clean up forward and inverse hybrid transform

Rebased.

Remove the old matrix multiplication transform computation. The 16x16
ADST/DCT can be switched on/off and evaluated by setting ACTIVE_HT16
300/0 in vp9/common/vp9_blockd.h.

Change-Id: Icab2dbd18538987e1dc4e88c45abfc4cfc6e133f
This commit is contained in:
Jingning Han 2013-02-22 16:29:28 -08:00
parent 499fe05dc0
commit 77a3becf92
10 changed files with 0 additions and 912 deletions

3
configure vendored
View File

@ -246,9 +246,6 @@ EXPERIMENT_LIST="
cnvcontext
enable_6tap
abovesprefmv
intht
intht4x4
intht16x16
"
CONFIG_LIST="
external_build

View File

@ -50,13 +50,11 @@ static const int cospi_29_64 = 2404;
static const int cospi_30_64 = 1606;
static const int cospi_31_64 = 804;
#if CONFIG_INTHT4X4
// 16384 * sqrt(2) * sin(kPi/9) * 2 / 3
static const int sinpi_1_9 = 5283;
static const int sinpi_2_9 = 9929;
static const int sinpi_3_9 = 13377;
static const int sinpi_4_9 = 15212;
#endif
static INLINE int dct_const_round_shift(int input) {
int rv = (input + DCT_CONST_ROUNDING) >> DCT_CONST_BITS;

