summaryrefslogtreecommitdiff
path: root/thirdparty/libtheora/x86_vc/mmxstate.c
diff options
context:
space:
mode:
Diffstat (limited to 'thirdparty/libtheora/x86_vc/mmxstate.c')
-rw-r--r--thirdparty/libtheora/x86_vc/mmxstate.c75
1 files changed, 20 insertions, 55 deletions
diff --git a/thirdparty/libtheora/x86_vc/mmxstate.c b/thirdparty/libtheora/x86_vc/mmxstate.c
index 73bd1981cf..f532ee1b6f 100644
--- a/thirdparty/libtheora/x86_vc/mmxstate.c
+++ b/thirdparty/libtheora/x86_vc/mmxstate.c
@@ -11,7 +11,7 @@
********************************************************************
function:
- last mod: $Id: mmxstate.c 16584 2009-09-26 19:35:55Z tterribe $
+ last mod: $Id$
********************************************************************/
@@ -19,17 +19,16 @@
Originally written by Rudolf Marek.*/
#include <string.h>
#include "x86int.h"
-#include "mmxfrag.h"
#include "mmxloop.h"
#if defined(OC_X86_ASM)
void oc_state_frag_recon_mmx(const oc_theora_state *_state,ptrdiff_t _fragi,
- int _pli,ogg_int16_t _dct_coeffs[64],int _last_zzi,ogg_uint16_t _dc_quant){
+ int _pli,ogg_int16_t _dct_coeffs[128],int _last_zzi,ogg_uint16_t _dc_quant){
unsigned char *dst;
ptrdiff_t frag_buf_off;
int ystride;
- int mb_mode;
+ int refi;
/*Apply the inverse transform.*/
/*Special case only having a DC component.*/
if(_last_zzi<2){
@@ -45,6 +44,7 @@ void oc_state_frag_recon_mmx(const oc_theora_state *_state,ptrdiff_t _fragi,
#define P ecx
mov Y,_dct_coeffs
movzx P,p
+ lea Y,[Y+128]
/*mm0=0000 0000 0000 AAAA*/
movd mm0,P
/*mm0=0000 0000 AAAA AAAA*/
@@ -74,65 +74,32 @@ void oc_state_frag_recon_mmx(const oc_theora_state *_state,ptrdiff_t _fragi,
else{
/*Dequantize the DC coefficient.*/
_dct_coeffs[0]=(ogg_int16_t)(_dct_coeffs[0]*(int)_dc_quant);
- oc_idct8x8_mmx(_dct_coeffs,_last_zzi);
+ oc_idct8x8_mmx(_dct_coeffs+64,_dct_coeffs,_last_zzi);
}
/*Fill in the target buffer.*/
frag_buf_off=_state->frag_buf_offs[_fragi];
- mb_mode=_state->frags[_fragi].mb_mode;
+ refi=_state->frags[_fragi].refi;
ystride=_state->ref_ystride[_pli];
- dst=_state->ref_frame_data[_state->ref_frame_idx[OC_FRAME_SELF]]+frag_buf_off;
- if(mb_mode==OC_MODE_INTRA)oc_frag_recon_intra_mmx(dst,ystride,_dct_coeffs);
+ dst=_state->ref_frame_data[OC_FRAME_SELF]+frag_buf_off;
+ if(refi==OC_FRAME_SELF)oc_frag_recon_intra_mmx(dst,ystride,_dct_coeffs+64);
else{
const unsigned char *ref;
int mvoffsets[2];
- ref=
- _state->ref_frame_data[_state->ref_frame_idx[OC_FRAME_FOR_MODE(mb_mode)]]
- +frag_buf_off;
+ ref=_state->ref_frame_data[refi]+frag_buf_off;
if(oc_state_get_mv_offsets(_state,mvoffsets,_pli,
- _state->frag_mvs[_fragi][0],_state->frag_mvs[_fragi][1])>1){
+ _state->frag_mvs[_fragi])>1){
oc_frag_recon_inter2_mmx(dst,ref+mvoffsets[0],ref+mvoffsets[1],ystride,
- _dct_coeffs);
+ _dct_coeffs+64);
}
- else oc_frag_recon_inter_mmx(dst,ref+mvoffsets[0],ystride,_dct_coeffs);
+ else oc_frag_recon_inter_mmx(dst,ref+mvoffsets[0],ystride,_dct_coeffs+64);
}
}
/*We copy these entire function to inline the actual MMX routines so that we
use only a single indirect call.*/
-/*Copies the fragments specified by the lists of fragment indices from one
- frame to another.
