1/*
2 * Copyright (c) 2012
3 *      MIPS Technologies, Inc., California.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 * 1. Redistributions of source code must retain the above copyright
9 *    notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 *    notice, this list of conditions and the following disclaimer in the
12 *    documentation and/or other materials provided with the distribution.
13 * 3. Neither the name of the MIPS Technologies, Inc., nor the names of its
14 *    contributors may be used to endorse or promote products derived from
15 *    this software without specific prior written permission.
16 *
17 * THIS SOFTWARE IS PROVIDED BY THE MIPS TECHNOLOGIES, INC. ``AS IS'' AND
18 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
19 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
20 * ARE DISCLAIMED.  IN NO EVENT SHALL THE MIPS TECHNOLOGIES, INC. BE LIABLE
21 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
22 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
23 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
24 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
25 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
26 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
27 * SUCH DAMAGE.
28 *
29 * Author:  Bojan Zivkovic (bojan@mips.com)
30 *
31 * Compute antialias function optimised for MIPS fixed-point architecture
32 *
33 * This file is part of FFmpeg.
34 *
35 * FFmpeg is free software; you can redistribute it and/or
36 * modify it under the terms of the GNU Lesser General Public
37 * License as published by the Free Software Foundation; either
38 * version 2.1 of the License, or (at your option) any later version.
39 *
40 * FFmpeg is distributed in the hope that it will be useful,
41 * but WITHOUT ANY WARRANTY; without even the implied warranty of
42 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
43 * Lesser General Public License for more details.
44 *
45 * You should have received a copy of the GNU Lesser General Public
46 * License along with FFmpeg; if not, write to the Free Software
47 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
48 */
49
50/**
51 * @file
52 * Reference: libavcodec/mpegaudiodec.c
53 */
54
55#ifndef AVCODEC_MIPS_COMPUTE_ANTIALIAS_FIXED_H
56#define AVCODEC_MIPS_COMPUTE_ANTIALIAS_FIXED_H
57
58#if HAVE_INLINE_ASM
59static void compute_antialias_mips_fixed(MPADecodeContext *s,
60                                        GranuleDef *g)
61{
62    const int32_t *csa;
63    int32_t *ptr;
64    int n, i;
65    int MAX_lo = 0xffffffff;
66
67    /* we antialias only "long" bands */
68    if (g->block_type == 2) {
69        if (!g->switch_point)
70            return;
71        /* XXX: check this for 8000Hz case */
72        n = 1;
73    } else {
74        n = SBLIMIT - 1;
75    }
76
77
78    ptr = g->sb_hybrid + 18;
79
80    for(i = n;i > 0;i--) {
81        int tmp0, tmp1, tmp2, tmp00, tmp11;
82        int temp_reg1, temp_reg2, temp_reg3, temp_reg4, temp_reg5, temp_reg6;
83        csa = &csa_table[0][0];
84
85        /**
86         * instructions are scheduled to minimize pipeline stall.
