[FFmpeg-devel] [PATCH 1/2] lavc/aacpsdsp: rework RISC-V add_squares

[Rémi Denis-Courmont]

Segmented loads are kinda slow, so this advantageously uses a
unit-strided load and narrowing shifts instead.

Before:
ps_add_squares_rvv_f32: 30352.2

After:
ps_add_squares_rvv_f32: 11973.7
---
 libavcodec/riscv/aacpsdsp_rvv.S | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/libavcodec/riscv/aacpsdsp_rvv.S b/libavcodec/riscv/aacpsdsp_rvv.S
index 80bd19f6ad..b7ea314fc3 100644
--- a/libavcodec/riscv/aacpsdsp_rvv.S
+++ b/libavcodec/riscv/aacpsdsp_rvv.S
@@ -1,5 +1,5 @@
 /*
- * Copyright © 2022 Rémi Denis-Courmont.
+ * Copyright © 2022-2023 Rémi Denis-Courmont.
  *
  * This file is part of FFmpeg.
  *
@@ -21,13 +21,16 @@
 #include "libavutil/riscv/asm.S"
 
 func ff_ps_add_squares_rvv, zve32f
+        li          t1, 32
 1:
         vsetvli     t0, a2, e32, m1, ta, ma
-        vlseg2e32.v v24, (a1)
-        sub         a2, a2, t0
+        vle64.v     v8, (a1)
+        vnsrl.wx    v24, v8, zero
         vle32.v     v16, (a0)
-        sh3add      a1, t0, a1
+        sub         a2, a2, t0
+        vnsrl.wx    v25, v8, t1
         vfmacc.vv   v16, v24, v24
+        sh3add      a1, t0, a1
         vfmacc.vv   v16, v25, v25
         vse32.v     v16, (a0)
         sh2add      a0, t0, a0
-- 
2.40.1