lavc/vp8dsp: R-V V put_bilin_hv

C908:
vp8_put_bilin4_hv_c: 561.0
vp8_put_bilin4_hv_rvv_i32: 232.7
vp8_put_bilin8_hv_c: 2162.7
vp8_put_bilin8_hv_rvv_i32: 506.7
vp8_put_bilin16_hv_c: 4769.7
vp8_put_bilin16_hv_rvv_i32: 556.7

Signed-off-by: Rémi Denis-Courmont <remi@remlab.net>

libavcodec/riscv/vp8dsp_init.c

@@ -67,6 +67,19 @@ av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c)
         c->put_vp8_bilinear_pixels_tab[1][2][0] = ff_put_vp8_bilin8_v_rvv;
         c->put_vp8_bilinear_pixels_tab[2][1][0] = ff_put_vp8_bilin4_v_rvv;
         c->put_vp8_bilinear_pixels_tab[2][2][0] = ff_put_vp8_bilin4_v_rvv;
+
+        c->put_vp8_bilinear_pixels_tab[0][1][1] = ff_put_vp8_bilin16_hv_rvv;
+        c->put_vp8_bilinear_pixels_tab[0][1][2] = ff_put_vp8_bilin16_hv_rvv;
+        c->put_vp8_bilinear_pixels_tab[0][2][1] = ff_put_vp8_bilin16_hv_rvv;
+        c->put_vp8_bilinear_pixels_tab[0][2][2] = ff_put_vp8_bilin16_hv_rvv;
+        c->put_vp8_bilinear_pixels_tab[1][1][1] = ff_put_vp8_bilin8_hv_rvv;
+        c->put_vp8_bilinear_pixels_tab[1][1][2] = ff_put_vp8_bilin8_hv_rvv;
+        c->put_vp8_bilinear_pixels_tab[1][2][1] = ff_put_vp8_bilin8_hv_rvv;
+        c->put_vp8_bilinear_pixels_tab[1][2][2] = ff_put_vp8_bilin8_hv_rvv;
+        c->put_vp8_bilinear_pixels_tab[2][1][1] = ff_put_vp8_bilin4_hv_rvv;
+        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;
     }
 #endif
 #endif

libavcodec/riscv/vp8dsp_rvv.S

@@ -116,7 +116,33 @@ func ff_put_vp8_bilin\len\()_\type\()_rvv, zve32x
 endfunc
 .endm
 
+.macro put_vp8_bilin_hv len
+func ff_put_vp8_bilin\len\()_hv_rvv, zve32x
+        vsetvlstatic8   \len
+        li              t3, 8
+        sub             t1, t3, a5
+        sub             t2, t3, a6
+        li              t4, 4
+        bilin_load      v4, \len, h, a5
+        add             a2, a2, a3
+1:
+        addi            a4, a4, -1
+        vwmulu.vx       v20, v4, t2
+        bilin_load      v4, \len, h, a5
+        vwmaccu.vx      v20, a6, v4
+        vwaddu.wx       v24, v20, t4
+        vnsra.wi        v0, v24, 3
+        vse8.v          v0, (a0)
+        add             a2, a2, a3
+        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
 .endr