x264 video encoding benchmark

[graysky]

At stock 2.1Ghz(10.5x200)

Thanks for running the benchmark... I need your mem timings and core rate as well as your o/s

 

[graysky]

@Kursah and DOM_ATI - thanks for the data, guys!

 

[newtekie1]

My E2160 Rig below:
---------- RUN1PASS1.LOG
encoded 1749 frames, 90.86 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 86.37 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 88.70 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 91.00 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 91.16 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 21.52 fps, 1826.38 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 20.81 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 21.69 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 21.71 fps, 1826.33 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 21.39 fps, 1826.37 kb/s

 

[graysky]

My E2160 Rig below

Thanks for the data... what is the multiplier and FSB? Also the mem core rate and your o/s?

 

[DOM]

---------- RUN1PASS1.LOG
encoded 1749 frames, 103.45 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 103.17 fps, 1850.63 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 103.84 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 103.07 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 103.55 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 25.26 fps, 1826.05 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 25.21 fps, 1826.08 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 25.20 fps, 1826.20 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 25.22 fps, 1826.15 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 25.27 fps, 1826.36 kb/s

 

[graysky]

Thanks dude

 

[newtekie1]

Thanks for the data... what is the multiplier and FSB? Also the mem core rate and your o/s?

Multiplier:9
FSB:370
Memory Speed: 740(4-4-4-12 2T)
Chipset: P965
OS: Windows XP SP2

Also, here is my E6600:

---------- RUN1PASS1.LOG
encoded 1749 frames, 119.46 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 118.96 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 118.96 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 119.34 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 119.84 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 26.25 fps, 1826.38 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 26.18 fps, 1826.20 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 26.25 fps, 1826.38 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 26.25 fps, 1826.38 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 26.38 fps, 1826.37 kb/s

Multiplier: 9
FSB: 400
Memory Speed: 800(4-4-4-12 2T)
Chipset: 680i
OS: Windows XP

 

[graysky]

got em, thanks

 

[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:

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!

 

[graysky]

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

Xeon E5330 (Dual board)
Q9550
Q9350

 

[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.

 

[wiak]

add some 1920x1080i > 1280x720p and i will be happy to run it ^^

 

[graysky]

@wiak - Originally, I thought about 1080i or 720p but since I have yet to see someone encode full-frame @ 60 fps, I felt that 480p was more relevant.

 

[Deleted member 3]

---------- RUN1PASS1.LOG
encoded 1749 frames, 133.09 fps, 1849.61 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 130.62 fps, 1849.61 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 132.94 fps, 1849.61 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 131.07 fps, 1849.61 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 133.89 fps, 1849.61 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 58.82 fps, 1834.21 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 58.85 fps, 1834.21 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 58.76 fps, 1834.86 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 59.13 fps, 1834.86 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 58.79 fps, 1834.22 kb/s



First pass seems to scale worse on multiple cores? High clocked Kentsfields are faster than my system yet the second pass my system is faster. (see specs <<<)

 

[graysky]

@banjoman - yeah, the first pass never uses 100 % of the CPUs. I wrote a FAQ that covers this and other questions in detail.

 

[wiak]

we need a benchmark for 1080i>720p and 1080i>1080p
low res says nothing to me

good tool anyway

 

[graysky]

@wiak - I will, but it's just not ready now. Sharktooth has some "experimental" settings for HD-DVD, but since the nal hrd patch isn't in a finalized form and incorported into x264.exe yet, it's kinda pointless.

 

[graysky]

First off, thanks to all who contributed data.

24-Feb-2008 - Finally updated the data tables on the x264 benchmark page. 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.