| Message ID | tencent_3553AA0116564325C5B573CC589061313C08@qq.com |
|---|---|
| State | New |
| Headers | show |
| Series | [FFmpeg-devel,01/10] lavc/vp8dsp: R-V V put_vp8_pixels | expand |
Le lauantaina 4. toukokuuta 2024, 17.48.31 EEST uk7b@foxmail.com a écrit : > From: sunyuechi <sunyuechi@iscas.ac.cn> > > C908: > vp8_put_bilin4_h_c: 373.5 > vp8_put_bilin4_h_rvv_i32: 158.7 > vp8_put_bilin8_h_c: 1437.7 > vp8_put_bilin8_h_rvv_i32: 318.7 > vp8_put_bilin16_h_c: 2845.7 > vp8_put_bilin16_h_rvv_i32: 374.7 > --- > libavcodec/riscv/vp8dsp_init.c | 11 +++++++ > libavcodec/riscv/vp8dsp_rvv.S | 54 ++++++++++++++++++++++++++++++++++ > 2 files changed, 65 insertions(+) > > diff --git a/libavcodec/riscv/vp8dsp_init.c b/libavcodec/riscv/vp8dsp_init.c > index c364de3dc9..32cb4893a4 100644 > --- a/libavcodec/riscv/vp8dsp_init.c > +++ b/libavcodec/riscv/vp8dsp_init.c > @@ -34,6 +34,10 @@ VP8_EPEL(16, rvv); > VP8_EPEL(8, rvv); > VP8_EPEL(4, rvv); > > +VP8_BILIN(16, rvv); > +VP8_BILIN(8, rvv); > +VP8_BILIN(4, rvv); > + > av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c) > { > #if HAVE_RVV > @@ -47,6 +51,13 @@ av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c) > c->put_vp8_bilinear_pixels_tab[0][0][0] = ff_put_vp8_pixels16_rvv; > c->put_vp8_bilinear_pixels_tab[1][0][0] = ff_put_vp8_pixels8_rvv; > c->put_vp8_bilinear_pixels_tab[2][0][0] = ff_put_vp8_pixels4_rvv; > + > + c->put_vp8_bilinear_pixels_tab[0][0][1] = ff_put_vp8_bilin16_h_rvv; > + c->put_vp8_bilinear_pixels_tab[0][0][2] = > ff_put_vp8_bilin16_h_rvv; + c->put_vp8_bilinear_pixels_tab[1][0][1] > = ff_put_vp8_bilin8_h_rvv; + c->put_vp8_bilinear_pixels_tab[1][0][2] > = ff_put_vp8_bilin8_h_rvv; + c->put_vp8_bilinear_pixels_tab[2][0][1] > = ff_put_vp8_bilin4_h_rvv; + c->put_vp8_bilinear_pixels_tab[2][0][2] > = ff_put_vp8_bilin4_h_rvv; } > #endif > } > diff --git a/libavcodec/riscv/vp8dsp_rvv.S b/libavcodec/riscv/vp8dsp_rvv.S > index 063ab7110c..c8d265e516 100644 > --- a/libavcodec/riscv/vp8dsp_rvv.S > +++ b/libavcodec/riscv/vp8dsp_rvv.S > @@ -98,3 +98,57 @@ func ff_put_vp8_pixels4_rvv, zve32x > vsetivli zero, 4, e8, mf4, ta, ma > put_vp8_pixels > endfunc > + > +.macro bilin_h_load dst len > +.ifc \len,4 > + vsetivli zero, 5, e8, mf2, ta, ma > +.elseif \len == 8 > + vsetivli zero, 9, e8, m1, ta, ma > +.else > + vsetivli zero, 17, e8, m2, ta, ma > +.endif It might be worth defining a pseudo-instruction macro in asm.S that would statically compute the minimal LMUL from just the AVL and SEW. Then we don't to repeat these if blocks times and again, we can just do: vsetvlstatic \len + 1, e8 or something like that > + > + vle8.v \dst, (a2) > + vslide1down.vx v2, \dst, t5 > + > +.ifc \len,4 > + vsetivli zero, 4, e8, mf4, ta, ma > +.elseif \len == 8 > + vsetivli zero, 8, e8, mf2, ta, ma > +.else > + vsetivli zero, 16, e8, m1, ta, ma > +.endif > + > + vwmulu.vx v28, \dst, t1 > + vwmaccu.vx v28, a5, v2 > + vwaddu.wx v24, v28, t4 > + vnsra.wi \dst, v24, 3 > +.endm > + > +.macro put_vp8_bilin_h len > + li t1, 8 > + li t4, 4 > + li t5, 1 > + sub t1, t1, a5 > +1: > + addi a4, a4, -1 > + bilin_h_load v0, \len > + vse8.v v0, (a0) > + add a2, a2, a3 > + add a0, a0, a1 > + bnez a4, 1b > + > + ret > +.endm FWIW, it should be possible to include func and endfunc in the macro too. > + > +func ff_put_vp8_bilin16_h_rvv, zve32x > + put_vp8_bilin_h 16 > +endfunc > + > +func ff_put_vp8_bilin8_h_rvv, zve32x > + put_vp8_bilin_h 8 > +endfunc > + > +func ff_put_vp8_bilin4_h_rvv, zve32x > + put_vp8_bilin_h 4 > +endfunc
