search for: oc_theora_state

...ts>>SIGN_SHIFT[_token]]; *_zzi=zzi; } diff -Naur ../mergeSTATE/test/lib/internal.h test/lib/internal.h --- ../mergeSTATE/test/lib/internal.h 2005-08-17 10:05:34.000000000 +0200 +++ test/lib/internal.h 2005-08-20 11:39:38.797310000 +0200 @@ -239,7 +239,7 @@ void (*state_frag_copy)(const oc_theora_state *_state, const int *_fragis,int _nfragis,int _dst_frame,int _src_frame,int _pli); void (*state_frag_recon)(oc_theora_state *_state,const oc_fragment *_frag, - int _pli,ogg_int16_t _dct_coeffs[64],int _last_zzi,int _ncoefs, + int _pli,ogg_int16_t _dct_coeffs[128],int _last_zzi,int _ncoefs...

Hi all-- I tried building the ARM-optimized theora codec from the theorarm- merge-branch, and encountered the following compile and runtime problems before getting something to run. If there is another way to build it, it would be nice to know, but I got the sense that its current state in svn is incomplete. I'm using a gcc cross-compiler for ARM on an x86 Linux PC. After running

...b/fragment.c --- theora-exp/lib/fragment.c 2005-03-23 08:54:44.163819664 +0100 +++ theora-rel/lib/fragment.c 2005-03-23 09:42:29.000000000 +0100 @@ -1,6 +1,11 @@ #include "internal.h" -void oc_frag_recon_intra(unsigned char *_dst,int _dst_ystride, +inline void oc_frag_recon_intra(const oc_theora_state *_state,unsigned char *_dst,int _dst_ystride, + const ogg_int16_t *_residue){ +_state->opt_vtable.oc_frag_recon_intra(_dst,_dst_ystride,_residue); +} + +void oc_frag_recon_intra__c(unsigned char *_dst,int _dst_ystride, const ogg_int16_t *_residue){ int i; for(i=0;i<8;i++){ @@ -10,7 +1...

...b/fragment.c --- theora-exp/lib/fragment.c 2005-03-23 08:54:44.163819664 +0100 +++ theora-rel/lib/fragment.c 2005-03-23 09:42:29.000000000 +0100 @@ -1,6 +1,11 @@ #include "internal.h" -void oc_frag_recon_intra(unsigned char *_dst,int _dst_ystride, +inline void oc_frag_recon_intra(const oc_theora_state *_state,unsigned char *_dst,int _dst_ystride, + const ogg_int16_t *_residue){ +_state->opt_vtable.oc_frag_recon_intra(_dst,_dst_ystride,_residue); +} + +void oc_frag_recon_intra__c(unsigned char *_dst,int _dst_ystride, const ogg_int16_t *_residue){ int i; for(i=0;i<8;i++){ @@ -10,7 +1...

...57.318872500 +0200 +++ b/lib/internal.h 2005-08-17 10:05:34.076411500 +0200 @@ -242,6 +242,8 @@ int _pli,ogg_int16_t _dct_coeffs[64],int _last_zzi,int _ncoefs, ogg_uint16_t _dc_iquant,const ogg_uint16_t _ac_iquant[64]); void (*restore_fpu)(void); + void (*oc_state_loop_filter_frag_rows)(oc_theora_state *_state,int *_bv, + int _refi,int _pli,int _fragy0,int _fragy_end); }oc_base_opt_vtable; @@ -391,8 +393,6 @@ int oc_state_loop_filter_init(oc_theora_state *_state,int *_bv); void oc_state_loop_filter(oc_theora_state *_state,int _frame); -void oc_state_loop_filter_frag_rows(oc_theora_stat...

..._x[64]); +void oc_idct8x8_10_c(ogg_int16_t _y[64],const ogg_int16_t _x[64]); #endif diff -Naur a/lib/internal.h b/lib/internal.h --- a/lib/internal.h 2005-07-20 11:39:30.355887750 +0200 +++ b/lib/internal.h 2005-07-20 11:46:53.083556500 +0200 @@ -239,6 +239,9 @@ void (*state_frag_copy)(const oc_theora_state *_state, const int *_fragis,int _nfragis,int _dst_frame,int _src_frame,int _pli); void (*restore_fpu)(void); + void (*oc_state_frag_recon)(oc_theora_state *_state,const oc_fragment *_frag, + int _pli,ogg_int16_t _dct_coeffs[64],int _last_zzi,...

Hi, This patch adds Altivec-optimized implementations of oc_enc_frag_sad and oc_enc_frag_ssd. This patch is against the latest svn revision of theora-ptalarbvorm. Speeds up encode on a plant stop-motion clip on a 1 GHz PPC 7447 by ~3%, timewise. Time spent in oc_enc_frag_sad is reduced from 4.2% to 2.3% and oc_enc_frag_ssd from 1.2% to 1.0%, as reported by Shark. Currently this is only