From: Christoph Weber (weber_at_scripps.edu)
Date: Mon Jul 17 2006 - 16:18:00 CDT

John's suggestions piqued my interest, so I ran a few tests on a
MacBook Pro under MacOSX and Windows XP Pro. The x1600 chipset's
performance seems insensitive to chosen screen resolution between
640x480 and the native 1440x900 on both OSes. Bitdepth degraded
performance by about 30% under MacOSX when I chose 256 colors (8bit).
Thousands (16bit) and Millions (24bit) of colors were identical. Under
Windows I have 32bit and 16bit available, both of which yield the same
performance.
What sets the ATI graphics apart from nVidia offerings is that VMD
performance is not dependent on the size of the 3D window. With the
nVidia cards I've seen performance degrades noticeably if you enlarge
the 3D window.

Christoph

John Stone wrote:
> Hi Ben,
> The x1600 may simply be suffering because it's a new chipset and has
> relatively young/immature drivers. I agree that one would expect the x1600 to
> decimate the EG2, GMA900 etc. What color depth and display resolution are you
> using on your machine? I've seen a number of ATI cards that would perform
> nicely at medium resolution, but would start losing performance fast when
> the display resolution was raised beyond a particular threshold, or when
> the color depth was set to anything other than 32-bit truecolor. (for
> some reason the ATI cards historically favored particular color depth modes)
> You'll want to check the documentation of your card for their best performance
> suggestions. Try running the card at 1280x1024 and see if your performance
> changes at all. Also, be sure that you're running the latest driver of course.
>
> John Stone
> vmd_at_ks.uiuc.edu

-- 
|  Dr. Christoph Weber              Sen. Applications Specialist
|  Research Computing, TPC21        858-784-9869 (phone)
|  The Scripps Research Institute   858-784-9301 (FAX)
|  La Jolla  CA  92037-1027         weber_at_scripps.edu
|  http://www.scripps.edu/~weber/
"When a distinguished but elderly scientist states that something
is possible, he is almost certainly right. When he states that
something is impossible, he is very probably wrong."  - Arthur C. Clarke