hashirama/uvg266
1
0
Fork 0
mirror of https://github.com/ultravideo/uvg266.git synced 2024-11-24 02:24:07 +00:00
Code Issues Actions Projects Releases Wiki Activity

Align DCT matrices and temp transform buffers

Browse source
This commit is contained in:
Pauli Oikkonen 2019-06-27 14:25:09 +03:00
parent 148a150522
commit 8e9c65dca6
2 changed files with 13 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
src/strategies/avx2/dct-avx2.c
View file

@ -378,7 +378,7 @@ static void matrix_idct_8x8_avx2(int8_t bitdepth, const int16_t *input, int16_t
{
int32_t shift_1st = 7;
int32_t shift_2nd = 12 - (bitdepth - 8);
int16_t tmp[8 * 8];
ALIGNED(64) int16_t tmp[8 * 8];
const int16_t *tdct = &kvz_g_dct_8_t[0][0];
const int16_t *dct = &kvz_g_dct_8 [0][0];
@ -702,7 +702,7 @@ static void mul_clip_matrix_32x32_avx2(const int16_t *left, const int16_t *right
{\
int32_t shift_1st = kvz_g_convert_to_bit[n] + 1 + (bitdepth - 8); \
int32_t shift_2nd = kvz_g_convert_to_bit[n] + 8; \
int16_t tmp[n * n];\
ALIGNED(64) int16_t tmp[n * n];\
const int16_t *tdct = &kvz_g_ ## type ## _ ## n ## _t[0][0];\
const int16_t *dct = &kvz_g_ ## type ## _ ## n [0][0];\
\
@ -718,7 +718,7 @@ static void matrix_i ## type ## _## n ## x ## n ## _avx2(int8_t bitdepth, const
{\
int32_t shift_1st = 7; \
int32_t shift_2nd = 12 - (bitdepth - 8); \
int16_t tmp[n * n];\
ALIGNED(64) int16_t tmp[n * n];\
const int16_t *tdct = &kvz_g_ ## type ## _ ## n ## _t[0][0];\
const int16_t *dct = &kvz_g_ ## type ## _ ## n [0][0];\
\

20
src/strategies/generic/dct-generic.c
View file

@ -23,7 +23,7 @@
#include "strategyselector.h"
#include "tables.h"
const int16_t kvz_g_dst_4[4][4] =
ALIGNED(32) const int16_t kvz_g_dst_4[4][4] =
{
{ 29, 55, 74, 84 },
{ 74, 74, 0, -74 },
@ -31,7 +31,7 @@ const int16_t kvz_g_dst_4[4][4] =
{ 55, -84, 74, -29 }
};
const int16_t kvz_g_dct_4[4][4] =
ALIGNED(32) const int16_t kvz_g_dct_4[4][4] =
{
{ 64, 64, 64, 64 },
{ 83, 36, -36, -83 },
@ -39,7 +39,7 @@ const int16_t kvz_g_dct_4[4][4] =
{ 36, -83, 83, -36 }
};
const int16_t kvz_g_dct_8[8][8] =
ALIGNED(64) const int16_t kvz_g_dct_8[8][8] =
{
{ 64, 64, 64, 64, 64, 64, 64, 64 },
{ 89, 75, 50, 18, -18, -50, -75, -89 },
@ -51,7 +51,7 @@ const int16_t kvz_g_dct_8[8][8] =
{ 18, -50, 75, -89, 89, -75, 50, -18 }
};
const int16_t kvz_g_dct_16[16][16] =
ALIGNED(64) const int16_t kvz_g_dct_16[16][16] =
{
{ 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64 },
{ 90, 87, 80, 70, 57, 43, 25, 9, -9, -25, -43, -57, -70, -80, -87, -90 },
@ -71,7 +71,7 @@ const int16_t kvz_g_dct_16[16][16] =
{ 9, -25, 43, -57, 70, -80, 87, -90, 90, -87, 80, -70, 57, -43, 25, -9 }
};
const int16_t kvz_g_dct_32[32][32] =
ALIGNED(64) const int16_t kvz_g_dct_32[32][32] =
{
{ 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64 },
{ 90, 90, 88, 85, 82, 78, 73, 67, 61, 54, 46, 38, 31, 22, 13, 4, -4, -13, -22, -31, -38, -46, -54, -61, -67, -73, -78, -82, -85, -88, -90, -90 },
@ -107,7 +107,7 @@ const int16_t kvz_g_dct_32[32][32] =
{ 4, -13, 22, -31, 38, -46, 54, -61, 67, -73, 78, -82, 85, -88, 90, -90, 90, -90, 88, -85, 82, -78, 73, -67, 61, -54, 46, -38, 31, -22, 13, -4 }
};
const int16_t kvz_g_dst_4_t[4][4] =
ALIGNED(32) const int16_t kvz_g_dst_4_t[4][4] =
{
{ 29, 74, 84, 55 },
{ 55, 74, -29, -84 },
@ -115,7 +115,7 @@ const int16_t kvz_g_dst_4_t[4][4] =
{ 84, -74, 55, -29 }
};
const int16_t kvz_g_dct_4_t[4][4] =
ALIGNED(32) const int16_t kvz_g_dct_4_t[4][4] =
{
{ 64, 83, 64, 36, },
{ 64, 36, -64, -83, },
@ -123,7 +123,7 @@ const int16_t kvz_g_dct_4_t[4][4] =
{ 64, -83, 64, -36 }
};
const int16_t kvz_g_dct_8_t[8][8] =
ALIGNED(64) const int16_t kvz_g_dct_8_t[8][8] =
{
{ 64, 89, 83, 75, 64, 50, 36, 18, },
{ 64, 75, 36, -18, -64, -89, -83, -50, },
@ -135,7 +135,7 @@ const int16_t kvz_g_dct_8_t[8][8] =
{ 64, -89, 83, -75, 64, -50, 36, -18 }
};
const int16_t kvz_g_dct_16_t[16][16] =
ALIGNED(64) const int16_t kvz_g_dct_16_t[16][16] =
{
{ 64, 90, 89, 87, 83, 80, 75, 70, 64, 57, 50, 43, 36, 25, 18, 9, },
{ 64, 87, 75, 57, 36, 9, -18, -43, -64, -80, -89, -90, -83, -70, -50, -25, },
@ -155,7 +155,7 @@ const int16_t kvz_g_dct_16_t[16][16] =
{ 64, -90, 89, -87, 83, -80, 75, -70, 64, -57, 50, -43, 36, -25, 18, -9 }
};
const int16_t kvz_g_dct_32_t[32][32] =
ALIGNED(64) const int16_t kvz_g_dct_32_t[32][32] =
{
{ 64, 90, 90, 90, 89, 88, 87, 85, 83, 82, 80, 78, 75, 73, 70, 67, 64, 61, 57, 54, 50, 46, 43, 38, 36, 31, 25, 22, 18, 13, 9, 4, },
{ 64, 90, 87, 82, 75, 67, 57, 46, 36, 22, 9, -4, -18, -31, -43, -54, -64, -73, -80, -85, -89, -90, -90, -88, -83, -78, -70, -61, -50, -38, -25, -13, },