From 210dc5b2db5de75b6cdd97e0bf79e7fb2bc11cba Mon Sep 17 00:00:00 2001 From: Deb Mukherjee Date: Tue, 11 Dec 2012 17:06:35 -0800 Subject: [PATCH] Further improvements on the hybrid dwt/dct expt Modifies the scanning pattern and uses a floating point 16x16 dct implementation for now to handle scaling better. Also experiments are in progress with 2/6 and 9/7 wavelets. Results have improved to within ~0.25% of 32x32 dct for std-hd and about 0.03% for derf. This difference can probably be bridged by re-optimizing the entropy stats for these transforms. Currently the stats used are common between 32x32 dct and dwt/dct. Experiments are in progress with various scan pattern - wavelet combinations. Ideally the subbands should be tokenized separately, and an experiment will be condcuted next on that. Change-Id: Ia9cbfc2d63cb7a47e562b2cd9341caf962bcc110 --- vp9/common/vp9_entropy.c | 296 ++++++++++++-- vp9/common/vp9_idctllm.c | 861 +++++++++++++++++++++++++++++---------- vp9/encoder/vp9_dct.c | 439 ++++++++++++++++++-- 3 files changed, 1323 insertions(+), 273 deletions(-) diff --git a/vp9/common/vp9_entropy.c b/vp9/common/vp9_entropy.c index 9d8e924d5..b5da685ac 100644 --- a/vp9/common/vp9_entropy.c +++ b/vp9/common/vp9_entropy.c @@ -96,42 +96,271 @@ DECLARE_ALIGNED(64, const int, vp9_default_zig_zag1d_8x8[64]) = { // Table can be optimized. DECLARE_ALIGNED(16, const int, vp9_coef_bands_16x16[256]) = { - 0, 1, 2, 3, 5, 4, 4, 5, 5, 3, 6, 3, 5, 4, 6, 6, - 6, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, - 6, 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, - 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 0, 1, 2, 3, 5, 4, 4, 5, 5, 3, 6, 3, 5, 4, 6, 6, + 6, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, }; + DECLARE_ALIGNED(16, const int, vp9_default_zig_zag1d_16x16[256]) = { - 0, 1, 16, 32, 17, 2, 3, 18, 33, 48, 64, 49, 34, 19, 4, 5, - 20, 35, 50, 65, 80, 96, 81, 66, 51, 36, 21, 6, 7, 22, 37, 52, - 67, 82, 97, 112, 128, 113, 98, 83, 68, 53, 38, 23, 8, 9, 24, 39, - 54, 69, 84, 99, 114, 129, 144, 160, 145, 130, 115, 100, 85, 70, 55, 40, - 25, 10, 11, 26, 41, 56, 71, 86, 101, 116, 131, 146, 161, 176, 192, 177, - 162, 147, 132, 117, 102, 87, 72, 57, 42, 27, 12, 13, 28, 43, 58, 73, - 88, 103, 118, 133, 148, 163, 178, 193, 208, 224, 209, 194, 179, 164, 149, 134, - 119, 104, 89, 74, 59, 44, 29, 14, 15, 30, 45, 60, 75, 90, 105, 120, - 135, 150, 165, 180, 195, 210, 225, 240, 241, 226, 211, 196, 181, 166, 151, 136, - 121, 106, 91, 76, 61, 46, 31, 47, 62, 77, 92, 107, 122, 137, 152, 167, - 182, 197, 212, 227, 242, 243, 228, 213, 198, 183, 168, 153, 138, 123, 108, 93, - 78, 63, 79, 94, 109, 124, 139, 154, 169, 184, 199, 214, 229, 244, 245, 230, - 215, 200, 185, 170, 155, 140, 125, 110, 95, 111, 126, 141, 156, 171, 186, 201, - 216, 231, 246, 247, 232, 217, 202, 187, 172, 157, 142, 127, 143, 158, 173, 188, - 203, 218, 233, 248, 249, 234, 219, 204, 189, 174, 159, 175, 190, 205, 220, 235, - 250, 251, 236, 221, 206, 191, 207, 222, 237, 252, 253, 238, 223, 239, 254, 255, + 0, 1, 16, 32, 17, 2, 3, 18, + 33, 48, 64, 49, 34, 19, 4, 5, + 20, 35, 50, 65, 80, 96, 81, 66, + 51, 36, 21, 6, 7, 22, 37, 52, + 67, 82, 97, 112, 128, 113, 98, 83, + 68, 53, 38, 23, 8, 9, 24, 39, + 54, 69, 84, 99, 114, 129, 144, 160, + 145, 130, 115, 100, 85, 70, 55, 40, + 25, 10, 11, 26, 41, 56, 71, 86, + 101, 116, 131, 146, 161, 176, 192, 177, + 162, 147, 132, 117, 102, 87, 72, 57, + 42, 27, 12, 13, 28, 43, 58, 73, + 88, 103, 118, 133, 148, 163, 178, 193, + 208, 224, 209, 194, 179, 164, 149, 134, + 119, 104, 89, 74, 59, 44, 29, 14, + 15, 30, 45, 60, 75, 90, 105, 120, + 135, 150, 165, 180, 195, 210, 225, 240, + 241, 226, 211, 196, 181, 166, 151, 136, + 121, 106, 91, 76, 61, 46, 31, 47, + 62, 77, 92, 107, 122, 137, 152, 167, + 182, 197, 212, 227, 242, 243, 228, 213, + 198, 183, 168, 153, 138, 123, 108, 93, + 78, 63, 79, 94, 109, 124, 139, 154, + 169, 184, 199, 214, 229, 244, 245, 230, + 215, 200, 185, 170, 155, 140, 125, 110, + 95, 111, 126, 141, 156, 171, 186, 201, + 216, 231, 246, 247, 232, 217, 202, 187, + 172, 157, 142, 127, 143, 158, 173, 188, + 203, 218, 233, 248, 249, 234, 219, 204, + 189, 174, 159, 175, 190, 205, 220, 235, + 250, 251, 236, 221, 206, 191, 207, 222, + 237, 252, 253, 238, 223, 239, 254, 255, }; +#if CONFIG_TX32X32 && CONFIG_SUPERBLOCKS +#if CONFIG_DWT32X32HYBRID +DECLARE_ALIGNED(16, const int, vp9_coef_bands_32x32[1024]) = { + 0, 1, 2, 3, 5, 4, 4, 5, 5, 3, 6, 3, 5, 4, 6, + 6, 6, 6, + 6, + 6, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, + 6, 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, + 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, +}; + +DECLARE_ALIGNED(16, const int, vp9_default_zig_zag1d_32x32[1024]) = { + 0, 1, 32, 64, 33, 2, 3, 34, + 65, 96, 128, 97, 66, 35, 4, + 16, 512, 528, + 5, + 36, 67, 98, 129, 160, 192, 161, 130, + 99, 68, 37, 6, 7, 38, 69, 100, + 131, 162, 193, 224, 256, 225, 194, 163, + 132, 101, 70, 39, 8, 9, 40, 71, + 102, 133, 164, 195, 226, 257, 288, 320, + 289, 258, 227, 196, 165, 134, 103, 72, + 41, 10, 11, 42, 73, 104, 135, 166, + 197, 228, 259, 290, 321, 352, 384, 353, + 322, 291, 260, 229, 198, 167, 136, 105, + 74, 43, 12, 13, 44, 75, 106, 137, + 168, 199, 230, 261, 292, 323, 354, 385, + 416, 448, 417, 386, 355, 324, 293, 262, + 231, 200, 169, 138, 107, 76, 45, 14, + 15, 46, 77, 108, 139, 170, 201, 232, + 263, 294, 325, 356, 387, 418, 449, 480, + 481, 450, 419, 388, 357, 326, 295, 264, + 233, 202, 171, 140, 109, 78, 47, 79, + 110, 141, 172, 203, 234, 265, 296, 327, + 358, 389, 420, 451, 482, 483, 452, 421, + 390, 359, 328, 297, 266, 235, 204, 173, + 142, 111, 143, 174, 205, 236, 267, 298, + 329, 360, 391, 422, 453, 484, 485, 454, + 423, 392, 361, 330, 299, 268, 237, 206, + 175, 207, 238, 269, 300, 331, 362, 393, + 424, 455, 486, 487, 456, 425, 394, 363, + 332, 301, 270, 239, 271, 302, 333, 364, + 395, 426, 457, 488, 489, 458, 427, 396, + 365, 334, 303, 335, 366, 397, 428, 459, + 490, 491, 460, 429, 398, 367, 399, 430, + 461, 492, 493, 462, 431, 463, 494, 495, + + 17, 513, 529, 48, 544, + 560, 80, 576, 592, 49, 545, 561, 18, + 514, 530, 19, 515, 531, 50, 546, 562, + 81, 577, 593, 112, 608, 624, 144, 640, + 656, 113, 609, 625, 82, 578, 594, 51, + 547, 563, 20, 516, 532, 21, 517, 533, + 52, 548, 564, 83, 579, 595, 114, 610, + 626, 145, 641, 657, 176, 672, 688, 208, + 704, 720, 177, 673, 689, 146, 642, 658, + 115, 611, 627, 84, 580, 596, 53, 549, + 565, 22, 518, 534, 23, 519, 535, 54, + 550, 566, 85, 581, 597, 116, 612, 628, + 147, 643, 659, 178, 674, 690, 209, 705, + 721, 240, 736, 752, 272, 768, 784, 241, + 737, 753, 210, 706, 722, 179, 675, 691, + 148, 644, 660, 117, 613, 629, 86, 582, + 598, 55, 551, 567, 24, 520, 536, 25, + 521, 537, 56, 552, 568, 87, 583, 599, + 118, 614, 630, 149, 645, 661, 180, 676, + 692, 211, 707, 723, 242, 738, 754, 273, + 769, 785, 304, 800, 816, 336, 832, 848, + 305, 801, 817, 274, 770, 786, 243, 739, + 755, 212, 708, 724, 181, 677, 693, 150, + 646, 662, 119, 615, 631, 88, 584, 600, + 57, 553, 569, 26, 522, 538, 27, 523, + 539, 58, 554, 570, 89, 585, 601, 120, + 616, 632, 151, 647, 663, 182, 678, 694, + 213, 709, 725, 244, 740, 756, 275, 771, + 787, 306, 802, 818, 337, 833, 849, 368, + 864, 880, 400, 896, 912, 