[FFmpeg-devel] [PATCH 1/5] lavc/aacpsdsp: simplify R-V V stereo interpolate
Rémi Denis-Courmont
remi at remlab.net
Fri Sep 29 19:26:01 EEST 2023
Remove some useless vector splat.
---
libavcodec/riscv/aacpsdsp_rvv.S | 12 ++++--------
1 file changed, 4 insertions(+), 8 deletions(-)
diff --git a/libavcodec/riscv/aacpsdsp_rvv.S b/libavcodec/riscv/aacpsdsp_rvv.S
index b581383f77..b85a5cc92c 100644
--- a/libavcodec/riscv/aacpsdsp_rvv.S
+++ b/libavcodec/riscv/aacpsdsp_rvv.S
@@ -238,20 +238,16 @@ func ff_ps_stereo_interpolate_rvv, zve32f
flw ft1, 4(a3)
vfmv.v.f v19, ft3
flw ft2, 8(a3)
- vfmv.v.f v20, ft0
flw ft3, 12(a3)
- vfmv.v.f v21, ft1
fcvt.s.wu ft4, t0 // (float)(vlenb / sizeof (float))
- vfmv.v.f v22, ft2
+ vfmacc.vf v16, ft0, v24 // h0 += (i + 1) * h0_step
fmul.s ft0, ft0, ft4
- vfmv.v.f v23, ft3
+ vfmacc.vf v17, ft1, v24
fmul.s ft1, ft1, ft4
- vfmacc.vv v16, v24, v20 // h0 += (i + 1) * h0_step
+ vfmacc.vf v18, ft2, v24
fmul.s ft2, ft2, ft4
- vfmacc.vv v17, v24, v21
+ vfmacc.vf v19, ft3, v24
fmul.s ft3, ft3, ft4
- vfmacc.vv v18, v24, v22
- vfmacc.vv v19, v24, v23
1:
vsetvli t0, a4, e32, m1, ta, ma
vlseg2e32.v v8, (a0) // v8:l_re, v9:l_im
--
2.40.1
More information about the ffmpeg-devel
mailing list