View File

@ -30,274 +30,6 @@
#include "vp9/common/vp9_common.h"
#include "vp9/common/vp9_idct.h"
static const int16_t idct_i4[16] = {
8192, 10703, 8192, 4433,
8192, 4433, -8192, -10703,
8192, -4433, -8192, 10703,
8192, -10703, 8192, -4433
};
static const int16_t iadst_i4[16] = {
3736, 9459, 10757, 7021,
7021, 9459, -3736, -10757,
9459, 0, -9459, 9459,
10757, -9459, 7021, -3736
};
static const int16_t idct_i8[64] = {
5793, 8035, 7568, 6811,
5793, 4551, 3135, 1598,
5793, 6811, 3135, -1598,
-5793, -8035, -7568, -4551,
5793, 4551, -3135, -8035,
-5793, 1598, 7568, 6811,
5793, 1598, -7568, -4551,
5793, 6811, -3135, -8035,
5793, -1598, -7568, 4551,
5793, -6811, -3135, 8035,
5793, -4551, -3135, 8035,
-5793, -1598, 7568, -6811,
5793, -6811, 3135, 1598,
-5793, 8035, -7568, 4551,
5793, -8035, 7568, -6811,
5793, -4551, 3135, -1598
};
static const int16_t iadst_i8[64] = {
1460, 4184, 6342, 7644,
7914, 7114, 5354, 2871,
2871, 7114, 7644, 4184,
-1460, -6342, -7914, -5354,
4184, 7914, 2871, -5354,
-7644, -1460, 6342, 7114,
5354, 6342, -4184, -7114,
2871, 7644, -1460, -7914,
6342, 2871, -7914, 1460,
7114, -5354, -4184, 7644,
7114, -1460, -5354, 7914,
-4184, -2871, 7644, -6342,
7644, -5354, 1460, 2871,
-6342, 7914, -7114, 4184,
7914, -7644, 7114, -6342,
5354, -4184, 2871, -1460
};
static const int16_t idct_i16[256] = {
4096, 5765, 5681, 5543, 5352, 5109, 4816, 4478,
4096, 3675, 3218, 2731, 2217, 1682, 1130, 568,
4096, 5543, 4816, 3675, 2217, 568, -1130, -2731,
-4096, -5109, -5681, -5765, -5352, -4478, -3218, -1682,
4096, 5109, 3218, 568, -2217, -4478, -5681, -5543,
-4096, -1682, 1130, 3675, 5352, 5765, 4816, 2731,
4096, 4478, 1130, -2731, -5352, -5543, -3218, 568,
4096, 5765, 4816, 1682, -2217, -5109, -5681, -3675,
4096, 3675, -1130, -5109, -5352, -1682, 3218, 5765,
4096, -568, -4816, -5543, -2217, 2731, 5681, 4478,
4096, 2731, -3218, -5765, -2217, 3675, 5681, 1682,
-4096, -5543, -1130, 4478, 5352, 568, -4816, -5109,
4096, 1682, -4816, -4478, 2217, 5765, 1130, -5109,
-4096, 2731, 5681, 568, -5352, -3675, 3218, 5543,
4096, 568, -5681, -1682, 5352, 2731, -4816, -3675,
4096, 4478, -3218, -5109, 2217, 5543, -1130, -5765,
4096, -568, -5681, 1682, 5352, -2731, -4816, 3675,
4096, -4478, -3218, 5109, 2217, -5543, -1130, 5765,
4096, -1682, -4816, 4478, 2217, -5765, 1130, 5109,
-4096, -2731, 5681, -568, -5352, 3675, 3218, -5543,
4096, -2731, -3218, 5765, -2217, -3675, 5681, -1682,
-4096, 5543, -1130, -4478, 5352, -568, -4816, 5109,
4096, -3675, -1130, 5109, -5352, 1682, 3218, -5765,
4096, 568, -4816, 5543, -2217, -2731, 5681, -4478,
4096, -4478, 1130, 2731, -5352, 5543, -3218, -568,
4096, -5765, 4816, -1682, -2217, 5109, -5681, 3675,
4096, -5109, 3218, -568, -2217, 4478, -5681, 5543,
-4096, 1682, 1130, -3675, 5352, -5765, 4816, -2731,
4096, -5543, 4816, -3675, 2217, -568, -1130, 2731,
-4096, 5109, -5681, 5765, -5352, 4478, -3218, 1682,
4096, -5765, 5681, -5543, 5352, -5109, 4816, -4478,
4096, -3675, 3218, -2731, 2217, -1682, 1130, -568
};
#if CONFIG_INTHT
static const int16_t iadst_i16[256] = {
284, 850, 1407, 1951, 2476, 2977, 3450, 3889,
4291, 4652, 4967, 5235, 5453, 5618, 5729, 5784,
850, 2476, 3889, 4967, 5618, 5784, 5453, 4652,
3450, 1951, 284, -1407, -2977, -4291, -5235, -5729,
1407, 3889, 5453, 5729, 4652, 2476, -284, -2977,
-4967, -5784, -5235, -3450, -850, 1951, 4291, 5618,
1951, 4967, 5729, 3889, 284, -3450, -5618, -5235,
-2476, 1407, 4652, 5784, 4291, 850, -2977, -5453,
2476, 5618, 4652, 284, -4291, -5729, -2977, 1951,
5453, 4967, 850, -3889, -5784, -3450, 1407, 5235,
2977, 5784, 2476, -3450, -5729, -1951, 3889, 5618,
1407, -4291, -5453, -850, 4652, 5235, 284, -4967,
3450, 5453, -284, -5618, -2977, 3889, 5235, -850,
-5729, -2476, 4291, 4967, -1407, -5784, -1951, 4652,
3889, 4652, -2977, -5235, 1951, 5618, -850, -5784,
-284, 5729, 1407, -5453, -2476, 4967, 3450, -4291,
4291, 3450, -4967, -2476, 5453, 1407, -5729, -284,
5784, -850, -5618, 1951, 5235, -2977, -4652, 3889,
4652, 1951, -5784, 1407, 4967, -4291, -2476, 5729,
-850, -5235, 3889, 2977, -5618, 284, 5453, -3450,
4967, 284, -5235, 4652, 850, -5453, 4291, 1407,
-5618, 3889, 1951, -5729, 3450, 2476, -5784, 2977,
5235, -1407, -3450, 5784, -3889, -850, 4967, -5453,
1951, 2977, -5729, 4291, 284, -4652, 5618, -2476,
5453, -2977, -850, 4291, -5784, 4652, -1407, -2476,
5235, -5618, 3450, 284, -3889, 5729, -4967, 1951,
5618, -4291, 1951, 850, -3450, 5235, -5784, 4967,
-2977, 284, 2476, -4652, 5729, -5453, 3889, -1407,
5729, -5235, 4291, -2977, 1407, 284, -1951, 3450,
-4652, 5453, -5784, 5618, -4967, 3889, -2476, 850,
5784, -5729, 5618, -5453, 5235, -4967, 4652, -4291,
3889, -3450, 2977, -2476, 1951, -1407, 850, -284
};
#else
static const int16_t iadst_i16[256] = {
542, 1607, 2614, 3526, 4311, 4940, 5390, 5646,
5698, 5543, 5189, 4646, 3936, 3084, 2120, 1080,
1080, 3084, 4646, 5543, 5646, 4940, 3526, 1607,
-542, -2614, -4311, -5390, -5698, -5189, -3936, -2120,
1607, 4311, 5646, 5189, 3084, 0, -3084, -5189,
-5646, -4311, -1607, 1607, 4311, 5646, 5189, 3084,
2120, 5189, 5390, 2614, -1607, -4940, -5543, -3084,
