/src/theora/lib/x86/mmxstate.c

Source (jump to first uncovered line)
/********************************************************************
 *                                                                  *
 * THIS FILE IS PART OF THE OggTheora SOFTWARE CODEC SOURCE CODE.   *
 * USE, DISTRIBUTION AND REPRODUCTION OF THIS LIBRARY SOURCE IS     *
 * GOVERNED BY A BSD-STYLE SOURCE LICENSE INCLUDED WITH THIS SOURCE *
 * IN 'COPYING'. PLEASE READ THESE TERMS BEFORE DISTRIBUTING.       *
 *                                                                  *
 * THE Theora SOURCE CODE IS COPYRIGHT (C) 2002-2009                *
 * by the Xiph.Org Foundation and contributors http://www.xiph.org/ *
 *                                                                  *
 ********************************************************************

  function:
    last mod: $Id$

 ********************************************************************/

/*MMX acceleration of complete fragment reconstruction algorithm.
  Originally written by Rudolf Marek.*/
#include <string.h>
#include "x86int.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[128],int _last_zzi,ogg_uint16_t _dc_quant){
  unsigned char *dst;
  ptrdiff_t      frag_buf_off;
  int            ystride;
  int            refi;
  /*Apply the inverse transform.*/
  /*Special case only having a DC component.*/
  if(_last_zzi<2){
    /*Note that this value must be unsigned, to keep the __asm__ block from
       sign-extending it when it puts it in a register.*/
    ogg_uint16_t p;
    int          i;
    /*We round this dequant product (and not any of the others) because there's
       no iDCT rounding.*/
    p=(ogg_int16_t)(_dct_coeffs[0]*(ogg_int32_t)_dc_quant+15>>5);
    /*Fill _dct_coeffs with p.*/
    __asm__ __volatile__(
      /*mm0=0000 0000 0000 AAAA*/
      "movd %[p],%%mm0\n\t"
      /*mm0=0000 0000 AAAA AAAA*/
      "punpcklwd %%mm0,%%mm0\n\t"
      /*mm0=AAAA AAAA AAAA AAAA*/
      "punpckldq %%mm0,%%mm0\n\t"
      :
      :[p]"r"((unsigned)p)
    );
    for(i=0;i<4;i++){
      __asm__ __volatile__(
        "movq %%mm0,"OC_MEM_OFFS(0x00,y)"\n\t"
        "movq %%mm0,"OC_MEM_OFFS(0x08,y)"\n\t"
        "movq %%mm0,"OC_MEM_OFFS(0x10,y)"\n\t"
        "movq %%mm0,"OC_MEM_OFFS(0x18,y)"\n\t"
        :[y]"=m"OC_ARRAY_OPERAND(ogg_int16_t,_dct_coeffs+64+16*i,16)
      );
    }
  }
  else{
    /*Dequantize the DC coefficient.*/
    _dct_coeffs[0]=(ogg_int16_t)(_dct_coeffs[0]*(int)_dc_quant);
    oc_idct8x8(_state,_dct_coeffs+64,_dct_coeffs,_last_zzi);
  }
  /*Fill in the target buffer.*/
  frag_buf_off=_state->frag_buf_offs[_fragi];
  refi=_state->frags[_fragi].refi;
  ystride=_state->ref_ystride[_pli];
  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[refi]+frag_buf_off;
    if(oc_state_get_mv_offsets(_state,mvoffsets,_pli,
     _state->frag_mvs[_fragi])>1){
      oc_frag_recon_inter2_mmx(dst,ref+mvoffsets[0],ref+mvoffsets[1],ystride,
       _dct_coeffs+64);
    }
    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.*/

void oc_loop_filter_init_mmx(signed char _bv[256],int _flimit){
  memset(_bv,_flimit,8);
}

