ffmpeg | branch: master | Clément Bœsch <cboesch at gopro.com> | Tue Jan 31 15:47:58 2017 +0100| [2456efcc0fe27a38b287abe38a98be49cf9247d5] | committer: Clément Bœsch
Merge commit '4f247de3b797cdc9d243d26534412f81c306e5b5'
* commit '4f247de3b797cdc9d243d26534412f81c306e5b5':
hevcdsp_template: Templatize IDCT
This commit is a noop as we already have that code from a previous
commits (see 92cccb7bcd79845020ed8abebf35170c182443b2).
Spacing is adjusted to reduce the diff.
Merged-by: Clément Bœsch <cboesch at gopro.com>
> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=2456efcc0fe27a38b287abe38a98be49cf9247d5
---
libavcodec/hevcdsp_template.c | 158 +++++++++++++++++++++---------------------
1 file changed, 79 insertions(+), 79 deletions(-)
diff --git a/libavcodec/hevcdsp_template.c b/libavcodec/hevcdsp_template.c
index 66b1ac0..ae32dcc 100644
--- a/libavcodec/hevcdsp_template.c
+++ b/libavcodec/hevcdsp_template.c
@@ -170,97 +170,97 @@ static void FUNC(transform_4x4_luma)(int16_t *coeffs)
#undef TR_4x4_LUMA
-#define TR_4(dst, src, dstep, sstep, assign, end) \
- do { \
- const int e0 = 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 o1 = 36 * src[1 * sstep] - 83 * src[3 * sstep]; \
- \
- assign(dst[0 * dstep], e0 + o0); \
- assign(dst[1 * dstep], e1 + o1); \
- assign(dst[2 * dstep], e1 - o1); \
- assign(dst[3 * dstep], e0 - o0); \
+#define TR_4(dst, src, dstep, sstep, assign, end) \
+ do { \
+ const int e0 = 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 o1 = 36 * src[1 * sstep] - 83 * src[3 * sstep]; \
+ \
+ assign(dst[0 * dstep], e0 + o0); \
+ assign(dst[1 * dstep], e1 + o1); \
+ assign(dst[2 * dstep], e1 - o1); \
+ assign(dst[3 * dstep], e0 - o0); \
} while (0)
-#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 < end; j += 2) \
- o_8[i] += transform[4 * j][i] * src[j * sstep]; \
- 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]); \
- assign(dst[(7 - i) * dstep], e_8[i] - o_8[i]); \
- } \
+#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 < end; j += 2) \
+ o_8[i] += transform[4 * j][i] * src[j * sstep]; \
+ 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]); \
+ assign(dst[(7 - i) * dstep], e_8[i] - o_8[i]); \
+ } \
} while (0)
-#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 < end; j += 2) \
- o_16[i] += transform[2 * j][i] * src[j * sstep]; \
- 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]); \
- assign(dst[(15 - i) * dstep], e_16[i] - o_16[i]); \
- } \
+#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 < end; j += 2) \
+ o_16[i] += transform[2 * j][i] * src[j * sstep]; \
+ 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]); \
+ assign(dst[(15 - i) * dstep], e_16[i] - o_16[i]); \
+ } \
} while (0)
-#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 < end; j += 2) \
- o_32[i] += transform[j][i] * src[j * sstep]; \
- 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]); \
- assign(dst[(31 - i) * dstep], e_32[i] - o_32[i]); \
- } \
+#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 < end; j += 2) \
+ o_32[i] += transform[j][i] * src[j * sstep]; \
+ 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]); \
+ assign(dst[(31 - i) * dstep], e_32[i] - o_32[i]); \
+ } \
} while (0)
-#define IDCT_VAR4(H) \
+#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_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, 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, 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, limit); \
- coeffs += H; \
- } \
+#define IDCT(H) \
