mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2025-01-19 05:49:09 +02:00
lavc/h264dsp: stick R-V V biweight to 16-bit
T-Head C908 (ns): h264_biweight2_8_c: 2414.5 h264_biweight2_8_rvv_i32: 701.8 (before) h264_biweight2_8_rvv_i32: 468.5 (after) h264_biweight4_8_c: 4655.3 h264_biweight4_8_rvv_i32: 1377.5 (before) h264_biweight4_8_rvv_i32: 931.8 (after) h264_biweight8_8_c: 9701.5 h264_biweight8_8_rvv_i32: 2896.0 (before) h264_biweight8_8_rvv_i32: 2070.5 (after) h264_biweight16_8_c: 18025.0 h264_biweight16_8_rvv_i32: 3460.8 (before) h264_biweight16_8_rvv_i32: 1978.0 (after) SpacemiT X60 (ns): h264_biweight2_8_c: 2415.5 h264_biweight2_8_rvv_i32: 478.2 (before) h264_biweight2_8_rvv_i32: 362.8 (after) h264_biweight4_8_c: 4655.3 h264_biweight4_8_rvv_i32: 946.7 (before) h264_biweight4_8_rvv_i32: 727.3 (after) h264_biweight8_8_c: 9061.8 h264_biweight8_8_rvv_i32: 2071.7 (before) h264_biweight8_8_rvv_i32: 1685.8 (after) h264_biweight16_8_c: 18020.5 h264_biweight16_8_rvv_i32: 3457.2 (before) h264_biweight16_8_rvv_i32: 1935.8 (after)
This commit is contained in:
parent
670ff6c7ce
commit
afd45c7ff7
@ -56,22 +56,21 @@ func ff_h264_biweight_pixels_simple_8_rvv, zve32x
|
|||||||
addi a7, a7, 1
|
addi a7, a7, 1
|
||||||
ori a7, a7, 1
|
ori a7, a7, 1
|
||||||
sll a7, a7, a4
|
sll a7, a7, a4
|
||||||
|
addi a4, a4, 1
|
||||||
1:
|
1:
|
||||||
vsetvli zero, t6, e32, m4, ta, ma
|
vsetvli zero, t6, e16, m2, ta, ma
|
||||||
vle8.v v8, (a0)
|
vle8.v v8, (a0)
|
||||||
addi a3, a3, -1
|
addi a3, a3, -1
|
||||||
vle8.v v12, (a1)
|
vle8.v v12, (a1)
|
||||||
add a1, a1, a2
|
add a1, a1, a2
|
||||||
vmv.v.x v16, a7
|
vmv.v.x v16, a7
|
||||||
vsetvli zero, zero, e16, m2, ta, ma
|
vsetvli zero, zero, e8, m1, ta, ma
|
||||||
vzext.vf2 v24, v8
|
vwmaccsu.vx v16, a5, v8
|
||||||
vzext.vf2 v28, v12
|
vwmaccsu.vx v16, a6, v12
|
||||||
vwmaccsu.vx v16, a5, v24
|
vsetvli zero, zero, e16, m2, ta, ma
|
||||||
vwmaccsu.vx v16, a6, v28
|
|
||||||
vnclip.wx v16, v16, a4
|
|
||||||
vmax.vx v16, v16, zero
|
vmax.vx v16, v16, zero
|
||||||
vsetvli zero, zero, e8, m1, ta, ma
|
vsetvli zero, zero, e8, m1, ta, ma
|
||||||
vnclipu.wi v8, v16, 1
|
vnclipu.wx v8, v16, a4
|
||||||
vse8.v v8, (a0)
|
vse8.v v8, (a0)
|
||||||
add a0, a0, a2
|
add a0, a0, a2
|
||||||
bnez a3, 1b
|
bnez a3, 1b
|
||||||
@ -121,33 +120,29 @@ func ff_h264_biweight_pixels_8_rvv, zve32x
|
|||||||
addi a7, a7, 1
|
addi a7, a7, 1
|
||||||
ori a7, a7, 1
|
ori a7, a7, 1
|
||||||
sll a7, a7, a4
|
sll a7, a7, a4
|
||||||
|
addi a4, a4, 1
|
||||||
1:
|
1:
|
||||||
mv t0, a0
|
mv t0, a0
|
||||||
mv t1, a1
|
mv t1, a1
|
||||||
mv t5, t6
|
mv t5, t6
|
||||||
2:
|
2:
|
||||||
vsetvli t2, a3, e32, m8, ta, ma
|
vsetvli t2, a3, e16, m8, ta, ma
|
||||||
vlsseg2e8.v v0, (t0), a2
|
vlsseg2e8.v v0, (t0), a2
|
||||||
vlsseg2e8.v v4, (t1), a2
|
vlsseg2e8.v v8, (t1), a2
|
||||||
addi t5, t5, -2
|
addi t5, t5, -2
|
||||||
vmv.v.x v16, a7
|
vmv.v.x v16, a7
|
||||||
vmv.v.x v24, a7
|
vmv.v.x v24, a7
|
||||||
vsetvli zero, zero, e16, m4, ta, ma
|
vsetvli zero, zero, e8, m4, ta, ma
|
||||||
vzext.vf2 v8, v0
|
vwmaccsu.vx v16, a5, v0
|
||||||
vzext.vf2 v12, v2
|
vwmaccsu.vx v24, a5, v4
|
||||||
vwmaccsu.vx v16, a5, v8
|
|
||||||
vwmaccsu.vx v24, a5, v12
|
|
||||||
vzext.vf2 v8, v4
|
|
||||||
vzext.vf2 v12, v6
|
|
||||||
vwmaccsu.vx v16, a6, v8
|
vwmaccsu.vx v16, a6, v8
|
||||||
vwmaccsu.vx v24, a6, v12
|
vwmaccsu.vx v24, a6, v12
|
||||||
vnclip.wx v8, v16, a4
|
vsetvli zero, zero, e16, m8, ta, ma
|
||||||
vnclip.wx v12, v24, a4
|
vmax.vx v16, v16, zero
|
||||||
vmax.vx v8, v8, zero
|
vmax.vx v24, v24, zero
|
||||||
vmax.vx v12, v12, zero
|
vsetvli zero, zero, e8, m4, ta, ma
|
||||||
vsetvli zero, zero, e8, m2, ta, ma
|
vnclipu.wx v0, v16, a4
|
||||||
vnclipu.wi v0, v8, 1
|
vnclipu.wx v4, v24, a4
|
||||||
vnclipu.wi v2, v12, 1
|
|
||||||
vssseg2e8.v v0, (t0), a2
|
vssseg2e8.v v0, (t0), a2
|
||||||
addi t0, t0, 2
|
addi t0, t0, 2
|
||||||
addi t1, t1, 2
|
addi t1, t1, 2
|
||||||
|
Loading…
x
Reference in New Issue
Block a user