/*Apply the loop filter to a given set of fragment rows in the given plane.
  The filter may be run on the bottom edge, affecting pixels in the next row of
   fragments, so this row also needs to be available.
  _bv:        The bounding values array.
  _refi:      The index of the frame buffer to filter.
  _pli:       The color plane to filter.
  _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,
 signed char _bv[256],int _refi,int _pli,int _fragy0,int _fragy_end){
  OC_ALIGN8(unsigned char   ll[8]);
  const oc_fragment_plane *fplane;
  const oc_fragment       *frags;
  const ptrdiff_t         *frag_buf_offs;
  unsigned char           *ref_frame_data;
  ptrdiff_t                fragi_top;
  ptrdiff_t                fragi_bot;
  ptrdiff_t                fragi0;
  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;
  ystride=_state->ref_ystride[_pli];
  frags=_state->frags;
  frag_buf_offs=_state->frag_buf_offs;
  ref_frame_data=_state->ref_frame_data[_refi];
  /*The following loops are constructed somewhat non-intuitively on purpose.
    The main idea is: if a block boundary has at least one coded fragment on
     it, the filter is applied to it.
    However, the order that the filters are applied in matters, and VP3 chose
     the somewhat strange ordering used below.*/
  while(fragi0<fragi0_end){
    ptrdiff_t fragi;
    ptrdiff_t fragi_end;
    fragi=fragi0;
    fragi_end=fragi+nhfrags;
    while(fragi<fragi_end){
      if(frags[fragi].coded){
        unsigned char *ref;
        ref=ref_frame_data+frag_buf_offs[fragi];
        if(fragi>fragi0){
          OC_LOOP_FILTER_H(OC_LOOP_FILTER8_MMX,ref,ystride,ll);
        }
        if(fragi0>fragi_top){
          OC_LOOP_FILTER_V(OC_LOOP_FILTER8_MMX,ref,ystride,ll);
        }
        if(fragi+1<fragi_end&&!frags[fragi+1].coded){
          OC_LOOP_FILTER_H(OC_LOOP_FILTER8_MMX,ref+8,ystride,ll);
        }
        if(fragi+nhfrags<fragi_bot&&!frags[fragi+nhfrags].coded){
          OC_LOOP_FILTER_V(OC_LOOP_FILTER8_MMX,ref+(ystride<<3),ystride,ll);
        }
      }
      fragi++;
    }
    fragi0+=nhfrags;
  }
}

void oc_loop_filter_init_mmxext(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.
  The filter may be run on the bottom edge, affecting pixels in the next row of
   fragments, so this row also needs to be available.
  _bv:        The bounding values array.
  _refi:      The index of the frame buffer to filter.
  _pli:       The color plane to filter.
  _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_mmxext(const oc_theora_state *_state,
 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;
  unsigned char           *ref_frame_data;
  ptrdiff_t                fragi_top;
  ptrdiff_t                fragi_bot;
  ptrdiff_t                fragi0;
  ptrdiff_t                fragi0_end;
  int                      ystride;
  int                      nhfrags;
  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=fragi_top+_fragy_end*(ptrdiff_t)nhfrags;
  ystride=_state->ref_ystride[_pli];
  frags=_state->frags;
  frag_buf_offs=_state->frag_buf_offs;
  ref_frame_data=_state->ref_frame_data[_refi];
  /*The following loops are constructed somewhat non-intuitively on purpose.
    The main idea is: if a block boundary has at least one coded fragment on
     it, the filter is applied to it.
    However, the order that the filters are applied in matters, and VP3 chose
     the somewhat strange ordering used below.*/
  while(fragi0<fragi0_end){
    ptrdiff_t fragi;
    ptrdiff_t fragi_end;
    fragi=fragi0;
    fragi_end=fragi+nhfrags;
    while(fragi<fragi_end){
      if(frags[fragi].coded){
        unsigned char *ref;
        ref=ref_frame_data+frag_buf_offs[fragi];
        if(fragi>fragi0){
          OC_LOOP_FILTER_H(OC_LOOP_FILTER8_MMXEXT,ref,ystride,_bv);
        }
        if(fragi0>fragi_top){
          OC_LOOP_FILTER_V(OC_LOOP_FILTER8_MMXEXT,ref,ystride,_bv);
        }
        if(fragi+1<fragi_end&&!frags[fragi+1].coded){
          OC_LOOP_FILTER_H(OC_LOOP_FILTER8_MMXEXT,ref+8,ystride,_bv);
        }
        if(fragi+nhfrags<fragi_bot&&!frags[fragi+nhfrags].coded){
          OC_LOOP_FILTER_V(OC_LOOP_FILTER8_MMXEXT,ref+(ystride<<3),ystride,_bv);
        }
      }
      fragi++;
    }
    fragi0+=nhfrags;
  }
}

