From: Yunqing Wang Date: Thu, 18 Oct 2012 23:31:59 +0000 (-0700) Subject: Convert the transforms to integer forms. X-Git-Tag: v1.3.0~1217^2~144 X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=8a9e4e8a618016b45eba148f167def81d80db103;p=libvpx Convert the transforms to integer forms. Converted the forward and inverse transforms to integer forms. Modify #define TEST_INT 1/0 in the code to call integer/float version of transforms. The tests showed that average OVERALL PSNR loss was less than 0.1%. Change-Id: I1dfa4eeab6412597e3b970ce299cf0e116a917e6 --- diff --git a/vp8/common/idct.h b/vp8/common/idct.h index ae33df668..0496ca2c7 100644 --- a/vp8/common/idct.h +++ b/vp8/common/idct.h @@ -110,7 +110,7 @@ extern prototype_second_order(vp8_short_inv_walsh4x4_1_lossless_c); #endif #include "vp8/common/blockd.h" -void vp8_ihtllm_c(short *input, short *output, int pitch, +void vp8_ihtllm_c(const int16_t *input, int16_t *output, int pitch, TX_TYPE tx_type, int tx_dim); typedef prototype_idct((*vp8_idct_fn_t)); diff --git a/vp8/common/idctllm.c b/vp8/common/idctllm.c index c7369b2e2..a0313bd2a 100644 --- a/vp8/common/idctllm.c +++ b/vp8/common/idctllm.c @@ -28,6 +28,7 @@ #include "vp8/common/blockd.h" +#include #include static const int cospi8sqrt2minus1 = 20091; @@ -88,6 +89,58 @@ float iadst_8[64] = { 0.326790388032145, -0.255357107325375, 0.175227946595736, -0.089131608307532 }; +const int16_t idct_i4[16] = { + 8192, 10703, 8192, 4433, + 8192, 4433, -8192, -10703, + 8192, -4433, -8192, 10703, + 8192, -10703, 8192, -4433 +}; + +const int16_t iadst_i4[16] = { + 3736, 9459, 10757, 7021, + 7021, 9459, -3736, -10757, + 9459, 0, -9459, 9459, + 10757, -9459, 7021, -3736 +}; + +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 +}; + +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 +}; + float idct_16[256] = { 0.250000, 0.351851, 0.346760, 0.338330, 0.326641, 0.311806, 0.293969, 0.273300, 0.250000, 0.224292, 0.196424, 0.166664, 0.135299, 0.102631, 0.068975, 0.034654, @@ -158,22 +211,94 @@ float iadst_16[256] = { 0.240255, -0.215215, 0.188227, -0.159534, 0.129396, -0.098087, 0.065889, -0.033094 }; -void vp8_ihtllm_c(short *input, short *output, int pitch, - TX_TYPE tx_type, int tx_dim) { +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 +}; - vp8_clear_system_state(); // Make it simd safe : __asm emms; +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 +}; + +/* For test */ +#define TEST_INT 1 +#if TEST_INT +#define vp8_ihtllm_int_c vp8_ihtllm_c +#else +#define vp8_ihtllm_float_c vp8_ihtllm_c +#endif + +void vp8_ihtllm_float_c(const int16_t *input, int16_t *output, int pitch, + TX_TYPE tx_type, int tx_dim) { + vp8_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 - - // further notice, since we are thinking to use - // one function for both 4x4 and 8x8 transforms - // the temporary buffers are simply initialized - // with 64. - short *ip = input; - short *op = output; + 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; int shortpitch = pitch >> 1; float *pfa = &bufa[0]; @@ -272,8 +397,8 @@ void vp8_ihtllm_c(short *input, short *output, int pitch, for(j = 0; j < tx_dim; j++) { for(i = 0; i < tx_dim; i++) { - op[i] = (pfa[i] > 0 ) ? (short)( pfa[i] / 8 + 0.49) : - -(short)( - pfa[i] / 8 + 0.49); + op[i] = (pfa[i] > 0 ) ? (int16_t)( pfa[i] / 8 + 0.49) : + -(int16_t)( - pfa[i] / 8 + 0.49); } op += shortpitch; @@ -283,6 +408,90 @@ void vp8_ihtllm_c(short *input, short *output, int pitch, vp8_clear_system_state(); // Make it simd safe : __asm emms; } +/* Converted the transforms to integer form. */ +#define VERTICAL_SHIFT 14 //16 +#define VERTICAL_ROUNDING ((1 << (VERTICAL_SHIFT - 1)) - 1) +#define HORIZONTAL_SHIFT 17 //15 +#define HORIZONTAL_ROUNDING ((1 << (HORIZONTAL_SHIFT - 1)) - 1) +void vp8_ihtllm_int_c(const int16_t *input, int16_t *output, int pitch, + 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; + 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; + } + + /* 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 * tx_dim)]; + } + + 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 += shortpitch; + } +} + void vp8_short_idct4x4llm_c(short *input, short *output, int pitch) { int i; int a1, b1, c1, d1; diff --git a/vp8/encoder/dct.c b/vp8/encoder/dct.c index 0983b1c0a..edb667425 100644 --- a/vp8/encoder/dct.c +++ b/vp8/encoder/dct.c @@ -9,6 +9,7 @@ */ +#include #include #include "vpx_ports/config.h" #include "vp8/common/idct.h" @@ -70,6 +71,59 @@ float adst_8[64] = { 0.466553967085785, -0.387095214016348, 0.255357107325376, -0.089131608307532 }; +/* Converted the transforms to integers. */ +const int16_t dct_i4[16] = { + 16384, 16384, 16384, 16384, + 21407, 8867, -8867, -21407, + 16384, -16384, -16384, 16384, + 8867, -21407, 21407, -8867 +}; + +const int16_t adst_i4[16] = { + 7472, 14042, 18919, 21513, + 18919, 18919, 0, -18919, + 21513, -7472, -18919, 14042, + 14042, -21513, 18919, -7472 +}; + +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 +}; + +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 +}; + 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, @@ -140,6 +194,77 @@ float adst_16[256] = { 0.344612, -0.329007, 0.301511, -0.263118, 0.215215, -0.159534, 0.098087, -0.033094 }; +/* Converted the transforms to integers. */ +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 +}; + +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 +}; + static const int xC1S7 = 16069; static const int xC2S6 = 15137; static const int xC3S5 = 13623; @@ -395,17 +520,24 @@ void vp8_short_fhaar2x2_c(short *input, short *output, int pitch) { // pitch = 8 } -void vp8_fht_c(short *input, short *output, int pitch, - TX_TYPE tx_type, int tx_dim) { +/* For test */ +#define TEST_INT 1 +#if TEST_INT +#define vp8_fht_int_c vp8_fht_c +#else +#define vp8_fht_float_c vp8_fht_c +#endif - vp8_clear_system_state(); // Make it simd safe : __asm emms; +void vp8_fht_float_c(const int16_t *input, int pitch, int16_t *output, + TX_TYPE tx_type, int tx_dim) { + vp8_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 - short *ip = input; - short *op = output; + 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]; @@ -415,8 +547,8 @@ void vp8_fht_c(short *input, short *output, int pitch, 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++) { + for (j = 0; j < tx_dim; j++) { + for (i = 0; i < tx_dim; i++) { pfa[i] = (float)ip[i]; } pfa += tx_dim; @@ -427,7 +559,7 @@ void vp8_fht_c(short *input, short *output, int pitch, pfa = &bufa[0]; pfb = &bufb[0]; - switch(tx_type) { + switch (tx_type) { case ADST_ADST : case ADST_DCT : ptv = (tx_dim == 4) ? &adst_4[0] : @@ -440,10 +572,10 @@ void vp8_fht_c(short *input, short *output, int pitch, break; } - for(j = 0; j < tx_dim; j++) { - for(i = 0; i < tx_dim; i++) { + for (j = 0; j < tx_dim; j++) { + for (i = 0; i < tx_dim; i++) { pfb[i] = 0; - for(k = 0; k < tx_dim; k++) { + for (k = 0; k < tx_dim; k++) { pfb[i] += ptv[k] * pfa[(k * tx_dim)]; } pfa += 1; @@ -457,7 +589,7 @@ void vp8_fht_c(short *input, short *output, int pitch, pfa = &bufa[0]; pfb = &bufb[0]; - switch(tx_type) { + switch (tx_type) { case ADST_ADST : case DCT_ADST : pth = (tx_dim == 4) ? &adst_4[0] : @@ -470,10 +602,10 @@ void vp8_fht_c(short *input, short *output, int pitch, break; } - for(j = 0; j < tx_dim; j++) { - for(i = 0; i < tx_dim; i++) { + for (j = 0; j < tx_dim; j++) { + for (i = 0; i < tx_dim; i++) { pfa[i] = 0; - for(k = 0; k < tx_dim; k++) { + for (k = 0; k < tx_dim; k++) { pfa[i] += pfb[k] * pth[k]; } pth += tx_dim; @@ -483,7 +615,7 @@ void vp8_fht_c(short *input, short *output, int pitch, pfb += tx_dim; // pth -= tx_dim * tx_dim; - switch(tx_type) { + switch (tx_type) { case ADST_ADST : case DCT_ADST : pth = (tx_dim == 4) ? &adst_4[0] : @@ -498,19 +630,102 @@ void vp8_fht_c(short *input, short *output, int pitch, } // convert to short integer format and load BLOCKD buffer - op = output ; - pfa = &bufa[0] ; + op = output; + pfa = &bufa[0]; - for(j = 0; j < tx_dim; j++) { - for(i = 0; i < tx_dim; i++) { - op[i] = (pfa[i] > 0 ) ? (short)( 8 * pfa[i] + 0.49) : - -(short)(- 8 * pfa[i] + 0.49); + 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; } } - vp8_clear_system_state(); // Make it simd safe : __asm emms; + vp8_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 vp8_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; + } } void vp8_short_fdct4x4_c(short *input, short *output, int pitch) { diff --git a/vp8/encoder/encodeintra.c b/vp8/encoder/encodeintra.c index 508e5aaa5..d23c2305b 100644 --- a/vp8/encoder/encodeintra.c +++ b/vp8/encoder/encodeintra.c @@ -73,7 +73,7 @@ void vp8_encode_intra4x4block(const VP8_ENCODER_RTCD *rtcd, tx_type = get_tx_type(&x->e_mbd, b); if (tx_type != DCT_DCT) { - vp8_fht_c(be->src_diff, be->coeff, 32, tx_type, 4); + vp8_fht_c(be->src_diff, 32, be->coeff, tx_type, 4); vp8_ht_quantize_b_4x4(be, b, tx_type); vp8_ihtllm_c(b->dqcoeff, b->diff, 32, tx_type, 4); } else { @@ -114,7 +114,7 @@ void vp8_encode_intra16x16mby(const VP8_ENCODER_RTCD *rtcd, MACROBLOCK *x) { BLOCKD *bd = &xd->block[0]; tx_type = get_tx_type(xd, bd); if (tx_type != DCT_DCT) { - vp8_fht_c(b->src_diff, b->coeff, 32, tx_type, 16); + vp8_fht_c(b->src_diff, 32, b->coeff, tx_type, 16); vp8_quantize_mby_16x16(x); if (x->optimize) vp8_optimize_mby_16x16(x, rtcd); @@ -205,7 +205,7 @@ void vp8_encode_intra8x8(const VP8_ENCODER_RTCD *rtcd, tx_type = get_tx_type(xd, xd->block + idx); if (tx_type != DCT_DCT) { - vp8_fht_c(be->src_diff, (x->block + idx)->coeff, 32, + vp8_fht_c(be->src_diff, 32, (x->block + idx)->coeff, tx_type, 8); x->quantize_b_8x8(x->block + idx, xd->block + idx); vp8_ihtllm_c(xd->block[idx].dqcoeff, xd->block[ib].diff, 32, diff --git a/vp8/encoder/rdopt.c b/vp8/encoder/rdopt.c index 9ead1bd36..8207574dd 100644 --- a/vp8/encoder/rdopt.c +++ b/vp8/encoder/rdopt.c @@ -834,7 +834,7 @@ static void macro_block_yrd_16x16(MACROBLOCK *mb, int *Rate, int *Distortion, tx_type = get_tx_type_16x16(xd, b); if (tx_type != DCT_DCT) { - vp8_fht_c(be->src_diff, be->coeff, 32, tx_type, 16); + vp8_fht_c(be->src_diff, 32, be->coeff, tx_type, 16); } else vp8_transform_mby_16x16(mb); @@ -1116,7 +1116,7 @@ static int64_t rd_pick_intra4x4block(VP8_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) { - vp8_fht_c(be->src_diff, be->coeff, 32, tx_type, 4); + vp8_fht_c(be->src_diff, 32, be->coeff, tx_type, 4); vp8_ht_quantize_b_4x4(be, b, tx_type); } else { x->vp8_short_fdct4x4(be->src_diff, be->coeff, 32); @@ -1441,7 +1441,7 @@ static int64_t rd_pick_intra8x8block(VP8_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) - vp8_fht_c(be->src_diff, (x->block + idx)->coeff, 32, tx_type, 8); + vp8_fht_c(be->src_diff, 32, (x->block + idx)->coeff, tx_type, 8); else x->vp8_short_fdct8x8(be->src_diff, (x->block + idx)->coeff, 32); x->quantize_b_8x8(x->block + idx, xd->block + idx);