From: dwex@mtgzfs3.att.com (David E. Wexelblat) Subject: Re: PEX Performance Date: Tue, 1 Jun 1993 00:11:05 GMT
In article <1udmju$e24@Tut.MsState.Edu> seyfarth@whale.st.usm.edu (Ray Seyfarth) writes:
> We are considering using Linux with PEX for graphics classes.
> The Xfree86 FAQ says the PEX software has poor performance.
> However we expect student projects to be fairly small.
>
> There are a few questions:
>
> 1. Will installing PEX impact X11 performace if no PEX applications
> are running? Specifically how much memory would be needed by PEX
> and does it consume CPU time while idle?
PEX makes the X server about 350k larger, as I recall. Linking with PEX
has no impact on performance if no PEX applications are running (except
perhaps with swapping - I have no idea if binary size impacts paging
performance on Linux).
>
> 2. Does PEX produce reasonable output under Linux? The CPU time
> should not matter much.
PEX produces reasonable output on any 8-bit pseudo-color platform.
The results are not an issue; the performance is.
>
> 3. Does a 66MHz 486 system with 8 MB RAM and 200 MB disk sound
> reasonable for running PEX on Linux?
No. In my opinion, NO Intel box is a reasonable platform for PEX.
PEX is floating-point hungry like nobody's business. I've run PEX on
a SparcStation LX (which includes the GX graphics coprocessor - 106k
xStones). The performance there is horrible. On an SVGA-based 486,
it's unbelievably bad; acceleration won't make much difference, because
the issue is the calculation, not the display.
I don't believe that any platform with 3D support in hardware can
possibly be considered a reasonable platform for PEX.
I think people would be far better off writing their own simple 3D
packages to use on top of standard X. The 'sphigs' package, used
in Foley, van Dam, Feiner, and Hughes is available from Brown (I
don't remember the FTP site, unfortunately), runs on top of X, and
likely does everything you need for your class.
>
> Thanks,
>
> Ray Seyfarth
> --
> Ray Seyfarth University of Southern Mississippi
> seyfarth@whale.st.usm.edu (601)266-4859