[Bf-committers] blender as a hardware benchmarking tool

[Campbell Barton]

Tom M wrote:
>> Anyway as a benchmark blender would need to use latest technologies to
>> be a usefull benchmark imho.
>>     
>
> ??  Cinebench and POVRay don't use 'latest technologies' indeed the
> Cinebench OpenGL test appears to be even a more limited OpenGL subset
> than Blender uses.
>
> For high end opengl performance the latest gameengines are used.  The
> tests that I'm refering to are for testing performance for regular
> working with a 3D accellerated application.
>
> LetterRip
>   
Agree- These benchmarks would be good for anybody interested in buying a 
3d card for Blending and possibly useful to people in the 3d industry- 
even Maya/Max/Lightwave users (except where there using DirectX)

I look at the game benchmarks and dont care about half the stuff they 
are testing because I dont play high end 3d games.

Another good thing about this type of benchmark is it quantify's 
performance- so if somebody makes a commit that has a problem, one can say
Hey, Since your commit- the IK/Particl Animation test is 20% slower.

Or you can say- I upgraded my drivers and its X% faster/slower

-- 
Campbell J Barton

133 Hope Street
Geelong West, Victoria 3218 Australia

URL:    http://www.metavr.com
e-mail: cbarton at metavr.com
phone: AU (03) 5229 0241