[FFmpeg-cvslog] lavc/rv34dsp: use saturating add/sub for R-V V DC add

[Rémi Denis-Courmont]

ffmpeg | branch: master | Rémi Denis-Courmont <remi at remlab.net> | Sun Jul 28 21:40:52 2024 +0300| [54ae270213b5a98f923bfd4506e450b2e764ede2] | committer: Rémi Denis-Courmont

lavc/rv34dsp: use saturating add/sub for R-V V DC add

T-Head C908 (cycles):
rv34_idct_dc_add_c:      113.2
rv34_idct_dc_add_rvv_i32: 48.5 (before)
rv34_idct_dc_add_rvv_i32: 39.5 (after)

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=54ae270213b5a98f923bfd4506e450b2e764ede2
---

 libavcodec/riscv/rv34dsp_rvv.S | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/libavcodec/riscv/rv34dsp_rvv.S b/libavcodec/riscv/rv34dsp_rvv.S
index 478bc0a860..fc0ffec4fe 100644
--- a/libavcodec/riscv/rv34dsp_rvv.S
+++ b/libavcodec/riscv/rv34dsp_rvv.S
@@ -41,14 +41,17 @@ func ff_rv34_idct_dc_add_rvv, zve32x
         mul           t1, t1, a2
         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
-        vsetivli      zero, 4, e8, mf4, ta, ma
-        vsse32.v      v0, (a0), a1
+        vsetivli    zero, 4*4, e8, m2, ta, ma
+        bgez    t1, 1f
 
+        neg     t1, t1
+        vssubu.vx   v0, v0, t1
+        vsetivli    zero, 4, e8, mf4, ta, ma
+        vsse32.v    v0, (a0), a1
+        ret
+1:
+        vsaddu.vx   v0, v0, t1
+        vsetivli    zero, 4, e8, mf4, ta, ma
+        vsse32.v    v0, (a0), a1
         ret
 endfunc