87         */
88        __asm__ volatile (
89            "lw   %[tmp0],      -1*4(%[ptr])                            \n\t"
90            "lw   %[tmp1],      0*4(%[ptr])                             \n\t"
91            "lw   %[temp_reg1], 0*4(%[csa])                             \n\t"
92            "lw   %[temp_reg2], 2*4(%[csa])                             \n\t"
93            "add  %[tmp2],      %[tmp0],      %[tmp1]                   \n\t"
94            "lw   %[temp_reg3], 3*4(%[csa])                             \n\t"
95            "mult $ac0,         %[tmp2],      %[temp_reg1]              \n\t"
96            "mult $ac1,         %[tmp2],      %[temp_reg1]              \n\t"
97            "lw   %[tmp00],     -2*4(%[ptr])                            \n\t"
98            "lw   %[tmp11],     1*4(%[ptr])                             \n\t"
99            "lw   %[temp_reg4], 4*4(%[csa])                             \n\t"
100            "mtlo %[MAX_lo],    $ac0                                    \n\t"
101            "mtlo $zero,        $ac1                                    \n\t"
102            "msub $ac0,         %[tmp1],      %[temp_reg2]              \n\t"
103            "madd $ac1,         %[tmp0],      %[temp_reg3]              \n\t"
104            "add  %[tmp2],      %[tmp00],     %[tmp11]                  \n\t"
105            "lw   %[temp_reg5], 6*4(%[csa])                             \n\t"
106            "mult $ac2,         %[tmp2],      %[temp_reg4]              \n\t"
107            "mult $ac3,         %[tmp2],      %[temp_reg4]              \n\t"
108            "mfhi %[temp_reg1], $ac0                                    \n\t"
109            "mfhi %[temp_reg2], $ac1                                    \n\t"
110            "lw   %[temp_reg6], 7*4(%[csa])                             \n\t"
111            "mtlo %[MAX_lo],    $ac2                                    \n\t"
112            "msub $ac2,         %[tmp11],     %[temp_reg5]              \n\t"
113            "mtlo $zero,        $ac3                                    \n\t"
114            "madd $ac3,         %[tmp00],     %[temp_reg6]              \n\t"
115            "sll  %[temp_reg1], %[temp_reg1], 2                         \n\t"
116            "sw   %[temp_reg1], -1*4(%[ptr])                            \n\t"
117            "mfhi %[temp_reg4], $ac2                                    \n\t"
118            "sll  %[temp_reg2], %[temp_reg2], 2                         \n\t"
119            "mfhi %[temp_reg5], $ac3                                    \n\t"
120            "sw   %[temp_reg2], 0*4(%[ptr])                             \n\t"
121            "lw   %[tmp0],      -3*4(%[ptr])                            \n\t"
122            "lw   %[tmp1],      2*4(%[ptr])                             \n\t"
123            "lw   %[temp_reg1], 8*4(%[csa])                             \n\t"
124            "sll  %[temp_reg4], %[temp_reg4], 2                         \n\t"
125            "add  %[tmp2],      %[tmp0],      %[tmp1]                   \n\t"
126            "sll  %[temp_reg5], %[temp_reg5], 2                         \n\t"
127            "mult $ac0,         %[tmp2],      %[temp_reg1]              \n\t"
128            "mult $ac1,         %[tmp2],      %[temp_reg1]              \n\t"
129            "sw   %[temp_reg4], -2*4(%[ptr])                            \n\t"
130            "sw   %[temp_reg5], 1*4(%[ptr])                             \n\t"
131            "lw   %[temp_reg2], 10*4(%[csa])                            \n\t"
132            "mtlo %[MAX_lo],    $ac0                                    \n\t"
133            "lw   %[temp_reg3], 11*4(%[csa])                            \n\t"
134            "msub $ac0,         %[tmp1],      %[temp_reg2]              \n\t"
135            "mtlo $zero,        $ac1                                    \n\t"
136            "madd $ac1,         %[tmp0],      %[temp_reg3]              \n\t"
137            "lw   %[tmp00],     -4*4(%[ptr])                            \n\t"
138            "lw   %[tmp11],     3*4(%[ptr])                             \n\t"
139            "mfhi %[temp_reg1], $ac0                                    \n\t"
