x264 video encoding benchmark

[graysky]

@fallwind: Thanks again!

To compare back to the Q6600 results @ 9x333, you can drop it down to the 3/5 = 1,111 MHz divider and run it once last time

Actually, I don't under understand the 1,066 w/ 333 MHz FSB.

For 333 MHz FSB, the 5 ratios are:
1/1 = 667 MHz
5/4 = 833 MHz
3/2 = 1,000 MHz
5/3 = 1,111 MHz
2/1 = 1,333 MHz

Does the P5K support a divider of 5/8 = 1,066?

[tet5uo]

On my 680i you can just use 1333fsb and 5:4 divider to get 1066 ram.

[graysky]

@tet5uo... ok.. so there really as a 8/5 divider then. My P5B only has 5 of them listed above.

[graysky]

Updated the tables with another 45 nm chip: the QX9650 -- both at stock levels and @ overclocked to 4.2 GHz (thanks fallwind)! 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.

[ewitte]

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).

I hear reports of massive gains with SSE4. Like 60%.

[soulstaker]

Pentium 4 631 ( 2.4 Ghz ) @ 12x200, VIA P4M900, 4-4-4-12 @ 266 Mhz, XP Pro Sp2

---------- RUN1PASS1.LOG
encoded 1749 frames, 28.09 fps, 1850.89 kb/s

---------- RUN2PASS1.LOG
encoded 1749 frames, 28.24 fps, 1850.89 kb/s

---------- RUN3PASS1.LOG
encoded 1749 frames, 28.31 fps, 1850.89 kb/s

---------- RUN4PASS1.LOG
encoded 1749 frames, 28.29 fps, 1850.89 kb/s

---------- RUN5PASS1.LOG
encoded 1749 frames, 28.44 fps, 1850.89 kb/s

---------- RUN1PASS2.LOG
encoded 1749 frames, 7.19 fps, 1826.32 kb/s

---------- RUN2PASS2.LOG
encoded 1749 frames, 7.19 fps, 1826.38 kb/s

---------- RUN3PASS2.LOG
encoded 1749 frames, 7.20 fps, 1826.37 kb/s

---------- RUN4PASS2.LOG
encoded 1749 frames, 7.21 fps, 1826.38 kb/s

---------- RUN5PASS2.LOG
encoded 1749 frames, 7.21 fps, 1826.37 kb/s

I'm have been searching for a benchmarking tool like this for a while. Thanks for your efforts


I'll run it on my pc this weekend.

[mAJORD]

First Phenom result.. maybe?

Does quite well for clockspeed:

OS: WIN XP 32 SP2

[graysky]

Very cool - thanks for that result (this is the first Phenom actually)! What is the chipset on that MB? Also, I'm assuming 11x243 is overclocked, no? What is the stock speed and can you run it again @ stock?

[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.