2 * Copyright (c) 2008 Mans Rullgard <mans@mansr.com>
4 * This file is part of FFmpeg.
6 * FFmpeg is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public
8 * License as published by the Free Software Foundation; either
9 * version 2.1 of the License, or (at your option) any later version.
11 * FFmpeg is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 * Lesser General Public License for more details.
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with FFmpeg; if not, write to the Free Software
18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
28 function ff_h264_idct_add_neon, export=1
32 vld1.64 {d0-d3}, [r1,:128]
50 vld1.32 {d18[0]}, [r0,:32], r2
53 vld1.32 {d19[1]}, [r0,:32], r2
55 vld1.32 {d18[1]}, [r0,:32], r2
57 vld1.32 {d19[0]}, [r0,:32], r2
59 sub r0, r0, r2, lsl #2
72 vst1.32 {d0[0]}, [r0,:32], r2
73 vst1.32 {d1[1]}, [r0,:32], r2
74 vst1.32 {d0[1]}, [r0,:32], r2
75 vst1.32 {d1[0]}, [r0,:32], r2
80 function ff_h264_idct_dc_add_neon, export=1
81 vld1.16 {d2[],d3[]}, [r1,:16]
83 vld1.32 {d0[0]}, [r0,:32], r2
84 vld1.32 {d0[1]}, [r0,:32], r2
86 vld1.32 {d1[0]}, [r0,:32], r2
87 vld1.32 {d1[1]}, [r0,:32], r2
91 sub r0, r0, r2, lsl #2
92 vst1.32 {d0[0]}, [r0,:32], r2
93 vst1.32 {d0[1]}, [r0,:32], r2
94 vst1.32 {d1[0]}, [r0,:32], r2
95 vst1.32 {d1[1]}, [r0,:32], r2
99 function ff_h264_idct_add16_neon, export=1
117 adrne lr, ff_h264_idct_dc_add_neon
118 adreq lr, ff_h264_idct_add_neon
126 function ff_h264_idct_add16intra_neon, export=1
141 adrne lr, ff_h264_idct_add_neon
142 adreq lr, ff_h264_idct_dc_add_neon
151 function ff_h264_idct_add8_neon, export=1
168 adrne lr, ff_h264_idct_add_neon
169 adreq lr, ff_h264_idct_dc_add_neon
179 scan8: .byte 4+1*8, 5+1*8, 4+2*8, 5+2*8
180 .byte 6+1*8, 7+1*8, 6+2*8, 7+2*8
181 .byte 4+3*8, 5+3*8, 4+4*8, 5+4*8
182 .byte 6+3*8, 7+3*8, 6+4*8, 7+4*8