140            "lw   %[temp_reg4], 12*4(%[csa])                            \n\t"
141            "mfhi %[temp_reg2], $ac1                                    \n\t"
142            "add  %[tmp2],      %[tmp00],     %[tmp11]                  \n\t"
143            "mult $ac2,         %[tmp2],      %[temp_reg4]              \n\t"
144            "mult $ac3,         %[tmp2],      %[temp_reg4]              \n\t"
145            "lw   %[temp_reg5], 14*4(%[csa])                            \n\t"
146            "lw   %[temp_reg6], 15*4(%[csa])                            \n\t"
147            "sll  %[temp_reg1], %[temp_reg1], 2                         \n\t"
148            "mtlo %[MAX_lo],    $ac2                                    \n\t"
149            "msub $ac2,         %[tmp11],     %[temp_reg5]              \n\t"
150            "mtlo $zero,        $ac3                                    \n\t"
151            "madd $ac3,         %[tmp00],     %[temp_reg6]              \n\t"
152            "sll  %[temp_reg2], %[temp_reg2], 2                         \n\t"
153            "sw   %[temp_reg1], -3*4(%[ptr])                            \n\t"
154            "mfhi %[temp_reg4], $ac2                                    \n\t"
155            "sw   %[temp_reg2], 2*4(%[ptr])                             \n\t"
156            "mfhi %[temp_reg5], $ac3                                    \n\t"
157            "lw   %[tmp0],      -5*4(%[ptr])                            \n\t"
158            "lw   %[tmp1],      4*4(%[ptr])                             \n\t"
159            "lw   %[temp_reg1], 16*4(%[csa])                            \n\t"
160            "lw   %[temp_reg2], 18*4(%[csa])                            \n\t"
161            "add  %[tmp2],      %[tmp0],      %[tmp1]                   \n\t"
162            "lw   %[temp_reg3], 19*4(%[csa])                            \n\t"
163            "mult $ac0,         %[tmp2],      %[temp_reg1]              \n\t"
164            "mult $ac1,         %[tmp2],      %[temp_reg1]              \n\t"
165            "sll  %[temp_reg4], %[temp_reg4], 2                         \n\t"
166            "sll  %[temp_reg5], %[temp_reg5], 2                         \n\t"
167            "sw   %[temp_reg4], -4*4(%[ptr])                            \n\t"
168            "mtlo %[MAX_lo],    $ac0                                    \n\t"
169            "msub $ac0,         %[tmp1],      %[temp_reg2]              \n\t"
170            "mtlo $zero,        $ac1                                    \n\t"
171            "madd $ac1,         %[tmp0],      %[temp_reg3]              \n\t"
172            "sw   %[temp_reg5], 3*4(%[ptr])                             \n\t"
173            "lw   %[tmp00],     -6*4(%[ptr])                            \n\t"
174            "mfhi %[temp_reg1], $ac0                                    \n\t"
175            "lw   %[tmp11],     5*4(%[ptr])                             \n\t"
176            "mfhi %[temp_reg2], $ac1                                    \n\t"
177            "lw   %[temp_reg4], 20*4(%[csa])                            \n\t"
178            "add  %[tmp2],      %[tmp00],     %[tmp11]                  \n\t"
179            "lw   %[temp_reg5], 22*4(%[csa])                            \n\t"
180            "mult $ac2,         %[tmp2],      %[temp_reg4]              \n\t"
181            "mult $ac3,         %[tmp2],      %[temp_reg4]              \n\t"
182            "lw   %[temp_reg6], 23*4(%[csa])                            \n\t"
183            "sll  %[temp_reg1], %[temp_reg1], 2                         \n\t"
184            "sll  %[temp_reg2], %[temp_reg2], 2                         \n\t"
185            "mtlo %[MAX_lo],    $ac2                                    \n\t"
186            "msub $ac2,         %[tmp11],     %[temp_reg5]              \n\t"
187            "mtlo $zero,        $ac3                                    \n\t"
188            "madd $ac3,         %[tmp00],     %[temp_reg6]              \n\t"
189            "sw   %[temp_reg1], -5*4(%[ptr])                            \n\t"
190            "sw   %[temp_reg2], 4*4(%[ptr])                             \n\t"