Le lauantaina 4. toukokuuta 2024, 21.02.25 EEST Rémi Denis-Courmont a écrit : > Le lauantaina 4. toukokuuta 2024, 17.48.31 EEST uk7b@foxmail.com a écrit : > > From: sunyuechi <sunyuechi@iscas.ac.cn> > > > > C908: > > vp8_put_bilin4_h_c: 373.5 > > vp8_put_bilin4_h_rvv_i32: 158.7 > > vp8_put_bilin8_h_c: 1437.7 > > vp8_put_bilin8_h_rvv_i32: 318.7 > > vp8_put_bilin16_h_c: 2845.7 > > vp8_put_bilin16_h_rvv_i32: 374.7 > > --- > > > > libavcodec/riscv/vp8dsp_init.c | 11 +++++++ > > libavcodec/riscv/vp8dsp_rvv.S | 54 ++++++++++++++++++++++++++++++++++ > > 2 files changed, 65 insertions(+) > > > > diff --git a/libavcodec/riscv/vp8dsp_init.c > > b/libavcodec/riscv/vp8dsp_init.c index c364de3dc9..32cb4893a4 100644 > > --- a/libavcodec/riscv/vp8dsp_init.c > > +++ b/libavcodec/riscv/vp8dsp_init.c > > @@ -34,6 +34,10 @@ VP8_EPEL(16, rvv); > > > > VP8_EPEL(8, rvv); > > VP8_EPEL(4, rvv); > > > > +VP8_BILIN(16, rvv); > > +VP8_BILIN(8, rvv); > > +VP8_BILIN(4, rvv); > > + > > > > av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c) > > { > > #if HAVE_RVV > > > > @@ -47,6 +51,13 @@ av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c) > > > > c->put_vp8_bilinear_pixels_tab[0][0][0] = > > ff_put_vp8_pixels16_rvv; > > c->put_vp8_bilinear_pixels_tab[1][0][0] = ff_put_vp8_pixels8_rvv; > > c->put_vp8_bilinear_pixels_tab[2][0][0] = ff_put_vp8_pixels4_rvv; > > > > + > > + c->put_vp8_bilinear_pixels_tab[0][0][1] = > > ff_put_vp8_bilin16_h_rvv; + > > c->put_vp8_bilinear_pixels_tab[0][0][2] = > > ff_put_vp8_bilin16_h_rvv; + c->put_vp8_bilinear_pixels_tab[1][0][1] > > = ff_put_vp8_bilin8_h_rvv; + > > c->put_vp8_bilinear_pixels_tab[1][0][2] > > = ff_put_vp8_bilin8_h_rvv; + > > c->put_vp8_bilinear_pixels_tab[2][0][1] > > = ff_put_vp8_bilin4_h_rvv; + > > c->put_vp8_bilinear_pixels_tab[2][0][2] > > = ff_put_vp8_bilin4_h_rvv; } > > > > #endif > > } > > > > diff --git a/libavcodec/riscv/vp8dsp_rvv.S b/libavcodec/riscv/vp8dsp_rvv.S > > index 063ab7110c..c8d265e516 100644 > > --- a/libavcodec/riscv/vp8dsp_rvv.S > > +++ b/libavcodec/riscv/vp8dsp_rvv.S > > @@ -98,3 +98,57 @@ func ff_put_vp8_pixels4_rvv, zve32x > > > > vsetivli zero, 4, e8, mf4, ta, ma > > put_vp8_pixels > > > > endfunc > > > > + > > +.macro bilin_h_load dst len > > +.ifc \len,4 > > + vsetivli zero, 5, e8, mf2, ta, ma > > +.elseif \len == 8 > > + vsetivli zero, 9, e8, m1, ta, ma > > +.else > > + vsetivli zero, 17, e8, m2, ta, ma > > +.endif > > It might be worth defining a pseudo-instruction macro in asm.S that would > statically compute the minimal LMUL from just the AVL and SEW. Then we don't > to repeat these if blocks times and again, we can just do: > > vsetvlstatic \len + 1, e8 > > or something like that On second thought, concealing the LMUL from the programmer is perhaps not the smartest idea, since it heavily constrains register allocation.