+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, 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, limit); \
+ coeffs += H; \
+ } \
}
#define IDCT_DC(H) \
======================================================================
diff --cc libavcodec/hevcdsp_template.c
index 66b1ac0,2cde5a8..ae32dcc
--- a/libavcodec/hevcdsp_template.c
+++ b/libavcodec/hevcdsp_template.c
@@@ -170,114 -137,92 +170,114 @@@ static void FUNC(transform_4x4_luma)(in
#undef TR_4x4_LUMA
- #define TR_4(dst, src, dstep, sstep, assign, end) \
- do { \
- const int e0 = 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 o1 = 36 * src[1 * sstep] - 83 * src[3 * sstep]; \
- \
- assign(dst[0 * dstep], e0 + o0); \
- assign(dst[1 * dstep], e1 + o1); \
- assign(dst[2 * dstep], e1 - o1); \
- assign(dst[3 * dstep], e0 - o0); \
-#define TR_4(dst, src, dstep, sstep, assign) \
- do { \
- const int e0 = transform[8 * 0][0] * src[0 * sstep] + \
- transform[8 * 2][0] * src[2 * sstep]; \
- const int e1 = transform[8 * 0][1] * src[0 * sstep] + \
- transform[8 * 2][1] * src[2 * sstep]; \
- const int o0 = transform[8 * 1][0] * src[1 * sstep] + \
- transform[8 * 3][0] * src[3 * sstep]; \
- const int o1 = transform[8 * 1][1] * src[1 * sstep] + \
- transform[8 * 3][1] * src[3 * sstep]; \
- \
- assign(dst[0 * dstep], e0 + o0); \
- assign(dst[1 * dstep], e1 + o1); \
- assign(dst[2 * dstep], e1 - o1); \
- assign(dst[3 * dstep], e0 - o0); \
++#define TR_4(dst, src, dstep, sstep, assign, end) \
++ do { \
++ const int e0 = 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 o1 = 36 * src[1 * sstep] - 83 * src[3 * sstep]; \
++ \
++ assign(dst[0 * dstep], e0 + o0); \
++ assign(dst[1 * dstep], e1 + o1); \
++ assign(dst[2 * dstep], e1 - o1); \
++ assign(dst[3 * dstep], e0 - o0); \
} while (0)
- #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 < end; j += 2) \
- o_8[i] += transform[4 * j][i] * src[j * sstep]; \
- 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]); \
- assign(dst[(7 - i) * dstep], e_8[i] - o_8[i]); \
- } \
-#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]); \
+ assign(dst[(7 - i) * dstep], e_8[i] - o_8[i]); \
+ } \
} while (0)
- #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 < end; j += 2) \
- o_16[i] += transform[2 * j][i] * src[j * sstep]; \
- 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]); \
- assign(dst[(15 - i) * dstep], e_16[i] - o_16[i]); \
- } \
-#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]); \
+ assign(dst[(15 - i) * dstep], e_16[i] - o_16[i]); \
+ } \
} while (0)
- #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 < end; j += 2) \
- o_32[i] += transform[j][i] * src[j * sstep]; \
- 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]); \
- assign(dst[(31 - i) * dstep], e_32[i] - o_32[i]); \
- } \
-#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]); \
+ assign(dst[(31 - i) * dstep], e_32[i] - o_32[i]); \
+ } \
} while (0)
- #define IDCT_VAR4(H) \
++#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_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, 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, 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, limit); \
- coeffs += 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; \
+ } \
}
+#define IDCT_DC(H) \
+static void FUNC(idct_##H ##x ##H ##_dc)( \
+ int16_t *coeffs) { \
+ int i, j; \
+ int shift = 14 - BIT_DEPTH; \
+ int add = 1 << (shift - 1); \
+ int coeff = (((coeffs[0] + 1) >> 1) + add) >> shift; \
+ \
+ for (j = 0; j < H; j++) { \
+ for (i = 0; i < H; i++) { \
+ coeffs[i+j*H] = coeff; \
+ } \
+ } \
+}
+
IDCT( 4)
IDCT( 8)
IDCT(16)