#endif

Coverage Report

Created: 2024-09-06 07:53

Line	Count	Source (jump to first uncovered line)
1		/********************************************************************
2		* *
3		* THIS FILE IS PART OF THE OggTheora SOFTWARE CODEC SOURCE CODE. *
4		* USE, DISTRIBUTION AND REPRODUCTION OF THIS LIBRARY SOURCE IS *
5		* GOVERNED BY A BSD-STYLE SOURCE LICENSE INCLUDED WITH THIS SOURCE *
6		* IN 'COPYING'. PLEASE READ THESE TERMS BEFORE DISTRIBUTING. *
7		* *
8		* THE Theora SOURCE CODE IS COPYRIGHT (C) 2002-2009 *
9		* by the Xiph.Org Foundation and contributors http://www.xiph.org/ *
10		* *
11		********************************************************************
12
13		function:
14		last mod: $Id$
15
16		********************************************************************/
17
18		/*MMX acceleration of complete fragment reconstruction algorithm.
19		Originally written by Rudolf Marek.*/
20		#include <string.h>
21		#include "x86int.h"
22		#include "mmxloop.h"
23
24		#if defined(OC_X86_ASM)
25
26		void oc_state_frag_recon_mmx(const oc_theora_state *_state,ptrdiff_t _fragi,
27	0	int _pli,ogg_int16_t _dct_coeffs[128],int _last_zzi,ogg_uint16_t _dc_quant){
28	0	unsigned char *dst;
29	0	ptrdiff_t frag_buf_off;
30	0	int ystride;
31	0	int refi;
32		/Apply the inverse transform./
33		/Special case only having a DC component./
34	0	if(_last_zzi<2){
35		/*Note that this value must be unsigned, to keep the __asm__ block from
36		sign-extending it when it puts it in a register.*/
37	0	ogg_uint16_t p;
38	0	int i;
39		/*We round this dequant product (and not any of the others) because there's
40		no iDCT rounding.*/
41	0	p=(ogg_int16_t)(_dct_coeffs[0]*(ogg_int32_t)_dc_quant+15>>5);
42		/Fill _dct_coeffs with p./
43	0	__asm__ __volatile__(
44		/mm0=0000 0000 0000 AAAA/
45	0	"movd %[p],%%mm0\n\t"
46		/mm0=0000 0000 AAAA AAAA/
47	0	"punpcklwd %%mm0,%%mm0\n\t"
48		/mm0=AAAA AAAA AAAA AAAA/
49	0	"punpckldq %%mm0,%%mm0\n\t"
50	0	:
51	0	:[p]"r"((unsigned)p)
52	0	);
53	0	for(i=0;i<4;i++){
54	0	__asm__ __volatile__(
55	0	"movq %%mm0,"OC_MEM_OFFS(0x00,y)"\n\t"
56	0	"movq %%mm0,"OC_MEM_OFFS(0x08,y)"\n\t"
57	0	"movq %%mm0,"OC_MEM_OFFS(0x10,y)"\n\t"
58	0	"movq %%mm0,"OC_MEM_OFFS(0x18,y)"\n\t"
59	0	:[y]"=m"OC_ARRAY_OPERAND(ogg_int16_t,_dct_coeffs+64+16*i,16)
60	0	);
61	0	}
62	0	}
63	0	else{
64		/Dequantize the DC coefficient./
65	0	_dct_coeffs[0]=(ogg_int16_t)(_dct_coeffs[0]*(int)_dc_quant);
66	0	oc_idct8x8(_state,_dct_coeffs+64,_dct_coeffs,_last_zzi);
67	0	}
68		/Fill in the target buffer./
69	0	frag_buf_off=_state->frag_buf_offs[_fragi];
70	0	refi=_state->frags[_fragi].refi;
71	0	ystride=_state->ref_ystride[_pli];
72	0	dst=_state->ref_frame_data[OC_FRAME_SELF]+frag_buf_off;
73	0	if(refi==OC_FRAME_SELF)oc_frag_recon_intra_mmx(dst,ystride,_dct_coeffs+64);
74	0	else{
75	0	const unsigned char *ref;
76	0	int mvoffsets[2];
77	0	ref=_state->ref_frame_data[refi]+frag_buf_off;
78	0	if(oc_state_get_mv_offsets(_state,mvoffsets,_pli,
