• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Benchmarks, Quake3, and Mac OS X performance

H

halfadder

Golden Member
Here is the issue, there has been a lot of discussion about how Mac OS X for Intel is slower than Windows XP on the exact same hardware. Yet in at least two benchmarks, the Mac version of the applications were faster than the Windows versions of those applications.

http://barefeats.com/bootcamp.html

In the first case, it could be argued that Cinema4D is probably more optimized for Mac OS X, explaining why CineBench is slower on Windows.

But how about Quake 3? You would think that id software would have invested more resources to make Quake 3 run as good as possible on Windows systems. Also, unlike UT2004, WoW, etc, Quake 3 runs in OpenGL on *both* Windows and Mac, making it a good cross-platform benchmark.

One explanation put forth says that Quake 3 is an old application, written in the 600 MHz P3 days, and because of this, the crappy system call performance of Mac OS X is less of an issue. But, wouldn't that also imply that it should run faster on XP too?

Could someone please explain this to me? I know next to nothing about benchmarks and statistics. Do these two tests suggest that Mac OS X might be as fast or even faster than XP? Do they suggest that Quake 3 was poorly written? Is there a rational explanation why Mac OS X was faster for these two tests, but slower for the others?
 
Isn't OS X implimentation of Open GL more refined than XP's given that most XP games are DirectX based while OS X uses OpenGL much more? Thats what I've always beleived, not sure how true it is though.
 
Quake 3 is certainly a well-written game. I used to play it on a P3 450 MHz, 128 MB PC100 RAM, and a Voodoo2 and get decent framerates in Windows 98/2000. Just looking at their benchmark numbers makes me question their results. I can run Q3 on my computer (P4 2.4 GHz, 768 MB PC3200 RAM, GF6800GT) and get higher framerates than they're reporting. Unfortunately, they didn't post the demo that they used so I can't really give an apples-to-apples comparison, but their system is much better than mine and should give better framerates.
 
Maybe because quake 3 is less graphics card dependent? It was written pre many of the modern graphics card features, so perhaps more of its rendering and what not is offloaded onto the cpu, and if OSX has better SMP implementation then it makes a difference. Really though, at such high speeds, it doesn't matter that the Mac is faster, Doom 3 should be fairly similar to the quake 3 engine and the Mac loses there, it's probably just a driver or OS quirk.
 
You must log in or register to reply here.

TRENDING THREADS

Back
Top