369, 865, 881, + 338, 834, 850, 307, 803, 819, 276, 772, + 788, 245, 741, 757, 214, 710, 726, 183, + + 679, 695, 152, 648, 664, 121, 617, 633, + 90, 586, 602, 59, 555, 571, 28, 524, + 540, 29, 525, 541, 60, 556, 572, 91, + 587, 603, 122, 618, 634, 153, 649, 665, + 184, 680, 696, 215, 711, 727, 246, 742, + 758, 277, 773, 789, 308, 804, 820, 339, + 835, 851, 370, 866, 882, 401, 897, 913, + 432, 928, 944, 464, 960, 976, 433, 929, + 945, 402, 898, 914, 371, 867, 883, 340, + 836, 852, 309, 805, 821, 278, 774, 790, + 247, 743, 759, 216, 712, 728, 185, 681, + 697, 154, 650, 666, 123, 619, 635, 92, + 588, 604, 61, 557, 573, 30, 526, 542, + 31, 527, 543, 62, 558, 574, 93, 589, + 605, 124, 620, 636, 155, 651, 667, 186, + 682, 698, 217, 713, 729, 248, 744, 760, + 279, 775, 791, 310, 806, 822, 341, 837, + 853, 372, 868, 884, 403, 899, 915, 434, + 930, 946, 465, 961, 977, 496, 992, 1008, + 497, 993, 1009, 466, 962, 978, 435, 931, + 947, 404, 900, 916, 373, 869, 885, 342, + 838, 854, 311, 807, 823, 280, 776, 792, + 249, 745, 761, 218, 714, 730, 187, 683, + 699, 156, 652, 668, 125, 621, 637, 94, + 590, 606, 63, 559, 575, 95, 591, 607, + 126, 622, 638, 157, 653, 669, 188, 684, + 700, 219, 715, 731, 250, 746, 762, 281, + 777, 793, 312, 808, 824, 343, 839, 855, + 374, 870, 886, 405, 901, 917, 436, 932, + 948, 467, 963, 979, 498, 994, 1010, 499, + 995, 1011, 468, 964, 980, 437, 933, 949, + 406, 902, 918, 375, 871, 887, 344, 840, + + 856, 313, 809, 825, 282, 778, 794, 251, + 747, 763, 220, 716, 732, 189, 685, 701, + 158, 654, 670, 127, 623, 639, 159, 655, + 671, 190, 686, 702, 221, 717, 733, 252, + 748, 764, 283, 779, 795, 314, 810, 826, + 345, 841, 857, 376, 872, 888, 407, 903, + 919, 438, 934, 950, 469, 965, 981, 500, + 996, 1012, 501, 997, 1013, 470, 966, 982, + 439, 935, 951, 408, 904, 920, 377, 873, + 889, 346, 842, 858, 315, 811, 827, 284, + 780, 796, 253, 749, 765, 222, 718, 734, + 191, 687, 703, 223, 719, 735, 254, 750, + 766, 285, 781, 797, 316, 812, 828, 347, + 843, 859, 378, 874, 890, 409, 905, 921, + 440, 936, 952, 471, 967, 983, 502, 998, + 1014, 503, 999, 1015, 472, 968, 984, 441, + 937, 953, 410, 906, 922, 379, 875, 891, + 348, 844, 860, 317, 813, 829, 286, 782, + 798, 255, 751, 767, 287, 783, 799, 318, + 814, 830, 349, 845, 861, 380, 876, 892, + 411, 907, 923, 442, 938, 954, 473, 969, + 985, 504, 1000, 1016, 505, 1001, 1017, 474, + 970, 986, 443, 939, 955, 412, 908, 924, + 381, 877, 893, 350, 846, 862, 319, 815, + 831, 351, 847, 863, 382, 878, 894, 413, + 909, 925, 444, 940, 956, 475, 971, 987, + 506, 1002, 1018, 507, 1003, 1019, 476, 972, + 988, 445, 941, 957, 414, 910, 926, 383, + 879, 895, 415, 911, 927, 446, 942, 958, + 477, 973, 989, 508, 1004, 1020, 509, 1005, + 1021, 478, 974, 990, 447, 943, 959, 479, + 975, 991, 510, 1006, 1022, 511, 1007, 1023, +}; + +#else + DECLARE_ALIGNED(16, const int, vp9_coef_bands_32x32[1024]) = { 0, 1, 2, 3, 5, 4, 4, 5, 5, 3, 6, 3, 5, 4, 6, 6, 6, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, @@ -201,6 +430,7 @@ DECLARE_ALIGNED(16, const int, vp9_coef_bands_32x32[1024]) = { 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, }; + DECLARE_ALIGNED(16, const int, vp9_default_zig_zag1d_32x32[1024]) = { 0, 1, 32, 64, 33, 2, 3, 34, 65, 96, 128, 97, 66, 35, 4, 5, 36, 67, 98, 129, 160, 192, 161, 130, 99, 68, 37, 6, 7, 38, 69, 100, 131, 162, 193, 224, 256, 225, 194, 163, 132, 101, 70, 39, 8, 9, 40, 71, 102, 133, 164, 195, 226, 257, 288, 320, 289, 258, 227, 196, 165, 134, 103, 72, @@ -235,6 +465,8 @@ DECLARE_ALIGNED(16, const int, vp9_default_zig_zag1d_32x32[1024]) = { 951, 920, 889, 858, 827, 796, 765, 734, 703, 735, 766, 797, 828, 859, 890, 921, 952, 983, 1014, 1015, 984, 953, 922, 891, 860, 829, 798, 767, 799, 830, 861, 892, 923, 954, 985, 1016, 1017, 986, 955, 924, 893, 862, 831, 863, 894, 925, 956, 987, 1018, 1019, 988, 957, 926, 895, 927, 958, 989, 1020, 1021, 990, 959, 991, 1022, 1023, }; +#endif // CONFIG_DWT32X32HYBRID +#endif /* Array indices are identical to previously-existing CONTEXT_NODE indices */ diff --git a/vp9/common/vp9_idctllm.c b/vp9/common/vp9_idctllm.c index cc685b99e..b09f3bde6 100644 --- a/vp9/common/vp9_idctllm.c +++ b/vp9/common/vp9_idctllm.c @@ -888,8 +888,8 @@ static void idctcol(int *blk) { (x4 = blk[8 * 1]) | (x5 = blk[8 * 7]) | (x6 = blk[8 * 5]) | (x7 = blk[8 * 3]))) { blk[8 * 0] = blk[8 * 1] = blk[8 * 2] = blk[8 * 3] - = blk[8 * 4] = blk[8 * 5] = blk[8 * 6] - = blk[8 * 7] = ((blk[8 * 0] + 32) >> 6); + = blk[8 * 4] = blk[8 * 5] = blk[8 * 6] + = blk[8 * 7] = ((blk[8 * 0] + 32) >> 6); return; } @@ -1127,25 +1127,25 @@ void vp9_short_idct16x16_c(short *input, short *output, int pitch) { #define TEST_INT_16x16_IDCT 1 #if !TEST_INT_16x16_IDCT -static const double C1 = 0.995184726672197; -static const double C2 = 0.98078528040323; -static const double C3 = 0.956940335732209; -static const double C4 = 0.923879532511287; -static const double C5 = 0.881921264348355; -static const double C6 = 0.831469612302545; -static const double C7 = 0.773010453362737; -static const double C8 = 0.707106781186548; -static const double C9 = 0.634393284163646; -static const double C10 = 0.555570233019602; -static const double C11 = 0.471396736825998; -static const double C12 = 0.38268343236509; -static const double C13 = 0.290284677254462; -static const double C14 = 0.195090322016128; -static const double C15 = 0.098017140329561; - static void butterfly_16x16_idct_1d(double input[16], double output[16]) { + static const double C1 = 0.995184726672197; + static const double C2 = 0.98078528040323; + static const double C3 = 0.956940335732209; + static const double C4 = 0.923879532511287; + static const double C5 = 0.881921264348355; + static const double C6 = 0.831469612302545; + static const double C7 = 0.773010453362737; + static const double C8 = 0.707106781186548; + static const double C9 = 0.634393284163646; + static const double C10 = 0.555570233019602; + static const double C11 = 0.471396736825998; + static const double C12 = 0.38268343236509; + static const double C13 = 0.290284677254462; + static const double C14 = 0.195090322016128; + static const double C15 = 0.098017140329561; + vp9_clear_system_state(); // Make it simd safe : __asm emms; { double step[16]; @@ -1389,6 +1389,12 @@ void vp9_short_idct16x16_c(short *input, short *output, int pitch) { } #else + +#define INITIAL_SHIFT 2 +#define INITIAL_ROUNDING (1 << (INITIAL_SHIFT - 1)) +#define RIGHT_SHIFT 14 +#define RIGHT_ROUNDING (1 << (RIGHT_SHIFT - 1)) + static const int16_t C1 = 16305; static const int16_t C2 = 16069; static const int16_t C3 = 15679; @@ -1405,212 +1411,207 @@ static const int16_t C13 = 4756; static const int16_t C14 = 3196; static const int16_t C15 = 1606; -#define INITIAL_SHIFT 2 -#define INITIAL_ROUNDING (1 << (INITIAL_SHIFT - 1)) -#define RIGHT_SHIFT 14 -#define RIGHT_ROUNDING (1 << (RIGHT_SHIFT - 1)) - static void butterfly_16x16_idct_1d(int16_t input[16], int16_t output[16], int last_shift_bits) { - int16_t step[16]; - int intermediate[16]; - int temp1, temp2; + int16_t step[16]; + int intermediate[16]; + int temp1, temp2; - int step1_shift = RIGHT_SHIFT + INITIAL_SHIFT; - int step1_rounding = 1 << (step1_shift - 1); - int last_rounding = 0; + int