1080, 4646, 5646, 3526, -542, -4311, -5698, -3936,
2614, 5646, 3936, -1080, -5189, -4940, -542, 4311,
5543, 2120, -3084, -5698, -3526, 1607, 5390, 4646,
3084, 5646, 1607, -4311, -5189, 0, 5189, 4311,
-1607, -5646, -3084, 3084, 5646, 1607, -4311, -5189,
3526, 5189, -1080, -5698, -1607, 4940, 3936, -3084,
-5390, 542, 5646, 2120, -4646, -4311, 2614, 5543,
3936, 4311, -3526, -4646, 3084, 4940, -2614, -5189,
2120, 5390, -1607, -5543, 1080, 5646, -542, -5698,
4311, 3084, -5189, -1607, 5646, 0, -5646, 1607,
5189, -3084, -4311, 4311, 3084, -5189, -1607, 5646,
4646, 1607, -5698, 2120, 4311, -4940, -1080, 5646,
-2614, -3936, 5189, 542, -5543, 3084, 3526, -5390,
4940, 0, -4940, 4940, 0, -4940, 4940, 0,
-4940, 4940, 0, -4940, 4940, 0, -4940, 4940,
5189, -1607, -3084, 5646, -4311, 0, 4311, -5646,
3084, 1607, -5189, 5189, -1607, -3084, 5646, -4311,
5390, -3084, -542, 3936, -5646, 4940, -2120, -1607,
4646, -5698, 4311, -1080, -2614, 5189, -5543, 3526,
5543, -4311, 2120, 542, -3084, 4940, -5698, 5189,
-3526, 1080, 1607, -3936, 5390, -5646, 4646, -2614,
5646, -5189, 4311, -3084, 1607, 0, -1607, 3084,
-4311, 5189, -5646, 5646, -5189, 4311, -3084, 1607,
5698, -5646, 5543, -5390, 5189, -4940, 4646, -4311,
3936, -3526, 3084, -2614, 2120, -1607, 1080, -542
};
#endif
/* Converted the transforms to integer form. */
#define HORIZONTAL_SHIFT 14 // 16
#define HORIZONTAL_ROUNDING ((1 << (HORIZONTAL_SHIFT - 1)) - 1)
#define VERTICAL_SHIFT 17 // 15
#define VERTICAL_ROUNDING ((1 << (VERTICAL_SHIFT - 1)) - 1)
void vp9_ihtllm_c(const int16_t *input, int16_t *output, int pitch,
TX_TYPE tx_type, int tx_dim, uint16_t eobs) {
int i, j, k;
int nz_dim;
int16_t imbuf[256];
const int16_t *ip = input;
int16_t *op = output;
int16_t *im = &imbuf[0];
/* pointers to vertical and horizontal transforms. */
const int16_t *ptv = NULL, *pth = NULL;
int shortpitch = pitch >> 1;
switch (tx_type) {
case ADST_ADST :
ptv = pth = (tx_dim == 4) ? &iadst_i4[0]
: ((tx_dim == 8) ? &iadst_i8[0]
: &iadst_i16[0]);
break;
case ADST_DCT :
ptv = (tx_dim == 4) ? &iadst_i4[0]
: ((tx_dim == 8) ? &iadst_i8[0] : &iadst_i16[0]);
pth = (tx_dim == 4) ? &idct_i4[0]
: ((tx_dim == 8) ? &idct_i8[0] : &idct_i16[0]);
break;
case DCT_ADST :
ptv = (tx_dim == 4) ? &idct_i4[0]
: ((tx_dim == 8) ? &idct_i8[0] : &idct_i16[0]);
pth = (tx_dim == 4) ? &iadst_i4[0]
: ((tx_dim == 8) ? &iadst_i8[0] : &iadst_i16[0]);
break;
case DCT_DCT :
ptv = pth = (tx_dim == 4) ? &idct_i4[0]
: ((tx_dim == 8) ? &idct_i8[0]
: &idct_i16[0]);
break;
default:
assert(0);
break;
}
nz_dim = tx_dim;
if(tx_dim > 4) {
if(eobs < 36) {
vpx_memset(im, 0, 512);
nz_dim = 8;
if(eobs < 3) {
nz_dim = 2;
} else if(eobs < 10) {
nz_dim = 4;
}
}
}
/* 2-D inverse transform X = M1*Z*Transposed_M2 is calculated in 2 steps
* from right to left:
* 1. horizontal transform: Y= Z*Transposed_M2
* 2. vertical transform: X = M1*Y
* In SIMD, doing this way could eliminate the transpose needed if it is
* calculated from left to right.
*/
/* Horizontal transformation */
for (j = 0; j < tx_dim; j++) {
for (i = 0; i < nz_dim; i++) {
int temp = 0;
for (k = 0; k < nz_dim; k++) {
temp += ip[k] * pth[k];
}
/* Calculate im and store it in its transposed position. */
im[i] = (int16_t)((temp + HORIZONTAL_ROUNDING) >> HORIZONTAL_SHIFT);
ip += tx_dim;
}
im += tx_dim;
pth += tx_dim;
ip = input;
}
/* Vertical transformation */
im = &imbuf[0];
for (i = 0; i < tx_dim; i++) {
for (j = 0; j < tx_dim; j++) {
int temp = 0;
for (k = 0; k < nz_dim; k++) {
temp += ptv[k] * im[k];
}
op[j] = (int16_t)((temp + VERTICAL_ROUNDING) >> VERTICAL_SHIFT);
im += tx_dim;
}
im = &imbuf[0];
ptv += tx_dim;
op += shortpitch;
}
}
void vp9_short_inv_walsh4x4_x8_c(int16_t *input, int16_t *output, int pitch) {
int i;
int a1, b1, c1, d1;
@ -534,7 +266,6 @@ void vp9_short_idct8x8_c(int16_t *input, int16_t *output, int pitch) {
}
}
#if CONFIG_INTHT4X4
static void iadst4_1d(int16_t *input, int16_t *output) {
int x0, x1, x2, x3;
int s0, s1, s2, s3, s4, s5, s6, s7;
@ -626,9 +357,7 @@ void vp9_short_iht4x4_c(int16_t *input, int16_t *output,
output[j * short_pitch + i] = (temp_out[j] + 8) >> 4;
}
}
#endif
#if CONFIG_INTHT
static void iadst8_1d(int16_t *input, int16_t *output) {
int x0, x1, x2, x3, x4, x5, x6, x7;
int s0, s1, s2, s3, s4, s5, s6, s7;
@ -757,8 +486,6 @@ void vp9_short_iht8x8_c(int16_t *input, int16_t *output,
output[j * short_pitch + i] = (temp_out[j] + 16) >> 5;
}
}
#endif
void vp9_short_idct10_8x8_c(int16_t *input, int16_t *output, int pitch) {
int16_t out[8 * 8];
@ -980,7 +707,6 @@ void vp9_short_idct16x16_c(int16_t *input, int16_t *output, int pitch) {
}
}
#if CONFIG_INTHT16X16
void iadst16_1d(int16_t *input, int16_t *output) {
int x0, x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13, x14, x15;
int s0, s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15;
@ -1201,9 +927,6 @@ void vp9_short_iht16x16_c(int16_t *input, int16_t *output,
output[j * 16 + i] = (temp_out[j] + 32) >> 6;
}
}
#endif
void vp9_short_idct10_16x16_c(int16_t *input, int16_t *output, int pitch) {
int16_t out[16 * 16];

