search for: vorbis_lsp_to_curv

...orbis_book_clear vorbis_book_codelen vorbis_book_codeword vorbis_book_decode vorbis_book_decodev_add vorbis_book_decodevs_add vorbis_book_decodev_set vorbis_book_decodevv_add vorbis_book_encode vorbis_book_init_decode vorbis_book_init_encode vorbis_lpc_from_data vorbis_lpc_predict vorbis_lpc_to_lsp vorbis_lsp_to_curve vorbis_staticbook_destroy vorbis_staticbook_pack vorbis_staticbook_unpack vorbis_window _vorbis_window_get _vp_ampmax_decay _vp_couple_quantize_normalize _vp_global_free _vp_global_look _vp_noisemask _vp_offset_and_mix _vp_psy_clear _vp_psy_init _vp_tonemask -------------- next part --------------...

...1024 point mdct is a bit much to brute-force, and I'm not going to hand-unroll the whole thing either (the machine- unrolled version produced a 1.5M executable; understandably, it wasn't very fast. Still waiting for processors with 1.5M L1 code caches ;-) Slowest parts now are: -- mdct -- vorbis_lsp_to_curve (and the exp()'s afterwards, in fromdB macro; eliminated most of-em, but not all). -- main (the float to s16 loop) Hope to send a patch tomorrow, as the sneakernet had some transmission problems today :-| Dagdag, Segher --- >8 ---- List archives: http://www.xiph.org/archives/ O...

Hi, I think that the introduction of the lsp_look lookup array isn't ideal and found a better change that can be applied. in floor0_map_lazy_init() you can replace look->linearmap[W][j]=val; by look->linearmap[W][j]=vorbis_coslook(M_PI*val/look->ln); and in vorbis_lsp_to_curve you then replace float w=vorbis_coslook(wdel*k); ... }while(map[i]==k); by float w=map[i]; ... }while(map[i]==w); then get rid of the ln function parameter and the k local variable. <p><p>Next the fact that p and q are initialised to 1/sqrt(2), multiplied by a series of factors an...

...set (MMX, 3DNow, etc too?) There are one or two good optimization wins that resulted from code changes that have nothing to do with vectorization, too (moving branches and invariant code out of loops, forcing things into registers, etc). Overall, some .ogg files seem to spend a lot of time in vorbis_lsp_to_curve()...I assume this .ogg is from an older version of the vorbis spec, and such files tend to eat more CPU (although there are some wins here by inlining the the lookup table functions and using the frsqrte opcode instead of the invsqrt lookup table...memory access is a huge bottleneck on the Mac...

Vorbis does not appear to use any SIMD instructions. A short look around in the source code indicates that it would be possible and might even yield big performance improvements. Why has nobody done it yet? I am currently trying to learn using these instructions and would be willing to rewrite a few functions in SIMD instructions, if I understand how to vectorize them and if they make a