step1_shift = RIGHT_SHIFT + INITIAL_SHIFT; + int step1_rounding = 1 << (step1_shift - 1); + int last_rounding = 0; - if (last_shift_bits > 0) - last_rounding = 1 << (last_shift_bits - 1); + if (last_shift_bits > 0) + last_rounding = 1 << (last_shift_bits - 1); - // step 1 and 2 - step[ 0] = (input[0] + input[8] + INITIAL_ROUNDING) >> INITIAL_SHIFT; - step[ 1] = (input[0] - input[8] + INITIAL_ROUNDING) >> INITIAL_SHIFT; + // step 1 and 2 + step[ 0] = (input[0] + input[8] + INITIAL_ROUNDING) >> INITIAL_SHIFT; + step[ 1] = (input[0] - input[8] + INITIAL_ROUNDING) >> INITIAL_SHIFT; - temp1 = input[4] * C12; - temp2 = input[12] * C4; - temp1 = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 *= C8; - step[ 2] = (2 * (temp1) + step1_rounding) >> step1_shift; + temp1 = input[4] * C12; + temp2 = input[12] * C4; + temp1 = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 *= C8; + step[ 2] = (2 * (temp1) + step1_rounding) >> step1_shift; - temp1 = input[4] * C4; - temp2 = input[12] * C12; - temp1 = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 *= C8; - step[ 3] = (2 * (temp1) + step1_rounding) >> step1_shift; + temp1 = input[4] * C4; + temp2 = input[12] * C12; + temp1 = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 *= C8; + step[ 3] = (2 * (temp1) + step1_rounding) >> step1_shift; - temp1 = input[2] * C8; - temp1 = (2 * (temp1) + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp2 = input[6] + input[10]; - step[ 4] = (temp1 + temp2 + INITIAL_ROUNDING) >> INITIAL_SHIFT; - step[ 5] = (temp1 - temp2 + INITIAL_ROUNDING) >> INITIAL_SHIFT; + temp1 = input[2] * C8; + temp1 = (2 * (temp1) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp2 = input[6] + input[10]; + step[ 4] = (temp1 + temp2 + INITIAL_ROUNDING) >> INITIAL_SHIFT; + step[ 5] = (temp1 - temp2 + INITIAL_ROUNDING) >> INITIAL_SHIFT; - temp1 = input[14] * C8; - temp1 = (2 * (temp1) + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp2 = input[6] - input[10]; - step[ 6] = (temp2 - temp1 + INITIAL_ROUNDING) >> INITIAL_SHIFT; - step[ 7] = (temp2 + temp1 + INITIAL_ROUNDING) >> INITIAL_SHIFT; + temp1 = input[14] * C8; + temp1 = (2 * (temp1) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp2 = input[6] - input[10]; + step[ 6] = (temp2 - temp1 + INITIAL_ROUNDING) >> INITIAL_SHIFT; + step[ 7] = (temp2 + temp1 + INITIAL_ROUNDING) >> INITIAL_SHIFT; - // for odd input - temp1 = input[3] * C12; - temp2 = input[13] * C4; - temp1 = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 *= C8; - intermediate[ 8] = (2 * (temp1) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + // for odd input + temp1 = input[3] * C12; + temp2 = input[13] * C4; + temp1 = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 *= C8; + intermediate[ 8] = (2 * (temp1) + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 = input[3] * C4; - temp2 = input[13] * C12; - temp2 = (temp2 - temp1 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp2 *= C8; - intermediate[ 9] = (2 * (temp2) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = input[3] * C4; + temp2 = input[13] * C12; + temp2 = (temp2 - temp1 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp2 *= C8; + intermediate[ 9] = (2 * (temp2) + RIGHT_ROUNDING) >> RIGHT_SHIFT; - intermediate[10] = (2 * (input[9] * C8) + RIGHT_ROUNDING) >> RIGHT_SHIFT; - intermediate[11] = input[15] - input[1]; - intermediate[12] = input[15] + input[1]; - intermediate[13] = (2 * (input[7] * C8) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + intermediate[10] = (2 * (input[9] * C8) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + intermediate[11] = input[15] - input[1]; + intermediate[12] = input[15] + input[1]; + intermediate[13] = (2 * (input[7] * C8) + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 = input[11] * C12; - temp2 = input[5] * C4; - temp2 = (temp2 - temp1 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp2 *= C8; - intermediate[14] = (2 * (temp2) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = input[11] * C12; + temp2 = input[5] * C4; + temp2 = (temp2 - temp1 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp2 *= C8; + intermediate[14] = (2 * (temp2) + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 = input[11] * C4; - temp2 = input[5] * C12; - temp1 = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 *= C8; - intermediate[15] = (2 * (temp1) + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = input[11] * C4; + temp2 = input[5] * C12; + temp1 = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 *= C8; + intermediate[15] = (2 * (temp1) + RIGHT_ROUNDING) >> RIGHT_SHIFT; - step[ 8] = (intermediate[ 8] + intermediate[14] + INITIAL_ROUNDING) - >> INITIAL_SHIFT; - step[ 9] = (intermediate[ 9] + intermediate[15] + INITIAL_ROUNDING) - >> INITIAL_SHIFT; - step[10] = (intermediate[10] + intermediate[11] + INITIAL_ROUNDING) - >> INITIAL_SHIFT; - step[11] = (intermediate[10] - intermediate[11] + INITIAL_ROUNDING) - >> INITIAL_SHIFT; - step[12] = (intermediate[12] + intermediate[13] + INITIAL_ROUNDING) - >> INITIAL_SHIFT; - step[13] = (intermediate[12] - intermediate[13] + INITIAL_ROUNDING) - >> INITIAL_SHIFT; - step[14] = (intermediate[ 8] - intermediate[14] + INITIAL_ROUNDING) - >> INITIAL_SHIFT; - step[15] = (intermediate[ 9] - intermediate[15] + INITIAL_ROUNDING) - >> INITIAL_SHIFT; + step[ 8] = (intermediate[ 8] + intermediate[14] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[ 9] = (intermediate[ 9] + intermediate[15] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[10] = (intermediate[10] + intermediate[11] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[11] = (intermediate[10] - intermediate[11] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[12] = (intermediate[12] + intermediate[13] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[13] = (intermediate[12] - intermediate[13] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[14] = (intermediate[ 8] - intermediate[14] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; + step[15] = (intermediate[ 9] - intermediate[15] + INITIAL_ROUNDING) + >> INITIAL_SHIFT; - // step 3 - output[0] = step[ 0] + step[ 3]; - output[1] = step[ 1] + step[ 2]; - output[2] = step[ 1] - step[ 2]; - output[3] = step[ 0] - step[ 3]; + // step 3 + output[0] = step[ 0] + step[ 3]; + output[1] = step[ 1] + step[ 2]; + output[2] = step[ 1] - step[ 2]; + output[3] = step[ 0] - step[ 3]; - temp1 = step[ 4] * C14; - temp2 = step[ 7] * C2; - output[4] = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = step[ 4] * C14; + temp2 = step[ 7] * C2; + output[4] = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 = step[ 4] * C2; - temp2 = step[ 7] * C14; - output[7] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = step[ 4] * C2; + temp2 = step[ 7] * C14; + output[7] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 = step[ 5] * C10; - temp2 = step[ 6] * C6; - output[5] = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = step[ 5] * C10; + temp2 = step[ 6] * C6; + output[5] = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 = step[ 5] * C6; - temp2 = step[ 6] * C10; - output[6] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = step[ 5] * C6; + temp2 = step[ 