Chiebot-Mirror
/
FFmpeg
mirror of https://github.com/FFmpeg/FFmpeg.git
8
0
Fork 0
Code Issues Projects Releases Wiki Activity

hevc: Add coefficient limiting to speed up IDCT

Browse Source 
Integrated to libav by Josh de Kock <josh@itanimul.li>.

Signed-off-by: Alexandra Hájková <alexandra@khirnov.net>
pull/249/merge
Mickaël Raulet 8 years ago committed by Luca Barbato
parent a92fd8a062
commit cc16da75c2
3 changed files with 36 additions and 16 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 12
      libavcodec/hevc.c
  2. 2
      libavcodec/hevcdsp.h
  3. 38
      libavcodec/hevcdsp_template.c

12
libavcodec/hevc.c
Unescape View File

@ -1218,8 +1218,16 @@ static void hls_residual_coding(HEVCContext *s, int x0, int y0,
int max_xy = FFMAX(last_significant_coeff_x, last_significant_coeff_y);
if (max_xy == 0)
s->hevcdsp.idct_dc[log2_trafo_size - 2](coeffs);
else
s->hevcdsp.idct[log2_trafo_size - 2](coeffs);
else {
int col_limit = last_significant_coeff_x + last_significant_coeff_y + 4;
if (max_xy < 4)
col_limit = FFMIN(4, col_limit);
else if (max_xy < 8)
col_limit = FFMIN(8, col_limit);
else if (max_xy < 12)
col_limit = FFMIN(24, col_limit);
s->hevcdsp.idct[log2_trafo_size - 2](coeffs, col_limit);
}
}
}
s->hevcdsp.add_residual[log2_trafo_size - 2](dst, coeffs, stride);

2
libavcodec/hevcdsp.h
Unescape View File

@ -46,7 +46,7 @@ typedef struct HEVCDSPContext {
void (*dequant)(int16_t *coeffs);
void (*transform_4x4_luma)(int16_t *coeffs);
void (*idct[4])(int16_t *coeffs);
void (*idct[4])(int16_t *coeffs, int col_limit);
void (*idct_dc[4])(int16_t *coeffs);
void (*sao_band_filter[4])(uint8_t *dst, uint8_t *src, ptrdiff_t stride,

38
libavcodec/hevcdsp_template.c
Unescape View File

@ -137,7 +137,7 @@ static void FUNC(transform_4x4_luma)(int16_t *coeffs)
#undef TR_4x4_LUMA
#define TR_4(dst, src, dstep, sstep, assign) \
#define TR_4(dst, src, dstep, sstep, assign, end) \
do { \
const int e0 = transform[8 * 0][0] * src[0 * sstep] + \
transform[8 * 2][0] * src[2 * sstep]; \
@ -154,15 +154,15 @@ static void FUNC(transform_4x4_luma)(int16_t *coeffs)
assign(dst[3 * dstep], e0 - o0); \
} while (0)
#define TR_8(dst, src, dstep, sstep, assign) \
#define TR_8(dst, src, dstep, sstep, assign, end) \
do { \
int i, j; \
int e_8[4]; \
int o_8[4] = { 0 }; \
for (i = 0; i < 4; i++) \
for (j = 1; j < 8; j += 2) \
for (j = 1; j < end; j += 2) \
o_8[i] += transform[4 * j][i] * src[j * sstep]; \
TR_4(e_8, src, 1, 2 * sstep, SET); \
TR_4(e_8, src, 1, 2 * sstep, SET, 4); \
\
for (i = 0; i < 4; i++) { \
assign(dst[i * dstep], e_8[i] + o_8[i]); \
@ -170,15 +170,15 @@ static void FUNC(transform_4x4_luma)(int16_t *coeffs)
} \
} while (0)
#define TR_16(dst, src, dstep, sstep, assign) \
#define TR_16(dst, src, dstep, sstep, assign, end) \
do { \
int i, j; \
int e_16[8]; \
int o_16[8] = { 0 }; \
for (i = 0; i < 8; i++) \
for (j = 1; j < 16; j += 2) \
for (j = 1; j < end; j += 2) \
o_16[i] += transform[2 * j][i] * src[j * sstep]; \
TR_8(e_16, src, 1, 2 * sstep, SET); \
TR_8(e_16, src, 1, 2 * sstep, SET, 8); \
\
for (i = 0; i < 8; i++) { \
assign(dst[i * dstep], e_16[i] + o_16[i]); \
@ -186,15 +186,15 @@ static void FUNC(transform_4x4_luma)(int16_t *coeffs)
} \
} while (0)
#define TR_32(dst, src, dstep, sstep, assign) \
#define TR_32(dst, src, dstep, sstep, assign, end) \
do { \
int i, j; \
int e_32[16]; \
int o_32[16] = { 0 }; \
for (i = 0; i < 16; i++) \
for (j = 1; j < 32; j += 2) \
for (j = 1; j < end; j += 2) \
o_32[i] += transform[j][i] * src[j * sstep]; \
TR_16(e_32, src, 1, 2 * sstep, SET); \
TR_16(e_32, src, 1, 2 * sstep, SET, end / 2); \
\
for (i = 0; i < 16; i++) { \
assign(dst[i * dstep], e_32[i] + o_32[i]); \
@ -202,23 +202,35 @@ static void FUNC(transform_4x4_luma)(int16_t *coeffs)
} \
} while (0)
#define IDCT_VAR4(H) \
int limit2 = FFMIN(col_limit + 4, H)
#define IDCT_VAR8(H) \
int limit = FFMIN(col_limit, H); \
int limit2 = FFMIN(col_limit + 4, H)
#define IDCT_VAR16(H) IDCT_VAR8(H)
#define IDCT_VAR32(H) IDCT_VAR8(H)
#define IDCT(H) \
static void FUNC(idct_ ## H ## x ## H )(int16_t *coeffs) \
static void FUNC(idct_ ## H ## x ## H )(int16_t *coeffs, \
int col_limit) \
{ \
int i; \
int shift = 7; \
int add = 1 << (shift - 1); \
int16_t *src = coeffs; \
IDCT_VAR ## H(H); \
\
for (i = 0; i < H; i++) { \
TR_ ## H(src, src, H, H, SCALE); \
TR_ ## H(src, src, H, H, SCALE, limit2); \
if (limit2 < H && i%4 == 0 && !!i) \
limit2 -= 4; \
src++; \
} \
\
shift = 20 - BIT_DEPTH; \
add = 1 << (shift - 1); \
for (i = 0; i < H; i++) { \
TR_ ## H(coeffs, coeffs, 1, 1, SCALE); \
TR_ ## H(coeffs, coeffs, 1, 1, SCALE, limit); \
coeffs += H; \
} \
}

Write Preview
Loading…
Cancel
Save