Hi, After converting the Savage driver to use Ian's common texmem code I noticed a performance regression in Torcs. It's trashing textures a lot where it was running very smoothly before. I believe this is due to a different texture heap preference. If I reverse the preference I get back to the performance I had with my own texture memory management.
In my setup I have 6MB on the local heap and 30MB on the AGP heap. The common texmem code always tries to allocate a texture on the local heap first. Therefore there can be a lot of texture trashing on the small local heap while the bigger AGP heap is nearly unused, because it is basically only used for textures that are bigger than the local heap. I intend to improve the heuristics that chooses the texture heap in driAllocateTexture. This may involve the texture size to allocate, the heap sizes and the amount of free space on each heap and maybe the ages of textures on each heap. I haven't thought too much about the details yet. If anyone has already put some thought into this I'd appreciate your input. Regards, Felix -- | Felix Kühling <[EMAIL PROTECTED]> http://fxk.de.vu | | PGP Fingerprint: 6A3C 9566 5B30 DDED 73C3 B152 151C 5CC1 D888 E595 | ------------------------------------------------------- This SF.Net email is sponsored by: IntelliVIEW -- Interactive Reporting Tool for open source databases. Create drag-&-drop reports. Save time by over 75%! Publish reports on the web. Export to DOC, XLS, RTF, etc. Download a FREE copy at http://www.intelliview.com/go/osdn_nl -- _______________________________________________ Dri-devel mailing list Dri-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/dri-devel