79	0	_state->frag_mvs[_fragi])>1){
80	0	oc_frag_recon_inter2_mmx(dst,ref+mvoffsets[0],ref+mvoffsets[1],ystride,
81	0	_dct_coeffs+64);
82	0	}
83	0	else oc_frag_recon_inter_mmx(dst,ref+mvoffsets[0],ystride,_dct_coeffs+64);
84	0	}
85	0	}
86
87		/*We copy these entire function to inline the actual MMX routines so that we
88		use only a single indirect call.*/
89
90	0	void oc_loop_filter_init_mmx(signed char _bv[256],int _flimit){
91	0	memset(_bv,_flimit,8);
92	0	}
93
94		/*Apply the loop filter to a given set of fragment rows in the given plane.
95		The filter may be run on the bottom edge, affecting pixels in the next row of
96		fragments, so this row also needs to be available.
97		_bv: The bounding values array.
98		_refi: The index of the frame buffer to filter.
99		_pli: The color plane to filter.
100		_fragy0: The Y coordinate of the first fragment row to filter.
101		_fragy_end: The Y coordinate of the fragment row to stop filtering at.*/
102		void oc_state_loop_filter_frag_rows_mmx(const oc_theora_state *_state,
103	0	signed char _bv[256],int _refi,int _pli,int _fragy0,int _fragy_end){
104	0	OC_ALIGN8(unsigned char ll[8]);
105	0	const oc_fragment_plane *fplane;
106	0	const oc_fragment *frags;
107	0	const ptrdiff_t *frag_buf_offs;
108	0	unsigned char *ref_frame_data;
109	0	ptrdiff_t fragi_top;
110	0	ptrdiff_t fragi_bot;
111	0	ptrdiff_t fragi0;
112	0	ptrdiff_t fragi0_end;
113	0	int ystride;
114	0	int nhfrags;
115	0	memset(ll,_state->loop_filter_limits[_state->qis[0]],sizeof(ll));
116	0	fplane=_state->fplanes+_pli;
117	0	nhfrags=fplane->nhfrags;
118	0	fragi_top=fplane->froffset;
119	0	fragi_bot=fragi_top+fplane->nfrags;
120	0	fragi0=fragi_top+_fragy0*(ptrdiff_t)nhfrags;
121	0	fragi0_end=fragi0+(_fragy_end-_fragy0)*(ptrdiff_t)nhfrags;
122	0	ystride=_state->ref_ystride[_pli];
123	0	frags=_state->frags;
124	0	frag_buf_offs=_state->frag_buf_offs;
125	0	ref_frame_data=_state->ref_frame_data[_refi];
126		/*The following loops are constructed somewhat non-intuitively on purpose.
127		The main idea is: if a block boundary has at least one coded fragment on
128		it, the filter is applied to it.
129		However, the order that the filters are applied in matters, and VP3 chose
130		the somewhat strange ordering used below.*/
131	0	while(fragi0<fragi0_end){
132	0	ptrdiff_t fragi;
133	0	ptrdiff_t fragi_end;
134	0	fragi=fragi0;
135	0	fragi_end=fragi+nhfrags;
136	0	while(fragi<fragi_end){
137	0	if(frags[fragi].coded){
138	0	unsigned char *ref;
139	0	ref=ref_frame_data+frag_buf_offs[fragi];
140	0	if(fragi>fragi0){
141	0	OC_LOOP_FILTER_H(OC_LOOP_FILTER8_MMX,ref,ystride,ll);
142	0	}
143	0	if(fragi0>fragi_top){
144	0	OC_LOOP_FILTER_V(OC_LOOP_FILTER8_MMX,ref,ystride,ll);
145	0	}
146	0	if(fragi+1<fragi_end&&!frags[fragi+1].coded){
147	0	OC_LOOP_FILTER_H(OC_LOOP_FILTER8_MMX,ref+8,ystride,ll);
148	0	}
149	0	if(fragi+nhfrags<fragi_bot&&!frags[fragi+nhfrags].coded){
