[FFmpeg-devel] [PATCH 05/10] lavc/vp8dsp: R-V V put_epel h

[uk7b at foxmail.com]

From: sunyuechi <sunyuechi at iscas.ac.cn>

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
---
 libavcodec/riscv/vp8dsp_init.c |   7 +++
 libavcodec/riscv/vp8dsp_rvv.S  | 105 +++++++++++++++++++++++++++++++++
 2 files changed, 112 insertions(+)

diff --git a/libavcodec/riscv/vp8dsp_init.c b/libavcodec/riscv/vp8dsp_init.c
index 02dbda979e..6614d661f7 100644
--- a/libavcodec/riscv/vp8dsp_init.c
+++ b/libavcodec/riscv/vp8dsp_init.c
@@ -78,6 +78,13 @@ 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
 }
diff --git a/libavcodec/riscv/vp8dsp_rvv.S b/libavcodec/riscv/vp8dsp_rvv.S
index 9d4ffed255..84e8ec61de 100644
--- a/libavcodec/riscv/vp8dsp_rvv.S
+++ b/libavcodec/riscv/vp8dsp_rvv.S
@@ -223,3 +223,108 @@ endfunc
 func ff_put_vp8_bilin4_hv_rvv, zve32x
         put_vp8_bilin_hv 4
 endfunc
+
+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
+
+.ifc \len,4
+        vsetvli         zero, zero, e16, mf2, ta, ma
+.elseif \len == 8
+        vsetvli         zero, zero, e16, m1, ta, ma
+.else
+        vsetvli         zero, zero, e16, m2, ta, ma
+.endif
+
+        vwadd.vv        v24, v16, v20
+        vnsra.wi        v24, v24, 7
+        vmax.vx         v24, v24, zero
+.ifc \len,4
+        vsetvli         zero, zero, e8, mf4, ta, ma
+.elseif \len == 8
+        vsetvli         zero, zero, e8, mf2, ta, ma
+.else
+        vsetvli         zero, zero, e8, m1, ta, ma
+.endif
+        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
+        epel_filter     \size
+
+.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
+
+1:
+        addi            a4, a4, -1
+        epel_load_inc   v30 \len \size
+        vse8.v          v30, (a0)
+        add             a0, a0, a1
+        bnez            a4, 1b
+
+        ret
+.endm
+
+.irp len 16,8,4
+func ff_put_vp8_epel\len\()_h6_rvv, zve32x
+        epel \len 6
+endfunc
+
+func ff_put_vp8_epel\len\()_h4_rvv, zve32x
+        epel \len 4
+endfunc
+.endr
-- 
2.45.0