summaryrefslogtreecommitdiff
path: root/libavcodec/arm/ac3dsp_neon.S
diff options
context:
space:
mode:
Diffstat (limited to 'libavcodec/arm/ac3dsp_neon.S')
-rw-r--r--libavcodec/arm/ac3dsp_neon.S52
1 files changed, 48 insertions, 4 deletions
diff --git a/libavcodec/arm/ac3dsp_neon.S b/libavcodec/arm/ac3dsp_neon.S
index 82ff8af9fb..381f15868d 100644
--- a/libavcodec/arm/ac3dsp_neon.S
+++ b/libavcodec/arm/ac3dsp_neon.S
@@ -1,20 +1,20 @@
/*
* Copyright (c) 2011 Mans Rullgard <mans@mansr.com>
*
- * This file is part of Libav.
+ * This file is part of FFmpeg.
*
- * Libav is free software; you can redistribute it and/or
+ * 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.
*
- * Libav is distributed in the hope that it will be useful,
+ * 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 Libav; if not, write to the Free Software
+ * License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
@@ -108,3 +108,47 @@ function ff_ac3_extract_exponents_neon, export=1
bgt 1b
bx lr
endfunc
+
+function ff_ac3_sum_square_butterfly_int32_neon, export=1
+ vmov.i64 q0, #0
+ vmov.i64 q1, #0
+ vmov.i64 q2, #0
+ vmov.i64 q3, #0
+1:
+ vld1.32 {d16}, [r1]!
+ vld1.32 {d17}, [r2]!
+ vadd.s32 d18, d16, d17
+ vsub.s32 d19, d16, d17
+ vmlal.s32 q0, d16, d16
+ vmlal.s32 q1, d17, d17
+ vmlal.s32 q2, d18, d18
+ vmlal.s32 q3, d19, d19
+ subs r3, r3, #2
+ bgt 1b
+ vadd.s64 d0, d0, d1
+ vadd.s64 d1, d2, d3
+ vadd.s64 d2, d4, d5
+ vadd.s64 d3, d6, d7
+ vst1.64 {q0-q1}, [r0]
+ bx lr
+endfunc
+
+function ff_ac3_sum_square_butterfly_float_neon, export=1
+ vmov.f32 q0, #0.0
+ vmov.f32 q1, #0.0
+1:
+ vld1.32 {d16}, [r1]!
+ vld1.32 {d17}, [r2]!
+ vadd.f32 d18, d16, d17
+ vsub.f32 d19, d16, d17
+ vmla.f32 d0, d16, d16
+ vmla.f32 d1, d17, d17
+ vmla.f32 d2, d18, d18
+ vmla.f32 d3, d19, d19
+ subs r3, r3, #2
+ bgt 1b
+ vpadd.f32 d0, d0, d1
+ vpadd.f32 d1, d2, d3
+ vst1.32 {q0}, [r0]
+ bx lr
+endfunc