FFmpeg
Macros | Functions
vp9_intra_msa.c File Reference
#include "libavcodec/vp9dsp.h"
#include "libavutil/mips/generic_macros_msa.h"
#include "vp9dsp_mips.h"

Go to the source code of this file.

Macros

#define IPRED_SUBS_UH2_UH(in0, in1, out0, out1)
 
#define INTRA_DC_TL_4x4(dir)
 
#define INTRA_DC_TL_8x8(dir)
 
#define INTRA_DC_TL_16x16(dir)
 
#define INTRA_DC_TL_32x32(dir)
 
#define INTRA_PREDICT_VALDC_16X16_MSA(val)
 
#define INTRA_PREDICT_VALDC_32X32_MSA(val)
 

Functions

void ff_vert_16x16_msa (uint8_t *dst, ptrdiff_t dst_stride, const uint8_t *left, const uint8_t *src)
 
void ff_vert_32x32_msa (uint8_t *dst, ptrdiff_t dst_stride, const uint8_t *left, const uint8_t *src)
 
void ff_hor_16x16_msa (uint8_t *dst, ptrdiff_t dst_stride, const uint8_t *src, const uint8_t *top)
 
void ff_hor_32x32_msa (uint8_t *dst, ptrdiff_t dst_stride, const uint8_t *src, const uint8_t *top)
 
void ff_dc_4x4_msa (uint8_t *dst, ptrdiff_t dst_stride, const uint8_t *src_left, const uint8_t *src_top)
 
 INTRA_DC_TL_4x4 (top)
 
 INTRA_DC_TL_4x4 (left)
 
void ff_dc_8x8_msa (uint8_t *dst, ptrdiff_t dst_stride, const uint8_t *src_left, const uint8_t *src_top)
 
 INTRA_DC_TL_8x8 (top)
 
 INTRA_DC_TL_8x8 (left)
 
void ff_dc_16x16_msa (uint8_t *dst, ptrdiff_t dst_stride, const uint8_t *src_left, const uint8_t *src_top)
 
 INTRA_DC_TL_16x16 (top)
 
 INTRA_DC_TL_16x16 (left)
 
void ff_dc_32x32_msa (uint8_t *dst, ptrdiff_t dst_stride, const uint8_t *src_left, const uint8_t *src_top)
 
 INTRA_DC_TL_32x32 (top)
 
 INTRA_DC_TL_32x32 (left)
 
 INTRA_PREDICT_VALDC_16X16_MSA (127)
 
 INTRA_PREDICT_VALDC_16X16_MSA (128)
 
 INTRA_PREDICT_VALDC_16X16_MSA (129)
 
 INTRA_PREDICT_VALDC_32X32_MSA (127)
 
 INTRA_PREDICT_VALDC_32X32_MSA (128)
 
 INTRA_PREDICT_VALDC_32X32_MSA (129)
 
void ff_tm_4x4_msa (uint8_t *dst, ptrdiff_t dst_stride, const uint8_t *src_left, const uint8_t *src_top_ptr)
 
void ff_tm_8x8_msa (uint8_t *dst, ptrdiff_t dst_stride, const uint8_t *src_left, const uint8_t *src_top_ptr)
 
void ff_tm_16x16_msa (uint8_t *dst, ptrdiff_t dst_stride, const uint8_t *src_left, const uint8_t *src_top_ptr)
 
void ff_tm_32x32_msa (uint8_t *dst, ptrdiff_t dst_stride, const uint8_t *src_left, const uint8_t *src_top_ptr)
 

Macro Definition Documentation

◆ IPRED_SUBS_UH2_UH

#define IPRED_SUBS_UH2_UH (   in0,
  in1,
  out0,
  out1 
)
Value:
{ \
out0 = __msa_subs_u_h(out0, in0); \
out1 = __msa_subs_u_h(out1, in1); \
}

Definition at line 25 of file vp9_intra_msa.c.

