Nekochan Net

Official Chat Channel: #nekochan // irc.nekochan.net
It is currently Thu Nov 27, 2014 2:51 pm

All times are UTC - 8 hours [ DST ]


Forum rules


Any posts concerning pirated software or offering to buy/sell/trade commercial software are subject to removal.



Post new topic Reply to topic  [ 3 posts ] 
Author Message
Unread postPosted: Thu Sep 03, 2009 3:40 pm 
Offline
User avatar

Joined: Tue Jun 17, 2008 8:38 pm
Posts: 440
Location: Socal
My primary machine is a 2.4GHz MBP, and because I'm bored I decided to run the c-ray benchmark. Essentially I'm getting a repeatable result of about 876ms. With just one core, I get 1685ms.

Looking at Ian's numbers, a single 2.0GHz G5 does this test in 1073ms. Is the G5 really that much faster than the C2D in FP math? Also strange - my Octane2 completes this test in around 1250ms. That's pretty competitive, given my MBP is about four times faster than my Octane2 in the Blender benchmark. I know we're talking different benchmarks, but the discrepancy seems a little *too* large to me.

Is it possible I'm doing something wrong here? I've tried different combinations of threads from 8 up to 256. My idle time is better than 98%. I used gcc 4.0.1 to do the compile.

_________________
:Onyx2: :Fuel: :Indigo2: :Indigo2IMP: :O3x0:


Top
 Profile  
 
Unread postPosted: Sat Sep 05, 2009 10:47 am 
Offline
User avatar

Joined: Fri Jul 04, 2008 1:08 pm
Posts: 38
Location: Germany
Hi bigD,

which test setup did you actually use? I tried:

Code:
cat scene | ./c-ray-mt -r 1 -t 32 -s 800x600 > foo.ppm


I got an average of ~220 ms on a MBP with a 2,66 GHz Core2Duo (6 MB L2-Cache) using GCC 4.2.1 and Mac OS X 10.6.0.
And an average of ~620 ms on a MBA with a 1,6 GHz Core2Duo (4 MB L2-Cache) using GCC 4.0.1 and Mac OS X 10.5.8.

If you're using the same parameters, then the computation time of your machine should be less than 876 ms.

_________________
:Fuel: :Octane2: :O2: :O2: :1600SW: :Indy: :Indy:

Person A: "I'm going to hack the Internet."
Person B: "Which one?"
Person A: (dramatic pause) "ALL of them!"


Top
 Profile  
 
Unread postPosted: Sun Sep 06, 2009 2:57 pm 
Offline
User avatar

Joined: Tue Jun 17, 2008 8:38 pm
Posts: 440
Location: Socal
tomvos wrote:
Hi bigD,

which test setup did you actually use? I tried:

Code:
cat scene | ./c-ray-mt -r 1 -t 32 -s 800x600 > foo.ppm


I got an average of ~220 ms on a MBP with a 2,66 GHz Core2Duo (6 MB L2-Cache) using GCC 4.2.1 and Mac OS X 10.6.0.
And an average of ~620 ms on a MBA with a 1,6 GHz Core2Duo (4 MB L2-Cache) using GCC 4.0.1 and Mac OS X 10.5.8.

If you're using the same parameters, then the computation time of your machine should be less than 876 ms.


Thanks for the info! It was very helpful. I was using the same parameters that you were, so I decided to recompile c-ray. After a recompile, my computation time went down to 343ms. I realized that I never actually built c-ray before - I was using the stock binary that came with the archive.

Thanks!

_________________
:Onyx2: :Fuel: :Indigo2: :Indigo2IMP: :O3x0:


Top
 Profile  
 
Display posts from previous:  Sort by  
Post new topic Reply to topic  [ 3 posts ] 

All times are UTC - 8 hours [ DST ]


Who is online

Users browsing this forum: No registered users and 1 guest


You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot post attachments in this forum

Search for:
Jump to:  
cron
Powered by phpBB® Forum Software © phpBB Group