[FFmpeg-devel] [PATCH] lavc/rv34dsp: optimise R-V V idct_dc_add

[Rémi Denis-Courmont]

This removes one stray LI and reworks the vector arithmetic to avoid
changing the vector configuration. On K230, this takes the 46.5 cycle
count down from 46.5 to 43.5.
---
 libavcodec/riscv/rv34dsp_rvv.S | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/libavcodec/riscv/rv34dsp_rvv.S b/libavcodec/riscv/rv34dsp_rvv.S
index f1f6345012..e8aff7e570 100644
--- a/libavcodec/riscv/rv34dsp_rvv.S
+++ b/libavcodec/riscv/rv34dsp_rvv.S
@@ -36,16 +36,15 @@ func ff_rv34_idct_dc_add_rvv, zve32x
         vsetivli      zero, 4, e8, mf4, ta, ma
         vlse32.v      v0, (a0), a1
         li            t1, 169
+        li            t2, 128
         mul           t1, t1, a2
-        li            a2, 255
+        vsetivli      zero, 4*4, e8, m1, ta, ma
+        vwsubu.vx     v2, v0, t2
         addi          t1, t1, 512
         srai          t1, t1, 10
-        vsetivli      zero, 4*4, e16, m2, ta, ma
-        vzext.vf2     v2, v0
-        vadd.vx       v2, v2, t1
-        vmax.vx       v2, v2, zero
-        vsetvli       zero, zero, e8, m1, ta, ma
-        vnclipu.wi    v0, v2, 0
+        vwadd.wx      v2, v2, t1
+        vnclip.wi     v0, v2, 0
+        vxor.vx       v0, v0, t2
         vsetivli      zero, 4, e8, mf4, ta, ma
         vsse32.v      v0, (a0), a1
 
-- 
2.45.1