Commit 77a3becf authored by Jingning Han's avatar Jingning Han
Browse files

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
parent 499fe05d
......@@ -246,9 +246,6 @@ EXPERIMENT_LIST="
cnvcontext
enable_6tap
abovesprefmv
intht
intht4x4
intht16x16
"
CONFIG_LIST="
external_build
......
......@@ -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;
......
......@@ -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];
......
......@@ -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);
......
......@@ -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
......
......@@ -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);
......
This diff is collapsed.
......@@ -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);
......
......@@ -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