Video Encoding

Since MPlayer (MEncoder) do not come with RPMs, we compile the binaries from source with no optimizations. We go through the standard ./configure and make commands for the v1.0pre5 source code. Notice that this benchmark has changed since the last time we ran it.

Below is the command that we used to produce a DivX .avi from a 700MB MPEG2.

time mencoder sample.mpg - nosound - ovc lavc vcodec=mpeg4:vpass=2 - o sample.avi

Frames per Second, more are better. Frames per second are not calculated in the program, but taken by dividing the number of frames in the file by the time reported in the console.

MEncoder 3.3.1

Generally, our tolerance for this benchmark was about 1%.

Audio Encoding

Lame was compiled from source without optimizations. We only ran ./configure and make without any flags.

We ran lame on a 700MB .wav file using the command equivalent to the one below:

lame sample.wav -b 192 -m s -h >/dev/null

Encoding time, lower is better.

lame 3.96

Lame shows us that from platform to platform, there is not a significant difference between VIA or NVIDIA. Our tolerance for this test was less than 1% and was extremely replicable.

Index Rendering Tests
Comments Locked


View All Comments

  • - Saturday, October 24, 2009 - link">
    (air jordan, air max, shox tn, rift, puma, dunk sb, adidas) nike jordan shoes 1-24 $32
    lv, coach, chane bag $35
    COOGI(jeans, tshirts, hoody, jacket) $30
    christian audigier(jeans, tshirts, hoody) $13
    edhardy(shoes, tshirts, jeans, caps, watche, handbag) $25
    Armani(jeans, tshirts,) $24
    AF(jeans, coat, hoody, sweater, tshirts)Abercrombie & Fitch $31">
  • gherald - Wednesday, July 21, 2004 - link

    Must be something wrong with firefox then, because I've tried disabled all popup protection to the point where I get a lot of ads at other sites, but still cannot open this comments page.

    Even if it works perfectly for everyone else in the world, I still say it's stupid to have this in a popup.

    -posted from opera
  • TrogdorJW - Tuesday, July 20, 2004 - link

    #21 - does the registry corrupt itself, or does the user cause the corruption, or is it spyware/virus/trojan related? I'm betting on the last more than the others. Of course, if you're constantly tweaking your setup, problems can occur, but that happens with ANY operating system. Hell, after getting XP configured and setup properly, I didn't need to do a reinstall for over two years, and the only reason I ended up reinstalling was when my motherboard died on me.

    The only thing MS really needs to fix now is some of the default settings. Storing individual temp files for each user? Why would we actually want that? Setting aside 10% of your hard drive space for Temporary Internet Files (which are almost never used), and another 10% for System Restore!? That's stupid. If you need to use System Restore to return to a point more than three months in the past, there's a decent chance it won't work or will cause more problems than it fixes. However, these aren't huge problems; they're just annoyances.
  • sprockkets - Tuesday, July 20, 2004 - link

    No operating system should fatally crash by simply ending task or terminating a process.

    You are right 18#, it isn't hard keeping it clean, but then again I end up reinstalling it about every 8 months since the registry corrupts itself, not fatally, but just to make your favorite app not work anymore, or it take forever to boot up.
  • kd4yum - Tuesday, July 20, 2004 - link

    Kristopher: Any idea whatever happened to the MSI K8N 939-pin motherboard you folks used in the High End System Guide a few weeks ago? I can not find that motherboard anywhere. Has MSI scrapped it? When and where will it be for sale?
  • balzi - Tuesday, July 20, 2004 - link

    #15 -- I think something screwed up on the articles Gaming Benchmarks. UT2004 has a native Linux 64 bit version - so it would run a 64bit app. on 64 bit drivers, and i assume they saw awesome FPS gains. however this page:
    has no graphs relating to UT2004 64bit.. hmm?!?!?

    On the SATA RAID support.. I just bought a ASUS K8V (K8T800) .. granted it's a S754 board but the VIA southbridge remains the same [8237] I think.. anyway.. I had big problems getting hte RAID going, in fact I didn't get it going and had to opt for the Promise RAID controller onboard.. Gigabit Ethernet was provided by a Marvel Yukon chipset.. ASUS chose good here.. SuSE 9.0 picked it up eventually. though not straigth away.

    I sincerely hope VIA see some of these comments about their on-die SATA RAID support for Linux.

    as a consolation - I used the VIA instructions with some minor changes to get the Promise controller going.. they were sufficiently vague yet all-encompassing to be applicable. :)

  • tfranzese - Tuesday, July 20, 2004 - link

    Linux isn't without it's problems #17. I wish I had the time or willingness to get more into Linux, but for all my needs (programming) it gets the job done without me having to spend too much time learning anything extra. Bashing Windows is quite sad though on all your parts, it isn't too hard to keep a clean and stable Windows installation.
  • sprockkets - Tuesday, July 20, 2004 - link

    The last BSOD I got on someone's computer was simply to end process on a trojan horse in winxp. Sad.
  • tfranzese - Monday, July 19, 2004 - link

    I can't remember the last time I had a BSOD when I wasn't messing with my hardware setup changing things around.

    I'm sad for people who still live in the past.
  • TrogdorJW - Monday, July 19, 2004 - link

    #14 - Oh, yeah, I get blue screens ALL the time while gaming on XP. Mostly, it involves underwater scenes, though. Last time I had a BSOD on XP? Probably a few weeks ago. Last time I had a BSOD on a system that wasn't *overclocked*? I can't even remember.

    On the article:
    "Mental ray seems optimized for NVIDIA, but it does not seem to provide a distinct advantage going from 32-bit to 64-bit architecture." Duh - you mention that only a 32-bit version is available, so why should it benefit at all from 64-bit? Unlike games, which rely heavily on graphics drivers, Mental Ray is more of a CPU dependent application, so 64-bit graphics drivers aren't going to help it score higher.

    "Surprisingly, the difference between 64-bit and 32-bit UT2004 was a little more than we expected. The case for 64-bit is extremely strong with this benchmark." I'm a little confused here - it seems to me that the difference between 32-bit and 64-bit was much larger on W:ET than on UT2K4. Still, it's good to see *any* performance increase under 64-bit for a game. Is UT2K4 actually available in both 32-bit and 64-bit Linux binaries now? That wasn't made entirely clear in the article. IIRC, you're still running UT2K4 as a 32-bit game on a 64-bit OS, right? Only the drivers are 64-bit enabled.

    Overall, though, great article. With the updated Nvidia graphics drivers that provide support for 4K stack kernels (like Fedora Core 2), things are getting better. On a side note, I was finally able to get the Nvidia driver to run properly on my friend's 3000+ system (Chaintech ZNF-250 motherboard) by installing it manually from the command line and then run SaX2 to configure X. The old Nvidia driver crashed the system when I tried to install it, although AT never seemed to have that problem.

Log in

Don't have an account? Sign up now