View File

@ -25,13 +25,8 @@ void vp9_inverse_transform_mby_4x4(MACROBLOCKD *xd) {
for (i = 0; i < 16; i++) {
TX_TYPE tx_type = get_tx_type_4x4(xd, &xd->block[i]);
if (tx_type != DCT_DCT) {
#if CONFIG_INTHT4X4
vp9_short_iht4x4(xd->block[i].dqcoeff, xd->block[i].diff,
32, tx_type);
#else
vp9_ihtllm(xd->block[i].dqcoeff, xd->block[i].diff, 32,
tx_type, 4, xd->block[i].eob);
#endif
} else {
vp9_inverse_transform_b_4x4(xd, i, 32);
}
@ -63,13 +58,8 @@ void vp9_inverse_transform_mby_8x8(MACROBLOCKD *xd) {
for (i = 0; i < 9; i += 8) {
TX_TYPE tx_type = get_tx_type_8x8(xd, &xd->block[i]);
if (tx_type != DCT_DCT) {
#if CONFIG_INTHT
vp9_short_iht8x8(xd->block[i].dqcoeff, xd->block[i].diff,
32, tx_type);
#else
vp9_ihtllm(xd->block[i].dqcoeff, xd->block[i].diff, 32, tx_type, 8,
xd->block[i].eob);
#endif
} else {
vp9_inverse_transform_b_8x8(&blockd[i].dqcoeff[0],
&blockd[i].diff[0], 32);
@ -78,13 +68,8 @@ void vp9_inverse_transform_mby_8x8(MACROBLOCKD *xd) {
for (i = 2; i < 11; i += 8) {
TX_TYPE tx_type = get_tx_type_8x8(xd, &xd->block[i]);
if (tx_type != DCT_DCT) {
#if CONFIG_INTHT
vp9_short_iht8x8(xd->block[i + 2].dqcoeff, xd->block[i].diff,
32, tx_type);
#else
vp9_ihtllm(xd->block[i + 2].dqcoeff, xd->block[i].diff, 32, tx_type, 8,
xd->block[i + 2].eob);
#endif
} else {
vp9_inverse_transform_b_8x8(&blockd[i + 2].dqcoeff[0],
&blockd[i].diff[0], 32);
@ -116,11 +101,7 @@ void vp9_inverse_transform_mby_16x16(MACROBLOCKD *xd) {
BLOCKD *bd = &xd->block[0];
TX_TYPE tx_type = get_tx_type_16x16(xd, bd);
if (tx_type != DCT_DCT) {
#if CONFIG_INTHT16X16
vp9_short_iht16x16(bd->dqcoeff, bd->diff, 32, tx_type);
#else
vp9_ihtllm(bd->dqcoeff, bd->diff, 32, tx_type, 16, bd->eob);
#endif
} else {
vp9_inverse_transform_b_16x16(&xd->block[0].dqcoeff[0],
&xd->block[0].diff[0], 32);

View File

@ -284,24 +284,14 @@ specialize vp9_short_idct32x32
prototype void vp9_short_idct1_32x32 "int16_t *input, int16_t *output"
specialize vp9_short_idct1_32x32
#if CONFIG_INTHT
prototype void vp9_short_iht8x8 "int16_t *input, int16_t *output, int pitch, int tx_type"
specialize vp9_short_iht8x8
#endif
#if CONFIG_INTHT4X4
prototype void vp9_short_iht4x4 "int16_t *input, int16_t *output, int pitch, int tx_type"
specialize vp9_short_iht4x4
#endif
#if CONFIG_INTHT16X16
prototype void vp9_short_iht16x16 "int16_t *input, int16_t *output, int pitch, int tx_type"
specialize vp9_short_iht16x16
#endif
prototype void vp9_ihtllm "const int16_t *input, int16_t *output, int pitch, int tx_type, int tx_dim, int eob"
specialize vp9_ihtllm
# dct and add
@ -565,23 +555,14 @@ if [ "$CONFIG_INTERNAL_STATS" = "yes" ]; then
fi
# fdct functions
prototype void vp9_fht "const int16_t *input, int pitch, int16_t *output, int tx_type, int tx_dim"
specialize vp9_fht
#if CONFIG_INTHT4X4
prototype void vp9_short_fht4x4 "int16_t *InputData, int16_t *OutputData, int pitch, int tx_type"
specialize vp9_short_fht4x4
#endif
#if CONFIG_INTHT
prototype void vp9_short_fht8x8 "int16_t *InputData, int16_t *OutputData, int pitch, int tx_type"
specialize vp9_short_fht8x8
#endif
#if CONFIG_INTHT16X16
prototype void vp9_short_fht16x16 "int16_t *InputData, int16_t *OutputData, int pitch, int tx_type"
specialize vp9_short_fht16x16
#endif
prototype void vp9_short_fdct8x8 "int16_t *InputData, int16_t *OutputData, int pitch"
specialize vp9_short_fdct8x8

View File

@ -68,12 +68,7 @@ void vp9_ht_dequant_idct_add_c(TX_TYPE tx_type, int16_t *input,
input[i] = dq[i] * input[i];
}
#if CONFIG_INTHT4X4
vp9_short_iht4x4(input, output, 8, tx_type);
#else
vp9_ihtllm(input, output, 4 << 1, tx_type, 4, eob);
#endif
vpx_memset(input, 0, 32);
add_residual(diff_ptr, pred, pitch, dest, stride, 4, 4);
@ -95,11 +90,7 @@ void vp9_ht_dequant_idct_add_8x8_c(TX_TYPE tx_type, int16_t *input,
input[i] *= dq[1];
}
#if CONFIG_INTHT
vp9_short_iht8x8(input, output, 16, tx_type);
#else
vp9_ihtllm(input, output, 16, tx_type, 8, eob);
#endif
vpx_memset(input, 0, 128);
add_residual(diff_ptr, pred, pitch, dest, stride, 8, 8);
@ -264,11 +255,7 @@ void vp9_ht_dequant_idct_add_16x16_c(TX_TYPE tx_type, int16_t *input,
input[i] *= dq[1];
// inverse hybrid transform
#if CONFIG_INTHT16X16
vp9_short_iht16x16(input, output, 32, tx_type);
#else
vp9_ihtllm(input, output, 32, tx_type, 16, eob);
#endif
// the idct halves ( >> 1) the pitch
// vp9_short_idct16x16_c(input, output, 32);