◆ INTRA_DC_TL_4x4

#define INTRA_DC_TL_4x4 (   dir)
Value:
void ff_dc_##dir##_4x4_msa(uint8_t *dst, ptrdiff_t dst_stride, \
const uint8_t *left, \
const uint8_t *top) \
{ \
uint32_t val0; \
v16i8 store, data = { 0 }; \
v8u16 sum_h; \
v4u32 sum_w; \
\
val0 = LW(dir); \
data = (v16i8) __msa_insert_w((v4i32) data, 0, val0); \
sum_h = __msa_hadd_u_h((v16u8) data, (v16u8) data); \
sum_w = __msa_hadd_u_w(sum_h, sum_h); \
sum_w = (v4u32) __msa_srari_w((v4i32) sum_w, 2); \
store = __msa_splati_b((v16i8) sum_w, 0); \
val0 = __msa_copy_u_w((v4i32) store, 0); \
SW4(val0, val0, val0, val0, dst, dst_stride); \
}

Definition at line 130 of file vp9_intra_msa.c.

◆ INTRA_DC_TL_8x8

#define INTRA_DC_TL_8x8 (   dir)
Value:
void ff_dc_##dir##_8x8_msa(uint8_t *dst, ptrdiff_t dst_stride, \
const uint8_t *left, \
const uint8_t *top) \
{ \
uint64_t val0; \
v16i8 store; \
v16u8 data = { 0 }; \
v8u16 sum_h; \
v4u32 sum_w; \
v2u64 sum_d; \
\
val0 = LD(dir); \
data = (v16u8) __msa_insert_d((v2i64) data, 0, val0); \
sum_h = __msa_hadd_u_h(data, data); \
sum_w = __msa_hadd_u_w(sum_h, sum_h); \
sum_d = __msa_hadd_u_d(sum_w, sum_w); \
sum_w = (v4u32) __msa_srari_w((v4i32) sum_d, 3); \
store = __msa_splati_b((v16i8) sum_w, 0); \
val0 = __msa_copy_u_d((v2i64) store, 0); \
SD4(val0, val0, val0, val0, dst, dst_stride); \
dst += (4 * dst_stride); \
SD4(val0, val0, val0, val0, dst, dst_stride); \
}

Definition at line 180 of file vp9_intra_msa.c.

◆ INTRA_DC_TL_16x16

#define INTRA_DC_TL_16x16 (   dir)
Value:
void ff_dc_##dir##_16x16_msa(uint8_t *dst, ptrdiff_t dst_stride, \
const uint8_t *left, \
const uint8_t *top) \
{ \
v16u8 data, out; \
v8u16 sum_h; \
v4u32 sum_w; \
v2u64 sum_d; \
\
data = LD_UB(dir); \
sum_h = __msa_hadd_u_h(data, data); \
sum_w = __msa_hadd_u_w(sum_h, sum_h); \
sum_d = __msa_hadd_u_d(sum_w, sum_w); \
sum_w = (v4u32) __msa_pckev_w((v4i32) sum_d, (v4i32) sum_d); \
sum_d = __msa_hadd_u_d(sum_w, sum_w); \
sum_w = (v4u32) __msa_srari_w((v4i32) sum_d, 4); \
out = (v16u8) __msa_splati_b((v16i8) sum_w, 0); \
ST_UB8(out, out, out, out, out, out, out, out, dst, dst_stride); \
dst += (8 * dst_stride); \
ST_UB8(out, out, out, out, out, out, out, out, dst, dst_stride); \
}

Definition at line 233 of file vp9_intra_msa.c.

◆ INTRA_DC_TL_32x32

#define INTRA_DC_TL_32x32 (   dir)
Value:
void ff_dc_##dir##_32x32_msa(uint8_t *dst, ptrdiff_t dst_stride, \
const uint8_t *left, \
const uint8_t *top) \
{ \
uint32_t row; \
v16u8 data0, data1, out; \
v8u16 sum_h, sum_data0, sum_data1; \
v4u32 sum_w; \
v2u64 sum_d; \
LD_UB2(dir, 16, data0, data1); \
HADD_UB2_UH(data0, data1, sum_data0, sum_data1); \
sum_h = sum_data0 + sum_data1; \
sum_w = __msa_hadd_u_w(sum_h, sum_h); \
sum_d = __msa_hadd_u_d(sum_w, sum_w); \
sum_w = (v4u32) __msa_pckev_w((v4i32) sum_d, (v4i32) sum_d); \
sum_d = __msa_hadd_u_d(sum_w, sum_w); \
sum_w = (v4u32) __msa_srari_w((v4i32) sum_d, 5); \
out = (v16u8) __msa_splati_b((v16i8) sum_w, 0); \
for (row = 16; row--;) \
{ \
ST_UB2(out, out, dst, 16); \
dst += dst_stride; \
ST_UB2(out, out, dst, 16); \
dst += dst_stride; \
} \
}

Definition at line 290 of file vp9_intra_msa.c.

