On povbench it lists a 400 mhz G4 under OSX (not the obviously fake powerpc
listing) renderng skyvase.pov in twelve seconds, better than everything else
but the PS2.
Can that be correct? I thought the G4's had poor fpu's.
Any help would be much appreciated.
In article <3a932564@news.povray.org> , "Ed Kaiser"
<eka### [at] camdentdsnet> wrote:
> On povbench it lists a 400 mhz G4 under OSX (not the obviously fake powerpc> listing) renderng skyvase.pov in twelve seconds, better than everything else> but the PS2.> Can that be correct? I thought the G4's had poor fpu's.> Any help would be much appreciated.
The G4 FPU is slightly faster than that of the G3s, but surely not that
fast. The reason for this result is probably a completely wrong
setting. The Benchmark settings are supplied as command line parameters
which are not accessible to mac users in exactly the same way (even INi
files will work a bit different). In short, all mac results in there
are most likely not based on correct setings unless someone actually
looked into the Mac source code to find out what exactly to set.
On the other hand, too many people submit junk and apparently nobody
filters it out. Just look at the numerous different results for PCs -
twenty tests of the same processor cannot give you results that differ
in a range of about five times between the fastest and the slowest!
Thorsten
____________________________________________________
Thorsten Froehlich
e-mail: mac### [at] povrayorg
I am a member of the POV-Ray Team.
Visit POV-Ray on the web: http://mac.povray.org
On Wed, 21 Feb 2001 16:40:14 -0600 Thorsten Froehlich wrote:
>On the other hand, too many people submit junk and apparently nobody>filters it out. Just look at the numerous different results for PCs ->twenty tests of the same processor cannot give you results that differ>in a range of about five times between the fastest and the slowest!
I mean no disrespect to Mr. Haveland and his work on the PovBench site but
I look at the posted results with a grain of salt. I consider the benchmark
invalid if something other than an official binary was used. I see so many
listings for custom compiles and there is no way to tell how the source
might have been modified.
--
Alan - ako### [at] povrayorg - a k o n g <at> p o v r a y <dot> o r g
http://www.povray.org - Home of the Persistence of Vision Ray Tracer
PS2? Surely you don't mean PlayStation 2!?
>better than everything else>but the PS2.
______
David McCabe
mcc### [at] yahoocom
http://homepage.mac.com/davidmccabe/
Jesus loves you!
tds