[FFmpeg-devel] [PATCH] avutil/aarch64/float_dsp_neon: Refactor ff_vector_fmul_add_neon

[Krzysztof Pyrkosz]

Removed a branch, unrolled loop. Speed increase bumped from 3.95 to 5.60.

Krzysztof

---
 libavutil/aarch64/float_dsp_neon.S | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/libavutil/aarch64/float_dsp_neon.S b/libavutil/aarch64/float_dsp_neon.S
index 35e2715b87..0ee5c67b91 100644
--- a/libavutil/aarch64/float_dsp_neon.S
+++ b/libavutil/aarch64/float_dsp_neon.S
@@ -138,19 +138,21 @@ function ff_vector_fmul_window_neon, export=1
 endfunc
 
 function ff_vector_fmul_add_neon, export=1
-        ld1             {v0.4s, v1.4s},  [x1], #32
-        ld1             {v2.4s, v3.4s},  [x2], #32
-        ld1             {v4.4s, v5.4s},  [x3], #32
-1:      subs            w4,  w4,  #8
-        fmla            v4.4s,  v0.4s,  v2.4s
-        fmla            v5.4s,  v1.4s,  v3.4s
-        b.eq            2f
-        ld1             {v0.4s, v1.4s},  [x1], #32
-        ld1             {v2.4s, v3.4s},  [x2], #32
-        st1             {v4.4s, v5.4s},  [x0], #32
-        ld1             {v4.4s, v5.4s},  [x3], #32
-        b               1b
-2:      st1             {v4.4s, v5.4s},  [x0], #32
+1:
+        ldp            q0, q1, [x1], #32
+        ldp            q2, q3, [x2], #32
+        ldp            q4, q5, [x3], #32
+        fmla           v4.4s, v0.4s, v2.4s
+        fmla           v5.4s, v1.4s, v3.4s
+        stp            q4, q5, [x0], #32
+        ldp            q0, q1, [x1], #32
+        ldp            q2, q3, [x2], #32
+        ldp            q4, q5, [x3], #32
+        fmla           v4.4s, v0.4s, v2.4s
+        fmla           v5.4s, v1.4s, v3.4s
+        stp            q4, q5, [x0], #32
+        sub            w4, w4, #16
+        cbnz           w4, 1b
         ret
 endfunc
 
-- 
2.45.2