Optimize pixel_avg_pp_12x16_neon by using more suitable load and
store instructions. Using LD1 for the 32-bit lane is a constructive
operation - needing to merge the new value for lane 0 with the
existing top half of the vector. Using LDR turns this into a wholly
destructive operation since LDR zeros the rest of the vector -
removing the false dependency.
---
source/common/aarch64/mc-a.S | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/source/common/aarch64/mc-a.S b/source/common/aarch64/mc-a.S
index 8c2878b3e..130bf1a4a 100644
--- a/source/common/aarch64/mc-a.S
+++ b/source/common/aarch64/mc-a.S
@@ -73,13 +73,13 @@ function PFX(pixel_avg_pp_12x16_neon)
sub x3, x3, #4
sub x5, x5, #4
.rept 16
- ld1 {v0.s}[0], [x2], #4
+ ldr s0, [x2], #4
ld1 {v1.8b}, [x2], x3
- ld1 {v2.s}[0], [x4], #4
+ ldr s2, [x4], #4
ld1 {v3.8b}, [x4], x5
urhadd v4.8b, v0.8b, v2.8b
urhadd v5.8b, v1.8b, v3.8b
- st1 {v4.s}[0], [x0], #4
+ str s4, [x0], #4
st1 {v5.8b}, [x0], x1
.endr
ret
--
2.39.5 (Apple Git-154)
>From 56a22d5ea62fe1d86f4032c0858832bb80d88972 Mon Sep 17 00:00:00 2001
From: Gerda Zsejke More <gerdazsejke.m...@arm.com>
Date: Sun, 27 Apr 2025 10:32:45 +0200
Subject: [PATCH] AArch64: Optimize pixel_avg_pp_12x16_neon
Optimize pixel_avg_pp_12x16_neon by using more suitable load and
store instructions. Using LD1 for the 32-bit lane is a constructive
operation - needing to merge the new value for lane 0 with the
existing top half of the vector. Using LDR turns this into a wholly
destructive operation since LDR zeros the rest of the vector -
removing the false dependency.
---
source/common/aarch64/mc-a.S | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/source/common/aarch64/mc-a.S b/source/common/aarch64/mc-a.S
index 8c2878b3e..130bf1a4a 100644
--- a/source/common/aarch64/mc-a.S
+++ b/source/common/aarch64/mc-a.S
@@ -73,13 +73,13 @@ function PFX(pixel_avg_pp_12x16_neon)
sub x3, x3, #4
sub x5, x5, #4
.rept 16
- ld1 {v0.s}[0], [x2], #4
+ ldr s0, [x2], #4
ld1 {v1.8b}, [x2], x3
- ld1 {v2.s}[0], [x4], #4
+ ldr s2, [x4], #4
ld1 {v3.8b}, [x4], x5
urhadd v4.8b, v0.8b, v2.8b
urhadd v5.8b, v1.8b, v3.8b
- st1 {v4.s}[0], [x0], #4
+ str s4, [x0], #4
st1 {v5.8b}, [x0], x1
.endr
ret
--
2.39.5 (Apple Git-154)
_______________________________________________
x265-devel mailing list
x265-devel@videolan.org
https://mailman.videolan.org/listinfo/x265-devel
