[FFmpeg-devel] [PATCH v2 6/9] lavc/vp9dsp: R-V V mc bilin h v

[uk7b at foxmail.com]

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

C908:
vp9_avg_bilin_4h_8bpp_c: 5.2
vp9_avg_bilin_4h_8bpp_rvv_i64: 2.2
vp9_avg_bilin_4v_8bpp_c: 5.5
vp9_avg_bilin_4v_8bpp_rvv_i64: 2.2
vp9_avg_bilin_8h_8bpp_c: 20.0
vp9_avg_bilin_8h_8bpp_rvv_i64: 4.5
vp9_avg_bilin_8v_8bpp_c: 21.0
vp9_avg_bilin_8v_8bpp_rvv_i64: 4.2
vp9_avg_bilin_16h_8bpp_c: 78.2
vp9_avg_bilin_16h_8bpp_rvv_i64: 9.0
vp9_avg_bilin_16v_8bpp_c: 82.0
vp9_avg_bilin_16v_8bpp_rvv_i64: 9.0
vp9_avg_bilin_32h_8bpp_c: 325.5
vp9_avg_bilin_32h_8bpp_rvv_i64: 26.2
vp9_avg_bilin_32v_8bpp_c: 326.2
vp9_avg_bilin_32v_8bpp_rvv_i64: 26.2
vp9_avg_bilin_64h_8bpp_c: 1265.7
vp9_avg_bilin_64h_8bpp_rvv_i64: 91.5
vp9_avg_bilin_64v_8bpp_c: 1317.0
vp9_avg_bilin_64v_8bpp_rvv_i64: 91.2
vp9_put_bilin_4h_8bpp_c: 4.5
vp9_put_bilin_4h_8bpp_rvv_i64: 1.7
vp9_put_bilin_4v_8bpp_c: 4.7
vp9_put_bilin_4v_8bpp_rvv_i64: 1.7
vp9_put_bilin_8h_8bpp_c: 17.0
vp9_put_bilin_8h_8bpp_rvv_i64: 3.5
vp9_put_bilin_8v_8bpp_c: 18.0
vp9_put_bilin_8v_8bpp_rvv_i64: 3.5
vp9_put_bilin_16h_8bpp_c: 65.2
vp9_put_bilin_16h_8bpp_rvv_i64: 7.5
vp9_put_bilin_16v_8bpp_c: 85.7
vp9_put_bilin_16v_8bpp_rvv_i64: 7.5
vp9_put_bilin_32h_8bpp_c: 257.5
vp9_put_bilin_32h_8bpp_rvv_i64: 23.5
vp9_put_bilin_32v_8bpp_c: 274.5
vp9_put_bilin_32v_8bpp_rvv_i64: 23.5
vp9_put_bilin_64h_8bpp_c: 1040.5
vp9_put_bilin_64h_8bpp_rvv_i64: 82.5
vp9_put_bilin_64v_8bpp_c: 1108.7
vp9_put_bilin_64v_8bpp_rvv_i64: 82.2
---
 libavcodec/riscv/vp9_mc_rvv.S  | 43 ++++++++++++++++++++++++++++++++++
 libavcodec/riscv/vp9dsp_init.c | 22 +++++++++++++++++
 2 files changed, 65 insertions(+)

diff --git a/libavcodec/riscv/vp9_mc_rvv.S b/libavcodec/riscv/vp9_mc_rvv.S
index 81ecb49435..598a67fc94 100644
--- a/libavcodec/riscv/vp9_mc_rvv.S
+++ b/libavcodec/riscv/vp9_mc_rvv.S
@@ -53,6 +53,49 @@ func ff_avg\len\()_rvv, zve32x
 endfunc
 .endm
 
+.macro bilin_load dst len op type mn
+.ifc \type,v
+        add             t5, a2, a3
+.elseif \type == h
+        addi            t5, a2, 1
+.endif
+        vle8.v          v8, (a2)
+        vle8.v          v0, (t5)
+        vwmulu.vx       v16, v0, \mn
+        vwmaccsu.vx     v16, t1, v8
+        vwadd.wx        v16, v16, t4
+        vnsra.wi        v16, v16, 4
+        vadd.vv         \dst, v16, v8
+.ifc \op,avg
+        vle8.v          v16, (a0)
+        vaaddu.vv       \dst, \dst, v16
+.endif
+.endm
+
+.macro bilin_h_v len op type mn
+func ff_\op\()_bilin_\len\()\type\()_rvv, zve32x
+.ifc \op,avg
+        csrwi           vxrm, 0
+.endif
+        vsetvlstatic8   \len t0
+        li              t4, 8
+        neg             t1, \mn
+1:
+        addi            a4, a4, -1
+        bilin_load      v0, \len, \op, \type, \mn
+        vse8.v          v0, (a0)
+        add             a2, a2, a3
+        add             a0, a0, a1
+        bnez            a4, 1b
+
+        ret
+endfunc
+.endm
+
 .irp len 64, 32, 16, 8, 4
         copy_avg \len
+        .irp op put avg
+                bilin_h_v \len \op h a5
+                bilin_h_v \len \op v a6
+        .endr
 .endr
diff --git a/libavcodec/riscv/vp9dsp_init.c b/libavcodec/riscv/vp9dsp_init.c
index 2caaf732db..cfeaa06c0a 100644
--- a/libavcodec/riscv/vp9dsp_init.c
+++ b/libavcodec/riscv/vp9dsp_init.c
@@ -109,6 +109,28 @@ static av_cold void vp9dsp_mc_init_riscv(VP9DSPContext *dsp, int bpp)
     init_fpel(4, 4);
 
 #undef init_fpel
+
+#define init_subpel1(idx1, idx2, idxh, idxv, sz, dir, type)  \
+    dsp->mc[idx1][FILTER_BILINEAR    ][idx2][idxh][idxv] =   \
+        ff_##type##_bilin_##sz##dir##_rvv;                   \
+
+#define init_subpel2(idx, idxh, idxv, dir, type)      \
+    init_subpel1(0, idx, idxh, idxv, 64, dir, type);  \
+    init_subpel1(1, idx, idxh, idxv, 32, dir, type);  \
+    init_subpel1(2, idx, idxh, idxv, 16, dir, type);  \
+    init_subpel1(3, idx, idxh, idxv,  8, dir, type);  \
+    init_subpel1(4, idx, idxh, idxv,  4, dir, type)
+
+#define init_subpel3(idx, type)         \
+    init_subpel2(idx, 1, 0, h, type);   \
+    init_subpel2(idx, 0, 1, v, type);   \
+
+    init_subpel3(0, put);
+    init_subpel3(1, avg);
+
+#undef init_subpel1
+#undef init_subpel2
+#undef init_subpel3
     }
 #endif
 #endif
-- 
2.45.0