View File

@ -17,520 +17,6 @@
#include "vp9/common/vp9_blockd.h"
#include "vp9/common/vp9_idct.h"
// TODO: these transforms can be converted into integer forms to reduce
// the complexity
static const float dct_4[16] = {
0.500000000000000, 0.500000000000000, 0.500000000000000, 0.500000000000000,
0.653281482438188, 0.270598050073099, -0.270598050073099, -0.653281482438188,
0.500000000000000, -0.500000000000000, -0.500000000000000, 0.500000000000000,
0.270598050073099, -0.653281482438188, 0.653281482438188, -0.270598050073099
};
static const float adst_4[16] = {
0.228013428883779, 0.428525073124360, 0.577350269189626, 0.656538502008139,
0.577350269189626, 0.577350269189626, 0.000000000000000, -0.577350269189626,
0.656538502008139, -0.228013428883779, -0.577350269189626, 0.428525073124359,
0.428525073124360, -0.656538502008139, 0.577350269189626, -0.228013428883779
};
static const float dct_8[64] = {
0.353553390593274, 0.353553390593274, 0.353553390593274, 0.353553390593274,
0.353553390593274, 0.353553390593274, 0.353553390593274, 0.353553390593274,
0.490392640201615, 0.415734806151273, 0.277785116509801, 0.097545161008064,
-0.097545161008064, -0.277785116509801, -0.415734806151273, -0.490392640201615,
0.461939766255643, 0.191341716182545, -0.191341716182545, -0.461939766255643,
-0.461939766255643, -0.191341716182545, 0.191341716182545, 0.461939766255643,
0.415734806151273, -0.097545161008064, -0.490392640201615, -0.277785116509801,
0.277785116509801, 0.490392640201615, 0.097545161008064, -0.415734806151273,
0.353553390593274, -0.353553390593274, -0.353553390593274, 0.353553390593274,
0.353553390593274, -0.353553390593274, -0.353553390593274, 0.353553390593274,
0.277785116509801, -0.490392640201615, 0.097545161008064, 0.415734806151273,
-0.415734806151273, -0.097545161008064, 0.490392640201615, -0.277785116509801,
0.191341716182545, -0.461939766255643, 0.461939766255643, -0.191341716182545,
-0.191341716182545, 0.461939766255643, -0.461939766255643, 0.191341716182545,
0.097545161008064, -0.277785116509801, 0.415734806151273, -0.490392640201615,
0.490392640201615, -0.415734806151273, 0.277785116509801, -0.097545161008064
};
static const float adst_8[64] = {
0.089131608307533, 0.175227946595735, 0.255357107325376, 0.326790388032145,
0.387095214016349, 0.434217976756762, 0.466553967085785, 0.483002021635509,
0.255357107325376, 0.434217976756762, 0.483002021635509, 0.387095214016349,
0.175227946595735, -0.089131608307533, -0.326790388032145, -0.466553967085785,
0.387095214016349, 0.466553967085785, 0.175227946595735, -0.255357107325376,
-0.483002021635509, -0.326790388032145, 0.089131608307533, 0.434217976756762,
0.466553967085785, 0.255357107325376, -0.326790388032145, -0.434217976756762,
0.089131608307533, 0.483002021635509, 0.175227946595735, -0.387095214016348,
0.483002021635509, -0.089131608307533, -0.466553967085785, 0.175227946595735,
0.434217976756762, -0.255357107325376, -0.387095214016348, 0.326790388032145,
0.434217976756762, -0.387095214016348, -0.089131608307533, 0.466553967085786,
-0.326790388032145, -0.175227946595735, 0.483002021635509, -0.255357107325375,
0.326790388032145, -0.483002021635509, 0.387095214016349, -0.089131608307534,
-0.255357107325377, 0.466553967085785, -0.434217976756762, 0.175227946595736,
0.175227946595735, -0.326790388032145, 0.434217976756762, -0.483002021635509,
0.466553967085785, -0.387095214016348, 0.255357107325376, -0.089131608307532
};
/* Converted the transforms to integers. */
static const int16_t dct_i4[16] = {
16384, 16384, 16384, 16384,
21407, 8867, -8867, -21407,
16384, -16384, -16384, 16384,
8867, -21407, 21407, -8867
};
static const int16_t adst_i4[16] = {
7472, 14042, 18919, 21513,
18919, 18919, 0, -18919,
21513, -7472, -18919, 14042,
14042, -21513, 18919, -7472
};
static const int16_t dct_i8[64] = {
11585, 11585, 11585, 11585,
11585, 11585, 11585, 11585,
16069, 13623, 9102, 3196,
-3196, -9102, -13623, -16069,
15137, 6270, -6270, -15137,
-15137, -6270, 6270, 15137,
13623, -3196, -16069, -9102,
9102, 16069, 3196, -13623,
11585, -11585, -11585, 11585,
11585, -11585, -11585, 11585,
9102, -16069, 3196, 13623,
-13623, -3196, 16069, -9102,
6270, -15137, 15137, -6270,
-6270, 15137, -15137, 6270,
3196, -9102, 13623, -16069,
16069, -13623, 9102, -3196
};
#if CONFIG_INTHT
static const int16_t adst_i8[64] = {
1606, 4756, 7723, 10394,
12665, 14449, 15678, 16305,
4756, 12665, 16305, 14449,
7723, -1606, -10394, -15678,
7723, 16305, 10394, -4756,
-15678, -12665, 1606, 14449,
10394, 14449, -4756, -16305,
-1606, 15678, 7723, -12665,
12665, 7723, -15678, -1606,
16305, -4756, -14449, 10394,
14449, -1606, -12665, 15678,
-4756, -10394, 16305, -7723,
15678, -10394, 1606, 7723,
-14449, 16305, -12665, 4756,
16305, -15678, 14449, -12665,
10394, -7723, 4756, -1606
};
#else
static const int16_t adst_i8[64] = {
2921, 5742, 8368, 10708,
12684, 14228, 15288, 15827,
8368, 14228, 15827, 12684,
5742, -2921, -10708, -15288,
12684, 15288, 5742, -8368,
-15827, -10708, 2921, 14228,
15288, 8368, -10708, -14228,
2921, 15827, 5742, -12684,
15827, -2921, -15288, 5742,
14228, -8368, -12684, 10708,
14228, -12684, -2921, 15288,
-10708, -5742, 15827, -8368,
10708, -15827, 12684, -2921,
-8368, 15288, -14228, 5742,
5742, -10708, 14228, -15827,
15288, -12684, 8368, -2921
};
#endif
static const float dct_16[256] = {
0.250000, 0.250000, 0.250000, 0.250000, 0.250000, 0.250000, 0.250000, 0.250000,
0.250000, 0.250000, 0.250000, 0.250000, 0.250000, 0.250000, 0.250000, 0.250000,
0.351851, 0.338330, 0.311806, 0.273300, 0.224292, 0.166664, 0.102631, 0.034654,
-0.034654, -0.102631, -0.166664, -0.224292, -0.273300, -0.311806, -0.338330, -0.351851,
0.346760, 0.293969, 0.196424, 0.068975, -0.068975, -0.196424, -0.293969, -0.346760,
-0.346760, -0.293969, -0.196424, -0.068975, 0.068975, 0.196424, 0.293969, 0.346760,
0.338330, 0.224292, 0.034654, -0.166664, -0.311806, -0.351851, -0.273300, -0.102631,
0.102631, 0.273300, 0.351851, 0.311806, 0.166664, -0.034654, -0.224292, -0.338330,
0.326641, 0.135299, -0.135299, -0.326641, -0.326641, -0.135299, 0.135299, 0.326641,
0.326641, 0.135299, -0.135299, -0.326641, -0.326641, -0.135299, 0.135299, 0.326641,
0.311806, 0.034654, -0.273300, -0.338330, -0.102631, 0.224292, 0.351851, 0.166664,
-0.166664, -0.351851, -0.224292, 0.102631, 0.338330, 0.273300, -0.034654, -0.311806,
0.293969, -0.068975, -0.346760, -0.196424, 0.196424, 0.346760, 0.068975, -0.293969,
-0.293969, 0.068975, 0.346760, 0.196424, -0.196424, -0.346760, -0.068975, 0.293969,
0.273300, -0.166664, -0.338330, 0.034654, 0.351851, 0.102631, -0.311806, -0.224292,
0.224292, 0.311806, -0.102631, -0.351851, -0.034654, 0.338330, 0.166664, -0.273300,
0.250000, -0.250000, -0.250000, 0.250000, 0.250000, -0.250000, -0.250000, 0.250000,
0.250000, -0.250000, -0.250000, 0.250000, 0.250000, -0.250000, -0.250000, 0.250000,
0.224292, -0.311806, -0.102631, 0.351851, -0.034654, -0.338330, 0.166664, 0.273300,
-0.273300, -0.166664, 0.338330, 0.034654, -0.351851, 0.102631, 0.311806, -0.224292,
0.196424, -0.346760, 0.068975, 0.293969, -0.293969, -0.068975, 0.346760, -0.196424,
-0.196424, 0.346760, -0.068975, -0.293969, 0.293969, 0.068975, -0.346760, 0.196424,
0.166664, -0.351851, 0.224292, 0.102631, -0.338330, 0.273300, 0.034654, -0.311806,