◆ INTRA_PREDICT_VALDC_16X16_MSA

#define INTRA_PREDICT_VALDC_16X16_MSA (   val)
Value:
void ff_dc_##val##_16x16_msa(uint8_t *dst, ptrdiff_t dst_stride, \
const uint8_t *left, const uint8_t *top) \
{ \
v16u8 out = (v16u8) __msa_ldi_b(val); \
ST_UB8(out, out, out, out, out, out, out, out, dst, dst_stride); \
dst += (8 * dst_stride); \
ST_UB8(out, out, out, out, out, out, out, out, dst, dst_stride); \
}

Definition at line 322 of file vp9_intra_msa.c.

◆ INTRA_PREDICT_VALDC_32X32_MSA

#define INTRA_PREDICT_VALDC_32X32_MSA (   val)
Value:
void ff_dc_##val##_32x32_msa(uint8_t *dst, ptrdiff_t dst_stride, \
const uint8_t *left, const uint8_t *top) \
{ \
uint32_t row; \
v16u8 out = (v16u8) __msa_ldi_b(val); \
for (row = 16; row--;) \
{ \
ST_UB2(out, out, dst, 16); \
dst += dst_stride; \
ST_UB2(out, out, dst, 16); \
dst += dst_stride; \
} \
}

Definition at line 337 of file vp9_intra_msa.c.

Function Documentation

◆ ff_vert_16x16_msa()

void ff_vert_16x16_msa ( uint8_t dst,
ptrdiff_t  dst_stride,
const uint8_t left,
const uint8_t src 
)

Definition at line 31 of file vp9_intra_msa.c.

◆ ff_vert_32x32_msa()

void ff_vert_32x32_msa ( uint8_t dst,
ptrdiff_t  dst_stride,
const uint8_t left,
const uint8_t src 
)

Definition at line 45 of file vp9_intra_msa.c.

◆ ff_hor_16x16_msa()

void ff_hor_16x16_msa ( uint8_t dst,
ptrdiff_t  dst_stride,
const uint8_t src,
const uint8_t top 
)

Definition at line 60 of file vp9_intra_msa.c.

◆ ff_hor_32x32_msa()

void ff_hor_32x32_msa ( uint8_t dst,
ptrdiff_t  dst_stride,
const uint8_t src,
const uint8_t top 
)

Definition at line 81 of file vp9_intra_msa.c.

◆ ff_dc_4x4_msa()

void ff_dc_4x4_msa ( uint8_t dst,
ptrdiff_t  dst_stride,
const uint8_t src_left,
const uint8_t src_top 
)

Definition at line 108 of file vp9_intra_msa.c.

◆ INTRA_DC_TL_4x4() [1/2]

INTRA_DC_TL_4x4 ( top  )

◆ INTRA_DC_TL_4x4() [2/2]

INTRA_DC_TL_4x4 ( left  )

◆ ff_dc_8x8_msa()

void ff_dc_8x8_msa ( uint8_t dst,
ptrdiff_t  dst_stride,
const uint8_t src_left,
const uint8_t src_top 
)

Definition at line 153 of file vp9_intra_msa.c.

◆ INTRA_DC_TL_8x8() [1/2]

INTRA_DC_TL_8x8 ( top  )

◆ INTRA_DC_TL_8x8() [2/2]

INTRA_DC_TL_8x8 ( left  )

◆ ff_dc_16x16_msa()

void ff_dc_16x16_msa ( uint8_t dst,
ptrdiff_t  dst_stride,
const uint8_t src_left,
const uint8_t src_top 
)

Definition at line 209 of file vp9_intra_msa.c.

