[Reverend]

Daniel wanted another thread for this so here it is!

Hey Daniel, going a little off the path here but Tim told me that while we can record our own demos *and* benchmark said demo, it may not be best since there'll be other kinds of overhead - he said that with the included UPT, pure rendering performance is measured and not AI and/or game code which are stuff you guys don't attempt to benchmark since consistency of results can't be guaranteed.

I'd like to provide some arguments to Tim about what he said but know better of course . Question is, how reflective of gameplay (which is the most important thing about any benchmark, isn't it?) is UPT? Not very, based on what Tim said IMO.

[vogel]

Originally Posted by Reverend

Daniel wanted another thread for this so here it is!
Hey Daniel, going a little off the path here but Tim told me that while we can record our own demos *and* benchmark said demo, it may not be best since there'll be other kinds of overhead - he said that with the included UPT, pure rendering performance is measured and not AI and/or game code which are stuff you guys don't attempt to benchmark since consistency of results can't be guaranteed.

I'd like to provide some arguments to Tim about what he said but know better of course . Question is, how reflective of gameplay (which is the most important thing about any benchmark, isn't it?) is UPT? Not very, based on what Tim said IMO.

Didn't want to hijack the other thread

With UT2k3 you can benchmark botmatches as they are deterministic (was quite a PITA to get that sorted out) as long as they run on the same CPU. Haven't tried comparing AMD vs Intel but I wouldn't be surprised if minor precision differences manifested themself within a couple of frames causing the botmatches to differ. With botmatches you are much more CPU bound than with flybys. Usually more CPU bound than network games so both tests are extreme cases. Flybys for GPU performance and botmatches for CPU load. Real multiplayer performance is usually somewhere in between.

-- Daniel