These five patches implement the same bilinear scaling compositing functions as provided by the SSE2 code. They pass the test suite on x86, Loongson, and iwMMXt, but I haven't done extensive benchmarking yet on iwMMXt.
The fifth patch optimizes the functions for 7-bit bilinear interpolation, but doesn't give the performance differences I would expect. firefox-planet-gnome performance is increased by ~1% and firefox-fishtank performance is reduced. Matt _______________________________________________ Pixman mailing list Pixman@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/pixman