diff options
| author | Diego Biurrun <diego@biurrun.de> | 2014-01-16 17:30:19 +0100 |
|---|---|---|
| committer | Diego Biurrun <diego@biurrun.de> | 2014-06-22 06:20:15 -0700 |
| commit | 9a9e2f1c8aa4539a261625145e5c1f46a8106ac2 (patch) | |
| tree | 8df94d9ee621e07b5e5f9aad954cc68d92105e88 /libavcodec/arm/audiodsp_neon.S | |
| parent | ca1e36a8e4cd416142487071dbca734567bdaddf (diff) | |
dsputil: Split audio operations off into a separate context
Diffstat (limited to 'libavcodec/arm/audiodsp_neon.S')
| -rw-r--r-- | libavcodec/arm/audiodsp_neon.S | 64 |
1 files changed, 64 insertions, 0 deletions
diff --git a/libavcodec/arm/audiodsp_neon.S b/libavcodec/arm/audiodsp_neon.S new file mode 100644 index 0000000000..dfb998de32 --- /dev/null +++ b/libavcodec/arm/audiodsp_neon.S @@ -0,0 +1,64 @@ +/* + * ARM NEON optimised audio functions + * Copyright (c) 2008 Mans Rullgard <mans@mansr.com> + * + * This file is part of Libav. + * + * Libav 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. + * + * Libav 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 Libav; 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_vector_clipf_neon, export=1 +VFP vdup.32 q1, d0[1] +VFP vdup.32 q0, d0[0] +NOVFP vdup.32 q0, r2 +NOVFP vdup.32 q1, r3 +NOVFP ldr r2, [sp] + vld1.f32 {q2},[r1,:128]! + vmin.f32 q10, q2, q1 + vld1.f32 {q3},[r1,:128]! + vmin.f32 q11, q3, q1 +1: vmax.f32 q8, q10, q0 + vmax.f32 q9, q11, q0 + subs r2, r2, #8 + beq 2f + vld1.f32 {q2},[r1,:128]! + vmin.f32 q10, q2, q1 + vld1.f32 {q3},[r1,:128]! + vmin.f32 q11, q3, q1 + vst1.f32 {q8},[r0,:128]! + vst1.f32 {q9},[r0,:128]! + b 1b +2: vst1.f32 {q8},[r0,:128]! + vst1.f32 {q9},[r0,:128]! + bx lr +endfunc + +function ff_vector_clip_int32_neon, export=1 + vdup.32 q0, r2 + vdup.32 q1, r3 + ldr r2, [sp] +1: + vld1.32 {q2-q3}, [r1,:128]! + vmin.s32 q2, q2, q1 + vmin.s32 q3, q3, q1 + vmax.s32 q2, q2, q0 + vmax.s32 q3, q3, q0 + vst1.32 {q2-q3}, [r0,:128]! + subs r2, r2, #8 + bgt 1b + bx lr +endfunc |