0.311806, -0.034654, -0.273300, 0.338330, -0.102631, -0.224292, 0.351851, -0.166664,
0.135299, -0.326641, 0.326641, -0.135299, -0.135299, 0.326641, -0.326641, 0.135299,
0.135299, -0.326641, 0.326641, -0.135299, -0.135299, 0.326641, -0.326641, 0.135299,
0.102631, -0.273300, 0.351851, -0.311806, 0.166664, 0.034654, -0.224292, 0.338330,
-0.338330, 0.224292, -0.034654, -0.166664, 0.311806, -0.351851, 0.273300, -0.102631,
0.068975, -0.196424, 0.293969, -0.346760, 0.346760, -0.293969, 0.196424, -0.068975,
-0.068975, 0.196424, -0.293969, 0.346760, -0.346760, 0.293969, -0.196424, 0.068975,
0.034654, -0.102631, 0.166664, -0.224292, 0.273300, -0.311806, 0.338330, -0.351851,
0.351851, -0.338330, 0.311806, -0.273300, 0.224292, -0.166664, 0.102631, -0.034654
};
static const float adst_16[256] = {
0.033094, 0.065889, 0.098087, 0.129396, 0.159534, 0.188227, 0.215215, 0.240255,
0.263118, 0.283599, 0.301511, 0.316693, 0.329007, 0.338341, 0.344612, 0.347761,
0.098087, 0.188227, 0.263118, 0.316693, 0.344612, 0.344612, 0.316693, 0.263118,
0.188227, 0.098087, 0.000000, -0.098087, -0.188227, -0.263118, -0.316693, -0.344612,
0.159534, 0.283599, 0.344612, 0.329007, 0.240255, 0.098087, -0.065889, -0.215215,
-0.316693, -0.347761, -0.301511, -0.188227, -0.033094, 0.129396, 0.263118, 0.338341,
0.215215, 0.338341, 0.316693, 0.159534, -0.065889, -0.263118, -0.347761, -0.283599,
-0.098087, 0.129396, 0.301511, 0.344612, 0.240255, 0.033094, -0.188227, -0.329007,
0.263118, 0.344612, 0.188227, -0.098087, -0.316693, -0.316693, -0.098087, 0.188227,
0.344612, 0.263118, 0.000000, -0.263118, -0.344612, -0.188227, 0.098087, 0.316693,
0.301511, 0.301511, 0.000000, -0.301511, -0.301511, -0.000000, 0.301511, 0.301511,
0.000000, -0.301511, -0.301511, -0.000000, 0.301511, 0.301511, 0.000000, -0.301511,
0.329007, 0.215215, -0.188227, -0.338341, -0.033094, 0.316693, 0.240255, -0.159534,
-0.344612, -0.065889, 0.301511, 0.263118, -0.129396, -0.347761, -0.098087, 0.283599,
0.344612, 0.098087, -0.316693, -0.188227, 0.263118, 0.263118, -0.188227, -0.316693,
0.098087, 0.344612, 0.000000, -0.344612, -0.098087, 0.316693, 0.188227, -0.263118,
0.347761, -0.033094, -0.344612, 0.065889, 0.338341, -0.098087, -0.329007, 0.129396,
0.316693, -0.159534, -0.301511, 0.188227, 0.283599, -0.215215, -0.263118, 0.240255,
0.338341, -0.159534, -0.263118, 0.283599, 0.129396, -0.344612, 0.033094, 0.329007,
-0.188227, -0.240255, 0.301511, 0.098087, -0.347761, 0.065889, 0.316693, -0.215215,
0.316693, -0.263118, -0.098087, 0.344612, -0.188227, -0.188227, 0.344612, -0.098087,
-0.263118, 0.316693, 0.000000, -0.316693, 0.263118, 0.098087, -0.344612, 0.188227,
0.283599, -0.329007, 0.098087, 0.215215, -0.347761, 0.188227, 0.129396, -0.338341,
0.263118, 0.033094, -0.301511, 0.316693, -0.065889, -0.240255, 0.344612, -0.159534,
0.240255, -0.347761, 0.263118, -0.033094, -0.215215, 0.344612, -0.283599, 0.065889,
0.188227, -0.338341, 0.301511, -0.098087, -0.159534, 0.329007, -0.316693, 0.129396,
0.188227, -0.316693, 0.344612, -0.263118, 0.098087, 0.098087, -0.263118, 0.344612,
-0.316693, 0.188227, 0.000000, -0.188227, 0.316693, -0.344612, 0.263118, -0.098087,
0.129396, -0.240255, 0.316693, -0.347761, 0.329007, -0.263118, 0.159534, -0.033094,
-0.098087, 0.215215, -0.301511, 0.344612, -0.338341, 0.283599, -0.188227, 0.065889,
0.065889, -0.129396, 0.188227, -0.240255, 0.283599, -0.316693, 0.338341, -0.347761,
0.344612, -0.329007, 0.301511, -0.263118, 0.215215, -0.159534, 0.098087, -0.033094
};
/* Converted the transforms to integers. */
static const int16_t dct_i16[256] = {
8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192,
8192, 8192, 8192, 8192, 8192, 8192, 8192, 8192,
11529, 11086, 10217, 8955, 7350, 5461, 3363, 1136,
-1136, -3363, -5461, -7350, -8955, -10217, -11086, -11529,
11363, 9633, 6436, 2260, -2260, -6436, -9633, -11363,
-11363, -9633, -6436, -2260, 2260, 6436, 9633, 11363,
11086, 7350, 1136, -5461, -10217, -11529, -8955, -3363,
3363, 8955, 11529, 10217, 5461, -1136, -7350, -11086,
10703, 4433, -4433, -10703, -10703, -4433, 4433, 10703,
10703, 4433, -4433, -10703, -10703, -4433, 4433, 10703,
10217, 1136, -8955, -11086, -3363, 7350, 11529, 5461,
-5461, -11529, -7350, 3363, 11086, 8955, -1136, -10217,
9633, -2260, -11363, -6436, 6436, 11363, 2260, -9633,
-9633, 2260, 11363, 6436, -6436, -11363, -2260, 9633,
8955, -5461, -11086, 1136, 11529, 3363, -10217, -7350,
7350, 10217, -3363, -11529, -1136, 11086, 5461, -8955,
8192, -8192, -8192, 8192, 8192, -8192, -8192, 8192,
8192, -8192, -8192, 8192, 8192, -8192, -8192, 8192,
7350, -10217, -3363, 11529, -1136, -11086, 5461, 8955,
-8955, -5461, 11086, 1136, -11529, 3363, 10217, -7350,
6436, -11363, 2260, 9633, -9633, -2260, 11363, -6436,
-6436, 11363, -2260, -9633, 9633, 2260, -11363, 6436,
5461, -11529, 7350, 3363, -11086, 8955, 1136, -10217,
10217, -1136, -8955, 11086, -3363, -7350, 11529, -5461,
4433, -10703, 10703, -4433, -4433, 10703, -10703, 4433,
4433, -10703, 10703, -4433, -4433, 10703, -10703, 4433,
3363, -8955, 11529, -10217, 5461, 1136, -7350, 11086,
-11086, 7350, -1136, -5461, 10217, -11529, 8955, -3363,
2260, -6436, 9633, -11363, 11363, -9633, 6436, -2260,
-2260, 6436, -9633, 11363, -11363, 9633, -6436, 2260,
1136, -3363, 5461, -7350, 8955, -10217, 11086, -11529,
11529, -11086, 10217, -8955, 7350, -5461, 3363, -1136
};
#if CONFIG_INTHT
static const int16_t adst_i16[256] = {
568, 1700, 2815, 3903, 4953, 5956, 6901, 7780,
8584, 9305, 9937, 10473, 10908, 11238, 11459, 11571,
1700, 4953, 7780, 9937, 11238, 11571, 10908, 9305,
6901, 3903, 568, -2815, -5956, -8584, -10473, -11459,
2815, 7780, 10908, 11459, 9305, 4953, -568, -5956,
-9937, -11571, -10473, -6901, -1700, 3903, 8584, 11238,
3903, 9937, 11459, 7780, 568, -6901, -11238, -10473,
-4953, 2815, 9305, 11571, 8584, 1700, -5956, -10908,
4953, 11238, 9305, 568, -8584, -11459, -5956, 3903,
10908, 9937, 1700, -7780, -11571, -6901, 2815, 10473,
5956, 11571, 4953, -6901, -11459, -3903, 7780, 11238,
2815, -8584, -10908, -1700, 9305, 10473, 568, -9937,
6901, 10908, -568, -11238, -5956, 7780, 10473, -1700,
-11459, -4953, 8584, 9937, -2815, -11571, -3903, 9305,
7780, 9305, -5956, -10473, 3903, 11238, -1700, -11571,
-568, 11459, 2815, -10908, -4953, 9937, 6901, -8584,
8584, 6901, -9937, -4953, 10908, 2815, -11459, -568,
11571, -1700, -11238, 3903, 10473, -5956, -9305, 7780,
9305, 3903, -11571, 2815, 9937, -8584, -4953, 11459,
-1700, -10473, 7780, 5956, -11238, 568, 10908, -6901,
9937, 568, -10473, 9305, 1700, -10908, 8584, 2815,
-11238, 7780, 3903, -11459, 6901, 4953, -11571, 5956,
10473, -2815, -6901, 11571, -7780, -1700, 9937, -10908,
3903, 5956, -11459, 8584, 568, -9305, 11238, -4953,
10908, -5956, -1700, 8584, -11571, 9305, -2815, -4953,
10473, -11238, 6901, 568, -7780, 11459, -9937, 3903,
11238, -8584, 3903, 1700, -6901, 10473, -11571, 9937,
-5956, 568, 4953, -9305, 11459, -10908, 7780, -2815,
11459, -10473, 8584, -5956, 2815, 568, -3903, 6901,
-9305, 10908, -11571, 11238, -9937, 7780, -4953, 1700,
11571, -11459, 11238, -10908, 10473, -9937, 9305, -8584,
7780, -6901, 5956, -4953, 3903, -2815, 1700, -568
};
#else
static const int16_t adst_i16[256] = {
1084, 2159, 3214, 4240, 5228, 6168, 7052, 7873,
8622, 9293, 9880, 10377, 10781, 11087, 11292, 11395,