6] * C10; + output[6] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - output[8] = step[ 8] + step[11]; - output[9] = step[ 9] + step[10]; - output[10] = step[ 9] - step[10]; - output[11] = step[ 8] - step[11]; - output[12] = step[12] + step[15]; - output[13] = step[13] + step[14]; - output[14] = step[13] - step[14]; - output[15] = step[12] - step[15]; + output[8] = step[ 8] + step[11]; + output[9] = step[ 9] + step[10]; + output[10] = step[ 9] - step[10]; + output[11] = step[ 8] - step[11]; + output[12] = step[12] + step[15]; + output[13] = step[13] + step[14]; + output[14] = step[13] - step[14]; + output[15] = step[12] - step[15]; - // output 4 - step[ 0] = output[0] + output[7]; - step[ 1] = output[1] + output[6]; - step[ 2] = output[2] + output[5]; - step[ 3] = output[3] + output[4]; - step[ 4] = output[3] - output[4]; - step[ 5] = output[2] - output[5]; - step[ 6] = output[1] - output[6]; - step[ 7] = output[0] - output[7]; + // output 4 + step[ 0] = output[0] + output[7]; + step[ 1] = output[1] + output[6]; + step[ 2] = output[2] + output[5]; + step[ 3] = output[3] + output[4]; + step[ 4] = output[3] - output[4]; + step[ 5] = output[2] - output[5]; + step[ 6] = output[1] - output[6]; + step[ 7] = output[0] - output[7]; - temp1 = output[8] * C7; - temp2 = output[15] * C9; - step[ 8] = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = output[8] * C7; + temp2 = output[15] * C9; + step[ 8] = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 = output[9] * C11; - temp2 = output[14] * C5; - step[ 9] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = output[9] * C11; + temp2 = output[14] * C5; + step[ 9] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 = output[10] * C3; - temp2 = output[13] * C13; - step[10] = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = output[10] * C3; + temp2 = output[13] * C13; + step[10] = (temp1 - temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 = output[11] * C15; - temp2 = output[12] * C1; - step[11] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = output[11] * C15; + temp2 = output[12] * C1; + step[11] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 = output[11] * C1; - temp2 = output[12] * C15; - step[12] = (temp2 - temp1 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = output[11] * C1; + temp2 = output[12] * C15; + step[12] = (temp2 - temp1 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 = output[10] * C13; - temp2 = output[13] * C3; - step[13] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = output[10] * C13; + temp2 = output[13] * C3; + step[13] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 = output[9] * C5; - temp2 = output[14] * C11; - step[14] = (temp2 - temp1 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = output[9] * C5; + temp2 = output[14] * C11; + step[14] = (temp2 - temp1 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - temp1 = output[8] * C9; - temp2 = output[15] * C7; - step[15] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; + temp1 = output[8] * C9; + temp2 = output[15] * C7; + step[15] = (temp1 + temp2 + RIGHT_ROUNDING) >> RIGHT_SHIFT; - // step 5 - output[0] = (step[0] + step[15] + last_rounding) >> last_shift_bits; - output[1] = (step[1] + step[14] + last_rounding) >> last_shift_bits; - output[2] = (step[2] + step[13] + last_rounding) >> last_shift_bits; - output[3] = (step[3] + step[12] + last_rounding) >> last_shift_bits; - output[4] = (step[4] + step[11] + last_rounding) >> last_shift_bits; - output[5] = (step[5] + step[10] + last_rounding) >> last_shift_bits; - output[6] = (step[6] + step[ 9] + last_rounding) >> last_shift_bits; - output[7] = (step[7] + step[ 8] + last_rounding) >> last_shift_bits; + // step 5 + output[0] = (step[0] + step[15] + last_rounding) >> last_shift_bits; + output[1] = (step[1] + step[14] + last_rounding) >> last_shift_bits; + output[2] = (step[2] + step[13] + last_rounding) >> last_shift_bits; + output[3] = (step[3] + step[12] + last_rounding) >> last_shift_bits; + output[4] = (step[4] + step[11] + last_rounding) >> last_shift_bits; + output[5] = (step[5] + step[10] + last_rounding) >> last_shift_bits; + output[6] = (step[6] + step[ 9] + last_rounding) >> last_shift_bits; + output[7] = (step[7] + step[ 8] + last_rounding) >> last_shift_bits; - output[15] = (step[0] - step[15] + last_rounding) >> last_shift_bits; - output[14] = (step[1] - step[14] + last_rounding) >> last_shift_bits; - output[13] = (step[2] - step[13] + last_rounding) >> last_shift_bits; - output[12] = (step[3] - step[12] + last_rounding) >> last_shift_bits; - output[11] = (step[4] - step[11] + last_rounding) >> last_shift_bits; - output[10] = (step[5] - step[10] + last_rounding) >> last_shift_bits; - output[9] = (step[6] - step[ 9] + last_rounding) >> last_shift_bits; - output[8] = (step[7] - step[ 8] + last_rounding) >> last_shift_bits; + output[15] = (step[0] - step[15] + last_rounding) >> last_shift_bits; + output[14] = (step[1] - step[14] + last_rounding) >> last_shift_bits; + output[13] = (step[2] - step[13] + last_rounding) >> last_shift_bits; + output[12] = (step[3] - step[12] + last_rounding) >> last_shift_bits; + output[11] = (step[4] - step[11] + last_rounding) >> last_shift_bits; + output[10] = (step[5] - step[10] + last_rounding) >> last_shift_bits; + output[9] = (step[6] - step[ 9] + last_rounding) >> last_shift_bits; + output[8] = (step[7] - step[ 8] + last_rounding) >> last_shift_bits; } void vp9_short_idct16x16_c(int16_t *input, int16_t *output, int pitch) { - int16_t out[16 * 16]; - int16_t *outptr = &out[0]; - const int short_pitch = pitch >> 1; - int i, j; - int16_t temp_in[16], temp_out[16]; + int16_t out[16 * 16]; + int16_t *outptr = &out[0]; + const int short_pitch = pitch >> 1; + int i, j; + int16_t temp_in[16], temp_out[16]; - // First transform rows - for (i = 0; i < 16; ++i) { - butterfly_16x16_idct_1d(input, outptr, 0); - input += short_pitch; - outptr += 16; - } + // First transform rows + for (i = 0; i < 16; ++i) { + butterfly_16x16_idct_1d(input, outptr, 0); + input += short_pitch; + outptr += 16; + } - // Then transform columns - for (i = 0; i < 16; ++i) { - for (j = 0; j < 16; ++j) - temp_in[j] = out[j * 16 + i]; - butterfly_16x16_idct_1d(temp_in, temp_out, 3); - for (j = 0; j < 16; ++j) + // Then transform columns + for (i = 0; i < 16; ++i) { + for (j = 0; j < 16; ++j) + temp_in[j] = out[j * 16 + i]; + butterfly_16x16_idct_1d(temp_in, temp_out, 3); + for (j = 0; j < 16; ++j) output[j * 16 + i] = temp_out[j]; } } @@ -2120,16 +2121,20 @@ void vp9_short_idct32x32_c(short *input, short *output, int pitch) { } vp9_clear_system_state(); // Make it simd safe : __asm emms; } + #else // CONFIG_DWT32X32HYBRID -#define MAX_BLOCK_LENGTH 64 -#define ENH_PRECISION_BITS 1 -#define ENH_PRECISION_RND ((1 << ENH_PRECISION_BITS) / 2) +#define DWT_MAX_LENGTH 32 +#define DWT_TYPE 26 // 26/53/97 +#define DWT_PRECISION_BITS 2 +#define DWT_PRECISION_RND ((1 << DWT_PRECISION_BITS) / 2) + +#if DWT_TYPE == 53 // Note: block length must be even for this implementation static void synthesis_53_row(int length, short *lowpass, short *highpass, short *x) { - short r, * a, * b; + short r, *a, *b; int n; n = length >> 1; @@ -2148,13 +2153,13 @@ static void synthesis_53_row(int