[FFmpeg-devel] [PATCH 1/2] avcodec/aarch64/ac3dsp_neon.S: Optimize ac3_extract_exponents

[Krzysztof Pyrkosz]

Before and after:

A78
ac3_extract_exponents_n512_neon:                       503.2 ( 3.36x)
ac3_extract_exponents_n3072_neon:                     2986.2 ( 3.35x)

ac3_extract_exponents_n512_neon:                       211.2 ( 8.02x)
ac3_extract_exponents_n3072_neon:                     1251.5 ( 8.00x)

A72
ac3_extract_exponents_n512_neon:                       964.7 ( 2.39x)
ac3_extract_exponents_n3072_neon:                     5434.5 ( 2.47x)

ac3_extract_exponents_n512_neon:                       465.6 ( 4.87x)
ac3_extract_exponents_n3072_neon:                     2696.3 ( 4.97x)
---
This version handles 16 ints in one go and consolidates separate
extractions and writes into one. I assume the length of the input is a
multiple of 16 (there are no constraints defined in the template file),
but the tests are passing.

Krzysztof

 libavcodec/aarch64/ac3dsp_neon.S | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/libavcodec/aarch64/ac3dsp_neon.S b/libavcodec/aarch64/ac3dsp_neon.S
index 7e97cc39f7..b2ac9edc55 100644
--- a/libavcodec/aarch64/ac3dsp_neon.S
+++ b/libavcodec/aarch64/ac3dsp_neon.S
@@ -38,15 +38,26 @@ function ff_ac3_exponent_min_neon, export=1
 endfunc
 
 function ff_ac3_extract_exponents_neon, export=1
-        movi            v1.4s, #8
-1:      ld1             {v0.4s}, [x1], #16
+        movi            v4.16b, #8
+1:      ld1             {v0.4s - v3.4s}, [x1], #64
+        subs            w2, w2, #16
         abs             v0.4s, v0.4s
+        abs             v1.4s, v1.4s
+        abs             v2.4s, v2.4s
+        abs             v3.4s, v3.4s
+
         clz             v0.4s, v0.4s
-        sub             v0.4s, v0.4s, v1.4s
-        xtn             v0.4h, v0.4s
-        xtn             v0.8b, v0.8h
-        st1             {v0.s}[0], [x0], #4
-        subs            w2, w2, #4
+        clz             v1.4s, v1.4s
+        clz             v2.4s, v2.4s
+        clz             v3.4s, v3.4s
+
+        uzp1            v0.8h, v0.8h, v1.8h
+        uzp1            v2.8h, v2.8h, v3.8h
+        uzp1            v0.16b, v0.16b, v2.16b
+        sub             v0.16b, v0.16b, v4.16b
+
+        st1             {v0.16b}, [x0], #16
+
         b.gt            1b
         ret
 endfunc
-- 
2.47.2