◆ INTRA_DC_TL_16x16() [1/2]

INTRA_DC_TL_16x16 ( top  )

◆ INTRA_DC_TL_16x16() [2/2]

INTRA_DC_TL_16x16 ( left  )

◆ ff_dc_32x32_msa()

void ff_dc_32x32_msa ( uint8_t dst,
ptrdiff_t  dst_stride,
const uint8_t src_left,
const uint8_t src_top 
)

Definition at line 259 of file vp9_intra_msa.c.

◆ INTRA_DC_TL_32x32() [1/2]

INTRA_DC_TL_32x32 ( top  )

◆ INTRA_DC_TL_32x32() [2/2]

INTRA_DC_TL_32x32 ( left  )

◆ INTRA_PREDICT_VALDC_16X16_MSA() [1/3]

INTRA_PREDICT_VALDC_16X16_MSA ( 127  )

◆ INTRA_PREDICT_VALDC_16X16_MSA() [2/3]

INTRA_PREDICT_VALDC_16X16_MSA ( 128  )

◆ INTRA_PREDICT_VALDC_16X16_MSA() [3/3]

INTRA_PREDICT_VALDC_16X16_MSA ( 129  )

◆ INTRA_PREDICT_VALDC_32X32_MSA() [1/3]

INTRA_PREDICT_VALDC_32X32_MSA ( 127  )

◆ INTRA_PREDICT_VALDC_32X32_MSA() [2/3]

INTRA_PREDICT_VALDC_32X32_MSA ( 128  )

◆ INTRA_PREDICT_VALDC_32X32_MSA() [3/3]

INTRA_PREDICT_VALDC_32X32_MSA ( 129  )

◆ ff_tm_4x4_msa()

void ff_tm_4x4_msa ( uint8_t dst,
ptrdiff_t  dst_stride,
const uint8_t src_left,
const uint8_t src_top_ptr 
)

Definition at line 357 of file vp9_intra_msa.c.

◆ ff_tm_8x8_msa()

void ff_tm_8x8_msa ( uint8_t dst,
ptrdiff_t  dst_stride,
const uint8_t src_left,
const uint8_t src_top_ptr 
)

Definition at line 385 of file vp9_intra_msa.c.

◆ ff_tm_16x16_msa()

void ff_tm_16x16_msa ( uint8_t dst,
ptrdiff_t  dst_stride,
const uint8_t src_left,
const uint8_t src_top_ptr 
)

Definition at line 418 of file vp9_intra_msa.c.

◆ ff_tm_32x32_msa()

void ff_tm_32x32_msa ( uint8_t dst,
ptrdiff_t  dst_stride,
const uint8_t src_left,
const uint8_t src_top_ptr 
)

Definition at line 469 of file vp9_intra_msa.c.

