Skip to content

F
ffmpeg.wasm-core
Commit 2456efcc authored by Clément Bœsch's avatar Clément Bœsch
Browse files
Options

Merge commit '4f247de3' 

* commit '4f247de3':
  hevcdsp_template: Templatize IDCT

This commit is a noop as we already have that code from a previous
commits (see 92cccb7b).

Spacing is adjusted to reduce the diff.
Merged-by: 's avatarClément Bœsch <cboesch@gopro.com>
parents d0e132ba 4f247de3
Hide whitespace changes
Inline Side-by-side
Showing with 79 additions and 79 deletions
libavcodec/hevcdsp_template.c
View file @ 2456efcc
...@@ -170,97 +170,97 @@ static void FUNC(transform_4x4_luma)(int16_t *coeffs) ...@@ -170,97 +170,97 @@ static void FUNC(transform_4x4_luma)(int16_t *coeffs)
#undef TR_4x4_LUMA #undef TR_4x4_LUMA
#define TR_4(dst, src, dstep, sstep, assign, end) \ #define TR_4(dst, src, dstep, sstep, assign, end) \
do { \ do { \
const int e0 = 64 * src[0 * sstep] + 64 * src[2 * sstep]; \ const int e0 = 64 * src[0 * sstep] + 64 * src[2 * sstep]; \
const int e1 = 64 * src[0 * sstep] - 64 * src[2 * sstep]; \ const int e1 = 64 * src[0 * sstep] - 64 * src[2 * sstep]; \
const int o0 = 83 * src[1 * sstep] + 36 * src[3 * sstep]; \ const int o0 = 83 * src[1 * sstep] + 36 * src[3 * sstep]; \
const int o1 = 36 * src[1 * sstep] - 83 * src[3 * sstep]; \ const int o1 = 36 * src[1 * sstep] - 83 * src[3 * sstep]; \
\ \
assign(dst[0 * dstep], e0 + o0); \ assign(dst[0 * dstep], e0 + o0); \
assign(dst[1 * dstep], e1 + o1); \ assign(dst[1 * dstep], e1 + o1); \
assign(dst[2 * dstep], e1 - o1); \ assign(dst[2 * dstep], e1 - o1); \
assign(dst[3 * dstep], e0 - o0); \ assign(dst[3 * dstep], e0 - o0); \
} while (0) } while (0)
#define TR_8(dst, src, dstep, sstep, assign, end) \ #define TR_8(dst, src, dstep, sstep, assign, end) \
do { \ do { \
int i, j; \ int i, j; \
int e_8[4]; \ int e_8[4]; \
int o_8[4] = { 0 }; \ int o_8[4] = { 0 }; \
for (i = 0; i < 4; i++) \ for (i = 0; i < 4; i++) \
for (j = 1; j < end; j += 2) \ for (j = 1; j < end; j += 2) \
o_8[i] += transform[4 * j][i] * src[j * sstep]; \ o_8[i] += transform[4 * j][i] * src[j * sstep]; \
TR_4(e_8, src, 1, 2 * sstep, SET, 4); \ TR_4(e_8, src, 1, 2 * sstep, SET, 4); \
\ \
for (i = 0; i < 4; i++) { \ for (i = 0; i < 4; i++) { \
assign(dst[i * dstep], e_8[i] + o_8[i]); \ assign(dst[i * dstep], e_8[i] + o_8[i]); \
assign(dst[(7 - i) * dstep], e_8[i] - o_8[i]); \ assign(dst[(7 - i) * dstep], e_8[i] - o_8[i]); \
} \ } \
} while (0) } while (0)
#define TR_16(dst, src, dstep, sstep, assign, end) \ #define TR_16(dst, src, dstep, sstep, assign, end) \
do { \ do { \
int i, j; \ int i, j; \
int e_16[8]; \ int e_16[8]; \
int o_16[8] = { 0 }; \ int o_16[8] = { 0 }; \
for (i = 0; i < 8; i++) \ for (i = 0; i < 8; i++) \
for (j = 1; j < end; j += 2) \ for (j = 1; j < end; j += 2) \
