By: EduardoS (no.delete@this.spam.com), October 31, 2008 1:11 pm
Room: Moderated Discussions
Linus Torvalds (torvalds@linux-foundation.org) on 10/31/08 wrote:
---------------------------
>For example, let's assume that some of the benchmarks are
>almost entirely limited by the graphics card (which is not
>at all unlikely for the high-quality cases for some of the
>games). What does that lead to?
Another problem when testing games inthis way is that rendering doesn't have to happen at same speed of time.
For example, let's say someone thorw a ball against a wall, after 2 seconds it hits the wall, triggers a CPU intensive task and then the ball fall, triggering another CPU intensive task. Running this demo during the same period over two different CPUs would cause both to perform the two CPU intensive tasks, but the faster one would render more frames, ending with the faster one spending more time on rendering and the slower one with physics and game logic, different codepaths.
---------------------------
>For example, let's assume that some of the benchmarks are
>almost entirely limited by the graphics card (which is not
>at all unlikely for the high-quality cases for some of the
>games). What does that lead to?
Another problem when testing games inthis way is that rendering doesn't have to happen at same speed of time.
For example, let's say someone thorw a ball against a wall, after 2 seconds it hits the wall, triggers a CPU intensive task and then the ball fall, triggering another CPU intensive task. Running this demo during the same period over two different CPUs would cause both to perform the two CPU intensive tasks, but the faster one would render more frames, ending with the faster one spending more time on rendering and the slower one with physics and game logic, different codepaths.
