simple_idct.c 66.5 KB
Newer Older
1
/*
2 3 4 5
 * Simple IDCT MMX
 *
 * Copyright (c) 2001, 2002 Michael Niedermayer <michaelni@gmx.at>
 *
6 7 8
 * This file is part of FFmpeg.
 *
 * FFmpeg is free software; you can redistribute it and/or
9 10
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
11
 * version 2.1 of the License, or (at your option) any later version.
12
 *
13
 * FFmpeg is distributed in the hope that it will be useful,
14 15 16 17 18
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
19
 * License along with FFmpeg; if not, write to the Free Software
20
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
21
 */
22

23
#include "libavutil/mem.h"
24
#include "libavutil/x86/asm.h"
25 26 27

#include "libavcodec/idctdsp.h"

28
#include "idctdsp.h"
29
#include "simple_idct.h"
30

31 32
#if HAVE_INLINE_ASM

Michael Niedermayer's avatar
Michael Niedermayer committed
33 34 35 36 37 38 39 40 41 42
/*
23170.475006
22725.260826
21406.727617
19265.545870
16384.000000
12872.826198
8866.956905
4520.335430
*/
43 44 45 46
#define C0 23170 //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
#define C1 22725 //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
#define C2 21407 //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
#define C3 19266 //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
Michael Niedermayer's avatar
Michael Niedermayer committed
47
#define C4 16383 //cos(i*M_PI/16)*sqrt(2)*(1<<14) - 0.5
48
#define C5 12873 //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
49 50
#define C6 8867  //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
#define C7 4520  //cos(i*M_PI/16)*sqrt(2)*(1<<14) + 0.5
51 52 53 54

#define ROW_SHIFT 11
#define COL_SHIFT 20 // 6

55 56
DECLARE_ASM_CONST(8, uint64_t, wm1010)= 0xFFFF0000FFFF0000ULL;
DECLARE_ASM_CONST(8, uint64_t, d40000)= 0x0000000000040000ULL;
57

58
DECLARE_ALIGNED(8, static const int16_t, coeffs)[]= {
59 60 61 62 63 64 65
        1<<(ROW_SHIFT-1), 0, 1<<(ROW_SHIFT-1), 0,
//        1<<(COL_SHIFT-1), 0, 1<<(COL_SHIFT-1), 0,
//        0, 1<<(COL_SHIFT-1-16), 0, 1<<(COL_SHIFT-1-16),
        1<<(ROW_SHIFT-1), 1, 1<<(ROW_SHIFT-1), 0,
        // the 1 = ((1<<(COL_SHIFT-1))/C4)<<ROW_SHIFT :)
//        0, 0, 0, 0,
//        0, 0, 0, 0,
66

67 68
 C4,  C4,  C4,  C4,
 C4, -C4,  C4, -C4,
69

70 71
 C2,  C6,  C2,  C6,
 C6, -C2,  C6, -C2,
72

73 74
 C1,  C3,  C1,  C3,
 C5,  C7,  C5,  C7,
75

76 77
 C3, -C7,  C3, -C7,
-C1, -C5, -C1, -C5,
78

79 80
 C5, -C1,  C5, -C1,
 C7,  C3,  C7,  C3,
81

82 83 84 85
 C7, -C5,  C7, -C5,
 C3, -C1,  C3, -C1
};

86 87
static inline void idct(int16_t *block)
{
88
        LOCAL_ALIGNED_8(int64_t, align_tmp, [16]);
89
        int16_t * const temp= (int16_t*)align_tmp;
90

91
        __asm__ volatile(
92
#if 0 //Alternative, simpler variant
93 94

#define ROW_IDCT(src0, src4, src1, src5, dst, rounder, shift) \
95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq " #src4 ", %%mm1          \n\t" /* R6     R2      r6      r2 */\
        "movq " #src1 ", %%mm2          \n\t" /* R3     R1      r3      r1 */\
        "movq " #src5 ", %%mm3          \n\t" /* R7     R5      r7      r5 */\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 32(%2), %%mm5             \n\t" /* C6     C2      C6      C2 */\
        "pmaddwd %%mm1, %%mm5           \n\t" /* C6R6+C2R2      C6r6+C2r2 */\
        "movq 40(%2), %%mm6             \n\t" /* -C2    C6      -C2     C6 */\
        "pmaddwd %%mm6, %%mm1           \n\t" /* -C2R6+C6R2     -C2r6+C6r2 */\
        "movq 48(%2), %%mm7             \n\t" /* C3     C1      C3      C1 */\
        "pmaddwd %%mm2, %%mm7           \n\t" /* C3R3+C1R1      C3r3+C1r1 */\
        #rounder ", %%mm4               \n\t"\
        "movq %%mm4, %%mm6              \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "paddd %%mm5, %%mm4             \n\t" /* A0             a0 */\
        "psubd %%mm5, %%mm6             \n\t" /* A3             a3 */\
        "movq 56(%2), %%mm5             \n\t" /* C7     C5      C7      C5 */\
        "pmaddwd %%mm3, %%mm5           \n\t" /* C7R7+C5R5      C7r7+C5r5 */\
        #rounder ", %%mm0               \n\t"\
        "paddd %%mm0, %%mm1             \n\t" /* A1             a1 */\
        "paddd %%mm0, %%mm0             \n\t" \
        "psubd %%mm1, %%mm0             \n\t" /* A2             a2 */\
        "pmaddwd 64(%2), %%mm2          \n\t" /* -C7R3+C3R1     -C7r3+C3r1 */\
        "paddd %%mm5, %%mm7             \n\t" /* B0             b0 */\
        "movq 72(%2), %%mm5             \n\t" /* -C5    -C1     -C5     -C1 */\
        "pmaddwd %%mm3, %%mm5           \n\t" /* -C5R7-C1R5     -C5r7-C1r5 */\
        "paddd %%mm4, %%mm7             \n\t" /* A0+B0          a0+b0 */\
        "paddd %%mm4, %%mm4             \n\t" /* 2A0            2a0 */\
        "psubd %%mm7, %%mm4             \n\t" /* A0-B0          a0-b0 */\
        "paddd %%mm2, %%mm5             \n\t" /* B1             b1 */\
        "psrad $" #shift ", %%mm7       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "movq %%mm1, %%mm2              \n\t" /* A1             a1 */\
        "paddd %%mm5, %%mm1             \n\t" /* A1+B1          a1+b1 */\
        "psubd %%mm5, %%mm2             \n\t" /* A1-B1          a1-b1 */\
        "psrad $" #shift ", %%mm1       \n\t"\
        "psrad $" #shift ", %%mm2       \n\t"\
        "packssdw %%mm1, %%mm7          \n\t" /* A1+B1  a1+b1   A0+B0   a0+b0 */\
        "packssdw %%mm4, %%mm2          \n\t" /* A0-B0  a0-b0   A1-B1   a1-b1 */\
        "movq %%mm7, " #dst "           \n\t"\
        "movq " #src1 ", %%mm1          \n\t" /* R3     R1      r3      r1 */\
        "movq 80(%2), %%mm4             \n\t" /* -C1    C5      -C1     C5 */\
        "movq %%mm2, 24+" #dst "        \n\t"\
        "pmaddwd %%mm1, %%mm4           \n\t" /* -C1R3+C5R1     -C1r3+C5r1 */\
        "movq 88(%2), %%mm7             \n\t" /* C3     C7      C3      C7 */\
        "pmaddwd 96(%2), %%mm1          \n\t" /* -C5R3+C7R1     -C5r3+C7r1 */\
        "pmaddwd %%mm3, %%mm7           \n\t" /* C3R7+C7R5      C3r7+C7r5 */\
        "movq %%mm0, %%mm2              \n\t" /* A2             a2 */\
        "pmaddwd 104(%2), %%mm3         \n\t" /* -C1R7+C3R5     -C1r7+C3r5 */\
        "paddd %%mm7, %%mm4             \n\t" /* B2             b2 */\
        "paddd %%mm4, %%mm2             \n\t" /* A2+B2          a2+b2 */\
        "psubd %%mm4, %%mm0             \n\t" /* a2-B2          a2-b2 */\
        "psrad $" #shift ", %%mm2       \n\t"\
        "psrad $" #shift ", %%mm0       \n\t"\
        "movq %%mm6, %%mm4              \n\t" /* A3             a3 */\
        "paddd %%mm1, %%mm3             \n\t" /* B3             b3 */\
        "paddd %%mm3, %%mm6             \n\t" /* A3+B3          a3+b3 */\
        "psubd %%mm3, %%mm4             \n\t" /* a3-B3          a3-b3 */\
        "psrad $" #shift ", %%mm6       \n\t"\
        "packssdw %%mm6, %%mm2          \n\t" /* A3+B3  a3+b3   A2+B2   a2+b2 */\
        "movq %%mm2, 8+" #dst "         \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "packssdw %%mm0, %%mm4          \n\t" /* A2-B2  a2-b2   A3-B3   a3-b3 */\
        "movq %%mm4, 16+" #dst "        \n\t"\
161

