highperfocused/ffmpeg
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

lavc/vp8dsp: R-V V put_epel h

Browse Source 
C908:
vp8_put_epel4_h4_c: 10.7
vp8_put_epel4_h4_rvv_i32: 5.0
vp8_put_epel4_h6_c: 15.0
vp8_put_epel4_h6_rvv_i32: 6.2
vp8_put_epel8_h4_c: 43.2
vp8_put_epel8_h4_rvv_i32: 11.2
vp8_put_epel8_h6_c: 57.5
vp8_put_epel8_h6_rvv_i32: 13.5
vp8_put_epel16_h4_c: 92.5
vp8_put_epel16_h4_rvv_i32: 13.7
vp8_put_epel16_h6_c: 139.0
vp8_put_epel16_h6_rvv_i32: 16.5

Signed-off-by: Rémi Denis-Courmont <remi@remlab.net>
This commit is contained in:
sunyuechi
2024-05-08 00:54:07 +08:00
committed by Rémi Denis-Courmont
parent 538f217bbb
commit 109daea619
2 changed files with 97 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
libavcodec/riscv/vp8dsp_init.c
View File

@@ -33,6 +33,9 @@ void ff_vp8_idct_dc_add4uv_rvv(uint8_t *dst, int16_t block[4][16], ptrdiff_t str
VP8_EPEL(16, rvi);
VP8_EPEL(8, rvi);
VP8_EPEL(4, rvi);
VP8_EPEL(16, rvv);
VP8_EPEL(8, rvv);
VP8_EPEL(4, rvv);
VP8_BILIN(16, rvv);
VP8_BILIN(8, rvv);
@@ -80,6 +83,13 @@ av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c)
c->put_vp8_bilinear_pixels_tab[2][1][2] = ff_put_vp8_bilin4_hv_rvv;
c->put_vp8_bilinear_pixels_tab[2][2][1] = ff_put_vp8_bilin4_hv_rvv;
c->put_vp8_bilinear_pixels_tab[2][2][2] = ff_put_vp8_bilin4_hv_rvv;
c->put_vp8_epel_pixels_tab[0][0][2] = ff_put_vp8_epel16_h6_rvv;
c->put_vp8_epel_pixels_tab[1][0][2] = ff_put_vp8_epel8_h6_rvv;
c->put_vp8_epel_pixels_tab[2][0][2] = ff_put_vp8_epel4_h6_rvv;
c->put_vp8_epel_pixels_tab[0][0][1] = ff_put_vp8_epel16_h4_rvv;
c->put_vp8_epel_pixels_tab[1][0][1] = ff_put_vp8_epel8_h4_rvv;
c->put_vp8_epel_pixels_tab[2][0][1] = ff_put_vp8_epel4_h4_rvv;
}
#endif
#endif

87
libavcodec/riscv/vp8dsp_rvv.S
View File

@@ -32,6 +32,16 @@
.endif
.endm
.macro vsetvlstatic16 len
.if \len <= 4
vsetivli zero, \len, e16, mf2, ta, ma
.elseif \len <= 8
vsetivli zero, \len, e16, m1, ta, ma
.elseif \len <= 16
vsetivli zero, \len, e16, m2, ta, ma
.endif
.endm
.macro vp8_idct_dc_add
vlse32.v v0, (a0), a2
lh a5, 0(a1)
@@ -141,8 +151,85 @@ func ff_put_vp8_bilin\len\()_hv_rvv, zve32x
endfunc
.endm
const subpel_filters
.byte 0, -6, 123, 12, -1, 0
.byte 2, -11, 108, 36, -8, 1
.byte 0, -9, 93, 50, -6, 0
.byte 3, -16, 77, 77, -16, 3
.byte 0, -6, 50, 93, -9, 0
.byte 1, -8, 36, 108, -11, 2
.byte 0, -1, 12, 123, -6, 0
endconst
.macro epel_filter size
lla t2, subpel_filters
addi t0, a5, -1
li t1, 6
mul t0, t0, t1
add t0, t0, t2
.irp n 1,2,3,4
lb t\n, \n(t0)
.endr
.ifc \size,6
lb t5, 5(t0)
lb t0, (t0)
.endif
.endm
.macro epel_load dst len size
addi t6, a2, -1
addi a7, a2, 1
vle8.v v24, (a2)
vle8.v v22, (t6)
vle8.v v26, (a7)
addi a7, a7, 1
vle8.v v28, (a7)
vwmulu.vx v16, v24, t2
vwmulu.vx v20, v26, t3
.ifc \size,6
addi t6, t6, -1
addi a7, a7, 1
vle8.v v24, (t6)
vle8.v v26, (a7)
vwmaccu.vx v16, t0, v24
vwmaccu.vx v16, t5, v26
.endif
li t6, 64
vwmaccsu.vx v16, t1, v22
vwmaccsu.vx v16, t4, v28
vwadd.wx v16, v16, t6
vsetvlstatic16 \len
vwadd.vv v24, v16, v20
vnsra.wi v24, v24, 7
vmax.vx v24, v24, zero
vsetvlstatic8 \len
vnclipu.wi \dst, v24, 0
.endm
.macro epel_load_inc dst len size
epel_load \dst \len \size
add a2, a2, a3
.endm
.macro epel len size type
func ff_put_vp8_epel\len\()_\type\()\size\()_rvv, zve32x
epel_filter \size
vsetvlstatic8 \len
1:
addi a4, a4, -1
epel_load_inc v30 \len \size
vse8.v v30, (a0)
add a0, a0, a1
bnez a4, 1b
ret
endfunc
.endm
.irp len 16,8,4
put_vp8_bilin_h_v \len h a5
put_vp8_bilin_h_v \len v a6
put_vp8_bilin_hv \len
epel \len 6 h
epel \len 4 h
.endr