x264 HD Video Encoding Performance

Graysky's x264 HD test uses x264 to encode a 4Mbps 720p MPEG-2 source. The focus here is on quality rather than speed, thus the benchmark uses a 2-pass encode and reports the average frame rate in each pass.

 

x264 HD Encode Test - 1st Pass - x264 0.59.819

Video encoding and other thread heavy tasks are best suited for AMD's more-is-better core strategy. You get six cores on the 1100T and three with the 455, in both cases the competing Intel part doesn't stand a chance. In the second encoding pass the Athlon II X3 is over 30% faster than the Pentium G6950. Without unlocking additional cores, the Phenom II X2 565 BE doesn't impress here.

x264 HD Encode Test - 2nd Pass - x264 0.59.819

PAR2 Multithreaded Archive Recovery Performance

Par2 is an application used for reconstructing downloaded archives. It can generate parity data from a given archive and later use it to recover the archive

Chuchusoft took the source code of par2cmdline 0.4 and parallelized it using Intel’s Threading Building Blocks 2.1. The result is a version of par2cmdline that can spawn multiple threads to repair par2 archives. For this test we took a 708MB archive, corrupted nearly 60MB of it, and used the multithreaded par2cmdline to recover it. The scores reported are the repair and recover time in seconds.

Par2 - Multithreaded Par2cmdline 0.4

The Phenom II X6 is competitive in our Par2 test, the Athlon II X3 455 is significantly faster than the Pentium G6950 and the Phenom II X2 565 falls short of its target. Rinse and repeat.

7-Zip Benchmark Performance

Included in 7-zip is a pure algorithm test that completely removes IO from the equation. This test scales with core count and as a result we get a good theoretical picture of how these chips perform. Note that the actual 7-zip compression/decompression process is limited to 2 threads so there's no real world advantage to having more cores.

7-Zip Benchmark

3D Rendering Performance Gaming Performance
Comments Locked

65 Comments

View All Comments

  • Finally - Tuesday, December 7, 2010 - link

    one thing is missing.
    I'm much less interested in overclocking than I am interested in undervolting.
    3 Weeks ago I bought two Phenom II X2 555 BE C3s for my girlfriend's new PC and mine - and guess what? Both unlocked to quad-cores easily. I was even able to lower the CPU voltage from 1.251V to a mere 1.141V. As a power consumption-meter is on its way to me, I will be able to report power saving numbers, if anyone is interested.

    All this 4-core-goodness I got for a mere 75€ a pop.
    If that's not great performance for an unbeatable price I don't know what is...
  • chrnochime - Wednesday, December 8, 2010 - link

    And like was mentioned in the article it's not guaranteed that whoever buys the 555/565 BE would be able to unlock the other two cores and run them just fine without instability.

    When it's a gamble and not 100% success rate, people who value their time and not wanting to return CPUs and getting another to test tend to either go down to the cheaper x3 or pay a bit more for the i3.
  • ajp_anton - Tuesday, December 7, 2010 - link

    I noticed you're using the x264 pass1 test for load power consumption.
    Is this really a good choise? All cores aren't maxed out in this test. This is obvious when knowing what x264 is actually doing in pass1 versus pass2, and comparing the speeds confirm this.
    In pass2, all Phenom II's (x2, x4, x6) have exactly the same speed per core per GHz.
    In pass1, the speed bumps are far from the nice linear scaling in pass2. The x6 is only twice (2.13x) as fast as the x2, so almost two cores are idle.
  • Anand Lal Shimpi - Tuesday, December 7, 2010 - link

    You'll see this change in the next month when we revamp our Bench suite :)

    Take care,
    Anand
  • nitrousoxide - Tuesday, December 7, 2010 - link

    Yeah, expecting that. I don't quite understand why putting the stupid sysmark on the test...it just can't tell any difference between processors with different performance :)
  • iwodo - Tuesday, December 7, 2010 - link

    There are rumours floating around that Intel is gonna make BIG price cut soon for holiday season due to lower then expected demand, clearing stocks for Sandy Bridge, as well as more people buying iPad then PCs.

    SandyBridge will be a top to bottom chip, leaving Current Nehalem for Servers. ( Which is doing VERY well in that area )

    Some of the performance data are already leaked, the only things that is left is on the GPU side as well as Official benchmarks.
  • yuriylsh - Tuesday, December 7, 2010 - link

    just got a notification from Micro Center about $80 instant savings on i7-950, which means $200 for 3GHz Core i7 - not a bad deal. Is it starting?
  • RyuDeshi - Wednesday, December 8, 2010 - link

    MicroCenter has been selling the 950 for $199 for a long time now. It has been on SlickDeals front page many times.. They just do that to get traffic to their store, then try to sell you everything else you don't need.
  • jaydee - Tuesday, December 7, 2010 - link

    The Phenom II X2 565 is 18% (idle) and 23% (load) more efficient than the Phenom II X2 555?
  • MrSpadge - Tuesday, December 7, 2010 - link

    The board has changed to a much more efficient one. It's approximately a constant offset between both configurations, as evidenced by the differences in idle numbers.

    MrS

Log in

Don't have an account? Sign up now