File size: 4,921 Bytes
8ead80b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 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 |
/*
* Loongson LSX optimized swscale
*
* Copyright (c) 2023 Loongson Technology Corporation Limited
* Contributed by Lu Wang <[email protected]>
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* 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
* License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "libavcodec/loongarch/loongson_asm.S"
/* static void ff_yuv2planeX_8_lsx(const int16_t *filter, int filterSize,
* const int16_t **src, uint8_t *dest, int dstW,
* const uint8_t *dither, int offset)
*/
function ff_yuv2planeX_8_lsx
addi.w t1, a6, 1
addi.w t2, a6, 2
addi.w t3, a6, 3
addi.w t4, a6, 4
addi.w t5, a6, 5
addi.w t6, a6, 6
addi.w t7, a6, 7
andi t0, a6, 7
andi t1, t1, 7
andi t2, t2, 7
andi t3, t3, 7
andi t4, t4, 7
andi t5, t5, 7
andi t6, t6, 7
andi t7, t7, 7
ldx.bu t0, a5, t0
ldx.bu t1, a5, t1
ldx.bu t2, a5, t2
ldx.bu t3, a5, t3
ldx.bu t4, a5, t4
ldx.bu t5, a5, t5
ldx.bu t6, a5, t6
ldx.bu t7, a5, t7
vreplgr2vr.w vr0, t0
vreplgr2vr.w vr1, t1
vreplgr2vr.w vr2, t2
vreplgr2vr.w vr3, t3
vreplgr2vr.w vr4, t4
vreplgr2vr.w vr5, t5
vreplgr2vr.w vr6, t6
vreplgr2vr.w vr7, t7
vilvl.w vr0, vr2, vr0
vilvl.w vr4, vr6, vr4
vilvl.w vr1, vr3, vr1
vilvl.w vr5, vr7, vr5
vilvl.d vr12, vr4, vr0
vilvl.d vr13, vr5, vr1
li.w t5, 0
li.w t8, 8
bge a4, t8, .WIDTH8
blt zero, a4, .WIDTH
b .END
.WIDTH8:
li.d t1, 0
li.d t4, 0
vslli.w vr2, vr12, 12
vslli.w vr3, vr13, 12
move t3, a0
.FILTERSIZE8:
ldx.d t2, a2, t1
vldx vr4, t2, t5
vldrepl.h vr5, t3, 0
vmaddwev.w.h vr2, vr4, vr5
vmaddwod.w.h vr3, vr4, vr5
addi.d t1, t1, 8
addi.d t3, t3, 2
addi.d t4, t4, 1
blt t4, a1, .FILTERSIZE8
vsrai.w vr2, vr2, 19
vsrai.w vr3, vr3, 19
vclip255.w vr2, vr2
vclip255.w vr3, vr3
vpickev.h vr2, vr3, vr2
vpickev.b vr2, vr2, vr2
vbsrl.v vr3, vr2, 4
vilvl.b vr2, vr3, vr2
fst.d f2, a3, 0
addi.d t5, t5, 16
addi.d a4, a4, -8
addi.d a3, a3, 8
bge a4, t8, .WIDTH8
blt zero, a4, .WIDTH
b .END
.WIDTH:
li.d t1, 0
li.d t4, 0
vslli.w vr2, vr12, 12
vslli.w vr3, vr13, 12
.FILTERSIZE:
ldx.d t2, a2, t1
vldx vr4, t2, t5
vldrepl.h vr5, a0, 0
vmaddwev.w.h vr2, vr4, vr5
vmaddwod.w.h vr3, vr4, vr5
addi.d t1, t1, 8
addi.d a0, a0, 2
addi.d t4, t4, 1
blt t4, a1, .FILTERSIZE
vsrai.w vr2, vr2, 19
vsrai.w vr3, vr3, 19
vclip255.w vr2, vr2
vclip255.w vr3, vr3
vpickev.h vr2, vr3, vr2
vpickev.b vr2, vr2, vr2
vbsrl.v vr3, vr2, 4
vilvl.b vr2, vr3, vr2
.DEST:
vstelm.b vr2, a3, 0, 0
vbsrl.v vr2, vr2, 1
addi.d a4, a4, -1
addi.d a3, a3, 1
blt zero, a4, .DEST
.END:
endfunc
|