TC schrieb:
> I find the results rather shocking - I would not have guessed that switching 
> from 32 to 64 bit would make such a difference.

Neither would I. I had expected the difference to be quite marginal, 
having thought that the only significant benefit of 64-bit was in making 
more memory available for a single application.

> Since you seem to be intimately involved in Pov Ray beta testing,

I actually consider myself more involved in development than in testing, 
but of course I need to test what I have implemented, so yes.

 > maybe you
> can answer the question if the benchmark makes extensive use of memory. 
> Maybe the difference between 3 and 6 GB would account for the difference 
> between 32/64 OS.

Definitely not - I just checked: While rendering the benchmark, POV-Ray 
is utilizing just about 30 MB more than when idle.

I've actually never ever managed to reach even the 2 GB limit on my old 
32-bit machine (well, it didn't have more installed anyway). On the 
64-bit Linux machine, the worst thing I ever observed was about 700 MB 
continuous load with a peak of 800 MB during parsing, IIRC (which was 
actually a problem, becaue I had only 4 GB installed at that time, and 
was running a full-throttle MegaPOV render - i.e. four separate 
instances of POV-Ray. The initial peak memory load kicked the whole 
system into "permanent swapping mode", with the MegaPOV instances 
busying themselves kicking each other (and of course everything else) 
out of physical memory instead of doing anything productive. Operating 
the system was of course no fun anymore until I had managed to pause one 
of the processes. Sustained memory load was low enough that I could 
ultimately resume the fourth process again, but startig them up 
simultaneously was too much.)

Post a reply to this message