[FFmpeg-cvslog] swscale: inline ff_shuffle_bytes_3210_rvv

[Rémi Denis-Courmont]

ffmpeg | branch: master | Rémi Denis-Courmont <remi at remlab.net> | Tue Jul 18 21:11:15 2023 +0300| [d3948e4db50666da05368d2bc84134fea2e20006] | committer: Rémi Denis-Courmont

swscale: inline ff_shuffle_bytes_3210_rvv

No functional changes.

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=d3948e4db50666da05368d2bc84134fea2e20006
---

 libswscale/riscv/rgb2rgb_rvv.S | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/libswscale/riscv/rgb2rgb_rvv.S b/libswscale/riscv/rgb2rgb_rvv.S
index bbdfdbebbc..8f30d760cb 100644
--- a/libswscale/riscv/rgb2rgb_rvv.S
+++ b/libswscale/riscv/rgb2rgb_rvv.S
@@ -74,7 +74,24 @@ func ff_shuffle_bytes_3210_rvv, zve32x
         addi    t2, a0, 1
         addi    t3, a0, 0
         addi    a0, a0, 3
-        j       1b
+        srai    a2, a2, 2
+        li      t4, 4
+1:
+        vsetvli    t0, a2, e8, m1, ta, ma
+        sub        a2, a2, t0
+        vlse8.v    v8, (a0), t4
+        sh2add     a0, t0, a0
+        vlse8.v    v9, (t1), t4
+        sh2add     t1, t0, t1
+        vlse8.v    v10, (t2), t4
+        sh2add     t2, t0, t2
+        vlse8.v    v11, (t3), t4
+        sh2add     t3, t0, t3
+        vsseg4e8.v v8, (a1)
+        sh2add     a1, t0, a1
+        bnez       a2, 1b
+
+        ret
 endfunc
 
 func ff_interleave_bytes_rvv, zve32x