Thank you for the reply and the suggestion. It seems to me that changing the mag/min filter to nearest was a test I've already done in the past together with other combination of options but I retested it anyway and there is a slight improvement that is the fps at 90° pass from 8 to 11 for the 1 * (512*512) case and from 14 to 18 for the 16 * (128*128) case. Sure every improvement is welcome but I'd however like to know the reason for the fps drop and/or how to improve it.
You say that the MSM7200 contains optimizations for certain types of filling. It would be interesting to know of what kind they are to give so different fps and even for so little rotations. Do you perhaps have the references to some document where these optimizations are described? Knowing the chip internal behaviour can help writing code that better adapts to it. I've found some documents on this group and on the net: http://www.brewconference.com/brew_2007/pdf/Tech-303_Ligon.pdf http://www.brewconference.com/brew_2004/pdf/david_ligon_qualcomm_optimizing_games.pdf They give some good advice but not specific to MSM7200. Referring to platforms preceding the MSM7200 they talk about a 16KB texture cache and in my case a 512*512 16 bit texture is 512KB and a 128*128 one is 32KB. Maybe I can try to reduce the texture to 64*64. I will do some test. Michele -- You received this message because you are subscribed to the Google Groups "Android Developers" group. To post to this group, send email to android-developers@googlegroups.com To unsubscribe from this group, send email to android-developers+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/android-developers?hl=en