length, short *lowpass, short *highpass, *x++ = ((r = *a++) + 1) >> 1; *x++ = *b++ + ((r + (*a) + 2) >> 2); } - *x++ = ((r = *a) + 1)>>1; - *x++ = *b + ((r+1)>>1); + *x++ = ((r = *a) + 1) >> 1; + *x++ = *b + ((r + 1) >> 1); } static void synthesis_53_col(int length, short *lowpass, short *highpass, short *x) { - short r, * a, * b; + short r, *a, *b; int n; n = length >> 1; @@ -2170,19 +2175,18 @@ static void synthesis_53_col(int length, short *lowpass, short *highpass, b = highpass; a = lowpass; while (--n) { - *x++ = r = *a++; + r = *a++; + *x++ = r; *x++ = ((*b++) << 1) + ((r + (*a) + 1) >> 1); } - *x++ = r = *a; - *x++ = ((*b) << 1) + r; + *x++ = *a; + *x++ = ((*b) << 1) + *a; } -// NOTE: Using a 5/3 integer wavelet for now. Explore using a wavelet -// with a better response later -void dyadic_synthesize(int levels, int width, int height, short *c, int pitch_c, - short *x, int pitch_x) { +void dyadic_synthesize_53(int levels, int width, int height, short *c, + int pitch_c, short *x, int pitch_x) { int th[16], tw[16], lv, i, j, nh, nw, hh = height, hw = width; - short buffer[2 * MAX_BLOCK_LENGTH]; + short buffer[2 * DWT_MAX_LENGTH]; th[0] = hh; tw[0] = hw; @@ -2204,35 +2208,466 @@ void dyadic_synthesize(int levels, int width, int height, short *c, int pitch_c, c[i * pitch_c + j] = buffer[i + nh]; } for (i = 0; i < nh; i++) { - memcpy(buffer, &c[i * pitch_c], nw * sizeof(short)); + memcpy(buffer, &c[i * pitch_c], nw * sizeof(*buffer)); synthesis_53_row(nw, buffer, buffer + hw, &c[i * pitch_c]); } } + for (i = 0; i < height; i++) { + for (j = 0; j < width; j++) { + x[i * pitch_x + j] = c[i * pitch_c + j] >= 0 ? + ((c[i * pitch_c + j] + DWT_PRECISION_RND) >> DWT_PRECISION_BITS) : + -((-c[i * pitch_c + j] + DWT_PRECISION_RND) >> DWT_PRECISION_BITS); + } + } +} + +#elif DWT_TYPE == 26 + +// Note: block length must be even for this implementation +static void synthesis_26_row(int length, short *lowpass, short *highpass, + short *x) { + short r, s, *a, *b; + int i, n = length >> 1; + + if (n >= 4) { + a = lowpass; + b = highpass; + r = *lowpass; + while (--n) { + *b++ += (r - a[1] + 4) >> 3; + r = *a++; + } + *b += (r - *a + 4) >> 3; + } + a = lowpass; + b = highpass; + for (i = length >> 1; i; i--) { + s = *b++; + r = *a++; + *x++ = (r + s + 1) >> 1; + *x++ = (r - s + 1) >> 1; + } +} + +static void synthesis_26_col(int length, short *lowpass, short *highpass, + short *x) { + short r, s, *a, *b; + int i, n = length >> 1; + + if (n >= 4) { + a = lowpass; + b = highpass; + r = *lowpass; + while (--n) { + *b++ += (r - a[1] + 4) >> 3; + r = *a++; + } + *b += (r - *a + 4) >> 3; + } + a = lowpass; + b = highpass; + for (i = length >> 1; i; i--) { + s = *b++; + r = *a++; + *x++ = r + s; + *x++ = r - s; + } +} + +void dyadic_synthesize_26(int levels, int width, int height, short *c, + int pitch_c, short *x, int pitch_x) { + int th[16], tw[16], lv, i, j, nh, nw, hh = height, hw = width; + short buffer[2 * DWT_MAX_LENGTH]; + + th[0] = hh; + tw[0] = hw; + for (i = 1; i <= levels; i++) { + th[i] = (th[i - 1] + 1) >> 1; + tw[i] = (tw[i - 1] + 1) >> 1; + } + for (lv = levels - 1; lv >= 0; lv--) { + nh = th[lv]; + nw = tw[lv]; + hh = th[lv + 1]; + hw = tw[lv + 1]; + if ((nh < 2) || (nw < 2)) continue; + for (j = 0; j < nw; j++) { + for (i = 0; i < nh; i++) + buffer[i] = c[i * pitch_c + j]; + synthesis_26_col(nh, buffer, buffer + hh, buffer + nh); + for (i = 0; i < nh; i++) + c[i * pitch_c + j] = buffer[i + nh]; + } + for (i = 0; i < nh; i++) { + memcpy(buffer, &c[i * pitch_c], nw * sizeof(*buffer)); + synthesis_26_row(nw, buffer, buffer + hw, &c[i * pitch_c]); + } + } + for (i = 0; i < height; i++) { + for (j = 0; j < width; j++) { + x[i * pitch_x + j] = c[i * pitch_c + j] >= 0 ? + ((c[i * pitch_c + j] + DWT_PRECISION_RND) >> DWT_PRECISION_BITS) : + -((-c[i * pitch_c + j] + DWT_PRECISION_RND) >> DWT_PRECISION_BITS); + } + } +} + +#elif DWT_TYPE == 97 + +static void synthesis_97(int length, double *lowpass, double *highpass, + double *x) { + static const double a_predict1 = -1.586134342; + static const double a_update1 = -0.05298011854; + static const double a_predict2 = 0.8829110762; + static const double a_update2 = 0.4435068522; + static const double s_low = 1.149604398; + static const double s_high = 1/1.149604398; + static const double inv_s_low = 1 / s_low; + static const double inv_s_high = 1 / s_high; + int i; + double y[DWT_MAX_LENGTH]; + // Undo pack and scale + for (i = 0; i < length / 2; i++) { + y[i * 2] = lowpass[i] * inv_s_low; + y[i * 2 + 1] = highpass[i] * inv_s_high; + } + memcpy(x, y, sizeof(*y) * length); + // Undo update 2 + for (i = 2; i < length; i += 2) { + x[i] -= a_update2 * (x[i-1] + x[i+1]); + } + x[0] -= 2 * a_update2 * x[1]; + // Undo predict 2 + for (i = 1; i < length - 2; i += 2) { + x[i] -= a_predict2 * (x[i - 1] + x[i + 1]); + } + x[length - 1] -= 2 * a_predict2 * x[length - 2]; + // Undo update 1 + for (i = 2; i < length; i += 2) { + x[i] -= a_update1 * (x[i - 1] + x[i + 1]); + } + x[0] -= 2 * a_update1 * x[1]; + // Undo predict 1 + for (i = 1; i < length - 2; i += 2) { + x[i] -= a_predict1 * (x[i - 1] + x[i + 1]); + } + x[length - 1] -= 2 * a_predict1 * x[length - 2]; +} + +void dyadic_synthesize_97(int levels, int width, int height, short *c, + int pitch_c, short *x, int pitch_x) { + int th[16], tw[16], lv, i, j, nh, nw, hh = height, hw = width; + double buffer[2 * DWT_MAX_LENGTH]; + double y[DWT_MAX_LENGTH * DWT_MAX_LENGTH]; + + th[0] = hh; + tw[0] = hw; + for (i = 1; i <= levels; i++) { + th[i] = (th[i - 1] + 1) >> 1; + tw[i] = (tw[i - 1] + 1) >> 1; + } + for (lv = levels - 1; lv >= 0; lv--) { + nh = th[lv]; + nw = tw[lv]; + hh = th[lv + 1]; + hw = tw[lv + 1]; + if ((nh < 2) || (nw < 2)) continue; + for (j = 0; j < nw; j++) { + for (i = 0; i < nh; i++) + buffer[i] = c[i * pitch_c + j]; + synthesis_97(nh, buffer, buffer + hh, buffer + nh); + for (i = 0; i < nh; i++) + y[i * DWT_MAX_LENGTH + j] = buffer[i + nh]; + } + for (i = 0; i < nh; i++) { + memcpy(buffer, &y[i * DWT_MAX_LENGTH], nw * sizeof(*buffer)); + synthesis_97(nw, buffer, buffer + hw, &y[i * DWT_MAX_LENGTH]); + } + } for (i = 0; i < height; i++) for (j = 0; j < width; j++) - x[i * pitch_x + j] = (c[i * pitch_c + j] + ENH_PRECISION_RND) >> - ENH_PRECISION_BITS; + x[i * pitch_x + j] = round(y[i * DWT_MAX_LENGTH + j] / + (1 << DWT_PRECISION_BITS)); +} + +#endif // DWT_TYPE + +// TODO(debargha): Implement scaling differently so as not to have to use the +// floating point 16x16 dct +static void butterfly_16x16_idct_1d_f(double input[16], double output[16]) { + static const double C1 = 0.995184726672197; + static const double C2 = 0.98078528040323; + static const double C3 = 0.956940335732209; + static const double C4 = 0.923879532511287; + static const double C5 = 0.881921264348355; + static const double C6 = 0.831469612302545; + static const double C7 = 0.773010453362737; + static const double C8 = 0.707106781186548; + static const double C9 = 0.634393284163646; + static const double C10 = 0.555570233019602; + static const double C11 = 0.471396736825998; + static const double C12 = 0.38268343236509; + static const double C13 = 0.290284677254462; + static const double C14 = 0.195090322016128; + static