3214, 6168, 8622, 10377, 11292, 11292, 10377, 8622,
6168, 3214, 0, -3214, -6168, -8622, -10377, -11292,
5228, 9293, 11292, 10781, 7873, 3214, -2159, -7052,
-10377, -11395, -9880, -6168, -1084, 4240, 8622, 11087,
7052, 11087, 10377, 5228, -2159, -8622, -11395, -9293,
-3214, 4240, 9880, 11292, 7873, 1084, -6168, -10781,
8622, 11292, 6168, -3214, -10377, -10377, -3214, 6168,
11292, 8622, 0, -8622, -11292, -6168, 3214, 10377,
9880, 9880, 0, -9880, -9880, 0, 9880, 9880,
0, -9880, -9880, 0, 9880, 9880, 0, -9880,
10781, 7052, -6168, -11087, -1084, 10377, 7873, -5228,
-11292, -2159, 9880, 8622, -4240, -11395, -3214, 9293,
11292, 3214, -10377, -6168, 8622, 8622, -6168, -10377,
3214, 11292, 0, -11292, -3214, 10377, 6168, -8622,
11395, -1084, -11292, 2159, 11087, -3214, -10781, 4240,
10377, -5228, -9880, 6168, 9293, -7052, -8622, 7873,
11087, -5228, -8622, 9293, 4240, -11292, 1084, 10781,
-6168, -7873, 9880, 3214, -11395, 2159, 10377, -7052,
10377, -8622, -3214, 11292, -6168, -6168, 11292, -3214,
-8622, 10377, 0, -10377, 8622, 3214, -11292, 6168,
9293, -10781, 3214, 7052, -11395, 6168, 4240, -11087,
8622, 1084, -9880, 10377, -2159, -7873, 11292, -5228,
7873, -11395, 8622, -1084, -7052, 11292, -9293, 2159,
6168, -11087, 9880, -3214, -5228, 10781, -10377, 4240,
6168, -10377, 11292, -8622, 3214, 3214, -8622, 11292,
-10377, 6168, 0, -6168, 10377, -11292, 8622, -3214,
4240, -7873, 10377, -11395, 10781, -8622, 5228, -1084,
-3214, 7052, -9880, 11292, -11087, 9293, -6168, 2159,
2159, -4240, 6168, -7873, 9293, -10377, 11087, -11395,
11292, -10781, 9880, -8622, 7052, -5228, 3214, -1084
};
#endif
/* For test */
#define TEST_INT 1
#if TEST_INT
#define vp9_fht_int_c vp9_fht_c
#else
#define vp9_fht_float_c vp9_fht_c
#endif
void vp9_fht_float_c(const int16_t *input, int pitch, int16_t *output,
TX_TYPE tx_type, int tx_dim) {
vp9_clear_system_state(); // Make it simd safe : __asm emms;
{
int i, j, k;
float bufa[256], bufb[256]; // buffers are for floating-point test purpose
// the implementation could be simplified in
// conjunction with integer transform
const int16_t *ip = input;
int16_t *op = output;
float *pfa = &bufa[0];
float *pfb = &bufb[0];
// pointers to vertical and horizontal transforms
const float *ptv, *pth;
assert(tx_type != DCT_DCT);
// load and convert residual array into floating-point
for (j = 0; j < tx_dim; j++) {
for (i = 0; i < tx_dim; i++) {
pfa[i] = (float)ip[i];
}
pfa += tx_dim;
ip += pitch / 2;
}
// vertical transformation
pfa = &bufa[0];
pfb = &bufb[0];
switch (tx_type) {
case ADST_ADST :
case ADST_DCT :
ptv = (tx_dim == 4) ? &adst_4[0] :
((tx_dim == 8) ? &adst_8[0] : &adst_16[0]);
break;
default :
ptv = (tx_dim == 4) ? &dct_4[0] :
((tx_dim == 8) ? &dct_8[0] : &dct_16[0]);
break;
}
for (j = 0; j < tx_dim; j++) {
for (i = 0; i < tx_dim; i++) {
pfb[i] = 0;
for (k = 0; k < tx_dim; k++) {
pfb[i] += ptv[k] * pfa[(k * tx_dim)];
}
pfa += 1;
}
pfb += tx_dim;
ptv += tx_dim;
pfa = &bufa[0];
}
// horizontal transformation
pfa = &bufa[0];
pfb = &bufb[0];
switch (tx_type) {
case ADST_ADST :
case DCT_ADST :
pth = (tx_dim == 4) ? &adst_4[0] :
((tx_dim == 8) ? &adst_8[0] : &adst_16[0]);
break;
default :
pth = (tx_dim == 4) ? &dct_4[0] :
((tx_dim == 8) ? &dct_8[0] : &dct_16[0]);
break;
}
for (j = 0; j < tx_dim; j++) {
for (i = 0; i < tx_dim; i++) {
pfa[i] = 0;
for (k = 0; k < tx_dim; k++) {
pfa[i] += pfb[k] * pth[k];
}
pth += tx_dim;
}
pfa += tx_dim;
pfb += tx_dim;
// pth -= tx_dim * tx_dim;
switch (tx_type) {
case ADST_ADST :
case DCT_ADST :
pth = (tx_dim == 4) ? &adst_4[0] :
((tx_dim == 8) ? &adst_8[0] : &adst_16[0]);
break;
default :
pth = (tx_dim == 4) ? &dct_4[0] :
((tx_dim == 8) ? &dct_8[0] : &dct_16[0]);
break;
}
}
// convert to short integer format and load BLOCKD buffer
op = output;
pfa = &bufa[0];
for (j = 0; j < tx_dim; j++) {
for (i = 0; i < tx_dim; i++) {
op[i] = (pfa[i] > 0 ) ? (int16_t)( 8 * pfa[i] + 0.49) :
-(int16_t)(- 8 * pfa[i] + 0.49);
}
op += tx_dim;
pfa += tx_dim;
}
}
vp9_clear_system_state(); // Make it simd safe : __asm emms;
}
/* Converted the transforms to integer form. */
#define VERTICAL_SHIFT 11
#define VERTICAL_ROUNDING ((1 << (VERTICAL_SHIFT - 1)) - 1)
#define HORIZONTAL_SHIFT 16
#define HORIZONTAL_ROUNDING ((1 << (HORIZONTAL_SHIFT - 1)) - 1)
void vp9_fht_int_c(const int16_t *input, int pitch, int16_t *output,
TX_TYPE tx_type, int tx_dim) {
int i, j, k;
int16_t imbuf[256];
const int16_t *ip = input;
int16_t *op = output;
int16_t *im = &imbuf[0];
/* pointers to vertical and horizontal transforms. */
const int16_t *ptv = NULL, *pth = NULL;
switch (tx_type) {
case ADST_ADST :
ptv = pth = (tx_dim == 4) ? &adst_i4[0]
: ((tx_dim == 8) ? &adst_i8[0]
: &adst_i16[0]);
break;
case ADST_DCT :
ptv = (tx_dim == 4) ? &adst_i4[0]
: ((tx_dim == 8) ? &adst_i8[0] : &adst_i16[0]);
pth = (tx_dim == 4) ? &dct_i4[0]
: ((tx_dim == 8) ? &dct_i8[0] : &dct_i16[0]);
break;
case DCT_ADST :
ptv = (tx_dim == 4) ? &dct_i4[0]
: ((tx_dim == 8) ? &dct_i8[0] : &dct_i16[0]);
pth = (tx_dim == 4) ? &adst_i4[0]
: ((tx_dim == 8) ? &adst_i8[0] : &adst_i16[0]);
break;
case DCT_DCT :
ptv = pth = (tx_dim == 4) ? &dct_i4[0]
: ((tx_dim == 8) ? &dct_i8[0] : &dct_i16[0]);
break;
default:
assert(0);
break;
}
/* vertical transformation */
for (j = 0; j < tx_dim; j++) {
for (i = 0; i < tx_dim; i++) {
int temp = 0;
for (k = 0; k < tx_dim; k++) {
temp += ptv[k] * ip[(k * (pitch >> 1))];
}
im[i] = (int16_t)((temp + VERTICAL_ROUNDING) >> VERTICAL_SHIFT);
ip++;
}
im += tx_dim; // 16
ptv += tx_dim;
ip = input;
}
/* horizontal transformation */
im = &imbuf[0];
for (j = 0; j < tx_dim; j++) {
const int16_t *pthc = pth;
for (i = 0; i < tx_dim; i++) {
int temp = 0;
for (k = 0; k < tx_dim; k++) {
temp += im[k] * pthc[k];
}
op[i] = (int16_t)((temp + HORIZONTAL_ROUNDING) >> HORIZONTAL_SHIFT);
pthc += tx_dim;
}
im += tx_dim; // 16
op += tx_dim;
}
}
static void fdct4_1d(int16_t *input, int16_t *output) {
int16_t step[4];
int temp1, temp2;
@ -575,7 +61,6 @@ void vp9_short_fdct4x4_c(short *input, short *output, int pitch) {
}
}
#if CONFIG_INTHT4X4
static void fadst4_1d(int16_t *input, int16_t *output) {
int x0, x1, x2, x3;
int s0, s1, s2, s3, s4, s5, s6, s7;
@ -669,7 +154,6 @@ void vp9_short_fht4x4_c(int16_t *input, int16_t *output,
output[j + i * 4] = (temp_out[j] + 1) >> 2;
}
}
#endif
void vp9_short_fdct8x4_c(short *input, short *output, int pitch)
{
@ -748,7 +232,6 @@ void vp9_short_fdct8x8_c(int16_t *input, int16_t *output, int pitch) {
}
}
#if CONFIG_INTHT
static void fadst8_1d(int16_t *input, int16_t *output) {
int x0, x1, x2, x3, x4, x5, x6, x7;
int s0, s1, s2, s3, s4, s5, s6, s7;
@ -871,7 +354,6 @@ void vp9_short_fht8x8_c(int16_t *input, int16_t *output,
output[j + i * 8] = temp_out[j] >> 1;
}
}
#endif
void vp9_short_walsh4x4_x8_c(short *input, short *output, int pitch) {
int i;
@ -1048,7 +530,6 @@ void vp9_short_fdct16x16_c(int16_t *input, int16_t *out, int pitch) {
}
}
#if CONFIG_INTHT16X16
void fadst16_1d(int16_t *input, int16_t *output) {
int x0, x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13, x14, x15;
int s0, s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, s13, s14, s15;
@ -1262,7 +743,6 @@ void vp9_short_fht16x16_c(int16_t *input, int16_t *output,
output[j + i * 16] = temp_out[j];
}
}
#endif
#define TEST_INT_32x32_DCT 1

