[FFmpeg-cvslog] aarch64/ac3dsp: simplify the end of ff_ac3_sum_square_butterfly_float_neon

[Martin Storsjö]

ffmpeg | branch: master | Martin Storsjö <martin at martin.st> | Mon Apr  8 13:57:05 2024 +0300| [359b6a7f8aec3736451f5179deb98f173fbff0dd] | committer: J. Dekker

aarch64/ac3dsp: simplify the end of ff_ac3_sum_square_butterfly_float_neon

Before:                           Cortex A53     A72     A78      M1
ac3_sum_square_bufferfly_float_neon:  1005.7   516.5   224.5   194.0
After:
ac3_sum_square_bufferfly_float_neon:   981.7   504.5   223.2   189.5

Signed-off-by: J. Dekker <jdek at itanimul.li>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=359b6a7f8aec3736451f5179deb98f173fbff0dd
---

 libavcodec/aarch64/ac3dsp_neon.S | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/libavcodec/aarch64/ac3dsp_neon.S b/libavcodec/aarch64/ac3dsp_neon.S
index 20beb6cc50..7e97cc39f7 100644
--- a/libavcodec/aarch64/ac3dsp_neon.S
+++ b/libavcodec/aarch64/ac3dsp_neon.S
@@ -103,17 +103,9 @@ function ff_ac3_sum_square_butterfly_float_neon, export=1
         fmla            v3.4s, v17.4s, v17.4s
         subs            w3, w3, #4
         b.gt            1b
-        faddp           v0.4s, v0.4s, v0.4s
-        faddp           v0.2s, v0.2s, v0.2s
-        st1             {v0.s}[0], [x0], #4
-        faddp           v1.4s, v1.4s, v1.4s
-        faddp           v1.2s, v1.2s, v1.2s
-        st1             {v1.s}[0], [x0], #4
-        faddp           v2.4s, v2.4s, v2.4s
-        faddp           v2.2s, v2.2s, v2.2s
-        st1             {v2.s}[0], [x0], #4
-        faddp           v3.4s, v3.4s, v3.4s
-        faddp           v3.2s, v3.2s, v3.2s
-        st1             {v3.s}[0], [x0]
+        faddp           v0.4s, v0.4s, v1.4s
+        faddp           v2.4s, v2.4s, v3.4s
+        faddp           v0.4s, v0.4s, v2.4s
+        st1             {v0.4s}, [x0]
         ret
 endfunc