const double C15 = 0.098017140329561; + + vp9_clear_system_state(); // Make it simd safe : __asm emms; + { + double step[16]; + double intermediate[16]; + double temp1, temp2; + + + // step 1 and 2 + step[ 0] = input[0] + input[8]; + step[ 1] = input[0] - input[8]; + + temp1 = input[4]*C12; + temp2 = input[12]*C4; + + temp1 -= temp2; + temp1 *= C8; + + step[ 2] = 2*(temp1); + + temp1 = input[4]*C4; + temp2 = input[12]*C12; + temp1 += temp2; + temp1 = (temp1); + temp1 *= C8; + step[ 3] = 2*(temp1); + + temp1 = input[2]*C8; + temp1 = 2*(temp1); + temp2 = input[6] + input[10]; + + step[ 4] = temp1 + temp2; + step[ 5] = temp1 - temp2; + + temp1 = input[14]*C8; + temp1 = 2*(temp1); + temp2 = input[6] - input[10]; + + step[ 6] = temp2 - temp1; + step[ 7] = temp2 + temp1; + + // for odd input + temp1 = input[3]*C12; + temp2 = input[13]*C4; + temp1 += temp2; + temp1 = (temp1); + temp1 *= C8; + intermediate[ 8] = 2*(temp1); + + temp1 = input[3]*C4; + temp2 = input[13]*C12; + temp2 -= temp1; + temp2 = (temp2); + temp2 *= C8; + intermediate[ 9] = 2*(temp2); + + intermediate[10] = 2*(input[9]*C8); + intermediate[11] = input[15] - input[1]; + intermediate[12] = input[15] + input[1]; + intermediate[13] = 2*((input[7]*C8)); + + temp1 = input[11]*C12; + temp2 = input[5]*C4; + temp2 -= temp1; + temp2 = (temp2); + temp2 *= C8; + intermediate[14] = 2*(temp2); + + temp1 = input[11]*C4; + temp2 = input[5]*C12; + temp1 += temp2; + temp1 = (temp1); + temp1 *= C8; + intermediate[15] = 2*(temp1); + + step[ 8] = intermediate[ 8] + intermediate[14]; + step[ 9] = intermediate[ 9] + intermediate[15]; + step[10] = intermediate[10] + intermediate[11]; + step[11] = intermediate[10] - intermediate[11]; + step[12] = intermediate[12] + intermediate[13]; + step[13] = intermediate[12] - intermediate[13]; + step[14] = intermediate[ 8] - intermediate[14]; + step[15] = intermediate[ 9] - intermediate[15]; + + // step 3 + output[0] = step[ 0] + step[ 3]; + output[1] = step[ 1] + step[ 2]; + output[2] = step[ 1] - step[ 2]; + output[3] = step[ 0] - step[ 3]; + + temp1 = step[ 4]*C14; + temp2 = step[ 7]*C2; + temp1 -= temp2; + output[4] = (temp1); + + temp1 = step[ 4]*C2; + temp2 = step[ 7]*C14; + temp1 += temp2; + output[7] = (temp1); + + temp1 = step[ 5]*C10; + temp2 = step[ 6]*C6; + temp1 -= temp2; + output[5] = (temp1); + + temp1 = step[ 5]*C6; + temp2 = step[ 6]*C10; + temp1 += temp2; + output[6] = (temp1); + + output[8] = step[ 8] + step[11]; + output[9] = step[ 9] + step[10]; + output[10] = step[ 9] - step[10]; + output[11] = step[ 8] - step[11]; + output[12] = step[12] + step[15]; + output[13] = step[13] + step[14]; + output[14] = step[13] - step[14]; + output[15] = step[12] - step[15]; + + // output 4 + step[ 0] = output[0] + output[7]; + step[ 1] = output[1] + output[6]; + step[ 2] = output[2] + output[5]; + step[ 3] = output[3] + output[4]; + step[ 4] = output[3] - output[4]; + step[ 5] = output[2] - output[5]; + step[ 6] = output[1] - output[6]; + step[ 7] = output[0] - output[7]; + + temp1 = output[8]*C7; + temp2 = output[15]*C9; + temp1 -= temp2; + step[ 8] = (temp1); + + temp1 = output[9]*C11; + temp2 = output[14]*C5; + temp1 += temp2; + step[ 9] = (temp1); + + temp1 = output[10]*C3; + temp2 = output[13]*C13; + temp1 -= temp2; + step[10] = (temp1); + + temp1 = output[11]*C15; + temp2 = output[12]*C1; + temp1 += temp2; + step[11] = (temp1); + + temp1 = output[11]*C1; + temp2 = output[12]*C15; + temp2 -= temp1; + step[12] = (temp2); + + temp1 = output[10]*C13; + temp2 = output[13]*C3; + temp1 += temp2; + step[13] = (temp1); + + temp1 = output[9]*C5; + temp2 = output[14]*C11; + temp2 -= temp1; + step[14] = (temp2); + + temp1 = output[8]*C9; + temp2 = output[15]*C7; + temp1 += temp2; + step[15] = (temp1); + + // step 5 + output[0] = (step[0] + step[15]); + output[1] = (step[1] + step[14]); + output[2] = (step[2] + step[13]); + output[3] = (step[3] + step[12]); + output[4] = (step[4] + step[11]); + output[5] = (step[5] + step[10]); + output[6] = (step[6] + step[ 9]); + output[7] = (step[7] + step[ 8]); + + output[15] = (step[0] - step[15]); + output[14] = (step[1] - step[14]); + output[13] = (step[2] - step[13]); + output[12] = (step[3] - step[12]); + output[11] = (step[4] - step[11]); + output[10] = (step[5] - step[10]); + output[9] = (step[6] - step[ 9]); + output[8] = (step[7] - step[ 8]); + } + vp9_clear_system_state(); // Make it simd safe : __asm emms; +} + +void vp9_short_idct16x16_c_f(short *input, short *output, int pitch) { + vp9_clear_system_state(); // Make it simd safe : __asm emms; + { + double out[16*16], out2[16*16]; + const int short_pitch = pitch >> 1; + int i, j; + // First transform rows + for (i = 0; i < 16; ++i) { + double temp_in[16], temp_out[16]; + for (j = 0; j < 16; ++j) + temp_in[j] = input[j + i*short_pitch]; + butterfly_16x16_idct_1d_f(temp_in, temp_out); + for (j = 0; j < 16; ++j) + out[j + i*16] = temp_out[j]; + } + // Then transform columns + for (i = 0; i < 16; ++i) { + double temp_in[16], temp_out[16]; + for (j = 0; j < 16; ++j) + temp_in[j] = out[j*16 + i]; + butterfly_16x16_idct_1d_f(temp_in, temp_out); + for (j = 0; j < 16; ++j) + out2[j*16 + i] = temp_out[j]; + } + for (i = 0; i < 16*16; ++i) + output[i] = round(out2[i] / (64 >> DWT_PRECISION_BITS)); + } + vp9_clear_system_state(); // Make it simd safe : __asm emms; } void vp9_short_idct32x32_c(short *input, short *output, int pitch) { // assume out is a 32x32 buffer + // Temporary buffer to hold a 16x16 block for 16x16 inverse dct short buffer[16 * 16]; + // Temporary buffer to hold a 32x32 block for inverse 32x32 dwt short buffer2[32 * 32]; + // Note: pitch is in bytes, short_pitch is in short units const int short_pitch = pitch >> 1; int i; + // TODO(debargha): Implement more efficiently by adding output pitch // argument to the idct16x16 function - vp9_short_idct16x16_c(input, buffer, pitch); + vp9_short_idct16x16_c_f(input, buffer, pitch); for (i = 0; i < 16; ++i) { - vpx_memcpy(buffer2 + i * 32, buffer + i * 16, sizeof(short) * 16); - vpx_memcpy(buffer2 + i * 32 + 16, input + i * short_pitch + 16, - sizeof(short) * 16); + vpx_memcpy(buffer2 + i * 32, buffer + i * 16, sizeof(*buffer2) * 16); } - for (; i < 32; ++i) { - vpx_memcpy(buffer2 + i * 32, input + i * short_pitch, - sizeof(short) * 32); + vp9_short_idct16x16_c_f(input + 16, buffer, pitch); + for (i = 0; i < 16; ++i) { + vpx_memcpy(buffer2 + i * 32 + 16, buffer + i * 16, sizeof(*buffer2) * 16); } - dyadic_synthesize(1, 32, 32, buffer2, 32, output, 32); + vp9_short_idct16x16_c_f(input + 16 * short_pitch, buffer, pitch); + for (i = 0; i < 16; ++i) { + vpx_memcpy(buffer2 + i * 32 + 16 * 32, buffer + i * 16, + sizeof(*buffer2) * 16); + } + vp9_short_idct16x16_c_f(input + 16 * short_pitch + 16, buffer, pitch); + for (i = 0; i < 16; ++i) { + vpx_memcpy(buffer2 + i * 32 + 16 * 33, buffer + i * 16, + sizeof(*buffer2) * 16); + } +#if DWT_TYPE == 26 + dyadic_synthesize_26(1, 32, 32, buffer2, 32, output, 32); +#elif DWT_TYPE == 97 + dyadic_synthesize_97(1, 32, 32, buffer2, 32, output, 32); +#elif DWT_TYPE == 53 + dyadic_synthesize_53(1, 32, 32, buffer2, 32, output, 32); +#endif } #endif // CONFIG_DWT32X32HYBRID #endif // CONFIG_TX32X32 diff --git a/vp9/encoder/vp9_dct.c