MacWorld posted some basic benchmarks of Doom 3 on the Mac.
Doom 3 for MacOSX benchmarks at Macworld.com
About The Author
Eugenia Loli
Ex-programmer, ex-editor in chief at OSNews.com, now a visual artist/filmmaker.
Follow me on Twitter @EugeniaLoli
so, do you people recomend the doom3 engine, or do you prefer some other engine like the one hl2 uses, or farcry maybe?
Since this topic is about the Mac. I think so. Havok is NEVER coming to OSX. The Doom3 engine and the Unreal3 engine are about the only major next gen ‘cross platform’ engines.
when i saw that mac results i almost fell off my chair. How could this wonderfurl machine , with that very nice OS (no kidding here), perform so abismally with that game?
I mean, watching the results at 1280×1024 (which is what my 17″ monitor can handle), i remembered that when i had my 9800XT, it was capable of delivering almost 36 fps at the same quality settings. The rest of my system is a 2.1 GHz AthlonXP (barton 2800+), 1GByte DDR400, dual channel nforce2 ultra400 motherboard, …
So, what’s the point in saying that the MHz myth is true for games? My CPU is 400 MHz slower than the MAC, it had a slower video card, and performed almost the same.
Not only that, i changed that 9800XT for a Radeon X800XT (PC edition of course), and now i get much higher scores: without antialias i get 64 fps , and with 4x antialias i get 48 fps, comparing that to the MAC scores (36 and 24), i’m getting almost TWICE the performance with the SAME video card and same video settings (1280×1024).
Video drivers CAN improve the performance, in fact comparing catalyst 4.8 with 5.1 on my 9800XT, i got almost 20% improvement with it, but that is nowhere a 100% improvement it would require for MAC to catch up with my PC.
Oh, and just wait next week or so, then i’ll get a 2.4 GHz Athlon64 3400+ CPU, and i guess performance numbers will go up a little more.
Something is wrong with this Doom 3 port: very little optimization for MAC platform, bad OpenGL drivers for ATI cards with MAC, or some other factor which i don’t quite understand.
“The Mac’s OpenGL system is faster then the Windows OpenGL system.”
You have some evidence for this?
>Mac’s OpenGL system is faster then the Windows OpenGL
>system.
Not against AMD Athlon 64/Opteron based system e.g. refer to Cinebench 2003 OpenGL benchmarks.
I wonder if they tried changing the priority of the game? Something like “nice -20 doom3” would have improved performance, I’m sure. Maybe drastically, maybe not, but it definitely would be better. That would give you your “single tasking” pretty well.
The test was on a dual-processor machine, so by default, Mac OS X will schedule all other threads on the 2nd processor.
Some Altivec specific code wouldn’t hurt. I couldn’t care less about Doom3…
Doom 3 is already Altivec-ized a heap. They’ve gone on the record as saying that Apple has helped out in this regard. Also, on the benchmark page, they noted that raw CPU performance (i.e. without the GPU) was equivalent to x86.
Find Doom3 X86 benchmark with r_skiprender value to 1.
>Also, on the benchmark page, they noted that raw CPU
>performance (i.e. without the GPU) was equivalent to x86.
Note that, Dell PCs is Intel only PC vendor.