| 1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950 |
- /*
- * ARM NEON optimised integer operations
- * Copyright (c) 2009 Konstantin Shishkov
- *
- * 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 "libavutil/arm/asm.S"
- function ff_scalarproduct_int16_neon, export=1
- vmov.i16 q0, #0
- vmov.i16 q1, #0
- vmov.i16 q2, #0
- vmov.i16 q3, #0
- 1: vld1.16 {d16-d17}, [r0]!
- vld1.16 {d20-d21}, [r1,:128]!
- vmlal.s16 q0, d16, d20
- vld1.16 {d18-d19}, [r0]!
- vmlal.s16 q1, d17, d21
- vld1.16 {d22-d23}, [r1,:128]!
- vmlal.s16 q2, d18, d22
- vmlal.s16 q3, d19, d23
- subs r2, r2, #16
- bgt 1b
- vpadd.s32 d16, d0, d1
- vpadd.s32 d17, d2, d3
- vpadd.s32 d18, d4, d5
- vpadd.s32 d19, d6, d7
- vpadd.s32 d0, d16, d17
- vpadd.s32 d1, d18, d19
- vpadd.s32 d2, d0, d1
- vpaddl.s32 d3, d2
- vmov.32 r0, d3[0]
- bx lr
- endfunc
|