162
#define COL_IDCT(src0, src4, src1, src5, dst, shift) \
163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq " #src4 ", %%mm1          \n\t" /* R6     R2      r6      r2 */\
        "movq " #src1 ", %%mm2          \n\t" /* R3     R1      r3      r1 */\
        "movq " #src5 ", %%mm3          \n\t" /* R7     R5      r7      r5 */\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 32(%2), %%mm5             \n\t" /* C6     C2      C6      C2 */\
        "pmaddwd %%mm1, %%mm5           \n\t" /* C6R6+C2R2      C6r6+C2r2 */\
        "movq 40(%2), %%mm6             \n\t" /* -C2    C6      -C2     C6 */\
        "pmaddwd %%mm6, %%mm1           \n\t" /* -C2R6+C6R2     -C2r6+C6r2 */\
        "movq %%mm4, %%mm6              \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 48(%2), %%mm7             \n\t" /* C3     C1      C3      C1 */\
        "pmaddwd %%mm2, %%mm7           \n\t" /* C3R3+C1R1      C3r3+C1r1 */\
        "paddd %%mm5, %%mm4             \n\t" /* A0             a0 */\
        "psubd %%mm5, %%mm6             \n\t" /* A3             a3 */\
        "movq %%mm0, %%mm5              \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "paddd %%mm1, %%mm0             \n\t" /* A1             a1 */\
        "psubd %%mm1, %%mm5             \n\t" /* A2             a2 */\
        "movq 56(%2), %%mm1             \n\t" /* C7     C5      C7      C5 */\
        "pmaddwd %%mm3, %%mm1           \n\t" /* C7R7+C5R5      C7r7+C5r5 */\
        "pmaddwd 64(%2), %%mm2          \n\t" /* -C7R3+C3R1     -C7r3+C3r1 */\
        "paddd %%mm1, %%mm7             \n\t" /* B0             b0 */\
        "movq 72(%2), %%mm1             \n\t" /* -C5    -C1     -C5     -C1 */\
        "pmaddwd %%mm3, %%mm1           \n\t" /* -C5R7-C1R5     -C5r7-C1r5 */\
        "paddd %%mm4, %%mm7             \n\t" /* A0+B0          a0+b0 */\
        "paddd %%mm4, %%mm4             \n\t" /* 2A0            2a0 */\
        "psubd %%mm7, %%mm4             \n\t" /* A0-B0          a0-b0 */\
        "paddd %%mm2, %%mm1             \n\t" /* B1             b1 */\
        "psrad $" #shift ", %%mm7       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "movq %%mm0, %%mm2              \n\t" /* A1             a1 */\
        "paddd %%mm1, %%mm0             \n\t" /* A1+B1          a1+b1 */\
        "psubd %%mm1, %%mm2             \n\t" /* A1-B1          a1-b1 */\
        "psrad $" #shift ", %%mm0       \n\t"\
        "psrad $" #shift ", %%mm2       \n\t"\
        "packssdw %%mm7, %%mm7          \n\t" /* A0+B0  a0+b0 */\
        "movd %%mm7, " #dst "           \n\t"\
        "packssdw %%mm0, %%mm0          \n\t" /* A1+B1  a1+b1 */\
        "movd %%mm0, 16+" #dst "        \n\t"\
        "packssdw %%mm2, %%mm2          \n\t" /* A1-B1  a1-b1 */\
        "movd %%mm2, 96+" #dst "        \n\t"\
        "packssdw %%mm4, %%mm4          \n\t" /* A0-B0  a0-b0 */\
        "movd %%mm4, 112+" #dst "       \n\t"\
        "movq " #src1 ", %%mm0          \n\t" /* R3     R1      r3      r1 */\
        "movq 80(%2), %%mm4             \n\t" /* -C1    C5      -C1     C5 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* -C1R3+C5R1     -C1r3+C5r1 */\
        "movq 88(%2), %%mm7             \n\t" /* C3     C7      C3      C7 */\
        "pmaddwd 96(%2), %%mm0          \n\t" /* -C5R3+C7R1     -C5r3+C7r1 */\
        "pmaddwd %%mm3, %%mm7           \n\t" /* C3R7+C7R5      C3r7+C7r5 */\
        "movq %%mm5, %%mm2              \n\t" /* A2             a2 */\
        "pmaddwd 104(%2), %%mm3         \n\t" /* -C1R7+C3R5     -C1r7+C3r5 */\
        "paddd %%mm7, %%mm4             \n\t" /* B2             b2 */\
        "paddd %%mm4, %%mm2             \n\t" /* A2+B2          a2+b2 */\
        "psubd %%mm4, %%mm5             \n\t" /* a2-B2          a2-b2 */\
        "psrad $" #shift ", %%mm2       \n\t"\
        "psrad $" #shift ", %%mm5       \n\t"\
        "movq %%mm6, %%mm4              \n\t" /* A3             a3 */\
        "paddd %%mm0, %%mm3             \n\t" /* B3             b3 */\
        "paddd %%mm3, %%mm6             \n\t" /* A3+B3          a3+b3 */\
        "psubd %%mm3, %%mm4             \n\t" /* a3-B3          a3-b3 */\
        "psrad $" #shift ", %%mm6       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "packssdw %%mm2, %%mm2          \n\t" /* A2+B2  a2+b2 */\
        "packssdw %%mm6, %%mm6          \n\t" /* A3+B3  a3+b3 */\
        "movd %%mm2, 32+" #dst "        \n\t"\
        "packssdw %%mm4, %%mm4          \n\t" /* A3-B3  a3-b3 */\
        "packssdw %%mm5, %%mm5          \n\t" /* A2-B2  a2-b2 */\
        "movd %%mm6, 48+" #dst "        \n\t"\
        "movd %%mm4, 64+" #dst "        \n\t"\
        "movd %%mm5, 80+" #dst "        \n\t"\
235

236

237
#define DC_COND_ROW_IDCT(src0, src4, src1, src5, dst, rounder, shift) \
238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq " #src4 ", %%mm1          \n\t" /* R6     R2      r6      r2 */\
        "movq " #src1 ", %%mm2          \n\t" /* R3     R1      r3      r1 */\
        "movq " #src5 ", %%mm3          \n\t" /* R7     R5      r7      r5 */\
        "movq "MANGLE(wm1010)", %%mm4   \n\t"\
        "pand %%mm0, %%mm4              \n\t"\
        "por %%mm1, %%mm4               \n\t"\
        "por %%mm2, %%mm4               \n\t"\
        "por %%mm3, %%mm4               \n\t"\
        "packssdw %%mm4,%%mm4           \n\t"\
        "movd %%mm4, %%eax              \n\t"\
        "orl %%eax, %%eax               \n\t"\
        "jz 1f                          \n\t"\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 32(%2), %%mm5             \n\t" /* C6     C2      C6      C2 */\
        "pmaddwd %%mm1, %%mm5           \n\t" /* C6R6+C2R2      C6r6+C2r2 */\
        "movq 40(%2), %%mm6             \n\t" /* -C2    C6      -C2     C6 */\
        "pmaddwd %%mm6, %%mm1           \n\t" /* -C2R6+C6R2     -C2r6+C6r2 */\
        "movq 48(%2), %%mm7             \n\t" /* C3     C1      C3      C1 */\
        "pmaddwd %%mm2, %%mm7           \n\t" /* C3R3+C1R1      C3r3+C1r1 */\
        #rounder ", %%mm4               \n\t"\
        "movq %%mm4, %%mm6              \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "paddd %%mm5, %%mm4             \n\t" /* A0             a0 */\
        "psubd %%mm5, %%mm6             \n\t" /* A3             a3 */\
        "movq 56(%2), %%mm5             \n\t" /* C7     C5      C7      C5 */\
        "pmaddwd %%mm3, %%mm5           \n\t" /* C7R7+C5R5      C7r7+C5r5 */\
        #rounder ", %%mm0               \n\t"\
        "paddd %%mm0, %%mm1             \n\t" /* A1             a1 */\
        "paddd %%mm0, %%mm0             \n\t" \
        "psubd %%mm1, %%mm0             \n\t" /* A2             a2 */\
        "pmaddwd 64(%2), %%mm2          \n\t" /* -C7R3+C3R1     -C7r3+C3r1 */\
        "paddd %%mm5, %%mm7             \n\t" /* B0             b0 */\
        "movq 72(%2), %%mm5             \n\t" /* -C5    -C1     -C5     -C1 */\
        "pmaddwd %%mm3, %%mm5           \n\t" /* -C5R7-C1R5     -C5r7-C1r5 */\
        "paddd %%mm4, %%mm7             \n\t" /* A0+B0          a0+b0 */\
        "paddd %%mm4, %%mm4             \n\t" /* 2A0            2a0 */\
        "psubd %%mm7, %%mm4             \n\t" /* A0-B0          a0-b0 */\
        "paddd %%mm2, %%mm5             \n\t" /* B1             b1 */\
        "psrad $" #shift ", %%mm7       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "movq %%mm1, %%mm2              \n\t" /* A1             a1 */\
        "paddd %%mm5, %%mm1             \n\t" /* A1+B1          a1+b1 */\
        "psubd %%mm5, %%mm2             \n\t" /* A1-B1          a1-b1 */\
        "psrad $" #shift ", %%mm1       \n\t"\
        "psrad $" #shift ", %%mm2       \n\t"\
        "packssdw %%mm1, %%mm7          \n\t" /* A1+B1  a1+b1   A0+B0   a0+b0 */\
        "packssdw %%mm4, %%mm2          \n\t" /* A0-B0  a0-b0   A1-B1   a1-b1 */\
        "movq %%mm7, " #dst "           \n\t"\
        "movq " #src1 ", %%mm1          \n\t" /* R3     R1      r3      r1 */\
        "movq 80(%2), %%mm4             \n\t" /* -C1    C5      -C1     C5 */\
        "movq %%mm2, 24+" #dst "        \n\t"\
        "pmaddwd %%mm1, %%mm4           \n\t" /* -C1R3+C5R1     -C1r3+C5r1 */\
        "movq 88(%2), %%mm7             \n\t" /* C3     C7      C3      C7 */\
        "pmaddwd 96(%2), %%mm1          \n\t" /* -C5R3+C7R1     -C5r3+C7r1 */\
        "pmaddwd %%mm3, %%mm7           \n\t" /* C3R7+C7R5      C3r7+C7r5 */\
        "movq %%mm0, %%mm2              \n\t" /* A2             a2 */\
        "pmaddwd 104(%2), %%mm3         \n\t" /* -C1R7+C3R5     -C1r7+C3r5 */\
        "paddd %%mm7, %%mm4             \n\t" /* B2             b2 */\
        "paddd %%mm4, %%mm2             \n\t" /* A2+B2          a2+b2 */\
        "psubd %%mm4, %%mm0             \n\t" /* a2-B2          a2-b2 */\
        "psrad $" #shift ", %%mm2       \n\t"\
        "psrad $" #shift ", %%mm0       \n\t"\
        "movq %%mm6, %%mm4              \n\t" /* A3             a3 */\
        "paddd %%mm1, %%mm3             \n\t" /* B3             b3 */\
        "paddd %%mm3, %%mm6             \n\t" /* A3+B3          a3+b3 */\
        "psubd %%mm3, %%mm4             \n\t" /* a3-B3          a3-b3 */\
        "psrad $" #shift ", %%mm6       \n\t"\
        "packssdw %%mm6, %%mm2          \n\t" /* A3+B3  a3+b3   A2+B2   a2+b2 */\
        "movq %%mm2, 8+" #dst "         \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "packssdw %%mm0, %%mm4          \n\t" /* A2-B2  a2-b2   A3-B3   a3-b3 */\
        "movq %%mm4, 16+" #dst "        \n\t"\
        "jmp 2f                         \n\t"\
        "1:                             \n\t"\
        "pslld $16, %%mm0               \n\t"\
        "#paddd "MANGLE(d40000)", %%mm0 \n\t"\
        "psrad $13, %%mm0               \n\t"\
        "packssdw %%mm0, %%mm0          \n\t"\
        "movq %%mm0, " #dst "           \n\t"\
        "movq %%mm0, 8+" #dst "         \n\t"\
        "movq %%mm0, 16+" #dst "        \n\t"\
        "movq %%mm0, 24+" #dst "        \n\t"\
        "2:                             \n\t"
324 325


