Legit Reviews

Computer Hardware: Reviews - Facts - Issues
https://forums.legitreviews.com/

x264 video encoding benchmark

https://forums.legitreviews.com/viewtopic.php?f=9&t=11483

Page 1 of 2

x264 video encoding benchmark

Posted: Sat Sep 08, 2007 7:42 pm
by graysky
I put together a self-contained x264 video encoding benchmark. Techarp kindly agreed to host the file and results at this URL.

Basically, you run the test encode and it will report back frames-per-second values for your machine @ it's clock/overclock level. You can run it at your stock settings and at your overclock settings to see how your machine compares to others in the database.

The database is small right now (as of 08-sep), but as you guys report in results, I will populate it. My goal is to have a representative set of data for many different chips and chipsets. Hopefully, we'll get some Penryn and Phenom data when they become available. Also, if anyone out here has some of the high end AMD chips, please contribute. Instructions and the file are at that url.

Also, please report your results here in this thread. I will keep the data at that url to keep things simple.

Thanks all.

Re: x264 video encoding benchmark

Posted: Sun Sep 09, 2007 9:09 am
by DMB2000uk
---------- RUN1PASS1.LOG
encoded 1749 frames, 68.00 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 68.30 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 68.50 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 68.42 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 68.09 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 16.61 fps, 1826.38 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 14.91 fps, 1826.38 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 16.66 fps, 1826.38 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 16.55 fps, 1826.38 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 16.63 fps, 1826.38 kb/s
Intel E6600 (272*9)
Abit AW9D (975X)
2GB 4-4-4-12 @ 408
XP Pro

Man that benchmark was a lot of messing about to get setup >_<

I think you should get a clever installer now that the program is complete. And I think you should change whatever the dependencies are to relative links so that it doesn't have to run from C:\work2 (I don't like having program folders in the root C: :P)

Dan

Re: x264 video encoding benchmark

Posted: Sun Sep 09, 2007 10:51 am
by graysky
Thanks for the result. Problem with an auto installer is that people don't trust them (myself included). Forcing people to do it manually is much more transparent. About your comment on rel paths. The d2v file requires a known path to the mpg file (just edit it in notepad to see) so it's pretty much required. I chose c:\ because the vast majority of windows systems out there will have a c: to write to :)

Re: x264 video encoding benchmark

Posted: Sun Sep 09, 2007 11:09 am
by DMB2000uk
ok, well you could just leave it like that then 8-)
(I just think more people might be inclined to test if they didnt have to muck around so much :P)

I suppose it is overkill to get the program to tempararily copy the mpg to the c: while it is in use? That way the main program can be anywhere.

Dan

Re: x264 video encoding benchmark

Posted: Tue Sep 11, 2007 1:22 am
by ibleet
---------- RUN1PASS1.LOG
encoded 1749 frames, 69.53 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 69.79 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 69.83 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 69.70 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 69.87 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 16.87 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 16.80 fps, 1826.38 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 16.88 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 16.86 fps, 1826.32 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 16.90 fps, 1826.38 kb/s
See specs in my Sig

Re: x264 video encoding benchmark

Posted: Tue Sep 11, 2007 2:11 am
by graysky
@ibleet - Thanks for running the benchmark... I need a few more things....
1) mem timings and mem core speed you're running it
2) which o/s
3) cpu multiplier and FSB
Asus Crosshair 590 SLI
AMD X2 5200+ Windsor
Evga 7900 GS
Corsair 520w PSU
Corsair xms2 2Gb DDR2 800

Re: x264 video encoding benchmark

Posted: Tue Sep 11, 2007 12:28 pm
by kenc51
Dell Inspiron 6400 Laptop (945PM Chip Set)
Intel T5500 (1.66GHz C2D) 166x10
2GB DDR667 5-5-5-15
X1400 GFX
XP Media Center Edition
Running two instances of FAH, E-Mail and Bittorrent in the backround

Code: Select all

---------- RUN1PASS1.LOG
encoded 1749 frames, 41.86 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 41.97 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 42.08 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 42.07 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 42.30 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 10.26 fps, 1826.21 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 10.32 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 10.27 fps, 1826.38 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 10.30 fps, 1826.37 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 10.29 fps, 1826.33 kb/s
When I get the main rig back up, I'll post more results but it won't be this month!
PS. You made me boot into windows for this :( ;)

Re: x264 video encoding benchmark

Posted: Tue Sep 11, 2007 2:01 pm
by graysky
kenc51 wrote:Dell Inspiron 6400 Laptop (945PM Chip Set)
Intel T5500 (1.66GHz C2D) 166x10
2GB DDR667 5-5-5-15
X1400 GFX
XP Media Center Edition
Running two instances of FAH, E-Mail and Bittorrent in the backround

When I get the main rig back up, I'll post more results but it won't be this month!
PS. You made me boot into windows for this :( ;)
Thanks for the results dude. You had to boot into windows, eh :)

Re: x264 video encoding benchmark

Posted: Tue Sep 11, 2007 11:43 pm
by ibleet
graysky wrote:@ibleet - Thanks for running the benchmark... I need a few more things....
1) mem timings and mem core speed you're running it
2) which o/s
3) cpu multiplier and FSB


1) 5-5-5-18, 2612 MHz
2) windows pro MCE
3) x13, 200.9

I have not done any overclocking whatsoever, so its all stock as per my SIG. Hope this helps.