diff --git a/libavcodec/riscv/vp8dsp_init.c b/libavcodec/riscv/vp8dsp_init.c index c364de3dc9..32cb4893a4 100644 --- a/libavcodec/riscv/vp8dsp_init.c +++ b/libavcodec/riscv/vp8dsp_init.c @@ -34,6 +34,10 @@ VP8_EPEL(16, rvv); VP8_EPEL(8, rvv); VP8_EPEL(4, rvv); +VP8_BILIN(16, rvv); +VP8_BILIN(8, rvv); +VP8_BILIN(4, rvv); + av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c) { #if HAVE_RVV @@ -47,6 +51,13 @@ av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c) c->put_vp8_bilinear_pixels_tab[0][0][0] = ff_put_vp8_pixels16_rvv; c->put_vp8_bilinear_pixels_tab[1][0][0] = ff_put_vp8_pixels8_rvv; c->put_vp8_bilinear_pixels_tab[2][0][0] = ff_put_vp8_pixels4_rvv; + + c->put_vp8_bilinear_pixels_tab[0][0][1] = ff_put_vp8_bilin16_h_rvv; + c->put_vp8_bilinear_pixels_tab[0][0][2] = ff_put_vp8_bilin16_h_rvv; + c->put_vp8_bilinear_pixels_tab[1][0][1] = ff_put_vp8_bilin8_h_rvv; + c->put_vp8_bilinear_pixels_tab[1][0][2] = ff_put_vp8_bilin8_h_rvv; + c->put_vp8_bilinear_pixels_tab[2][0][1] = ff_put_vp8_bilin4_h_rvv; + c->put_vp8_bilinear_pixels_tab[2][0][2] = ff_put_vp8_bilin4_h_rvv; } #endif } diff --git a/libavcodec/riscv/vp8dsp_rvv.S b/libavcodec/riscv/vp8dsp_rvv.S index 063ab7110c..c8d265e516 100644 --- a/libavcodec/riscv/vp8dsp_rvv.S +++ b/libavcodec/riscv/vp8dsp_rvv.S @@ -98,3 +98,57 @@ func ff_put_vp8_pixels4_rvv, zve32x vsetivli zero, 4, e8, mf4, ta, ma put_vp8_pixels endfunc + +.macro bilin_h_load dst len +.ifc \len,4 + vsetivli zero, 5, e8, mf2, ta, ma +.elseif \len == 8 + vsetivli zero, 9, e8, m1, ta, ma +.else + vsetivli zero, 17, e8, m2, ta, ma +.endif + + vle8.v \dst, (a2) + vslide1down.vx v2, \dst, t5 + +.ifc \len,4 + vsetivli zero, 4, e8, mf4, ta, ma +.elseif \len == 8 + vsetivli zero, 8, e8, mf2, ta, ma +.else + vsetivli zero, 16, e8, m1, ta, ma +.endif + + vwmulu.vx v28, \dst, t1 + vwmaccu.vx v28, a5, v2 + vwaddu.wx v24, v28, t4 + vnsra.wi \dst, v24, 3 +.endm + +.macro put_vp8_bilin_h len + li t1, 8 + li t4, 4 + li t5, 1 + sub t1, t1, a5 +1: + addi a4, a4, -1 + bilin_h_load v0, \len + vse8.v v0, (a0) + add a2, a2, a3 + add a0, a0, a1 + bnez a4, 1b + + ret +.endm + +func ff_put_vp8_bilin16_h_rvv, zve32x + put_vp8_bilin_h 16 +endfunc + +func ff_put_vp8_bilin8_h_rvv, zve32x + put_vp8_bilin_h 8 +endfunc + +func ff_put_vp8_bilin4_h_rvv, zve32x + put_vp8_bilin_h 4 +endfunc
From: sunyuechi <sunyuechi@iscas.ac.cn> C908: vp8_put_bilin4_h_c: 373.5 vp8_put_bilin4_h_rvv_i32: 158.7 vp8_put_bilin8_h_c: 1437.7 vp8_put_bilin8_h_rvv_i32: 318.7 vp8_put_bilin16_h_c: 2845.7 vp8_put_bilin16_h_rvv_i32: 374.7 --- libavcodec/riscv/vp8dsp_init.c | 11 +++++++ libavcodec/riscv/vp8dsp_rvv.S | 54 ++++++++++++++++++++++++++++++++++ 2 files changed, 65 insertions(+)