326 327 328 329 330 331 332 333 334 335 336
//IDCT(      src0,   src4,   src1,   src5,    dst,    rounder, shift)
ROW_IDCT(    (%0),  8(%0), 16(%0), 24(%0),  0(%1),paddd 8(%2), 11)
/*ROW_IDCT(  32(%0), 40(%0), 48(%0), 56(%0), 32(%1), paddd (%2), 11)
ROW_IDCT(  64(%0), 72(%0), 80(%0), 88(%0), 64(%1), paddd (%2), 11)
ROW_IDCT(  96(%0),104(%0),112(%0),120(%0), 96(%1), paddd (%2), 11)*/

DC_COND_ROW_IDCT(  32(%0), 40(%0), 48(%0), 56(%0), 32(%1),paddd (%2), 11)
DC_COND_ROW_IDCT(  64(%0), 72(%0), 80(%0), 88(%0), 64(%1),paddd (%2), 11)
DC_COND_ROW_IDCT(  96(%0),104(%0),112(%0),120(%0), 96(%1),paddd (%2), 11)


337 338 339 340 341
//IDCT(      src0,   src4,   src1,    src5,    dst, shift)
COL_IDCT(    (%1), 64(%1), 32(%1),  96(%1),  0(%0), 20)
COL_IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0), 20)
COL_IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0), 20)
COL_IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20)
342

343 344 345
#else

#define DC_COND_IDCT(src0, src4, src1, src5, dst, rounder, shift) \
346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq " #src4 ", %%mm1          \n\t" /* R6     R2      r6      r2 */\
        "movq " #src1 ", %%mm2          \n\t" /* R3     R1      r3      r1 */\
        "movq " #src5 ", %%mm3          \n\t" /* R7     R5      r7      r5 */\
        "movq "MANGLE(wm1010)", %%mm4   \n\t"\
        "pand %%mm0, %%mm4              \n\t"\
        "por %%mm1, %%mm4               \n\t"\
        "por %%mm2, %%mm4               \n\t"\
        "por %%mm3, %%mm4               \n\t"\
        "packssdw %%mm4,%%mm4           \n\t"\
        "movd %%mm4, %%eax              \n\t"\
        "orl %%eax, %%eax               \n\t"\
        "jz 1f                          \n\t"\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 32(%2), %%mm5             \n\t" /* C6     C2      C6      C2 */\
        "pmaddwd %%mm1, %%mm5           \n\t" /* C6R6+C2R2      C6r6+C2r2 */\
        "movq 40(%2), %%mm6             \n\t" /* -C2    C6      -C2     C6 */\
        "pmaddwd %%mm6, %%mm1           \n\t" /* -C2R6+C6R2     -C2r6+C6r2 */\
        "movq 48(%2), %%mm7             \n\t" /* C3     C1      C3      C1 */\
        "pmaddwd %%mm2, %%mm7           \n\t" /* C3R3+C1R1      C3r3+C1r1 */\
        #rounder ", %%mm4               \n\t"\
        "movq %%mm4, %%mm6              \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "paddd %%mm5, %%mm4             \n\t" /* A0             a0 */\
        "psubd %%mm5, %%mm6             \n\t" /* A3             a3 */\
        "movq 56(%2), %%mm5             \n\t" /* C7     C5      C7      C5 */\
        "pmaddwd %%mm3, %%mm5           \n\t" /* C7R7+C5R5      C7r7+C5r5 */\
        #rounder ", %%mm0               \n\t"\
        "paddd %%mm0, %%mm1             \n\t" /* A1             a1 */\
        "paddd %%mm0, %%mm0             \n\t" \
        "psubd %%mm1, %%mm0             \n\t" /* A2             a2 */\
        "pmaddwd 64(%2), %%mm2          \n\t" /* -C7R3+C3R1     -C7r3+C3r1 */\
        "paddd %%mm5, %%mm7             \n\t" /* B0             b0 */\
        "movq 72(%2), %%mm5             \n\t" /* -C5    -C1     -C5     -C1 */\
        "pmaddwd %%mm3, %%mm5           \n\t" /* -C5R7-C1R5     -C5r7-C1r5 */\
        "paddd %%mm4, %%mm7             \n\t" /* A0+B0          a0+b0 */\
        "paddd %%mm4, %%mm4             \n\t" /* 2A0            2a0 */\
        "psubd %%mm7, %%mm4             \n\t" /* A0-B0          a0-b0 */\
        "paddd %%mm2, %%mm5             \n\t" /* B1             b1 */\
        "psrad $" #shift ", %%mm7       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "movq %%mm1, %%mm2              \n\t" /* A1             a1 */\
        "paddd %%mm5, %%mm1             \n\t" /* A1+B1          a1+b1 */\
        "psubd %%mm5, %%mm2             \n\t" /* A1-B1          a1-b1 */\
        "psrad $" #shift ", %%mm1       \n\t"\
        "psrad $" #shift ", %%mm2       \n\t"\
        "packssdw %%mm1, %%mm7          \n\t" /* A1+B1  a1+b1   A0+B0   a0+b0 */\
        "packssdw %%mm4, %%mm2          \n\t" /* A0-B0  a0-b0   A1-B1   a1-b1 */\
        "movq %%mm7, " #dst "           \n\t"\
        "movq " #src1 ", %%mm1          \n\t" /* R3     R1      r3      r1 */\
        "movq 80(%2), %%mm4             \n\t" /* -C1    C5      -C1     C5 */\
        "movq %%mm2, 24+" #dst "        \n\t"\
        "pmaddwd %%mm1, %%mm4           \n\t" /* -C1R3+C5R1     -C1r3+C5r1 */\
        "movq 88(%2), %%mm7             \n\t" /* C3     C7      C3      C7 */\
        "pmaddwd 96(%2), %%mm1          \n\t" /* -C5R3+C7R1     -C5r3+C7r1 */\
        "pmaddwd %%mm3, %%mm7           \n\t" /* C3R7+C7R5      C3r7+C7r5 */\
        "movq %%mm0, %%mm2              \n\t" /* A2             a2 */\
        "pmaddwd 104(%2), %%mm3         \n\t" /* -C1R7+C3R5     -C1r7+C3r5 */\
        "paddd %%mm7, %%mm4             \n\t" /* B2             b2 */\
        "paddd %%mm4, %%mm2             \n\t" /* A2+B2          a2+b2 */\
        "psubd %%mm4, %%mm0             \n\t" /* a2-B2          a2-b2 */\
        "psrad $" #shift ", %%mm2       \n\t"\
        "psrad $" #shift ", %%mm0       \n\t"\
        "movq %%mm6, %%mm4              \n\t" /* A3             a3 */\
        "paddd %%mm1, %%mm3             \n\t" /* B3             b3 */\
        "paddd %%mm3, %%mm6             \n\t" /* A3+B3          a3+b3 */\
        "psubd %%mm3, %%mm4             \n\t" /* a3-B3          a3-b3 */\
        "psrad $" #shift ", %%mm6       \n\t"\
        "packssdw %%mm6, %%mm2          \n\t" /* A3+B3  a3+b3   A2+B2   a2+b2 */\
        "movq %%mm2, 8+" #dst "         \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "packssdw %%mm0, %%mm4          \n\t" /* A2-B2  a2-b2   A3-B3   a3-b3 */\
        "movq %%mm4, 16+" #dst "        \n\t"\
        "jmp 2f                         \n\t"\
        "1:                             \n\t"\
        "pslld $16, %%mm0               \n\t"\
        "paddd "MANGLE(d40000)", %%mm0  \n\t"\
        "psrad $13, %%mm0               \n\t"\
        "packssdw %%mm0, %%mm0          \n\t"\
        "movq %%mm0, " #dst "           \n\t"\
        "movq %%mm0, 8+" #dst "         \n\t"\
        "movq %%mm0, 16+" #dst "        \n\t"\
        "movq %%mm0, 24+" #dst "        \n\t"\
        "2:                             \n\t"
432