191            "mfhi %[temp_reg4], $ac2                                    \n\t"
192            "lw   %[tmp0],      -7*4(%[ptr])                            \n\t"
193            "mfhi %[temp_reg5], $ac3                                    \n\t"
194            "lw   %[tmp1],      6*4(%[ptr])                             \n\t"
195            "lw   %[temp_reg1], 24*4(%[csa])                            \n\t"
196            "lw   %[temp_reg2], 26*4(%[csa])                            \n\t"
197            "add  %[tmp2],      %[tmp0],      %[tmp1]                   \n\t"
198            "lw   %[temp_reg3], 27*4(%[csa])                            \n\t"
199            "mult $ac0,         %[tmp2],      %[temp_reg1]              \n\t"
200            "mult $ac1,         %[tmp2],      %[temp_reg1]              \n\t"
201            "sll  %[temp_reg4], %[temp_reg4], 2                         \n\t"
202            "sll  %[temp_reg5], %[temp_reg5], 2                         \n\t"
203            "sw   %[temp_reg4], -6*4(%[ptr])                            \n\t"
204            "mtlo %[MAX_lo],    $ac0                                    \n\t"
205            "msub $ac0,         %[tmp1],      %[temp_reg2]              \n\t"
206            "mtlo $zero,        $ac1                                    \n\t"
207            "madd $ac1,         %[tmp0],      %[temp_reg3]              \n\t"
208            "sw   %[temp_reg5], 5*4(%[ptr])                             \n\t"
209            "lw   %[tmp00],     -8*4(%[ptr])                            \n\t"
210            "mfhi %[temp_reg1], $ac0                                    \n\t"
211            "lw   %[tmp11],     7*4(%[ptr])                             \n\t"
212            "mfhi %[temp_reg2], $ac1                                    \n\t"
213            "lw   %[temp_reg4], 28*4(%[csa])                            \n\t"
214            "add  %[tmp2],      %[tmp00],     %[tmp11]                  \n\t"
215            "lw   %[temp_reg5], 30*4(%[csa])                            \n\t"
216            "mult $ac2,         %[tmp2],      %[temp_reg4]              \n\t"
217            "mult $ac3,         %[tmp2],      %[temp_reg4]              \n\t"
218            "lw   %[temp_reg6], 31*4(%[csa])                            \n\t"
219            "sll  %[temp_reg1], %[temp_reg1], 2                         \n\t"
220            "sll  %[temp_reg2], %[temp_reg2], 2                         \n\t"
221            "mtlo %[MAX_lo],    $ac2                                    \n\t"
222            "msub $ac2,         %[tmp11],     %[temp_reg5]              \n\t"
223            "mtlo $zero,        $ac3                                    \n\t"
224            "madd $ac3,         %[tmp00],     %[temp_reg6]              \n\t"
225            "sw   %[temp_reg1], -7*4(%[ptr])                            \n\t"
226            "sw   %[temp_reg2], 6*4(%[ptr])                             \n\t"
227            "mfhi %[temp_reg4], $ac2                                    \n\t"
228            "mfhi %[temp_reg5], $ac3                                    \n\t"
229            "sll  %[temp_reg4], %[temp_reg4], 2                         \n\t"
230            "sll  %[temp_reg5], %[temp_reg5], 2                         \n\t"
231            "sw   %[temp_reg4], -8*4(%[ptr])                            \n\t"
232            "sw   %[temp_reg5], 7*4(%[ptr])                             \n\t"
233
234            : [tmp0] "=&r" (tmp0), [tmp1] "=&r" (tmp1), [tmp2] "=&r" (tmp2),
235              [tmp00] "=&r" (tmp00), [tmp11] "=&r" (tmp11),
236              [temp_reg1] "=&r" (temp_reg1), [temp_reg2] "=&r" (temp_reg2),
237              [temp_reg3] "=&r" (temp_reg3), [temp_reg4] "=&r" (temp_reg4),
238              [temp_reg5] "=&r" (temp_reg5), [temp_reg6] "=&r" (temp_reg6)
239            : [csa] "r" (csa), [ptr] "r" (ptr),
240              [MAX_lo] "r" (MAX_lo)
241            : "memory", "hi", "lo", "$ac1hi", "$ac1lo", "$ac2hi", "$ac2lo",
242              "$ac3hi", "$ac3lo"
243         );
244
245        ptr += 18;
246    }
247}
248#define compute_antialias compute_antialias_mips_fixed
249#endif /* HAVE_INLINE_ASM */
250
251#endif /* AVCODEC_MIPS_COMPUTE_ANTIALIAS_FIXED_H */
252