x264 HD Benchmark Released
 

Simply put, it is a reproducible measure of fast your machine can encode a short, HD-quality video clip into a high quality x264 video file. It's nice because everyone running it will use the same video clip and software. The video encoder (x264.exe) reports a fairly accurate internal benchmark (in frames per second) for each pass of the video encode and it also uses multi-core processors very efficiently. All these factors make this an ideal benchmark to compare different processors and systems to each other.

What's x264? It's more or less the next generation Xvid/DivX codec for many people.

http://www.techarp.com/showarticle.aspx?artno=520

The original x264 benchmark encoded a 720x480 @ 1.823kbps clip
the x264 benchmark uses a HD source 1280x720 @ 3.963kbps

Stock Q6600 does it in ~2min
An Athlon XP 3200+ needs 13min
A P4 @ 3ghz needs 14+min
A P2 @ 450Mhz takes a while... 5hours12min

How fast can your PC decode the x264 HD sample?

Look for it in our next memory review(s) as well ;)

I had a go with my laptop:

---------- RUN1PASS1.LOG
encoded 1442 frames, 22.40 fps, 3905.08 kb/s

---------- RUN2PASS1.LOG
encoded 1442 frames, 22.59 fps, 3905.08 kb/s

---------- RUN3PASS1.LOG
encoded 1442 frames, 22.51 fps, 3905.08 kb/s

---------- RUN4PASS1.LOG
encoded 1442 frames, 22.51 fps, 3905.08 kb/s

---------- RUN1PASS2.LOG
encoded 1442 frames, 5.61 fps, 3942.92 kb/s

---------- RUN2PASS2.LOG
encoded 1442 frames, 5.60 fps, 3942.92 kb/s

---------- RUN3PASS2.LOG
encoded 1442 frames, 5.61 fps, 3942.92 kb/s

---------- RUN4PASS2.LOG
encoded 1442 frames, 5.61 fps, 3942.92 kb/s


But it doesn't provide an overall time for completion ...

ya, realized that too, I'm at 10fps for the RUN1PASS1, what CPU you got? ;

Testing Core 2 Quad at 3.2Ghz, figures in the high 60's for pass 1.

A64+ 3000+ S754 is dated ;)
E8300 ready for install!

I'm still alittle confused by this as well. This is what I have running about ten different settings;

9x333FSB Q6600 P35C-DS3R Patriot DDR3-1600 running 1333MHz 7-7-7-20

---------- RUN1PASS1.LOG
encoded 1749 frames, 160.83 fps, 1850.94 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 160.59 fps, 1850.94 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 160.15 fps, 1850.94 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 160.59 fps, 1850.94 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 161.05 fps, 1850.94 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 42.64 fps, 1829.42 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 42.77 fps, 1829.16 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 42.66 fps, 1829.24 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 42.56 fps, 1829.36 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 42.68 fps, 1829.15 kb/s

Next Q6600 7x400FSB Patriot DDR3-1600 running at 1600MHz 7-7-7-20

---------- RUN1PASS1.LOG
encoded 1749 frames, 154.82 fps, 1850.94 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 155.25 fps, 1850.94 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 155.26 fps, 1850.94 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 155.47 fps, 1850.94 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 155.47 fps, 1850.94 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 40.24 fps, 1829.19 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 40.24 fps, 1829.31 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 40.32 fps, 1829.44 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 40.24 fps, 1829.45 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 40.19 fps, 1829.19 kb/s

Shouldn't the FPS be better in the latter benchamrk?

3ghz vs 2.8Ghz, normal that the first run is faster, you got a 200mhz CPU advantage.

FSB/MEM hasn't been impacting performance for quite a while now...

Here's a quick chart with all data.

The articloe is finished it's this I need help on. I deciced to forgo ViMArk until next (the DDR3 Round-Up).

Can you email / explain which figures you want me to use from this data?

maybe take averages from Pass1 and Pass2, keeping 2 numbers in total? would reduce clutter and increase readability :)

Guys, the benchmark wasn't meant to be a standalone thing... if you run it and then post your results, I enter the data into the ongoing excel sheet and update the main table.

@Liquid3D - great dataset dude. I'll get them all in there if you can provide me with some extra info on that test system (the info I need is described on the techarp page towards the bottom).

It'd be cool to see you guys use my benchmark in your reviews :)

P.S. I just discovered this place via a google search for something unrelated, otherwise I would've replied sooner :)

@Liquid3D - with results this fast I'm thinking you actually ran the older SDTV benchmark. Even dual quad Xeon Skulltrail system didn't score into the 160's on the HD test.

used here

http://www.madshrimps.be/?action=get...&articID=6 71

Did you still need that? The info provided in these benchmarks derives from the Gigabyte P35C-DS3R (F10 Rev.1.0) Windows XP SP2 OS, I will be running the DDR3 round-up on a Gigabyte X48T-DQ6 with the same Q6600 (95W TDP SLACR) processor, the same BFG 8800Ultra, and Seagate Barracuda 167GB SATA-II