433
#define Z_COND_IDCT(src0, src4, src1, src5, dst, rounder, shift, bt) \
434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq " #src4 ", %%mm1          \n\t" /* R6     R2      r6      r2 */\
        "movq " #src1 ", %%mm2          \n\t" /* R3     R1      r3      r1 */\
        "movq " #src5 ", %%mm3          \n\t" /* R7     R5      r7      r5 */\
        "movq %%mm0, %%mm4              \n\t"\
        "por %%mm1, %%mm4               \n\t"\
        "por %%mm2, %%mm4               \n\t"\
        "por %%mm3, %%mm4               \n\t"\
        "packssdw %%mm4,%%mm4           \n\t"\
        "movd %%mm4, %%eax              \n\t"\
        "orl %%eax, %%eax               \n\t"\
        "jz " #bt "                     \n\t"\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 32(%2), %%mm5             \n\t" /* C6     C2      C6      C2 */\
        "pmaddwd %%mm1, %%mm5           \n\t" /* C6R6+C2R2      C6r6+C2r2 */\
        "movq 40(%2), %%mm6             \n\t" /* -C2    C6      -C2     C6 */\
        "pmaddwd %%mm6, %%mm1           \n\t" /* -C2R6+C6R2     -C2r6+C6r2 */\
        "movq 48(%2), %%mm7             \n\t" /* C3     C1      C3      C1 */\
        "pmaddwd %%mm2, %%mm7           \n\t" /* C3R3+C1R1      C3r3+C1r1 */\
        #rounder ", %%mm4               \n\t"\
        "movq %%mm4, %%mm6              \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "paddd %%mm5, %%mm4             \n\t" /* A0             a0 */\
        "psubd %%mm5, %%mm6             \n\t" /* A3             a3 */\
        "movq 56(%2), %%mm5             \n\t" /* C7     C5      C7      C5 */\
        "pmaddwd %%mm3, %%mm5           \n\t" /* C7R7+C5R5      C7r7+C5r5 */\
        #rounder ", %%mm0               \n\t"\
        "paddd %%mm0, %%mm1             \n\t" /* A1             a1 */\
        "paddd %%mm0, %%mm0             \n\t" \
        "psubd %%mm1, %%mm0             \n\t" /* A2             a2 */\
        "pmaddwd 64(%2), %%mm2          \n\t" /* -C7R3+C3R1     -C7r3+C3r1 */\
        "paddd %%mm5, %%mm7             \n\t" /* B0             b0 */\
        "movq 72(%2), %%mm5             \n\t" /* -C5    -C1     -C5     -C1 */\
        "pmaddwd %%mm3, %%mm5           \n\t" /* -C5R7-C1R5     -C5r7-C1r5 */\
        "paddd %%mm4, %%mm7             \n\t" /* A0+B0          a0+b0 */\
        "paddd %%mm4, %%mm4             \n\t" /* 2A0            2a0 */\
        "psubd %%mm7, %%mm4             \n\t" /* A0-B0          a0-b0 */\
        "paddd %%mm2, %%mm5             \n\t" /* B1             b1 */\
        "psrad $" #shift ", %%mm7       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "movq %%mm1, %%mm2              \n\t" /* A1             a1 */\
        "paddd %%mm5, %%mm1             \n\t" /* A1+B1          a1+b1 */\
        "psubd %%mm5, %%mm2             \n\t" /* A1-B1          a1-b1 */\
        "psrad $" #shift ", %%mm1       \n\t"\
        "psrad $" #shift ", %%mm2       \n\t"\
        "packssdw %%mm1, %%mm7          \n\t" /* A1+B1  a1+b1   A0+B0   a0+b0 */\
        "packssdw %%mm4, %%mm2          \n\t" /* A0-B0  a0-b0   A1-B1   a1-b1 */\
        "movq %%mm7, " #dst "           \n\t"\
        "movq " #src1 ", %%mm1          \n\t" /* R3     R1      r3      r1 */\
        "movq 80(%2), %%mm4             \n\t" /* -C1    C5      -C1     C5 */\
        "movq %%mm2, 24+" #dst "        \n\t"\
        "pmaddwd %%mm1, %%mm4           \n\t" /* -C1R3+C5R1     -C1r3+C5r1 */\
        "movq 88(%2), %%mm7             \n\t" /* C3     C7      C3      C7 */\
        "pmaddwd 96(%2), %%mm1          \n\t" /* -C5R3+C7R1     -C5r3+C7r1 */\
        "pmaddwd %%mm3, %%mm7           \n\t" /* C3R7+C7R5      C3r7+C7r5 */\
        "movq %%mm0, %%mm2              \n\t" /* A2             a2 */\
        "pmaddwd 104(%2), %%mm3         \n\t" /* -C1R7+C3R5     -C1r7+C3r5 */\
        "paddd %%mm7, %%mm4             \n\t" /* B2             b2 */\
        "paddd %%mm4, %%mm2             \n\t" /* A2+B2          a2+b2 */\
        "psubd %%mm4, %%mm0             \n\t" /* a2-B2          a2-b2 */\
        "psrad $" #shift ", %%mm2       \n\t"\
        "psrad $" #shift ", %%mm0       \n\t"\
        "movq %%mm6, %%mm4              \n\t" /* A3             a3 */\
        "paddd %%mm1, %%mm3             \n\t" /* B3             b3 */\
        "paddd %%mm3, %%mm6             \n\t" /* A3+B3          a3+b3 */\
        "psubd %%mm3, %%mm4             \n\t" /* a3-B3          a3-b3 */\
        "psrad $" #shift ", %%mm6       \n\t"\
        "packssdw %%mm6, %%mm2          \n\t" /* A3+B3  a3+b3   A2+B2   a2+b2 */\
        "movq %%mm2, 8+" #dst "         \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "packssdw %%mm0, %%mm4          \n\t" /* A2-B2  a2-b2   A3-B3   a3-b3 */\
        "movq %%mm4, 16+" #dst "        \n\t"\
508 509

#define ROW_IDCT(src0, src4, src1, src5, dst, rounder, shift) \
510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq " #src4 ", %%mm1          \n\t" /* R6     R2      r6      r2 */\
        "movq " #src1 ", %%mm2          \n\t" /* R3     R1      r3      r1 */\
        "movq " #src5 ", %%mm3          \n\t" /* R7     R5      r7      r5 */\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 32(%2), %%mm5             \n\t" /* C6     C2      C6      C2 */\
        "pmaddwd %%mm1, %%mm5           \n\t" /* C6R6+C2R2      C6r6+C2r2 */\
        "movq 40(%2), %%mm6             \n\t" /* -C2    C6      -C2     C6 */\
        "pmaddwd %%mm6, %%mm1           \n\t" /* -C2R6+C6R2     -C2r6+C6r2 */\
        "movq 48(%2), %%mm7             \n\t" /* C3     C1      C3      C1 */\
        "pmaddwd %%mm2, %%mm7           \n\t" /* C3R3+C1R1      C3r3+C1r1 */\
        #rounder ", %%mm4               \n\t"\
        "movq %%mm4, %%mm6              \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "paddd %%mm5, %%mm4             \n\t" /* A0             a0 */\
        "psubd %%mm5, %%mm6             \n\t" /* A3             a3 */\
        "movq 56(%2), %%mm5             \n\t" /* C7     C5      C7      C5 */\
        "pmaddwd %%mm3, %%mm5           \n\t" /* C7R7+C5R5      C7r7+C5r5 */\
        #rounder ", %%mm0               \n\t"\
        "paddd %%mm0, %%mm1             \n\t" /* A1             a1 */\
        "paddd %%mm0, %%mm0             \n\t" \
        "psubd %%mm1, %%mm0             \n\t" /* A2             a2 */\
        "pmaddwd 64(%2), %%mm2          \n\t" /* -C7R3+C3R1     -C7r3+C3r1 */\
        "paddd %%mm5, %%mm7             \n\t" /* B0             b0 */\
        "movq 72(%2), %%mm5             \n\t" /* -C5    -C1     -C5     -C1 */\
        "pmaddwd %%mm3, %%mm5           \n\t" /* -C5R7-C1R5     -C5r7-C1r5 */\
        "paddd %%mm4, %%mm7             \n\t" /* A0+B0          a0+b0 */\
        "paddd %%mm4, %%mm4             \n\t" /* 2A0            2a0 */\
        "psubd %%mm7, %%mm4             \n\t" /* A0-B0          a0-b0 */\
        "paddd %%mm2, %%mm5             \n\t" /* B1             b1 */\
        "psrad $" #shift ", %%mm7       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "movq %%mm1, %%mm2              \n\t" /* A1             a1 */\
        "paddd %%mm5, %%mm1             \n\t" /* A1+B1          a1+b1 */\
        "psubd %%mm5, %%mm2             \n\t" /* A1-B1          a1-b1 */\
        "psrad $" #shift ", %%mm1       \n\t"\
        "psrad $" #shift ", %%mm2       \n\t"\
        "packssdw %%mm1, %%mm7          \n\t" /* A1+B1  a1+b1   A0+B0   a0+b0 */\
        "packssdw %%mm4, %%mm2          \n\t" /* A0-B0  a0-b0   A1-B1   a1-b1 */\
        "movq %%mm7, " #dst "           \n\t"\
        "movq " #src1 ", %%mm1          \n\t" /* R3     R1      r3      r1 */\
        "movq 80(%2), %%mm4             \n\t" /* -C1    C5      -C1     C5 */\
        "movq %%mm2, 24+" #dst "        \n\t"\
        "pmaddwd %%mm1, %%mm4           \n\t" /* -C1R3+C5R1     -C1r3+C5r1 */\
        "movq 88(%2), %%mm7             \n\t" /* C3     C7      C3      C7 */\
        "pmaddwd 96(%2), %%mm1          \n\t" /* -C5R3+C7R1     -C5r3+C7r1 */\
        "pmaddwd %%mm3, %%mm7           \n\t" /* C3R7+C7R5      C3r7+C7r5 */\
        "movq %%mm0, %%mm2              \n\t" /* A2             a2 */\
        "pmaddwd 104(%2), %%mm3         \n\t" /* -C1R7+C3R5     -C1r7+C3r5 */\
        "paddd %%mm7, %%mm4             \n\t" /* B2             b2 */\
        "paddd %%mm4, %%mm2             \n\t" /* A2+B2          a2+b2 */\
        "psubd %%mm4, %%mm0             \n\t" /* a2-B2          a2-b2 */\
        "psrad $" #shift ", %%mm2       \n\t"\
        "psrad $" #shift ", %%mm0       \n\t"\
        "movq %%mm6, %%mm4              \n\t" /* A3             a3 */\
        "paddd %%mm1, %%mm3             \n\t" /* B3             b3 */\
        "paddd %%mm3, %%mm6             \n\t" /* A3+B3          a3+b3 */\
        "psubd %%mm3, %%mm4             \n\t" /* a3-B3          a3-b3 */\
        "psrad $" #shift ", %%mm6       \n\t"\
        "packssdw %%mm6, %%mm2          \n\t" /* A3+B3  a3+b3   A2+B2   a2+b2 */\
        "movq %%mm2, 8+" #dst "         \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "packssdw %%mm0, %%mm4          \n\t" /* A2-B2  a2-b2   A3-B3   a3-b3 */\
        "movq %%mm4, 16+" #dst "        \n\t"\
576 577 578 579 580 581 582 583

//IDCT(         src0,   src4,   src1,   src5,    dst,   rounder, shift)
DC_COND_IDCT(  0(%0),  8(%0), 16(%0), 24(%0),  0(%1),paddd 8(%2), 11)
Z_COND_IDCT(  32(%0), 40(%0), 48(%0), 56(%0), 32(%1),paddd (%2), 11, 4f)
Z_COND_IDCT(  64(%0), 72(%0), 80(%0), 88(%0), 64(%1),paddd (%2), 11, 2f)
Z_COND_IDCT(  96(%0),104(%0),112(%0),120(%0), 96(%1),paddd (%2), 11, 1f)

#undef IDCT
584
#define IDCT(src0, src4, src1, src5, dst, shift) \
585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq " #src4 ", %%mm1          \n\t" /* R6     R2      r6      r2 */\
        "movq " #src1 ", %%mm2          \n\t" /* R3     R1      r3      r1 */\
        "movq " #src5 ", %%mm3          \n\t" /* R7     R5      r7      r5 */\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 32(%2), %%mm5             \n\t" /* C6     C2      C6      C2 */\
        "pmaddwd %%mm1, %%mm5           \n\t" /* C6R6+C2R2      C6r6+C2r2 */\
        "movq 40(%2), %%mm6             \n\t" /* -C2    C6      -C2     C6 */\
        "pmaddwd %%mm6, %%mm1           \n\t" /* -C2R6+C6R2     -C2r6+C6r2 */\
        "movq %%mm4, %%mm6              \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 48(%2), %%mm7             \n\t" /* C3     C1      C3      C1 */\
        "pmaddwd %%mm2, %%mm7           \n\t" /* C3R3+C1R1      C3r3+C1r1 */\
        "paddd %%mm5, %%mm4             \n\t" /* A0             a0 */\
        "psubd %%mm5, %%mm6             \n\t" /* A3             a3 */\
        "movq %%mm0, %%mm5              \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "paddd %%mm1, %%mm0             \n\t" /* A1             a1 */\
        "psubd %%mm1, %%mm5             \n\t" /* A2             a2 */\
        "movq 56(%2), %%mm1             \n\t" /* C7     C5      C7      C5 */\
        "pmaddwd %%mm3, %%mm1           \n\t" /* C7R7+C5R5      C7r7+C5r5 */\
        "pmaddwd 64(%2), %%mm2          \n\t" /* -C7R3+C3R1     -C7r3+C3r1 */\
        "paddd %%mm1, %%mm7             \n\t" /* B0             b0 */\
        "movq 72(%2), %%mm1             \n\t" /* -C5    -C1     -C5     -C1 */\
        "pmaddwd %%mm3, %%mm1           \n\t" /* -C5R7-C1R5     -C5r7-C1r5 */\
        "paddd %%mm4, %%mm7             \n\t" /* A0+B0          a0+b0 */\
        "paddd %%mm4, %%mm4             \n\t" /* 2A0            2a0 */\
        "psubd %%mm7, %%mm4             \n\t" /* A0-B0          a0-b0 */\
        "paddd %%mm2, %%mm1             \n\t" /* B1             b1 */\
        "psrad $" #shift ", %%mm7       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "movq %%mm0, %%mm2              \n\t" /* A1             a1 */\
        "paddd %%mm1, %%mm0             \n\t" /* A1+B1          a1+b1 */\
        "psubd %%mm1, %%mm2             \n\t" /* A1-B1          a1-b1 */\
        "psrad $" #shift ", %%mm0       \n\t"\
        "psrad $" #shift ", %%mm2       \n\t"\
        "packssdw %%mm7, %%mm7          \n\t" /* A0+B0  a0+b0 */\
        "movd %%mm7, " #dst "           \n\t"\
        "packssdw %%mm0, %%mm0          \n\t" /* A1+B1  a1+b1 */\
        "movd %%mm0, 16+" #dst "        \n\t"\
        "packssdw %%mm2, %%mm2          \n\t" /* A1-B1  a1-b1 */\
        "movd %%mm2, 96+" #dst "        \n\t"\
        "packssdw %%mm4, %%mm4          \n\t" /* A0-B0  a0-b0 */\
        "movd %%mm4, 112+" #dst "       \n\t"\
        "movq " #src1 ", %%mm0          \n\t" /* R3     R1      r3      r1 */\
        "movq 80(%2), %%mm4             \n\t" /* -C1    C5      -C1     C5 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* -C1R3+C5R1     -C1r3+C5r1 */\
        "movq 88(%2), %%mm7             \n\t" /* C3     C7      C3      C7 */\
        "pmaddwd 96(%2), %%mm0          \n\t" /* -C5R3+C7R1     -C5r3+C7r1 */\
        "pmaddwd %%mm3, %%mm7           \n\t" /* C3R7+C7R5      C3r7+C7r5 */\
        "movq %%mm5, %%mm2              \n\t" /* A2             a2 */\
        "pmaddwd 104(%2), %%mm3         \n\t" /* -C1R7+C3R5     -C1r7+C3r5 */\
        "paddd %%mm7, %%mm4             \n\t" /* B2             b2 */\
        "paddd %%mm4, %%mm2             \n\t" /* A2+B2          a2+b2 */\
        "psubd %%mm4, %%mm5             \n\t" /* a2-B2          a2-b2 */\
        "psrad $" #shift ", %%mm2       \n\t"\
        "psrad $" #shift ", %%mm5       \n\t"\
        "movq %%mm6, %%mm4              \n\t" /* A3             a3 */\
        "paddd %%mm0, %%mm3             \n\t" /* B3             b3 */\
        "paddd %%mm3, %%mm6             \n\t" /* A3+B3          a3+b3 */\
        "psubd %%mm3, %%mm4             \n\t" /* a3-B3          a3-b3 */\
        "psrad $" #shift ", %%mm6       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "packssdw %%mm2, %%mm2          \n\t" /* A2+B2  a2+b2 */\
        "packssdw %%mm6, %%mm6          \n\t" /* A3+B3  a3+b3 */\
        "movd %%mm2, 32+" #dst "        \n\t"\
        "packssdw %%mm4, %%mm4          \n\t" /* A3-B3  a3-b3 */\
        "packssdw %%mm5, %%mm5          \n\t" /* A2-B2  a2-b2 */\
        "movd %%mm6, 48+" #dst "        \n\t"\
        "movd %%mm4, 64+" #dst "        \n\t"\
        "movd %%mm5, 80+" #dst "        \n\t"
657 658


659 660 661 662 663
//IDCT(  src0,   src4,   src1,    src5,    dst, shift)
IDCT(    (%1), 64(%1), 32(%1),  96(%1),  0(%0), 20)
IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0), 20)
IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0), 20)
IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20)
664
        "jmp 9f                         \n\t"
665

666
        "# .p2align 4                   \n\t"\
667
        "4:                             \n\t"
668 669
Z_COND_IDCT(  64(%0), 72(%0), 80(%0), 88(%0), 64(%1),paddd (%2), 11, 6f)
Z_COND_IDCT(  96(%0),104(%0),112(%0),120(%0), 96(%1),paddd (%2), 11, 5f)
670

671
#undef IDCT
672
#define IDCT(src0, src4, src1, src5, dst, shift) \
673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq " #src4 ", %%mm1          \n\t" /* R6     R2      r6      r2 */\
        "movq " #src5 ", %%mm3          \n\t" /* R7     R5      r7      r5 */\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 32(%2), %%mm5             \n\t" /* C6     C2      C6      C2 */\
        "pmaddwd %%mm1, %%mm5           \n\t" /* C6R6+C2R2      C6r6+C2r2 */\
        "movq 40(%2), %%mm6             \n\t" /* -C2    C6      -C2     C6 */\
        "pmaddwd %%mm6, %%mm1           \n\t" /* -C2R6+C6R2     -C2r6+C6r2 */\
        "movq %%mm4, %%mm6              \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "paddd %%mm5, %%mm4             \n\t" /* A0             a0 */\
        "psubd %%mm5, %%mm6             \n\t" /* A3             a3 */\
        "movq %%mm0, %%mm5              \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "paddd %%mm1, %%mm0             \n\t" /* A1             a1 */\
        "psubd %%mm1, %%mm5             \n\t" /* A2             a2 */\
        "movq 56(%2), %%mm1             \n\t" /* C7     C5      C7      C5 */\
        "pmaddwd %%mm3, %%mm1           \n\t" /* C7R7+C5R5      C7r7+C5r5 */\
        "movq 72(%2), %%mm7             \n\t" /* -C5    -C1     -C5     -C1 */\
        "pmaddwd %%mm3, %%mm7           \n\t" /* -C5R7-C1R5     -C5r7-C1r5 */\
        "paddd %%mm4, %%mm1             \n\t" /* A0+B0          a0+b0 */\
        "paddd %%mm4, %%mm4             \n\t" /* 2A0            2a0 */\
        "psubd %%mm1, %%mm4             \n\t" /* A0-B0          a0-b0 */\
        "psrad $" #shift ", %%mm1       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "movq %%mm0, %%mm2              \n\t" /* A1             a1 */\
        "paddd %%mm7, %%mm0             \n\t" /* A1+B1          a1+b1 */\
        "psubd %%mm7, %%mm2             \n\t" /* A1-B1          a1-b1 */\
        "psrad $" #shift ", %%mm0       \n\t"\
        "psrad $" #shift ", %%mm2       \n\t"\
        "packssdw %%mm1, %%mm1          \n\t" /* A0+B0  a0+b0 */\
        "movd %%mm1, " #dst "           \n\t"\
        "packssdw %%mm0, %%mm0          \n\t" /* A1+B1  a1+b1 */\
        "movd %%mm0, 16+" #dst "        \n\t"\
        "packssdw %%mm2, %%mm2          \n\t" /* A1-B1  a1-b1 */\
        "movd %%mm2, 96+" #dst "        \n\t"\
        "packssdw %%mm4, %%mm4          \n\t" /* A0-B0  a0-b0 */\
        "movd %%mm4, 112+" #dst "       \n\t"\
        "movq 88(%2), %%mm1             \n\t" /* C3     C7      C3      C7 */\
        "pmaddwd %%mm3, %%mm1           \n\t" /* C3R7+C7R5      C3r7+C7r5 */\
        "movq %%mm5, %%mm2              \n\t" /* A2             a2 */\
        "pmaddwd 104(%2), %%mm3         \n\t" /* -C1R7+C3R5     -C1r7+C3r5 */\
        "paddd %%mm1, %%mm2             \n\t" /* A2+B2          a2+b2 */\
        "psubd %%mm1, %%mm5             \n\t" /* a2-B2          a2-b2 */\
        "psrad $" #shift ", %%mm2       \n\t"\
        "psrad $" #shift ", %%mm5       \n\t"\
        "movq %%mm6, %%mm1              \n\t" /* A3             a3 */\
        "paddd %%mm3, %%mm6             \n\t" /* A3+B3          a3+b3 */\
        "psubd %%mm3, %%mm1             \n\t" /* a3-B3          a3-b3 */\
        "psrad $" #shift ", %%mm6       \n\t"\
        "psrad $" #shift ", %%mm1       \n\t"\
        "packssdw %%mm2, %%mm2          \n\t" /* A2+B2  a2+b2 */\
        "packssdw %%mm6, %%mm6          \n\t" /* A3+B3  a3+b3 */\
        "movd %%mm2, 32+" #dst "        \n\t"\
        "packssdw %%mm1, %%mm1          \n\t" /* A3-B3  a3-b3 */\
        "packssdw %%mm5, %%mm5          \n\t" /* A2-B2  a2-b2 */\
        "movd %%mm6, 48+" #dst "        \n\t"\
        "movd %%mm1, 64+" #dst "        \n\t"\
        "movd %%mm5, 80+" #dst "        \n\t"
733

734 735 736 737 738
//IDCT(  src0,   src4,   src1,    src5,    dst, shift)
IDCT(    (%1), 64(%1), 32(%1),  96(%1),  0(%0), 20)
IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0), 20)
IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0), 20)
IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20)
739
        "jmp 9f                         \n\t"
740

741
        "# .p2align 4                   \n\t"\
742
        "6:                             \n\t"
743
Z_COND_IDCT(  96(%0),104(%0),112(%0),120(%0), 96(%1),paddd (%2), 11, 7f)
744

745
#undef IDCT
746
#define IDCT(src0, src4, src1, src5, dst, shift) \
747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq " #src5 ", %%mm3          \n\t" /* R7     R5      r7      r5 */\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq %%mm4, %%mm6              \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq %%mm0, %%mm5              \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 56(%2), %%mm1             \n\t" /* C7     C5      C7      C5 */\
        "pmaddwd %%mm3, %%mm1           \n\t" /* C7R7+C5R5      C7r7+C5r5 */\
        "movq 72(%2), %%mm7             \n\t" /* -C5    -C1     -C5     -C1 */\
        "pmaddwd %%mm3, %%mm7           \n\t" /* -C5R7-C1R5     -C5r7-C1r5 */\
        "paddd %%mm4, %%mm1             \n\t" /* A0+B0          a0+b0 */\
        "paddd %%mm4, %%mm4             \n\t" /* 2A0            2a0 */\
        "psubd %%mm1, %%mm4             \n\t" /* A0-B0          a0-b0 */\
        "psrad $" #shift ", %%mm1       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "movq %%mm0, %%mm2              \n\t" /* A1             a1 */\
        "paddd %%mm7, %%mm0             \n\t" /* A1+B1          a1+b1 */\
        "psubd %%mm7, %%mm2             \n\t" /* A1-B1          a1-b1 */\
        "psrad $" #shift ", %%mm0       \n\t"\
        "psrad $" #shift ", %%mm2       \n\t"\
        "packssdw %%mm1, %%mm1          \n\t" /* A0+B0  a0+b0 */\
        "movd %%mm1, " #dst "           \n\t"\
        "packssdw %%mm0, %%mm0          \n\t" /* A1+B1  a1+b1 */\
        "movd %%mm0, 16+" #dst "        \n\t"\
        "packssdw %%mm2, %%mm2          \n\t" /* A1-B1  a1-b1 */\
        "movd %%mm2, 96+" #dst "        \n\t"\
        "packssdw %%mm4, %%mm4          \n\t" /* A0-B0  a0-b0 */\
        "movd %%mm4, 112+" #dst "       \n\t"\
        "movq 88(%2), %%mm1             \n\t" /* C3     C7      C3      C7 */\
        "pmaddwd %%mm3, %%mm1           \n\t" /* C3R7+C7R5      C3r7+C7r5 */\
        "movq %%mm5, %%mm2              \n\t" /* A2             a2 */\
        "pmaddwd 104(%2), %%mm3         \n\t" /* -C1R7+C3R5     -C1r7+C3r5 */\
        "paddd %%mm1, %%mm2             \n\t" /* A2+B2          a2+b2 */\
        "psubd %%mm1, %%mm5             \n\t" /* a2-B2          a2-b2 */\
        "psrad $" #shift ", %%mm2       \n\t"\
        "psrad $" #shift ", %%mm5       \n\t"\
        "movq %%mm6, %%mm1              \n\t" /* A3             a3 */\
        "paddd %%mm3, %%mm6             \n\t" /* A3+B3          a3+b3 */\
        "psubd %%mm3, %%mm1             \n\t" /* a3-B3          a3-b3 */\
        "psrad $" #shift ", %%mm6       \n\t"\
        "psrad $" #shift ", %%mm1       \n\t"\
        "packssdw %%mm2, %%mm2          \n\t" /* A2+B2  a2+b2 */\
        "packssdw %%mm6, %%mm6          \n\t" /* A3+B3  a3+b3 */\
        "movd %%mm2, 32+" #dst "        \n\t"\
        "packssdw %%mm1, %%mm1          \n\t" /* A3-B3  a3-b3 */\
        "packssdw %%mm5, %%mm5          \n\t" /* A2-B2  a2-b2 */\
        "movd %%mm6, 48+" #dst "        \n\t"\
        "movd %%mm1, 64+" #dst "        \n\t"\
        "movd %%mm5, 80+" #dst "        \n\t"
798 799


800 801 802 803 804
//IDCT(  src0,   src4,   src1,    src5,    dst, shift)
IDCT(    (%1), 64(%1), 32(%1),  96(%1),  0(%0), 20)
IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0), 20)
IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0), 20)
IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20)
805
        "jmp 9f                         \n\t"
806

807
        "# .p2align 4                   \n\t"\
808
        "2:                             \n\t"
809
Z_COND_IDCT(  96(%0),104(%0),112(%0),120(%0), 96(%1),paddd (%2), 11, 3f)
810

811
#undef IDCT
812
#define IDCT(src0, src4, src1, src5, dst, shift) \
813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq " #src1 ", %%mm2          \n\t" /* R3     R1      r3      r1 */\
        "movq " #src5 ", %%mm3          \n\t" /* R7     R5      r7      r5 */\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq %%mm4, %%mm6              \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 48(%2), %%mm7             \n\t" /* C3     C1      C3      C1 */\
        "pmaddwd %%mm2, %%mm7           \n\t" /* C3R3+C1R1      C3r3+C1r1 */\
        "movq %%mm0, %%mm5              \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 56(%2), %%mm1             \n\t" /* C7     C5      C7      C5 */\
        "pmaddwd %%mm3, %%mm1           \n\t" /* C7R7+C5R5      C7r7+C5r5 */\
        "pmaddwd 64(%2), %%mm2          \n\t" /* -C7R3+C3R1     -C7r3+C3r1 */\
        "paddd %%mm1, %%mm7             \n\t" /* B0             b0 */\
        "movq 72(%2), %%mm1             \n\t" /* -C5    -C1     -C5     -C1 */\
        "pmaddwd %%mm3, %%mm1           \n\t" /* -C5R7-C1R5     -C5r7-C1r5 */\
        "paddd %%mm4, %%mm7             \n\t" /* A0+B0          a0+b0 */\
        "paddd %%mm4, %%mm4             \n\t" /* 2A0            2a0 */\
        "psubd %%mm7, %%mm4             \n\t" /* A0-B0          a0-b0 */\
        "paddd %%mm2, %%mm1             \n\t" /* B1             b1 */\
        "psrad $" #shift ", %%mm7       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "movq %%mm0, %%mm2              \n\t" /* A1             a1 */\
        "paddd %%mm1, %%mm0             \n\t" /* A1+B1          a1+b1 */\
        "psubd %%mm1, %%mm2             \n\t" /* A1-B1          a1-b1 */\
        "psrad $" #shift ", %%mm0       \n\t"\
        "psrad $" #shift ", %%mm2       \n\t"\
        "packssdw %%mm7, %%mm7          \n\t" /* A0+B0  a0+b0 */\
        "movd %%mm7, " #dst "           \n\t"\
        "packssdw %%mm0, %%mm0          \n\t" /* A1+B1  a1+b1 */\
        "movd %%mm0, 16+" #dst "        \n\t"\
        "packssdw %%mm2, %%mm2          \n\t" /* A1-B1  a1-b1 */\
        "movd %%mm2, 96+" #dst "        \n\t"\
        "packssdw %%mm4, %%mm4          \n\t" /* A0-B0  a0-b0 */\
        "movd %%mm4, 112+" #dst "       \n\t"\
        "movq " #src1 ", %%mm0          \n\t" /* R3     R1      r3      r1 */\
        "movq 80(%2), %%mm4             \n\t" /* -C1    C5      -C1     C5 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* -C1R3+C5R1     -C1r3+C5r1 */\
        "movq 88(%2), %%mm7             \n\t" /* C3     C7      C3      C7 */\
        "pmaddwd 96(%2), %%mm0          \n\t" /* -C5R3+C7R1     -C5r3+C7r1 */\
        "pmaddwd %%mm3, %%mm7           \n\t" /* C3R7+C7R5      C3r7+C7r5 */\
        "movq %%mm5, %%mm2              \n\t" /* A2             a2 */\
        "pmaddwd 104(%2), %%mm3         \n\t" /* -C1R7+C3R5     -C1r7+C3r5 */\
        "paddd %%mm7, %%mm4             \n\t" /* B2             b2 */\
        "paddd %%mm4, %%mm2             \n\t" /* A2+B2          a2+b2 */\
        "psubd %%mm4, %%mm5             \n\t" /* a2-B2          a2-b2 */\
        "psrad $" #shift ", %%mm2       \n\t"\
        "psrad $" #shift ", %%mm5       \n\t"\
        "movq %%mm6, %%mm4              \n\t" /* A3             a3 */\
        "paddd %%mm0, %%mm3             \n\t" /* B3             b3 */\
        "paddd %%mm3, %%mm6             \n\t" /* A3+B3          a3+b3 */\
        "psubd %%mm3, %%mm4             \n\t" /* a3-B3          a3-b3 */\
        "psrad $" #shift ", %%mm6       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "packssdw %%mm2, %%mm2          \n\t" /* A2+B2  a2+b2 */\
        "packssdw %%mm6, %%mm6          \n\t" /* A3+B3  a3+b3 */\
        "movd %%mm2, 32+" #dst "        \n\t"\
        "packssdw %%mm4, %%mm4          \n\t" /* A3-B3  a3-b3 */\
        "packssdw %%mm5, %%mm5          \n\t" /* A2-B2  a2-b2 */\
        "movd %%mm6, 48+" #dst "        \n\t"\
        "movd %%mm4, 64+" #dst "        \n\t"\
        "movd %%mm5, 80+" #dst "        \n\t"
876

877 878 879 880 881
//IDCT(  src0,   src4,   src1,    src5,    dst, shift)
IDCT(    (%1), 64(%1), 32(%1),  96(%1),  0(%0), 20)
IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0), 20)
IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0), 20)
IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20)
882
        "jmp 9f                         \n\t"
883

884
        "# .p2align 4                   \n\t"\
885
        "3:                             \n\t"
886
#undef IDCT
887
#define IDCT(src0, src4, src1, src5, dst, shift) \
888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq " #src1 ", %%mm2          \n\t" /* R3     R1      r3      r1 */\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq %%mm4, %%mm6              \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 48(%2), %%mm7             \n\t" /* C3     C1      C3      C1 */\
        "pmaddwd %%mm2, %%mm7           \n\t" /* C3R3+C1R1      C3r3+C1r1 */\
        "movq %%mm0, %%mm5              \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 64(%2), %%mm3             \n\t"\
        "pmaddwd %%mm2, %%mm3           \n\t" /* -C7R3+C3R1     -C7r3+C3r1 */\
        "paddd %%mm4, %%mm7             \n\t" /* A0+B0          a0+b0 */\
        "paddd %%mm4, %%mm4             \n\t" /* 2A0            2a0 */\
        "psubd %%mm7, %%mm4             \n\t" /* A0-B0          a0-b0 */\
        "psrad $" #shift ", %%mm7       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "movq %%mm0, %%mm1              \n\t" /* A1             a1 */\
        "paddd %%mm3, %%mm0             \n\t" /* A1+B1          a1+b1 */\
        "psubd %%mm3, %%mm1             \n\t" /* A1-B1          a1-b1 */\
        "psrad $" #shift ", %%mm0       \n\t"\
        "psrad $" #shift ", %%mm1       \n\t"\
        "packssdw %%mm7, %%mm7          \n\t" /* A0+B0  a0+b0 */\
        "movd %%mm7, " #dst "           \n\t"\
        "packssdw %%mm0, %%mm0          \n\t" /* A1+B1  a1+b1 */\
        "movd %%mm0, 16+" #dst "        \n\t"\
        "packssdw %%mm1, %%mm1          \n\t" /* A1-B1  a1-b1 */\
        "movd %%mm1, 96+" #dst "        \n\t"\
        "packssdw %%mm4, %%mm4          \n\t" /* A0-B0  a0-b0 */\
        "movd %%mm4, 112+" #dst "       \n\t"\
        "movq 80(%2), %%mm4             \n\t" /* -C1    C5      -C1     C5 */\
        "pmaddwd %%mm2, %%mm4           \n\t" /* -C1R3+C5R1     -C1r3+C5r1 */\
        "pmaddwd 96(%2), %%mm2          \n\t" /* -C5R3+C7R1     -C5r3+C7r1 */\
        "movq %%mm5, %%mm1              \n\t" /* A2             a2 */\
        "paddd %%mm4, %%mm1             \n\t" /* A2+B2          a2+b2 */\
        "psubd %%mm4, %%mm5             \n\t" /* a2-B2          a2-b2 */\
        "psrad $" #shift ", %%mm1       \n\t"\
        "psrad $" #shift ", %%mm5       \n\t"\
        "movq %%mm6, %%mm4              \n\t" /* A3             a3 */\
        "paddd %%mm2, %%mm6             \n\t" /* A3+B3          a3+b3 */\
        "psubd %%mm2, %%mm4             \n\t" /* a3-B3          a3-b3 */\
        "psrad $" #shift ", %%mm6       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "packssdw %%mm1, %%mm1          \n\t" /* A2+B2  a2+b2 */\
        "packssdw %%mm6, %%mm6          \n\t" /* A3+B3  a3+b3 */\
        "movd %%mm1, 32+" #dst "        \n\t"\
        "packssdw %%mm4, %%mm4          \n\t" /* A3-B3  a3-b3 */\
        "packssdw %%mm5, %%mm5          \n\t" /* A2-B2  a2-b2 */\
        "movd %%mm6, 48+" #dst "        \n\t"\
        "movd %%mm4, 64+" #dst "        \n\t"\
        "movd %%mm5, 80+" #dst "        \n\t"
939 940


941 942 943 944 945
//IDCT(  src0,   src4,   src1,    src5,    dst, shift)
IDCT(    (%1), 64(%1), 32(%1),  96(%1),  0(%0), 20)
IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0), 20)
IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0), 20)
IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20)
946
        "jmp 9f                         \n\t"
947

948
        "# .p2align 4                   \n\t"\
949
        "5:                             \n\t"
950
#undef IDCT
951
#define IDCT(src0, src4, src1, src5, dst, shift) \
952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq " #src4 ", %%mm1          \n\t" /* R6     R2      r6      r2 */\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 32(%2), %%mm5             \n\t" /* C6     C2      C6      C2 */\
        "pmaddwd %%mm1, %%mm5           \n\t" /* C6R6+C2R2      C6r6+C2r2 */\
        "movq 40(%2), %%mm6             \n\t" /* -C2    C6      -C2     C6 */\
        "pmaddwd %%mm6, %%mm1           \n\t" /* -C2R6+C6R2     -C2r6+C6r2 */\
        "movq %%mm4, %%mm6              \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "paddd %%mm5, %%mm4             \n\t" /* A0             a0 */\
        "psubd %%mm5, %%mm6             \n\t" /* A3             a3 */\
        "movq %%mm0, %%mm5              \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "paddd %%mm1, %%mm0             \n\t" /* A1             a1 */\
        "psubd %%mm1, %%mm5             \n\t" /* A2             a2 */\
        "movq 8+" #src0 ", %%mm2        \n\t" /* R4     R0      r4      r0 */\
        "movq 8+" #src4 ", %%mm3        \n\t" /* R6     R2      r6      r2 */\
        "movq 16(%2), %%mm1             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm2, %%mm1           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm7             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm7, %%mm2           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 32(%2), %%mm7             \n\t" /* C6     C2      C6      C2 */\
        "pmaddwd %%mm3, %%mm7           \n\t" /* C6R6+C2R2      C6r6+C2r2 */\
        "pmaddwd 40(%2), %%mm3          \n\t" /* -C2R6+C6R2     -C2r6+C6r2 */\
        "paddd %%mm1, %%mm7             \n\t" /* A0             a0 */\
        "paddd %%mm1, %%mm1             \n\t" /* 2C0            2c0 */\
        "psubd %%mm7, %%mm1             \n\t" /* A3             a3 */\
        "paddd %%mm2, %%mm3             \n\t" /* A1             a1 */\
        "paddd %%mm2, %%mm2             \n\t" /* 2C1            2c1 */\
        "psubd %%mm3, %%mm2             \n\t" /* A2             a2 */\
        "psrad $" #shift ", %%mm4       \n\t"\
        "psrad $" #shift ", %%mm7       \n\t"\
        "psrad $" #shift ", %%mm3       \n\t"\
        "packssdw %%mm7, %%mm4          \n\t" /* A0     a0 */\
        "movq %%mm4, " #dst "           \n\t"\
        "psrad $" #shift ", %%mm0       \n\t"\
        "packssdw %%mm3, %%mm0          \n\t" /* A1     a1 */\
        "movq %%mm0, 16+" #dst "        \n\t"\
        "movq %%mm0, 96+" #dst "        \n\t"\
        "movq %%mm4, 112+" #dst "       \n\t"\
        "psrad $" #shift ", %%mm5       \n\t"\
        "psrad $" #shift ", %%mm6       \n\t"\
        "psrad $" #shift ", %%mm2       \n\t"\
        "packssdw %%mm2, %%mm5          \n\t" /* A2-B2  a2-b2 */\
        "movq %%mm5, 32+" #dst "        \n\t"\
        "psrad $" #shift ", %%mm1       \n\t"\
        "packssdw %%mm1, %%mm6          \n\t" /* A3+B3  a3+b3 */\
        "movq %%mm6, 48+" #dst "        \n\t"\
        "movq %%mm6, 64+" #dst "        \n\t"\
        "movq %%mm5, 80+" #dst "        \n\t"
1003

1004

1005 1006 1007 1008 1009
//IDCT(  src0,   src4,   src1,    src5,    dst, shift)
IDCT(    0(%1), 64(%1), 32(%1),  96(%1),  0(%0), 20)
//IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0), 20)
IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0), 20)
//IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20)
1010
        "jmp 9f                         \n\t"
1011 1012


1013
        "# .p2align 4                   \n\t"\
1014
        "1:                             \n\t"
1015
#undef IDCT
1016
#define IDCT(src0, src4, src1, src5, dst, shift) \
1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq " #src4 ", %%mm1          \n\t" /* R6     R2      r6      r2 */\
        "movq " #src1 ", %%mm2          \n\t" /* R3     R1      r3      r1 */\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 32(%2), %%mm5             \n\t" /* C6     C2      C6      C2 */\
        "pmaddwd %%mm1, %%mm5           \n\t" /* C6R6+C2R2      C6r6+C2r2 */\
        "movq 40(%2), %%mm6             \n\t" /* -C2    C6      -C2     C6 */\
        "pmaddwd %%mm6, %%mm1           \n\t" /* -C2R6+C6R2     -C2r6+C6r2 */\
        "movq %%mm4, %%mm6              \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 48(%2), %%mm7             \n\t" /* C3     C1      C3      C1 */\
        "pmaddwd %%mm2, %%mm7           \n\t" /* C3R3+C1R1      C3r3+C1r1 */\
        "paddd %%mm5, %%mm4             \n\t" /* A0             a0 */\
        "psubd %%mm5, %%mm6             \n\t" /* A3             a3 */\
        "movq %%mm0, %%mm5              \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "paddd %%mm1, %%mm0             \n\t" /* A1             a1 */\
        "psubd %%mm1, %%mm5             \n\t" /* A2             a2 */\
        "movq 64(%2), %%mm1             \n\t"\
        "pmaddwd %%mm2, %%mm1           \n\t" /* -C7R3+C3R1     -C7r3+C3r1 */\
        "paddd %%mm4, %%mm7             \n\t" /* A0+B0          a0+b0 */\
        "paddd %%mm4, %%mm4             \n\t" /* 2A0            2a0 */\
        "psubd %%mm7, %%mm4             \n\t" /* A0-B0          a0-b0 */\
        "psrad $" #shift ", %%mm7       \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "movq %%mm0, %%mm3              \n\t" /* A1             a1 */\
        "paddd %%mm1, %%mm0             \n\t" /* A1+B1          a1+b1 */\
        "psubd %%mm1, %%mm3             \n\t" /* A1-B1          a1-b1 */\
        "psrad $" #shift ", %%mm0       \n\t"\
        "psrad $" #shift ", %%mm3       \n\t"\
        "packssdw %%mm7, %%mm7          \n\t" /* A0+B0  a0+b0 */\
        "movd %%mm7, " #dst "           \n\t"\
        "packssdw %%mm0, %%mm0          \n\t" /* A1+B1  a1+b1 */\
        "movd %%mm0, 16+" #dst "        \n\t"\
        "packssdw %%mm3, %%mm3          \n\t" /* A1-B1  a1-b1 */\
        "movd %%mm3, 96+" #dst "        \n\t"\
        "packssdw %%mm4, %%mm4          \n\t" /* A0-B0  a0-b0 */\
        "movd %%mm4, 112+" #dst "       \n\t"\
        "movq 80(%2), %%mm4             \n\t" /* -C1    C5      -C1     C5 */\
        "pmaddwd %%mm2, %%mm4           \n\t" /* -C1R3+C5R1     -C1r3+C5r1 */\
        "pmaddwd 96(%2), %%mm2          \n\t" /* -C5R3+C7R1     -C5r3+C7r1 */\
        "movq %%mm5, %%mm3              \n\t" /* A2             a2 */\
        "paddd %%mm4, %%mm3             \n\t" /* A2+B2          a2+b2 */\
        "psubd %%mm4, %%mm5             \n\t" /* a2-B2          a2-b2 */\
        "psrad $" #shift ", %%mm3       \n\t"\
        "psrad $" #shift ", %%mm5       \n\t"\
        "movq %%mm6, %%mm4              \n\t" /* A3             a3 */\
        "paddd %%mm2, %%mm6             \n\t" /* A3+B3          a3+b3 */\
        "psubd %%mm2, %%mm4             \n\t" /* a3-B3          a3-b3 */\
        "psrad $" #shift ", %%mm6       \n\t"\
        "packssdw %%mm3, %%mm3          \n\t" /* A2+B2  a2+b2 */\
        "movd %%mm3, 32+" #dst "        \n\t"\
        "psrad $" #shift ", %%mm4       \n\t"\
        "packssdw %%mm6, %%mm6          \n\t" /* A3+B3  a3+b3 */\
        "movd %%mm6, 48+" #dst "        \n\t"\
        "packssdw %%mm4, %%mm4          \n\t" /* A3-B3  a3-b3 */\
        "packssdw %%mm5, %%mm5          \n\t" /* A2-B2  a2-b2 */\
        "movd %%mm4, 64+" #dst "        \n\t"\
        "movd %%mm5, 80+" #dst "        \n\t"
1077

1078

1079 1080 1081 1082 1083
//IDCT(  src0,   src4,   src1,    src5,    dst, shift)
IDCT(    (%1), 64(%1), 32(%1),  96(%1),  0(%0), 20)
IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0), 20)
IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0), 20)
IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20)
1084
        "jmp 9f                         \n\t"
1085 1086


1087
        "# .p2align 4                   \n\t"
1088
        "7:                             \n\t"
1089
#undef IDCT
1090
#define IDCT(src0, src4, src1, src5, dst, shift) \
1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115
        "movq " #src0 ", %%mm0          \n\t" /* R4     R0      r4      r0 */\
        "movq 16(%2), %%mm4             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm0, %%mm4           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm5             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm5, %%mm0           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "psrad $" #shift ", %%mm4       \n\t"\
        "psrad $" #shift ", %%mm0       \n\t"\
        "movq 8+" #src0 ", %%mm2        \n\t" /* R4     R0      r4      r0 */\
        "movq 16(%2), %%mm1             \n\t" /* C4     C4      C4      C4 */\
        "pmaddwd %%mm2, %%mm1           \n\t" /* C4R4+C4R0      C4r4+C4r0 */\
        "movq 24(%2), %%mm7             \n\t" /* -C4    C4      -C4     C4 */\
        "pmaddwd %%mm7, %%mm2           \n\t" /* -C4R4+C4R0     -C4r4+C4r0 */\
        "movq 32(%2), %%mm7             \n\t" /* C6     C2      C6      C2 */\
        "psrad $" #shift ", %%mm1       \n\t"\
        "packssdw %%mm1, %%mm4          \n\t" /* A0     a0 */\
        "movq %%mm4, " #dst "           \n\t"\
        "psrad $" #shift ", %%mm2       \n\t"\
        "packssdw %%mm2, %%mm0          \n\t" /* A1     a1 */\
        "movq %%mm0, 16+" #dst "        \n\t"\
        "movq %%mm0, 96+" #dst "        \n\t"\
        "movq %%mm4, 112+" #dst "       \n\t"\
        "movq %%mm0, 32+" #dst "        \n\t"\
        "movq %%mm4, 48+" #dst "        \n\t"\
        "movq %%mm4, 64+" #dst "        \n\t"\
        "movq %%mm0, 80+" #dst "        \n\t"
1116

1117 1118 1119 1120 1121
//IDCT(  src0,   src4,   src1,    src5,    dst, shift)
IDCT(   0(%1), 64(%1), 32(%1),  96(%1),  0(%0), 20)
//IDCT(   8(%1), 72(%1), 40(%1), 104(%1),  4(%0), 20)
IDCT(  16(%1), 80(%1), 48(%1), 112(%1),  8(%0), 20)
//IDCT(  24(%1), 88(%1), 56(%1), 120(%1), 12(%0), 20)
1122 1123 1124 1125 1126 1127


#endif

/*
Input
1128 1129 1130
 00 40 04 44 20 60 24 64
 10 30 14 34 50 70 54 74
 01 41 03 43 21 61 23 63
1131
 11 31 13 33 51 71 53 73
1132 1133 1134 1135
 02 42 06 46 22 62 26 66
 12 32 16 36 52 72 56 76
 05 45 07 47 25 65 27 67
 15 35 17 37 55 75 57 77
1136

1137
Temp
1138 1139
 00 04 10 14 20 24 30 34
 40 44 50 54 60 64 70 74
1140 1141
 01 03 11 13 21 23 31 33
 41 43 51 53 61 63 71 73
1142 1143
 02 06 12 16 22 26 32 36
 42 46 52 56 62 66 72 76
1144 1145 1146 1147 1148
 05 07 15 17 25 27 35 37
 45 47 55 57 65 67 75 77
*/

"9: \n\t"
1149
                :: "r" (block), "r" (temp), "r" (coeffs)
1150
                   NAMED_CONSTRAINTS_ADD(wm1010,d40000)
1151 1152
                : "%eax"
        );
1153 1154
}

1155
void ff_simple_idct_mmx(int16_t *block)
1156
{
1157 1158 1159 1160 1161
    idct(block);
}

//FIXME merge add/put into the idct

Diego Biurrun's avatar
Diego Biurrun committed
1162
void ff_simple_idct_put_mmx(uint8_t *dest, int line_size, int16_t *block)
1163 1164
{
    idct(block);
1165
    ff_put_pixels_clamped(block, dest, line_size);
1166
}
Diego Biurrun's avatar
Diego Biurrun committed
1167
void ff_simple_idct_add_mmx(uint8_t *dest, int line_size, int16_t *block)
1168 1169
{
    idct(block);
1170
    ff_add_pixels_clamped(block, dest, line_size);
1171
}
1172 1173

#endif /* HAVE_INLINE_ASM */