[FFmpeg-devel] [PATCH] lavc/vvc_mc: reduce sequential dependency in R-V V sad

[uk7b at foxmail.com]

From: sunyuechi <sunyuechi at iscas.ac.cn>

---
 libavcodec/riscv/vvc/vvc_sad_rvv.S | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/libavcodec/riscv/vvc/vvc_sad_rvv.S b/libavcodec/riscv/vvc/vvc_sad_rvv.S
index 341167be1f..f325deee17 100644
--- a/libavcodec/riscv/vvc/vvc_sad_rvv.S
+++ b/libavcodec/riscv/vvc/vvc_sad_rvv.S
@@ -36,20 +36,20 @@ func ff_vvc_sad_rvv_\vlen, zve32x, zbb, zba
 SADVSET\vlen\w:
         vsetvlstatic32    \w, \vlen
         vmv.v.i           v0, 0
-        vmv.s.x           v24, zero
         vsetvlstatic16    \w, \vlen
 SAD\vlen\w:
         addi              a5, a5, -2
         vle16.v           v8, (a0)
         vle16.v           v16, (a1)
-        vsub.vv           v8, v8, v16
-        vneg.v            v16, v8
+        vsub.vv           v24, v8, v16
+        vsub.vv           v16, v16, v8
         addi              a0, a0, 2 * 128 * 2
-        vmax.vv           v8, v8, v16
-        vwaddu.wv         v0, v0, v8
+        vmax.vv           v8, v24, v16
         addi              a1, a1, 2 * 128 * 2
+        vwaddu.wv         v0, v0, v8
         bnez              a5, SAD\vlen\w
         vsetvlstatic32    \w, \vlen
+        vmv.s.x           v24, zero
         vredsum.vs        v24, v0, v24
         vmv.x.s           a0, v24
         ret
-- 
2.47.1