search for: seed_curve

Lancer 20060302 (based on aoTuV 4.51) http://homepage3.nifty.com/blacksword/ Changes: * update to oggenc v2.81 * optimized SSE2 code implementation * bark_noise_hybridmp and seed_curve are inline assembled * modified mdct_forward's SSE optimization * double step bresebham algorithm for render_line, render_line0 implementation

Is there any reason to avoid looking at optimizing the encoding process? From just a simple profile run, it looks like a big chunk of the time is in seed_curve, sqrt, dradf4 and log. Are there big changes to the encoding part that are coming that would invalidate optimizations done now? -tim --- >8 ---- List archives: http://www.xiph.org/archives/ Ogg project homepage: http://www.xiph.org/ogg/