o_16[i] += transform[2 * j][i] * src[j * sstep]; \ o_16[i] += transform[2 * j][i] * src[j * sstep]; \
TR_8(e_16, src, 1, 2 * sstep, SET, 8); \ TR_8(e_16, src, 1, 2 * sstep, SET, 8); \
\ \
for (i = 0; i < 8; i++) { \ for (i = 0; i < 8; i++) { \
assign(dst[i * dstep], e_16[i] + o_16[i]); \ assign(dst[i * dstep], e_16[i] + o_16[i]); \
assign(dst[(15 - i) * dstep], e_16[i] - o_16[i]); \ assign(dst[(15 - i) * dstep], e_16[i] - o_16[i]); \
} \ } \
} while (0) } while (0)
#define TR_32(dst, src, dstep, sstep, assign, end) \ #define TR_32(dst, src, dstep, sstep, assign, end) \
do { \ do { \
int i, j; \ int i, j; \
int e_32[16]; \ int e_32[16]; \
int o_32[16] = { 0 }; \ int o_32[16] = { 0 }; \
for (i = 0; i < 16; i++) \ for (i = 0; i < 16; i++) \
for (j = 1; j < end; j += 2) \ for (j = 1; j < end; j += 2) \
o_32[i] += transform[j][i] * src[j * sstep]; \ o_32[i] += transform[j][i] * src[j * sstep]; \
TR_16(e_32, src, 1, 2 * sstep, SET, end/2); \ TR_16(e_32, src, 1, 2 * sstep, SET, end/2); \
\ \
for (i = 0; i < 16; i++) { \ for (i = 0; i < 16; i++) { \
assign(dst[i * dstep], e_32[i] + o_32[i]); \ assign(dst[i * dstep], e_32[i] + o_32[i]); \
assign(dst[(31 - i) * dstep], e_32[i] - o_32[i]); \ assign(dst[(31 - i) * dstep], e_32[i] - o_32[i]); \
} \ } \
} while (0) } while (0)
#define IDCT_VAR4(H) \ #define IDCT_VAR4(H) \
int limit2 = FFMIN(col_limit + 4, H) int limit2 = FFMIN(col_limit + 4, H)
#define IDCT_VAR8(H) \ #define IDCT_VAR8(H) \
int limit = FFMIN(col_limit, H); \ int limit = FFMIN(col_limit, H); \
int limit2 = FFMIN(col_limit + 4, H) int limit2 = FFMIN(col_limit + 4, H)
#define IDCT_VAR16(H) IDCT_VAR8(H) #define IDCT_VAR16(H) IDCT_VAR8(H)
#define IDCT_VAR32(H) IDCT_VAR8(H) #define IDCT_VAR32(H) IDCT_VAR8(H)
#define IDCT(H) \ #define IDCT(H) \
static void FUNC(idct_##H ##x ##H )( \ static void FUNC(idct_ ## H ## x ## H )(int16_t *coeffs, \
int16_t *coeffs, int col_limit) { \ int col_limit) { \
int i; \ int i; \
int shift = 7; \ int shift = 7; \
int add = 1 << (shift - 1); \ int add = 1 << (shift - 1); \
int16_t *src = coeffs; \ int16_t *src = coeffs; \
IDCT_VAR ##H(H); \ IDCT_VAR ##H(H); \
\ \
for (i = 0; i < H; i++) { \ for (i = 0; i < H; i++) { \
TR_ ## H(src, src, H, H, SCALE, limit2); \ TR_ ## H(src, src, H, H, SCALE, limit2); \
if (limit2 < H && i%4 == 0 && !!i) \ if (limit2 < H && i%4 == 0 && !!i) \
limit2 -= 4; \ limit2 -= 4; \
src++; \ src++; \
} \ } \
\ \
shift = 20 - BIT_DEPTH; \ shift = 20 - BIT_DEPTH; \
add = 1 << (shift - 1); \ add = 1 << (shift - 1); \
for (i = 0; i < H; i++) { \ for (i = 0; i < H; i++) { \
TR_ ## H(coeffs, coeffs, 1, 1, SCALE, limit); \ TR_ ## H(coeffs, coeffs, 1, 1, SCALE, limit); \
coeffs += H; \ coeffs += H; \
} \ } \
} }
#define IDCT_DC(H) \ #define IDCT_DC(H) \
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment