[FFmpeg-cvslog] lavc/vp8dsp: R-V V put_bilin_h v

[sunyuechi]

ffmpeg | branch: master | sunyuechi <sunyuechi at iscas.ac.cn> | Wed May  8 00:54:05 2024 +0800| [bb5039b3cb79968bd1d36db60c272d5686e0b064] | committer: Rémi Denis-Courmont

lavc/vp8dsp: R-V V put_bilin_h v

C908:
vp8_put_bilin4_h_c: 367.0
vp8_put_bilin4_h_rvv_i32: 137.7
vp8_put_bilin4_v_c: 377.0
vp8_put_bilin4_v_rvv_i32: 137.7
vp8_put_bilin8_h_c: 1431.0
vp8_put_bilin8_h_rvv_i32: 297.5
vp8_put_bilin8_v_c: 1449.0
vp8_put_bilin8_v_rvv_i32: 297.5
vp8_put_bilin16_h_c: 2839.0
vp8_put_bilin16_h_rvv_i32: 344.7
vp8_put_bilin16_v_c: 2857.0
vp8_put_bilin16_v_rvv_i32: 344.7

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

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=bb5039b3cb79968bd1d36db60c272d5686e0b064
---

 libavcodec/riscv/vp8dsp_init.c | 21 ++++++++++++++++++
 libavcodec/riscv/vp8dsp_rvv.S  | 49 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+)

diff --git a/libavcodec/riscv/vp8dsp_init.c b/libavcodec/riscv/vp8dsp_init.c
index fa3feeacf7..afffa6de2f 100644
--- a/libavcodec/riscv/vp8dsp_init.c
+++ b/libavcodec/riscv/vp8dsp_init.c
@@ -34,6 +34,10 @@ VP8_EPEL(16, rvi);
 VP8_EPEL(8,  rvi);
 VP8_EPEL(4,  rvi);
 
+VP8_BILIN(16, rvv);
+VP8_BILIN(8,  rvv);
+VP8_BILIN(4,  rvv);
+
 av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c)
 {
 #if HAVE_RV
@@ -48,6 +52,23 @@ av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c)
         c->put_vp8_epel_pixels_tab[2][0][0] = ff_put_vp8_pixels4_rvi;
         c->put_vp8_bilinear_pixels_tab[2][0][0] = ff_put_vp8_pixels4_rvi;
     }
+#if HAVE_RVV
+    if (flags & AV_CPU_FLAG_RVV_I32 && ff_get_rv_vlenb() >= 16) {
+        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;
+
+        c->put_vp8_bilinear_pixels_tab[0][1][0] = ff_put_vp8_bilin16_v_rvv;
+        c->put_vp8_bilinear_pixels_tab[0][2][0] = ff_put_vp8_bilin16_v_rvv;
+        c->put_vp8_bilinear_pixels_tab[1][1][0] = ff_put_vp8_bilin8_v_rvv;
+        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;
+    }
+#endif
 #endif
 }
 
diff --git a/libavcodec/riscv/vp8dsp_rvv.S b/libavcodec/riscv/vp8dsp_rvv.S
index 8a0773f964..ec8ff917b9 100644
--- a/libavcodec/riscv/vp8dsp_rvv.S
+++ b/libavcodec/riscv/vp8dsp_rvv.S
@@ -20,6 +20,18 @@
 
 #include "libavutil/riscv/asm.S"
 
+.macro vsetvlstatic8 len
+.if \len <= 4
+        vsetivli        zero, \len, e8, mf4, ta, ma
+.elseif \len <= 8
+        vsetivli        zero, \len, e8, mf2, ta, ma
+.elseif \len <= 16
+        vsetivli        zero, \len, e8, m1, ta, ma
+.elseif \len <= 31
+        vsetivli        zero, \len, e8, m2, ta, ma
+.endif
+.endm
+
 .macro vp8_idct_dc_add
         vlse32.v      v0, (a0), a2
         lh            a5, 0(a1)
@@ -71,3 +83,40 @@ func ff_vp8_idct_dc_add4uv_rvv, zve32x
 
         ret
 endfunc
+
+.macro bilin_load dst len type mn
+.ifc \type,v
+        add             t5, a2, a3
+.else
+        addi            t5, a2, 1
+.endif
+        vle8.v          \dst, (a2)
+        vle8.v          v2, (t5)
+        vwmulu.vx       v28, \dst, t1
+        vwmaccu.vx      v28, \mn, v2
+        vwaddu.wx       v24, v28, t4
+        vnsra.wi        \dst, v24, 3
+.endm
+
+.macro put_vp8_bilin_h_v len type mn
+func ff_put_vp8_bilin\len\()_\type\()_rvv, zve32x
+        vsetvlstatic8   \len
+        li              t1, 8
+        li              t4, 4
+        sub             t1, t1, \mn
+1:
+        addi            a4, a4, -1
+        bilin_load      v0, \len, \type, \mn
+        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
+.endr