150	0	OC_LOOP_FILTER_V(OC_LOOP_FILTER8_MMX,ref+(ystride<<3),ystride,ll);
151	0	}
152	0	}
153	0	fragi++;
154	0	}
155	0	fragi0+=nhfrags;
156	0	}
157	0	}
158
159	33.6k	void oc_loop_filter_init_mmxext(signed char _bv[256],int _flimit){
160	33.6k	memset(_bv,~(_flimit<<1),8);
161	33.6k	}
162
163		/*Apply the loop filter to a given set of fragment rows in the given plane.
164		The filter may be run on the bottom edge, affecting pixels in the next row of
165		fragments, so this row also needs to be available.
166		_bv: The bounding values array.
167		_refi: The index of the frame buffer to filter.
168		_pli: The color plane to filter.
169		_fragy0: The Y coordinate of the first fragment row to filter.
170		_fragy_end: The Y coordinate of the fragment row to stop filtering at.*/
171		void oc_state_loop_filter_frag_rows_mmxext(const oc_theora_state *_state,
172	444k	signed char _bv[256],int _refi,int _pli,int _fragy0,int _fragy_end){
173	444k	const oc_fragment_plane *fplane;
174	444k	const oc_fragment *frags;
175	444k	const ptrdiff_t *frag_buf_offs;
176	444k	unsigned char *ref_frame_data;
177	444k	ptrdiff_t fragi_top;
178	444k	ptrdiff_t fragi_bot;
179	444k	ptrdiff_t fragi0;
180	444k	ptrdiff_t fragi0_end;
181	444k	int ystride;
182	444k	int nhfrags;
183	444k	fplane=_state->fplanes+_pli;
184	444k	nhfrags=fplane->nhfrags;
185	444k	fragi_top=fplane->froffset;
186	444k	fragi_bot=fragi_top+fplane->nfrags;
187	444k	fragi0=fragi_top+_fragy0*(ptrdiff_t)nhfrags;
188	444k	fragi0_end=fragi_top+_fragy_end*(ptrdiff_t)nhfrags;
189	444k	ystride=_state->ref_ystride[_pli];
190	444k	frags=_state->frags;
191	444k	frag_buf_offs=_state->frag_buf_offs;
192	444k	ref_frame_data=_state->ref_frame_data[_refi];
193		/*The following loops are constructed somewhat non-intuitively on purpose.
194		The main idea is: if a block boundary has at least one coded fragment on
195		it, the filter is applied to it.
196		However, the order that the filters are applied in matters, and VP3 chose
197		the somewhat strange ordering used below.*/
198	2.23M	while(fragi0<fragi0_end){
199	1.78M	ptrdiff_t fragi;
200	1.78M	ptrdiff_t fragi_end;
201	1.78M	fragi=fragi0;
202	1.78M	fragi_end=fragi+nhfrags;
203	12.4M	while(fragi<fragi_end){
204	10.6M	if(frags[fragi].coded){
205	10.1M	unsigned char *ref;
206	10.1M	ref=ref_frame_data+frag_buf_offs[fragi];
207	10.1M	if(fragi>fragi0){
208	8.38M	OC_LOOP_FILTER_H(OC_LOOP_FILTER8_MMXEXT,ref,ystride,_bv);
209	8.38M	}
210	10.1M	if(fragi0>fragi_top){
211	6.67M	OC_LOOP_FILTER_V(OC_LOOP_FILTER8_MMXEXT,ref,ystride,_bv);
212	6.67M	}
213	10.1M	if(fragi+1<fragi_end&&!frags[fragi+1].coded){
214	70.1k	OC_LOOP_FILTER_H(OC_LOOP_FILTER8_MMXEXT,ref+8,ystride,_bv);
215	70.1k	}
216	10.1M	if(fragi+nhfrags<fragi_bot&&!frags[fragi+nhfrags].coded){
217	88.6k	OC_LOOP_FILTER_V(OC_LOOP_FILTER8_MMXEXT,ref+(ystride<<3),ystride,_bv);
218	88.6k	}
219	10.1M	}
220	10.6M	fragi++;
221	10.6M	}
222	1.78M	fragi0+=nhfrags;
223	1.78M	}
224	444k	}
225
226		#endif