 51.79 fps, 1829.56 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 51.85 fps, 1829.56 kb/s

:)

[HarryM]

CPU Intel Dual-Core E2140 (nominal 8x200)
MB Intel i865G chipset, IGP not used (very old chipset, but prepared for C2D family too!)
http://www.giga-byte.com/Products/Motherboard/Products_Overview.aspx?ProductID=2562)
Memory DDR1 400MHz PC3200 2x512MB Dual Channel, timing for all tests is 2,5-3-3-7
Windows XP SP2

***********************************
Case A - nominal, 8x200MHz=1.6GHz, FSB:RAM divider = 1:1 (DDR1 running on 400MHz)

---------- RUN1PASS1.LOG
encoded 1749 frames, 46.70 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 46.81 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 46.82 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 46.76 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 46.70 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 10.98 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 10.96 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 10.99 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 10.97 fps, 1826.37 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 11.01 fps, 1826.38 kb/s

***********************************
Case B, 8x200MHz=1.6GHz, FSB:RAM divider = 5:4! (DDR1 running on 320MHz, underclocked)

---------- RUN1PASS1.LOG
encoded 1749 frames, 45.15 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 45.26 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 45.28 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 45.26 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 45.34 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 10.79 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 10.82 fps, 1826.38 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 10.81 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 10.80 fps, 1826.20 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 10.79 fps, 1826.26 kb/s

***********************************
Case C - overclocked, 8x266MHz=2.13GHz, FSB:RAM divider = 5:4! (DDR1 running on 426MHz)

---------- RUN1PASS1.LOG
encoded 1749 frames, 60.77 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 60.70 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 60.67 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 60.77 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 60.67 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 14.47 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 14.47 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 14.51 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 14.50 fps, 1826.38 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 14.51 fps, 1826.37 kb/s

[DJ Bobo]

OK, here I am... with unpleasant results.
I was expecting something higher with this system: Celeron D 320 (Prescott core), 18x133, VIA P4M800 chipset, RAM on 2.5-3-3-7 @ 166 MHz, Windows XP Pro SP2

---------- RUN1PASS1.LOG
encoded 1749 frames, 14.23 fps, 1854.10 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 14.32 fps, 1854.10 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 13.93 fps, 1854.10 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 13.99 fps, 1854.10 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 14.40 fps, 1854.10 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 3.01 fps, 1825.89 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 3.03 fps, 1825.89 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 3.03 fps, 1825.89 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 3.01 fps, 1825.89 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 3.02 fps, 1825.89 kb/s

[Lele-brz]

The results on my laptop

Intel Core Duo T2400, 6x166, i945PM, 4-4-4-12 @ 266MHz, XP Home SP2

---------- RUN1PASS1.LOG
encoded 1749 frames, 46.29 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 46.35 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 46.27 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 46.31 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 46.41 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 11.25 fps, 1826.38 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 11.23 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 11.21 fps, 1826.32 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 11.26 fps, 1826.37 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 11.24 fps, 1826.37 kb/s

[Lele-brz]

And this on my Windows Server:

Intel Xeon 5130, 6x332.5, Intel 5000X, DRAM Frequency 332.5 MHz, Windows Server 2003 R2 Standard Edition, Service Pack 2

---------- RUN1PASS1.LOG
encoded 1749 frames, 99.41 fps, 1850.94 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 100.30 fps, 1850.94 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 98.97 fps, 1850.94 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 99.41 fps, 1850.94 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 100.03 fps, 1850.94 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 27.56 fps, 1829.20 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 27.76 fps, 1829.45 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 27.75 fps, 1829.16 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 27.75 fps, 1829.54 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 27.69 fps, 1829.20 kb/s

[Konrad Klar]

Core2Duo E6600 @2997 MHz, Memory at 666 MHz. WindowsXP SP2 (x86).


---------- RUN1PASS1.LOG
encoded 1749 frames, 67.37 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 67.49 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 67.20 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 67.29 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 67.04 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 19.55 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 19.52 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 19.47 fps, 1826.38 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 19.41 fps, 1826.37 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 19.53 fps, 1826.26 kb/s

[Raptus]

C2D E4500 @ 8x350 (2.8Ghz), Gigabyte EP35-DS3, 4-4-4-12 @ 420Mhz, XP Pro SP2.
---------- RUN1PASS1.LOG
encoded 1749 frames, 80.53 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 80.35 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 80.47 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 80.30 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 80.35 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 19.77 fps, 1826.38 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 19.75 fps, 1826.38 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 19.76 fps, 1826.38 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 19.77 fps, 1826.37 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 19.75 fps, 1826.37 kb/s

EDIT: It's a nice and quick way to test x264 speed improvements in different versions (in this particular setting of course). Dropping in the current 736 I saw a speed gain of 3.5% for the first pass and 5% for the second compared to the version 663 used in this test.

[Konrad Klar]

Inspired by Raptus result I have dicided to make another test, this time with memory working at 864 MHz (still at Core2Duo E6600 @2997 MHz)

---------- RUN1PASS1.LOG
encoded 1749 frames, 72.69 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 74.13 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 74.52 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 74.52 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 74.18 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 20.01 fps, 1826.38 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 20.20 fps, 1826.38 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 20.21 fps, 1826.38 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 20.19 fps, 1826.37 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 20.21 fps, 1826.38 kb/s

So speed of memory does matter (more than size of L2 cache).

[Raptus]

So speed of memory does matter (more than size of L2 cache).
I was quite surprised to see my E4500 getting higher marks despite running slower. It seems x264 is quite sensitive to memory subsystem performance, so the different chipsets could explain the result, as demonstrated here (http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=2991&p=3).

[bibikul]

@graysky don't let go this project.

maybe on day we will see it on tomshardware for testing new cpu's!!!!!!

soon i'll post my results with 2xquad xeon E5410 penryn. I'm verry confidend in my new rigg :)

[graysky]

I won't forget about it... next big update is what techarp (the host) updates their back-end stuff so the data isn't a HUGE gif file.

[bibikul]

Intel Vernonia 5000X
2 x intel xeon E5410 2333 Mhz
4 x FBDIMM Kingston DDR2 667 5-5-5-15 @ 333 Mhz

Windows Vista 32, SP1




---------- RUN1PASS1.LOG
encoded 1749 frames, 128.13 fps, 1849.61 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 129.61 fps, 1849.61 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 129.16 fps, 1849.61 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 130.07 fps, 1849.61 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 128.57 fps, 1849.61 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 56.79 fps, 1834.85 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 57.14 fps, 1834.90 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 57.55 fps, 1834.86 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 57.35 fps, 1834.86 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 57.32 fps, 1834.21 kb/s

[graysky]

First off, thanks to all who contributed data.

24-Feb-2008 - Finally updated the data tables on the x264 benchmark page (http://www.techarp.com/showarticle.aspx?artno=442&pgno=0). They are now html based (not .gif images) which makes my life updating them much easier and I will keep this tables up-to-date daily as people post results. Have a look at the 'Data Tends' table that contains a look at the Phenom quad vs. both Kentfield and Yorkfield quads. There are also some comparisons of Wolfdale dual vs. Conroe dual, and some other good stuff.