- _fragis: A pointer to a list of fragment indices.
- _nfragis: The number of fragment indices to copy.
- _dst_frame: The reference frame to copy to.
- _src_frame: The reference frame to copy from.
- _pli: The color plane the fragments lie in.*/
-void oc_state_frag_copy_list_mmx(const oc_theora_state *_state,
- const ptrdiff_t *_fragis,ptrdiff_t _nfragis,
- int _dst_frame,int _src_frame,int _pli){
- const ptrdiff_t *frag_buf_offs;
- const unsigned char *src_frame_data;
- unsigned char *dst_frame_data;
- ptrdiff_t fragii;
- int ystride;
- dst_frame_data=_state->ref_frame_data[_state->ref_frame_idx[_dst_frame]];
- src_frame_data=_state->ref_frame_data[_state->ref_frame_idx[_src_frame]];
- ystride=_state->ref_ystride[_pli];
- frag_buf_offs=_state->frag_buf_offs;
- for(fragii=0;fragii<_nfragis;fragii++){
- ptrdiff_t frag_buf_off;
- frag_buf_off=frag_buf_offs[_fragis[fragii]];
-#define SRC edx
-#define DST eax
-#define YSTRIDE ecx
-#define YSTRIDE3 edi
- OC_FRAG_COPY_MMX(dst_frame_data+frag_buf_off,
- src_frame_data+frag_buf_off,ystride);
-#undef SRC
-#undef DST
-#undef YSTRIDE
-#undef YSTRIDE3
- }
+void oc_loop_filter_init_mmx(signed char _bv[256],int _flimit){
+ memset(_bv,~(_flimit<<1),8);
}
/*Apply the loop filter to a given set of fragment rows in the given plane.
@@ -144,8 +111,7 @@ void oc_state_frag_copy_list_mmx(const oc_theora_state *_state,
_fragy0: The Y coordinate of the first fragment row to filter.
_fragy_end: The Y coordinate of the fragment row to stop filtering at.*/
void oc_state_loop_filter_frag_rows_mmx(const oc_theora_state *_state,
- int _bv[256],int _refi,int _pli,int _fragy0,int _fragy_end){
- OC_ALIGN8(unsigned char ll[8]);
+ signed char _bv[256],int _refi,int _pli,int _fragy0,int _fragy_end){
const oc_fragment_plane *fplane;
const oc_fragment *frags;
const ptrdiff_t *frag_buf_offs;
@@ -156,13 +122,12 @@ void oc_state_loop_filter_frag_rows_mmx(const oc_theora_state *_state,
ptrdiff_t fragi0_end;
int ystride;
int nhfrags;
- memset(ll,_state->loop_filter_limits[_state->qis[0]],sizeof(ll));
fplane=_state->fplanes+_pli;
nhfrags=fplane->nhfrags;
fragi_top=fplane->froffset;
fragi_bot=fragi_top+fplane->nfrags;
fragi0=fragi_top+_fragy0*(ptrdiff_t)nhfrags;
- fragi0_end=fragi0+(_fragy_end-_fragy0)*(ptrdiff_t)nhfrags;
+ fragi0_end=fragi_top+_fragy_end*(ptrdiff_t)nhfrags;
ystride=_state->ref_ystride[_pli];
frags=_state->frags;
frag_buf_offs=_state->frag_buf_offs;
@@ -187,13 +152,13 @@ void oc_state_loop_filter_frag_rows_mmx(const oc_theora_state *_state,
#define LL edx
#define D esi
#define D_WORD si
- if(fragi>fragi0)OC_LOOP_FILTER_H_MMX(ref,ystride,ll);
- if(fragi0>fragi_top)OC_LOOP_FILTER_V_MMX(ref,ystride,ll);
+ if(fragi>fragi0)OC_LOOP_FILTER_H_MMX(ref,ystride,_bv);
+ if(fragi0>fragi_top)OC_LOOP_FILTER_V_MMX(ref,ystride,_bv);
if(fragi+1<fragi_end&&!frags[fragi+1].coded){
- OC_LOOP_FILTER_H_MMX(ref+8,ystride,ll);
+ OC_LOOP_FILTER_H_MMX(ref+8,ystride,_bv);
}
if(fragi+nhfrags<fragi_bot&&!frags[fragi+nhfrags].coded){
- OC_LOOP_FILTER_V_MMX(ref+(ystride<<3),ystride,ll);
+ OC_LOOP_FILTER_V_MMX(ref+(ystride<<3),ystride,_bv);
}
#undef PIX
#undef YSTRIDE3
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-21 22:38:11 +0000