out
FILE * out
Definition: movenc.c:54
data
const char data[16]
Definition: mxf.c:91
ST_UB8
#define ST_UB8(...)
Definition: generic_macros_msa.h:391
sum_d
static void sum_d(const int *input, int *output, int len)
Definition: dcadct.c:51
LD_UB
#define LD_UB(...)
Definition: generic_macros_msa.h:36
for
for(j=16;j >0;--j)
Definition: h264pred_template.c:469
LW
#define LW(psrc)
Definition: generic_macros_msa.h:108
SD4
#define SD4(in0, in1, in2, in3, pdst, stride)
Definition: generic_macros_msa.h:258
val
const char const char void * val
Definition: avisynth_c.h:863
SW4
#define SW4(in0, in1, in2, in3, pdst, stride)
Definition: generic_macros_msa.h:243
uint8_t
uint8_t
Definition: audio_convert.c:194
LD_UB2
#define LD_UB2(...)
Definition: generic_macros_msa.h:279
left
Tag MUST be and< 10hcoeff half pel interpolation filter coefficients, hcoeff[0] are the 2 middle coefficients[1] are the next outer ones and so on, resulting in a filter like:...eff[2], hcoeff[1], hcoeff[0], hcoeff[0], hcoeff[1], hcoeff[2] ... the sign of the coefficients is not explicitly stored but alternates after each coeff and coeff[0] is positive, so ...,+,-,+,-,+,+,-,+,-,+,... hcoeff[0] is not explicitly stored but found by subtracting the sum of all stored coefficients with signs from 32 hcoeff[0]=32 - hcoeff[1] - hcoeff[2] - ... a good choice for hcoeff and htaps is htaps=6 hcoeff={40,-10, 2} an alternative which requires more computations at both encoder and decoder side and may or may not be better is htaps=8 hcoeff={42,-14, 6,-2}ref_frames minimum of the number of available reference frames and max_ref_frames for example the first frame after a key frame always has ref_frames=1spatial_decomposition_type wavelet type 0 is a 9/7 symmetric compact integer wavelet 1 is a 5/3 symmetric compact integer wavelet others are reserved stored as delta from last, last is reset to 0 if always_reset||keyframeqlog quality(logarithmic quantizer scale) stored as delta from last, last is reset to 0 if always_reset||keyframemv_scale stored as delta from last, last is reset to 0 if always_reset||keyframe FIXME check that everything works fine if this changes between framesqbias dequantization bias stored as delta from last, last is reset to 0 if always_reset||keyframeblock_max_depth maximum depth of the block tree stored as delta from last, last is reset to 0 if always_reset||keyframequant_table quantization tableHighlevel bitstream structure:==============================--------------------------------------------|Header|--------------------------------------------|------------------------------------|||Block0||||split?||||yes no||||......... intra?||||:Block01 :yes no||||:Block02 :....... ..........||||:Block03 ::y DC ::ref index:||||:Block04 ::cb DC ::motion x :||||......... :cr DC ::motion y :||||....... ..........|||------------------------------------||------------------------------------|||Block1|||...|--------------------------------------------|------------ ------------ ------------|||Y subbands||Cb subbands||Cr subbands||||--- ---||--- ---||--- ---|||||LL0||HL0||||LL0||HL0||||LL0||HL0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||LH0||HH0||||LH0||HH0||||LH0||HH0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HL1||LH1||||HL1||LH1||||HL1||LH1|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HH1||HL2||||HH1||HL2||||HH1||HL2|||||...||...||...|||------------ ------------ ------------|--------------------------------------------Decoding process:=================------------|||Subbands|------------||||------------|Intra DC||||LL0 subband prediction ------------|\ Dequantization ------------------- \||Reference frames|\ IDWT|------- -------|Motion \|||Frame 0||Frame 1||Compensation . OBMC v -------|------- -------|--------------. \------> Frame n output Frame Frame<----------------------------------/|...|------------------- Range Coder:============Binary Range Coder:------------------- The implemented range coder is an adapted version based upon "Range encoding: an algorithm for removing redundancy from a digitised message." by G. N. N. Martin. The symbols encoded by the Snow range coder are bits(0|1). The associated probabilities are not fix but change depending on the symbol mix seen so far. bit seen|new state ---------+----------------------------------------------- 0|256 - state_transition_table[256 - old_state];1|state_transition_table[old_state];state_transition_table={ 0, 0, 0, 0, 0, 0, 0, 0, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 190, 191, 192, 194, 194, 195, 196, 197, 198, 199, 200, 201, 202, 202, 204, 205, 206, 207, 208, 209, 209, 210, 211, 212, 213, 215, 215, 216, 217, 218, 219, 220, 220, 222, 223, 224, 225, 226, 227, 227, 229, 229, 230, 231, 232, 234, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 248, 0, 0, 0, 0, 0, 0, 0};FIXME Range Coding of integers:------------------------- FIXME Neighboring Blocks:===================left and top are set to the respective blocks unless they are outside of the image in which case they are set to the Null block top-left is set to the top left block unless it is outside of the image in which case it is set to the left block if this block has no larger parent block or it is at the left side of its parent block and the top right block is not outside of the image then the top right block is used for top-right else the top-left block is used Null block y, cb, cr are 128 level, ref, mx and my are 0 Motion Vector Prediction:=========================1. the motion vectors of all the neighboring blocks are scaled to compensate for the difference of reference frames scaled_mv=(mv *(256 *(current_reference+1)/(mv.reference+1))+128)> the median of the scaled left
Definition: snow.txt:386
LD
#define LD(psrc)
Definition: generic_macros_msa.h:139