b/vp9/encoder/vp9_dct.c index 0fc8fa35e..90baafe53 100644 --- a/vp9/encoder/vp9_dct.c +++ b/vp9/encoder/vp9_dct.c @@ -902,23 +902,24 @@ void vp9_short_walsh8x4_x8_c(short *input, short *output, int pitch) { #define TEST_INT_16x16_DCT 1 #if !TEST_INT_16x16_DCT -static const double C1 = 0.995184726672197; -static const double C2 = 0.98078528040323; -static const double C3 = 0.956940335732209; -static const double C4 = 0.923879532511287; -static const double C5 = 0.881921264348355; -static const double C6 = 0.831469612302545; -static const double C7 = 0.773010453362737; -static const double C8 = 0.707106781186548; -static const double C9 = 0.634393284163646; -static const double C10 = 0.555570233019602; -static const double C11 = 0.471396736825998; -static const double C12 = 0.38268343236509; -static const double C13 = 0.290284677254462; -static const double C14 = 0.195090322016128; -static const double C15 = 0.098017140329561; static void dct16x16_1d(double input[16], double output[16]) { + static const double C1 = 0.995184726672197; + static const double C2 = 0.98078528040323; + static const double C3 = 0.956940335732209; + static const double C4 = 0.923879532511287; + static const double C5 = 0.881921264348355; + static const double C6 = 0.831469612302545; + static const double C7 = 0.773010453362737; + static const double C8 = 0.707106781186548; + static const double C9 = 0.634393284163646; + static const double C10 = 0.555570233019602; + static const double C11 = 0.471396736825998; + static const double C12 = 0.38268343236509; + static const double C13 = 0.290284677254462; + static const double C14 = 0.195090322016128; + static const double C15 = 0.098017140329561; + vp9_clear_system_state(); // Make it simd safe : __asm emms; { double step[16]; @@ -1686,15 +1687,18 @@ void vp9_short_fdct32x32_c(int16_t *input, int16_t *out, int pitch) { #else // CONFIG_DWT32X32HYBRID -#define MAX_BLOCK_LENGTH 64 -#define ENH_PRECISION_BITS 1 -#define ENH_PRECISION_RND ((1 << ENH_PRECISION_BITS) / 2) +#define DWT_MAX_LENGTH 64 +#define DWT_TYPE 26 // 26/53/97 +#define DWT_PRECISION_BITS 2 +#define DWT_PRECISION_RND ((1 << DWT_PRECISION_BITS) / 2) + +#if DWT_TYPE == 53 // Note: block length must be even for this implementation static void analysis_53_row(int length, short *x, short *lowpass, short *highpass) { int n; - short r, * a, * b; + short r, *a, *b; n = length >> 1; b = highpass; @@ -1720,7 +1724,7 @@ static void analysis_53_row(int length, short *x, static void analysis_53_col(int length, short *x, short *lowpass, short *highpass) { int n; - short r, * a, * b; + short r, *a, *b; n = length >> 1; b = highpass; @@ -1743,15 +1747,13 @@ static void analysis_53_col(int length, short *x, } } -// NOTE: Using a 5/3 integer wavelet for now. Explore using a wavelet -// with a better response later -static void dyadic_analyze(int levels, int width, int height, - short *x, int pitch_x, short *c, int pitch_c) { +static void dyadic_analyze_53(int levels, int width, int height, + short *x, int pitch_x, short *c, int pitch_c) { int lv, i, j, nh, nw, hh = height, hw = width; - short buffer[2 * MAX_BLOCK_LENGTH]; + short buffer[2 * DWT_MAX_LENGTH]; for (i = 0; i < height; i++) { for (j = 0; j < width; j++) { - c[i * pitch_c + j] = x[i * pitch_x + j] << ENH_PRECISION_BITS; + c[i * pitch_c + j] = x[i * pitch_x + j] << DWT_PRECISION_BITS; } } for (lv = 0; lv < levels; lv++) { @@ -1774,17 +1776,398 @@ static void dyadic_analyze(int levels, int width, int height, } } +#elif DWT_TYPE == 26 + +static void analysis_26_row(int length, short *x, + short *lowpass, short *highpass) { + int i, n; + short r, s, *a, *b; + a = lowpass; + b = highpass; + for (i = length >> 1; i; i--) { + r = *x++; + s = *x++; + *a++ = r + s; + *b++ = r - s; + } + n = length >> 1; + if (n >= 4) { + a = lowpass; + b = highpass; + r = *lowpass; + while (--n) { + *b++ -= (r - a[1] + 4) >> 3; + r = *a++; + } + *b -= (r - *a + 4) >> 3; + } +} + +static void analysis_26_col(int length, short *x, + short *lowpass, short *highpass) { + int i, n; + short r, s, *a, *b; + a = lowpass; + b = highpass; + for (i = length >> 1; i; i--) { + r = *x++; + s = *x++; + *a++ = (r + s + 1) >> 1; + *b++ = (r - s + 1) >> 1; + } + n = length >> 1; + if (n >= 4) { + a = lowpass; + b = highpass; + r = *lowpass; + while (--n) { + *b++ -= (r - a[1] + 4) >> 3; + r = *a++; + } + *b -= (r - *a + 4) >> 3; + } +} + +static void dyadic_analyze_26(int levels, int width, int height, + short *x, int pitch_x, short *c, int pitch_c) { + int lv, i, j, nh, nw, hh = height, hw = width; + short buffer[2 * DWT_MAX_LENGTH]; + for (i = 0; i < height; i++) { + for (j = 0; j < width; j++) { + c[i * pitch_c + j] = x[i * pitch_x + j] << DWT_PRECISION_BITS; + } + } + for (lv = 0; lv < levels; lv++) { + nh = hh; + hh = (hh + 1) >> 1; + nw = hw; + hw = (hw + 1) >> 1; + if ((nh < 2) || (nw < 2)) return; + for (i = 0; i < nh; i++) { + memcpy(buffer, &c[i * pitch_c], nw * sizeof(short)); + analysis_26_row(nw, buffer, &c[i * pitch_c], &c[i * pitch_c] + hw); + } + for (j = 0; j < nw; j++) { + for (i = 0; i < nh; i++) + buffer[i + nh] = c[i * pitch_c + j]; + analysis_26_col(nh, buffer + nh, buffer, buffer + hh); + for (i = 0; i < nh; i++) + c[i * pitch_c + j] = buffer[i]; + } + } +} + +#elif DWT_TYPE == 97 + +static void analysis_97(int length, double *x, + double *lowpass, double *highpass) { + static const double a_predict1 = -1.586134342; + static const double a_update1 = -0.05298011854; + static const double a_predict2 = 0.8829110762; + static const double a_update2 = 0.4435068522; + static const double s_low = 1.149604398; + static const double s_high = 1/1.149604398; + int i; + double y[DWT_MAX_LENGTH]; + // Predict 1 + for (i = 1; i < length - 2; i += 2) { + x[i] += a_predict1 * (x[i - 1] + x[i + 1]); + } + x[length - 1] += 2 * a_predict1 * x[length - 2]; + // Update 1 + for (i = 2; i < length; i += 2) { + x[i] += a_update1 * (x[i - 1] + x[i + 1]); + } + x[0] += 2 * a_update1 * x[1]; + // Predict 2 + for (i = 1; i < length - 2; i += 2) { + x[i] += a_predict2 * (x[i - 1] + x[i + 1]); + } + x[length - 1] += 2 * a_predict2 * x[length - 2]; + // Update 2 + for (i = 2; i < length; i += 2) { + x[i] += a_update2 * (x[i - 1] + x[i + 1]); + } + x[0] += 2 * a_update2 * x[1]; + memcpy(y, x, sizeof(*y) * length); + // Scale and pack + for (i = 0; i < length / 2; i++) { + lowpass[i] = y[2 * i] * s_low; + highpass[i] = y[2 * i + 1] * s_high; + } +} + +static void dyadic_analyze_97(int levels, int width, int height, + short *x, int pitch_x, short *c, int pitch_c) { + int lv, i, j, nh, nw, hh = height, hw = width; + double buffer[2 * DWT_MAX_LENGTH]; + double y[DWT_MAX_LENGTH * DWT_MAX_LENGTH]; + for (i = 0; i < height; i++) { + for (j = 0; j < width; j++) { + y[i * DWT_MAX_LENGTH + j] = x[i * pitch_x + j] << DWT_PRECISION_BITS; + } + } + for (lv = 0; lv < levels; lv++) { + nh = hh; + hh = (hh + 1) >> 1; + nw = hw; + hw = (hw + 1) >> 1; + if ((nh < 2) || (nw < 2)) return; + for (i = 0; i < nh; i++) { + memcpy(buffer, &y[i * DWT_MAX_LENGTH], nw * sizeof(*buffer)); + analysis_97(nw, buffer, &y[i * DWT_MAX_LENGTH], + &y[i * DWT_MAX_LENGTH] + hw); + } + for (j = 0; j < nw; j++) { + for (i = 0; i < nh; i++) + buffer[i + nh] = y[i * DWT_MAX_LENGTH + j]; + analysis_97(nh, buffer + nh, buffer, buffer + hh); + for (i = 0; i < nh; i++) + c[i * pitch_c + j] = round(buffer[i]); + } + } +} + +#endif // DWT_TYPE + +// TODO(debargha): Implement the scaling differently so as not to have to +// use the floating point dct +static void dct16x16_1d_f(double input[16], double output[16]) { + static const double C1 = 0.995184726672197; + static const double C2 = 0.98078528040323; + static const double C3 = 0.956940335732209; + static const double C4 = 0.923879532511287; + static const double C5 = 0.881921264348355; + static const double C6 = 0.831469612302545; + static const double C7 = 0.773010453362737; + static const double C8 = 0.707106781186548; + static const double C9 = 0.634393284163646; + static const double C10 = 0.555570233019602; + static const double C11 = 0.471396736825998; + static const double C12 = 0.38268343236509; + static const double C13 = 0.290284677254462; + static const double C14 = 0.195090322016128; + static const double C15 = 0.098017140329561; + + vp9_clear_system_state(); // Make it simd safe : __asm emms; + { + double step[16]; + double intermediate[16]; + double temp1, temp2; + + // step 1 + step[ 0] = input[0] + input[15]; + step[ 1] = input[1] + input[14]; + step[ 2] = input[2] + input[13]; + step[ 3] = input[3] + input[12]; + step[ 4] = input[4] + input[11]; + step[ 5] = input[5] + input[10]; + step[ 6] = input[6] + input[ 9]; + step[ 7] = input[7] + input[ 8]; + step[ 8] = input[7] - input[ 8]; + step[ 9] = input[6] - input[ 9]; + step[10] = input[5] - input[10]; + step[11] = input[4] - input[11]; + step[12] = input[3] - input[12]; + step[13] = input[2] - input[13]; + step[14] = input[1] - input[14]; + step[15] = input[0] - input[15]; + + // step 2 + output[0] = step[0] + step[7]; + output[1] = step[1] + step[6]; + output[2] = step[2] + step[5]; + output[3] = step[3] + step[4]; + output[4] = step[3] - step[4]; + output[5] = step[2] - step[5]; + output[6] = step[1] - step[6]; + output[7] = step[0] - step[7]; + + temp1 = step[ 8]*C7; + temp2 = step[15]*C9; + output[ 8] = temp1 + temp2; + + temp1 = step[ 9]*C11; + temp2 = step[14]*C5; + output[ 9] = temp1 - temp2; + + temp1 = step[10]*C3; + temp2 = step[13]*C13; + output[10] = temp1 + temp2; + + temp1 = step[11]*C15; + temp2 = step[12]*C1; + output[11] = temp1 - temp2; + + temp1 = step[11]*C1; + temp2 = step[12]*C15; + output[12] = temp2 + temp1; + + temp1 = step[10]*C13; + temp2 = step[13]*C3; + output[13] = temp2 - temp1; + + temp1 = step[ 9]*C5; + temp2 = step[14]*C11; + output[14] = temp2 + temp1; + + temp1 = step[ 8]*C9; + temp2 = step[15]*C7; + output[15] = temp2 - temp1; + + // step 3 + step[ 0] = output[0] + output[3]; + step[ 1] = output[1] + output[2]; + step[ 2] = output[1] - output[2]; + step[ 3] = output[0] - output[3]; + + temp1 = output[4]*C14; + temp2 = output[7]*C2; + step[ 4] = temp1 + temp2; + + temp1 = output[5]*C10; + temp2 = output[6]*C6; + step[ 5] = temp1 + temp2; + + temp1 = output[5]*C6; + temp2 = output[6]*C10; + step[ 6] = temp2 - temp1; + + temp1 = output[4]*C2; + temp2 = output[7]*C14; + step[ 7] = temp2 - temp1; + + step[ 8] = output[ 8] + output[11]; + step[ 9] = output[ 9] + output[10]; + step[10] = output[ 9] - output[10]; + step[11] = output[ 8] - output[11]; + + step[12] = output[12] + output[15]; + step[13] = output[13] + output[14]; + step[14] = output[13] - output[14]; + step[15] = output[12] - output[15]; + + // step 4 + output[ 0] = (step[ 0] + step[ 1]); + output[ 8] = (step[ 0] - step[ 1]); + + temp1 = step[2]*C12; + temp2 = step[3]*C4; + temp1 = temp1 + temp2; + output[ 4] = 2*(temp1*C8); + + temp1 = step[2]*C4; + temp2 = step[3]*C12; + temp1 = temp2 - temp1; + output[12] = 2*(temp1*C8); + + output[ 2] = 2*((step[4] + step[ 5])*C8); + output[14] = 2*((step[7] - step[ 6])*C8); + + temp1 = step[4] - step[5]; + temp2 = step[6] + step[7]; + output[ 6] = (temp1 + temp2); + output[10] = (temp1 - temp2); + + intermediate[8] = step[8] + step[14]; + intermediate[9] = step[9] + step[15]; + + temp1 = intermediate[8]*C12; + temp2 = intermediate[9]*C4; + temp1 = temp1 - temp2; + output[3] = 2*(temp1*C8); + + temp1 = intermediate[8]*C4; + temp2 = intermediate[9]*C12; + temp1 = temp2 + temp1; + output[13] = 2*(temp1*C8); + + output[ 9] = 2*((step[10] + step[11])*C8); + + intermediate[11] = step[10] - step[11]; + intermediate[12] = step[12] + step[13]; + intermediate[13] = step[12] - step[13]; + intermediate[14] = step[ 8] - step[14]; + intermediate[15] = step[ 9] - step[15]; + + output[15] = (intermediate[11] + intermediate[12]); + output[ 1] = -(intermediate[11] - intermediate[12]); + + output[ 7] = 2*(intermediate[13]*C8); + + temp1 = intermediate[14]*C12; + temp2 = intermediate[15]*C4; + temp1 = temp1 - temp2; + output[11] = -2*(temp1*C8); + + temp1 = intermediate[14]*C4; + temp2 = intermediate[15]*C12; + temp1 = temp2 + temp1; + output[ 5] = 2*(temp1*C8); + } + vp9_clear_system_state(); // Make it simd safe : __asm emms; +} + +void vp9_short_fdct16x16_c_f(short *input, short *out, int pitch) { + vp9_clear_system_state(); // Make it simd safe : __asm emms; + { + int shortpitch = pitch >> 1; + int i, j; + double output[256]; + // First transform columns + for (i = 0; i < 16; i++) { + double temp_in[16], temp_out[16]; + for (j = 0; j < 16; j++) + temp_in[j] = input[j*shortpitch + i]; + dct16x16_1d_f(temp_in, temp_out); + for (j = 0; j < 16; j++) + output[j*16 + i] = temp_out[j]; + } + // Then transform rows + for (i = 0; i < 16; ++i) { + double temp_in[16], temp_out[16]; + for (j = 0; j < 16; ++j) + temp_in[j] = output[j + i*16]; + dct16x16_1d_f(temp_in, temp_out); + for (j = 0; j < 16; ++j) + output[j + i*16] = temp_out[j]; + } + // Scale by some magic number + for (i = 0; i < 256; i++) + out[i] = (short)round(output[i] / (4 << DWT_PRECISION_BITS)); + } + vp9_clear_system_state(); // Make it simd safe : __asm emms; +} + void vp9_short_fdct32x32_c(short *input, short *out, int pitch) { // assume out is a 32x32 buffer short buffer[16 * 16]; int i; const int short_pitch = pitch >> 1; - dyadic_analyze(1, 32, 32, input, short_pitch, out, 32); +#if DWT_TYPE == 26 + dyadic_analyze_26(1, 32, 32, input, short_pitch, out, 32); +#elif DWT_TYPE == 97 + dyadic_analyze_97(1, 32, 32, input, short_pitch, out, 32); +#elif DWT_TYPE == 53 + dyadic_analyze_53(1, 32, 32, input, short_pitch, out, 32); +#endif // TODO(debargha): Implement more efficiently by adding output pitch // argument to the dct16x16 function - vp9_short_fdct16x16_c(out, buffer, 64); + vp9_short_fdct16x16_c_f(out, buffer, 64); for (i = 0; i < 16; ++i) vpx_memcpy(out + i * 32, buffer + i * 16, sizeof(short) * 16); + + vp9_short_fdct16x16_c_f(out + 16, buffer, 64); + for (i = 0; i < 16; ++i) + vpx_memcpy(out + i * 32 + 16, buffer + i * 16, sizeof(short) * 16); + + vp9_short_fdct16x16_c_f(out + 32 * 16, buffer, 64); + for (i = 0; i < 16; ++i) + vpx_memcpy(out + i * 32 + 32 * 16, buffer + i * 16, sizeof(short) * 16); + + vp9_short_fdct16x16_c_f(out + 33 * 16, buffer, 64); + for (i = 0; i < 16; ++i) + vpx_memcpy(out + i * 32 + 33 * 16, buffer + i * 16, sizeof(short) * 16); } #endif // CONFIG_DWT32X32HYBRID #endif // CONFIG_TX32X32