 |
|
|
|
|
|
| |
| |
|
|
|
|
| |
| |
|
|
I whipped up a simple scene for the 256-character scene competition and now
after a friend rendered it on his machines I've got a dumb question about
different processors. Any thoughts as to how well each of the following
processors should perform compared to each other? I ask because results I
saw weren't what I expected... So before I say what the times were, can
somebody tell me how well they are *supposed* to perform? All running
version 3.6 and by now I think we should have all settings pretty much the
same, less whatever it is that I forgot. ;-)
Thanks,
Charles
generically and not in order of render time:
A) laptop p3 1ghz (windows)
B) laptop g4 867mhz (osx)
C) desktop p4 2.4ghz (windows)
D) desktop socket-a athlon 2.0ghz (windows)
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
Charles C wrote:
> Any thoughts as to how well each of the following
> processors should perform compared to each other? I ask because results I
> saw weren't what I expected... So before I say what the times were, can
> somebody tell me how well they are *supposed* to perform?
<snip>
> generically and not in order of render time:
> A) laptop p3 1ghz (windows)
> B) laptop g4 867mhz (osx)
> C) desktop p4 2.4ghz (windows)
> D) desktop socket-a athlon 2.0ghz (windows)
Assuming all systems have sufficient memory and the scene does not use
functions (that is, the function keyword, isosurfaces or parametric), I
would for most scenes expect, fastest to slowest, the order being (with
possible between 1st and 2nd depending on exact P4 and Athlon system
type/config):
C, D, A, B
Why?
Thorsten
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
> A) laptop p3 1ghz (windows)
> B) laptop g4 867mhz (osx)
> C) desktop p4 2.4ghz (windows)
> D) desktop socket-a athlon 2.0ghz (windows)
Using official 3.6.x binaries, from fastest to slowest: D > C > B > A
Wrong guess?
- NC
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
Nicolas Calimet nous apporta ses lumieres en ce 01/10/2006 18:22:
>> A) laptop p3 1ghz (windows)
>> B) laptop g4 867mhz (osx)
>> C) desktop p4 2.4ghz (windows)
>> D) desktop socket-a athlon 2.0ghz (windows)
>
> Using official 3.6.x binaries, from fastest to slowest: D > C > B > A
> Wrong guess?
>
> - NC
Considering that my 5~6 years old 1400MHz Athlon is only beaten by 21% by a P4
3GHz. I tend to agree with you.
--
Alain
-------------------------------------------------
HAMMER: Originally employed as a weapon of war, the hammer nowadays
is used as a kind of divining rod to locate expensive bike parts not
far from the object we are trying to hit.
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
Thorsten had it right, although it gets more interesting when you look at
the times. Here are the times:
3min 53sec C) desktop p4 2.4ghz (windows)
"5 & 1/2 min" D) desktop socket-a athlon 2.0ghz (windows)
7min +/- 15sec A) laptop p3 1ghz (windows)
"27min" B) laptop g4 867mhz (osx)
D) and B) belong to my friend who didn't give me exact seconds. On his
desktop athlon, he first ran it through VNC from the mac but then re-ran it
without to get the slightly better time reported here. The mac's time is
after he stopped playing mp3s etc. With that, the two desktop times are
"left-alone" times and the two laptop times include online communications,
pointing, clicking, typing; nothing too heavy. The p3 consistently got
about 6:45 if left alone.
Somewhere I got the idea that the G4 was pretty efficient per clock speed at
doing floating point so even at a slightly lower clock speed I would have
expected it to be somewhat faster or even just "somewhat" slower than the
p3 1ghz. Yet it took the g4 roughly 4 times as long as the p3. The same
thing goes for the athlon. Shouldn't it at 2ghz have been MORE than twice
as fast as the p3 at 1ghz? Shouldn't the athlon have met or beaten the
2.4ghz p4?
With this scene, memory shouldn't be an issue. The scene consists of a few
dozen simple primitives and nothing special or fancy, and no functions.
Like I said - it wasn't what I expected. Any more thoughts?
Thanks,
Charles
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
Charles C wrote:
> Somewhere I got the idea that the G4 was pretty efficient per clock speed at
> doing floating point so even at a slightly lower clock speed I would have
> expected it to be somewhat faster or even just "somewhat" slower than the
> p3 1ghz.
That applies only to a desktop system, and if you have it in a notebook most
likely power saving was enabled (it is by default, cuts clock by half), plus
if it was in an iBook rather than a PowerBook, memory will have been slower.
Plus, if it was running on Mac OS X rather than Mac OS 9, you lost another
10%-15% right there. Plus, if you did it with display enabled, that would
again change results, especially on Mac OS X that simply is slower due to
the double-buffered windows forced on applications (it especially hurts if
you have less than 32 MB of graphics card RAM).
Thorsten
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
Thorsten Froehlich <tho### [at] trf de> wrote:
> Plus, if it was running on Mac OS X rather than Mac OS 9, you lost another
> 10%-15% right there.
Didn't they fix that problem long time ago?
But naturally if the laptop is so old, it may be running a very old
version of MacOS X too...
--
- Warp
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
Warp wrote:
> Thorsten Froehlich <tho### [at] trfde> wrote:
>> Plus, if it was running on Mac OS X rather than Mac OS 9, you lost another
>> 10%-15% right there.
>
> Didn't they fix that problem long time ago?
It can't be fixed, the GUI eats that much.
Thorsten
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
Thorsten Froehlich <tho### [at] trfde> wrote:
> > Didn't they fix that problem long time ago?
> It can't be fixed, the GUI eats that much.
If that was true, then *all* GUI'ed OSes would eat 10-15% of CPU time
with POV-Ray. Obviously this is not the case.
I don't understand what do you mean by "it can't be fixed".
--
- Warp
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
| |
|
|
Warp wrote:
>> It can't be fixed, the GUI eats that much.
>
> If that was true, then *all* GUI'ed OSes would eat 10-15% of CPU time
> with POV-Ray. Obviously this is not the case.
> I don't understand what do you mean by "it can't be fixed".
It is the way Mac OS X is. Now, look, I don't care if you don't understand
it, or to get you understand it. It is just a fact, period. If you don't
believe me, get yourself a Mac and test yourself.
Thorsten
Post a reply to this message
|
|
| |
| |
|
|
|
|
| |