Re: x264 video encoding benchmark

Posted: Wed Sep 12, 2007 1:15 am
by graysky
ibleet wrote:
graysky wrote:@ibleet - Thanks for running the benchmark... I need a few more things....
1) mem timings and mem core speed you're running it
2) which o/s
3) cpu multiplier and FSB


1) 5-5-5-18, 2612 MHz
2) windows pro MCE
3) x13, 200.9

I have not done any overclocking whatsoever, so its all stock as per my SIG. Hope this helps.
THanks man... only one follow-up... your memory is clocked @ 2612??? Are you sure?

Re: x264 video encoding benchmark

Posted: Wed Sep 12, 2007 6:13 am
by DMB2000uk
lol, I think he means that his CPU is at 2612, and his RAM being at stock will be (close to) 400Mhz.

Dan

Re: x264 video encoding benchmark

Posted: Thu Sep 13, 2007 1:09 am
by ibleet
DMB2000uk wrote:lol, I think he means that his CPU is at 2612, and his RAM being at stock will be (close to) 400Mhz.

Dan
Ya, exactly what Dan said. LoL :lol:

Re: x264 video encoding benchmark

Posted: Thu Sep 20, 2007 3:41 pm
by 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:

Image

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!

Re: x264 video encoding benchmark

Posted: Fri Sep 21, 2007 12:20 am
by ibleet
Without me having to hurt my head analyzing all this data, what exactly did you hope to learn from this vs. what you actually did learn? Yes, I'm lazy that way. :lol:

Re: x264 video encoding benchmark

Posted: Fri Sep 21, 2007 4:45 am
by DMB2000uk
ibleet wrote:Without me having to hurt my head analyzing all this data, what exactly did you hope to learn from this vs. what you actually did learn? Yes, I'm lazy that way. :lol:
I second for a lazy man's summary paragraph :P

Dan

Re: x264 video encoding benchmark

Posted: Tue Oct 30, 2007 4:49 pm
by graysky
Updated the Intel table. It now contains several Yorkfield ES chips including:

Xeon E5330 (Dual board)
Q9550
Q9350

Re: x264 video encoding benchmark

Posted: Wed Oct 31, 2007 9:06 am
by DMB2000uk
do you still need a vista vs xp benchmark difference?

Dan

Re: x264 video encoding benchmark

Posted: Wed Oct 31, 2007 12:57 pm
by graysky
DMB2000uk wrote:do you still need a vista vs xp benchmark difference?
Not anymore... now I'm interested in capturing some new AMD and Intel chips. Thanks for the offer!

Re: x264 video encoding benchmark

Posted: Sat Nov 03, 2007 4:12 pm
by Zertz
Gigabyte P35-DS3L
E4400 @ 3.2Ghz (10x 320)
2x 1GB PC2-8500 5-5-5-15
32bit Vista

---------- RUN1PASS1.LOG
encoded 1749 frames, 89.33 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 90.78 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 89.13 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 90.27 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 90.20 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 22.30 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 22.20 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 22.37 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 22.35 fps, 1826.38 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 22.48 fps, 1826.37 kb/s

Re: x264 video encoding benchmark

Posted: Sun Nov 04, 2007 9:51 am
by kenc51
I thought I'd do some testing with memory speeds & latencies to see if this improves encoding times!

E6885 @ 3.6GHz (9x400)
2GB 1:1 @ DDR800 Cas 3-3-3-10
Vista Ultimate 32bit

Code: Select all

---------- RUN1PASS1.LOG
encoded 1749 frames, 95.25 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 92.39 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 95.79 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 96.31 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 95.97 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 23.94 fps, 1826.37 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 23.67 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 24.04 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 24.22 fps, 1826.37 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 23.97 fps, 1826.37 kb/s
E6850 @ 3.6GHz (8x450)
2GB 2:3 @ DDR1080 Cas 4-4-4-10
Vista Ultimate 32bit

Code: Select all

---------- RUN1PASS1.LOG
encoded 1749 frames, 100.47 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 101.91 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 100.70 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 101.17 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 101.76 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 25.05 fps, 1826.38 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 24.98 fps, 1826.37 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 24.98 fps, 1826.26 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 25.02 fps, 1826.37 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 25.09 fps, 1826.37 kb/s
E6850 @ 3.6GHz (7x514)
2GB 1:1 @ DDR1030 Cas 4-4-4-10
Vista Ultimate 32bit

Code: Select all

---------- RUN1PASS1.LOG
encoded 1749 frames, 101.60 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 101.44 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 101.29 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 102.17 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 102.16 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 25.03 fps, 1826.38 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 24.81 fps, 1826.38 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 25.07 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 25.09 fps, 1826.37 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 25.10 fps, 1826.21 kb/s
It looks like high RAM speed is more important than low latencies.
All times are UTC-06:00
Page 1 of 2

Powered by phpBB® Forum Software © phpBB Limited