View File

@ -54,17 +54,9 @@ void vp9_encode_intra4x4block(MACROBLOCK *x, int ib) {
tx_type = get_tx_type_4x4(&x->e_mbd, b);
if (tx_type != DCT_DCT) {
#if CONFIG_INTHT4X4
vp9_short_fht4x4(be->src_diff, be->coeff, 32, tx_type);
#else
vp9_fht(be->src_diff, 32, be->coeff, tx_type, 4);
#endif
vp9_ht_quantize_b_4x4(be, b, tx_type);
#if CONFIG_INTHT4X4
vp9_short_iht4x4(b->dqcoeff, b->diff, 32, tx_type);
#else
vp9_ihtllm(b->dqcoeff, b->diff, 32, tx_type, 4, b->eob);
#endif
} else {
x->fwd_txm4x4(be->src_diff, be->coeff, 32);
x->quantize_b_4x4(be, b) ;
@ -157,21 +149,10 @@ void vp9_encode_intra8x8(MACROBLOCK *x, int ib) {
tx_type = get_tx_type_8x8(xd, &xd->block[ib]);
if (tx_type != DCT_DCT) {
#if CONFIG_INTHT
vp9_short_fht8x8(be->src_diff, (x->block + idx)->coeff, 32, tx_type);
#else
vp9_fht(be->src_diff, 32, (x->block + idx)->coeff,
tx_type, 8);
#endif
x->quantize_b_8x8(x->block + idx, xd->block + idx);
#if CONFIG_INTHT
vp9_short_iht8x8(xd->block[idx].dqcoeff, xd->block[ib].diff,
32, tx_type);
#else
vp9_ihtllm(xd->block[idx].dqcoeff, xd->block[ib].diff, 32,
tx_type, 8, xd->block[idx].eob);
#endif
} else {
x->fwd_txm8x8(be->src_diff, (x->block + idx)->coeff, 32);
x->quantize_b_8x8(x->block + idx, xd->block + idx);
@ -183,17 +164,9 @@ void vp9_encode_intra8x8(MACROBLOCK *x, int ib) {
be = &x->block[ib + iblock[i]];
tx_type = get_tx_type_4x4(xd, b);
if (tx_type != DCT_DCT) {
#if CONFIG_INTHT4X4
vp9_short_fht4x4(be->src_diff, be->coeff, 32, tx_type);
#else
vp9_fht_c(be->src_diff, 32, be->coeff, tx_type, 4);
#endif
vp9_ht_quantize_b_4x4(be, b, tx_type);
#if CONFIG_INTHT4X4
vp9_short_iht4x4(b->dqcoeff, b->diff, 32, tx_type);
#else
vp9_ihtllm(b->dqcoeff, b->diff, 32, tx_type, 4, b->eob);
#endif
} else if (!(i & 1) && get_tx_type_4x4(xd, b + 1) == DCT_DCT) {
x->fwd_txm8x4(be->src_diff, be->coeff, 32);
x->quantize_b_4x4_pair(be, be + 1, b, b + 1);

View File

@ -174,11 +174,7 @@ void vp9_transform_mby_4x4(MACROBLOCK *x) {
BLOCK *b = &x->block[i];
TX_TYPE tx_type = get_tx_type_4x4(xd, &xd->block[i]);
if (tx_type != DCT_DCT) {
#if CONFIG_INTHT4X4
vp9_short_fht4x4(b->src_diff, b->coeff, 32, tx_type);
#else
vp9_fht_c(b->src_diff, 32, b->coeff, tx_type, 4);
#endif
} else if (!(i & 1) && get_tx_type_4x4(xd, &xd->block[i + 1]) == DCT_DCT) {
x->fwd_txm8x4(&x->block[i].src_diff[0],
&x->block[i].coeff[0], 32);
@ -213,11 +209,7 @@ void vp9_transform_mby_8x8(MACROBLOCK *x) {
BLOCK *b = &x->block[i];
tx_type = get_tx_type_8x8(xd, &xd->block[i]);
if (tx_type != DCT_DCT) {
#if CONFIG_INTHT
vp9_short_fht8x8(b->src_diff, b->coeff, 32, tx_type);
#else
vp9_fht_c(b->src_diff, 32, b->coeff, tx_type, 8);
#endif
} else {
x->fwd_txm8x8(&x->block[i].src_diff[0],
&x->block[i].coeff[0], 32);
@ -227,11 +219,7 @@ void vp9_transform_mby_8x8(MACROBLOCK *x) {
BLOCK *b = &x->block[i];
tx_type = get_tx_type_8x8(xd, &xd->block[i]);
if (tx_type != DCT_DCT) {
#if CONFIG_INTHT
vp9_short_fht8x8(b->src_diff, (b + 2)->coeff, 32, tx_type);
#else
vp9_fht_c(b->src_diff, 32, (b + 2)->coeff, tx_type, 8);
#endif
} else {
x->fwd_txm8x8(&x->block[i].src_diff[0],
&x->block[i + 2].coeff[0], 32);
@ -259,11 +247,7 @@ void vp9_transform_mby_16x16(MACROBLOCK *x) {
TX_TYPE tx_type = get_tx_type_16x16(xd, &xd->block[0]);
vp9_clear_system_state();
if (tx_type != DCT_DCT) {
#if CONFIG_INTHT16X16
vp9_short_fht16x16(b->src_diff, b->coeff, 32, tx_type);
#else
vp9_fht_c(b->src_diff, 32, b->coeff, tx_type, 16);
#endif
} else {
x->fwd_txm16x16(&x->block[0].src_diff[0],
&x->block[0].coeff[0], 32);

View File

@ -1013,11 +1013,7 @@ static int64_t rd_pick_intra4x4block(VP9_COMP *cpi, MACROBLOCK *x, BLOCK *be,
b->bmi.as_mode.first = mode;
tx_type = get_tx_type_4x4(xd, b);
if (tx_type != DCT_DCT) {
#if CONFIG_INTHT4X4
vp9_short_fht4x4(be->src_diff, be->coeff, 32, tx_type);
#else
vp9_fht(be->src_diff, 32, be->coeff, tx_type, 4);
#endif
vp9_ht_quantize_b_4x4(be, b, tx_type);
} else {
x->fwd_txm4x4(be->src_diff, be->coeff, 32);
@ -1050,11 +1046,7 @@ static int64_t rd_pick_intra4x4block(VP9_COMP *cpi, MACROBLOCK *x, BLOCK *be,
// inverse transform
if (best_tx_type != DCT_DCT)
#if CONFIG_INTHT4X4
vp9_short_iht4x4(best_dqcoeff, b->diff, 32, best_tx_type);
#else
vp9_ihtllm(best_dqcoeff, b->diff, 32, best_tx_type, 4, b->eob);
#endif
else
xd->inv_txm4x4(best_dqcoeff, b->diff, 32);
@ -1317,11 +1309,7 @@ static int64_t rd_pick_intra8x8block(VP9_COMP *cpi, MACROBLOCK *x, int ib,
if (xd->mode_info_context->mbmi.txfm_size == TX_8X8) {
TX_TYPE tx_type = get_tx_type_8x8(xd, b);
if (tx_type != DCT_DCT)
#if CONFIG_INTHT
vp9_short_fht8x8(be->src_diff, (x->block + idx)->coeff, 32, tx_type);
#else
vp9_fht(be->src_diff, 32, (x->block + idx)->coeff, tx_type, 8);
#endif
else
x->fwd_txm8x8(be->src_diff, (x->block + idx)->coeff, 32);
x->quantize_b_8x8(x->block + idx, xd->block + idx);
@ -1354,11 +1342,7 @@ static int64_t rd_pick_intra8x8block(VP9_COMP *cpi, MACROBLOCK *x, int ib,
be = &x->block[ib + iblock[i]];
tx_type = get_tx_type_4x4(xd, b);
if (tx_type != DCT_DCT) {
#if CONFIG_INTHT4X4
vp9_short_fht4x4(be->src_diff, be->coeff, 32, tx_type);
#else
vp9_fht_c(be->src_diff, 32, be->coeff, tx_type, 4);
#endif
vp9_ht_quantize_b_4x4(be, b, tx_type);
} else if (!(i & 1) && get_tx_type_4x4(xd, b + 1) == DCT_DCT) {
x->fwd_txm8x4(be->src_diff, be->coeff, 32);