RepoMirrors/ffmpeg
1
0
Fork 0
mirror of https://git.ffmpeg.org/ffmpeg.git synced 2024-12-27 01:42:20 +00:00
Code Issues Projects Releases Wiki Activity

lavu/float_dsp: rework RISC-V V scalar product

Browse Source 
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
This commit is contained in:
Rémi Denis-Courmont 2023-07-17 20:11:08 +03:00
parent b710f881ce
commit 29b9d616c2
1 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
libavutil/riscv/float_dsp_rvv.S
View File

@ -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