嗯, 我會錯意了! 不過用Colored mipmap的UT來看optimized後的差異準嗎? 連NV的卡都在Colored mipmap的UT中效能下降.

你又搞錯了,NV的效能差異是指優化ON/OFF的差異,有/無Colored mipmap並無變動~

意思是NV以開/關起動優化,而ATI要以Colored mipmap有/無來起動,一個明講,一個暗
來~

http://www.tomshardware.com/graphic...timized-08.html

quake3~ :D 又老又好玩.... *趴*

請看清楚我的post, 我說的是在"UT"(Unreal Tournament)中用Colored mipmap, NV的卡一樣有效能下降的問題, Lars也有提到:

Quite a different story in UT2003/2004. Here, all cards suffer loss of performance. That, however, is due to the way in which it is implemented. Here's what Epic has to say about this:

xxx @ NVIDIA just pointed out that filling textures with a constant color/alpha might cause more pixels to be written to the framebuffer (passing alpha test), which could affect performance. Totally forgot about that one and I should probably change the code to leave the alpha channel alone for our next generation engine :)

Lars沒有在THG中post UT2004的數據, 但早在半個多月前就已經post在Beyond3D: http://www.beyond3d.com/forum/viewt...ghlight=#284811

所以最後他們是拿Call of Duty來比較normal/Colored mipmap.