1) Take the reductive sum out of the loop,
leaving a regular vector addition in the loop.
2) Merge the addition and the multiplication.
3) Unroll.
Before:
scalarproduct_float_rvv_f32: 832.5
After:
scalarproduct_float_rvv_f32: 275.2
---
libavutil/riscv/float_dsp_rvv.S | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/libavutil/riscv/float_dsp_rvv.S b/libavutil/riscv/float_dsp_rvv.S
index 77961b7387..605729b1d4 100644
--- a/libavutil/riscv/float_dsp_rvv.S
+++ b/libavutil/riscv/float_dsp_rvv.S
@@ -166,20 +166,22 @@ endfunc
// a0 = (a0).(a1) [0..a2-1]
func ff_scalarproduct_float_rvv, zve32f
- vsetivli zero, 1, e32, m1, ta, ma
- vmv.s.x v8, zero
+ vsetvli t0, zero, e32, m8, ta, ma
+ vmv.v.x v8, zero
+ vmv.s.x v0, zero
1:
- vsetvli t0, a2, e32, m1, ta, ma
+ vsetvli t0, a2, e32, m8, tu, ma
vle32.v v16, (a0)
sub a2, a2, t0
vle32.v v24, (a1)
sh2add a0, t0, a0
- vfmul.vv v16, v16, v24
+ vfmacc.vv v8, v16, v24
sh2add a1, t0, a1
- vfredusum.vs v8, v16, v8
bnez a2, 1b
- vfmv.f.s fa0, v8
+ vsetvli t0, zero, e32, m8, ta, ma
+ vfredusum.vs v0, v8, v0
+ vfmv.f.s fa0, v0
NOHWF fmv.x.w a0, fa0
ret
endfunc
--
2.40.1
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
