Video Encoding

DivX 5.21 with AutoGK

Armed with the DivX 5.21 and AutoGK, we took all of the processors to task at encoding a chapter out of Pirates of the Caribbean. We set AutoGK to give us 75% quality of the original DVD rip and did not encode audio.

DivX 5.21

Dothan's DivX performance was dismal at best, and although Yonah's two cores improves things, it's still not enough to be competitive with the Athlon 64 X2.

Windows Media Encoder 9 HD

Our homebrew WME9 test is up next:

Windows Media Video Encoder 9

Much like the DivX test, we see that although Yonah has come a long way from Dothan, it is still not competitive with the likes of the Athlon 64 X2. It is a shame, as we were hoping for more out of Intel's FP/SSE enhancements.

Multimedia Content Creation Performance Gaming Performance
Comments Locked

135 Comments

View All Comments

  • lee1026 - Wednesday, November 30, 2005 - link

    They still can't beat the A64 3800+? sad, intel, sad.
  • Pythias - Wednesday, November 30, 2005 - link

    Graphs I looked at, it appeared the two were neck and neck. And the yonah cosumes less power.
  • Darth Farter - Wednesday, November 30, 2005 - link

    well, what about the RAM power consumption difference... is this censored or something?

    Yonah's 1.8V DDR2 ram opposed to the Athlon X2's 2.6V DDR ram

    if the reviewer really measured "Total System Power" this will factor in... the same reason why the Pentium M is still king of Battery Life on mobile platforms...


    When Socket M2 arrives Q2 2006 it could prove better for performance and less for power requirements again.... and without being transitioned to 65nm process yet.

    anyway, this is not cpu isolated and therefore I'd suggest just mentioning it includes the worse DDR power consumption (apples to apples) before the community blames the cpu only like in the comments here.

    (btw, if there would be any way to isolate the cpu power usage only without motherboard and ram I would really like to know. (I thought I saw something like that on overclockers.com a few moths back.)


    anyway could my point matter on the graphs on last page Anand?
  • coldpower27 - Wednesday, November 30, 2005 - link

    This is the price you pay for having an On Die Memory Controller, Intel can adopt new memory technologies quciker then AMD can as they don't need another revison of a CPU plus a Socket change due to the memory controller, this is the price AMD paid to get the added performance, and reduced power cosumption of having the memory cnotroller on Die and not needing a Northbridge. This is AMD's choice and they have to live with the consequences of this choice.
  • Zebo - Friday, December 2, 2005 - link

    Nevermind they did change thier socket.
  • coldpower27 - Sunday, December 11, 2005 - link

    I think they wanted to make sure that only the i945M Chipset series is compatible with the Dual Core Yonah and not run the risk of people sticking these into older i915M and the currently available desktop Pentium M boards.

    This is a move for profit of course, as Intel wants to sell their new i945M chipsets as a Centrino bundle with Yonah.
  • nserra - Wednesday, November 30, 2005 - link

    AMD 64 2.0Ghz at .13 at full load does 68W
    AMD 64 2.0Ghz at .09 at full load does 43W
    AMD 64 2.0Ghz at .65 at full load maybe ~27W


    AMD 64 2.0Ghz at .13 at idle does 19W
    AMD 64 2.0Ghz at .09 at idle does 13W
    AMD 64 2.0Ghz at .65 at idle maybe ~9W
  • tayhimself - Wednesday, November 30, 2005 - link

    90nm 3800x2 is around 68 W. Take out 8 or so for the northbridge. There is no 130nm x2 IIRC
  • nserra - Wednesday, November 30, 2005 - link

    Sorry I forgot to mention, its single core amd processors not dual.
  • Viditor - Wednesday, November 30, 2005 - link

    quote:

    90nm 3800x2 is around 68 W


    Someone who doesn't know the difference between TDP and power usage...

Log in

Don't have an account? Sign up now