[FFmpeg-cvslog] avcodec/aarch64/ac3dsp_neon.S: Optimize ac3_sum_square_butterfly_int32_neon

[Krzysztof Pyrkosz]

ffmpeg | branch: master | Krzysztof Pyrkosz <ffmpeg at szaka.eu> | Fri Feb 28 22:21:50 2025 +0100| [e8d4c559871ef93fc94a8efb8144f1738eba4c62] | committer: Martin Storsjö

avcodec/aarch64/ac3dsp_neon.S: Optimize ac3_sum_square_butterfly_int32_neon

Instead of calculating a^2, b^2, (a+b)^2 and (a-b)^2, calculate only
a^2, b^2 and 2*a*b in each iteration and derive the latter parts from
these three at the end.

Before and after:

A78
ac3_sum_square_bufferfly_int32_neon:                   484.8 ( 2.00x)
ac3_sum_square_bufferfly_int32_neon:                   468.2 ( 2.08x)

A72
ac3_sum_square_bufferfly_int32_neon:                   793.6 ( 1.26x)
ac3_sum_square_bufferfly_int32_neon:                   527.3 ( 1.92x)

Signed-off-by: Martin Storsjö <martin at martin.st>

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=e8d4c559871ef93fc94a8efb8144f1738eba4c62
---

 libavcodec/aarch64/ac3dsp_neon.S | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/libavcodec/aarch64/ac3dsp_neon.S b/libavcodec/aarch64/ac3dsp_neon.S
index 7e97cc39f7..c28e2082a9 100644
--- a/libavcodec/aarch64/ac3dsp_neon.S
+++ b/libavcodec/aarch64/ac3dsp_neon.S
@@ -69,21 +69,20 @@ function ff_ac3_sum_square_butterfly_int32_neon, export=1
         movi            v0.2d, #0
         movi            v1.2d, #0
         movi            v2.2d, #0
-        movi            v3.2d, #0
 1:      ld1             {v4.2s}, [x1], #8
         ld1             {v5.2s}, [x2], #8
-        add             v6.2s, v4.2s, v5.2s
-        sub             v7.2s, v4.2s, v5.2s
-        smlal           v0.2d, v4.2s, v4.2s
-        smlal           v1.2d, v5.2s, v5.2s
-        smlal           v2.2d, v6.2s, v6.2s
-        smlal           v3.2d, v7.2s, v7.2s
         subs            w3, w3, #2
+        smlal           v0.2d, v4.2s, v4.2s // sum of a^2
+        smlal           v1.2d, v5.2s, v5.2s // sum of b^2
+        sqdmlal         v2.2d, v4.2s, v5.2s // sum of 2ab
         b.gt            1b
         addp            d0, v0.2d
         addp            d1, v1.2d
         addp            d2, v2.2d
-        addp            d3, v3.2d
+        sub             d3, d0, d2 // a^2 + b^2 - 2ab
+        add             d2, d0, d2
+        add             d3, d3, d1 // a^2 + b^2 + 2ab
+        add             d2, d2, d1
         st1             {v0.1d-v3.1d}, [x0]
         ret
 endfunc