From: sunyuechi <sunyue...@iscas.ac.cn>
C908 X60
vp8_loop_filter8uv_v_c : 13.7 11.7
vp8_loop_filter8uv_v_rvv_i32 : 7.7 6.2
vp8_loop_filter16y_h_c : 12.2 11.2
vp8_loop_filter16y_h_rvv_i32 : 9.5 7.2
vp8_loop_filter16y_v_c : 13.2 12.0
vp8_loop_filter16y_v_rvv_i32 : 5.5 3.7
---
libavcodec/riscv/vp8dsp_init.c | 5 ++-
libavcodec/riscv/vp8dsp_rvv.S | 57 ++++++++++++++++++++++++++++++++++
2 files changed, 61 insertions(+), 1 deletion(-)
diff --git a/libavcodec/riscv/vp8dsp_init.c b/libavcodec/riscv/vp8dsp_init.c
index 94f78cd84b..72191f558b 100644
--- a/libavcodec/riscv/vp8dsp_init.c
+++ b/libavcodec/riscv/vp8dsp_init.c
@@ -157,7 +157,10 @@ av_cold void ff_vp8dsp_init_riscv(VP8DSPContext *c)
c->vp8_h_loop_filter_simple = ff_vp8_h_loop_filter16_simple_rvv##vlen; \
c->vp8_v_loop_filter16y_inner = ff_vp8_v_loop_filter16_inner_rvv##vlen; \
c->vp8_h_loop_filter16y_inner = ff_vp8_h_loop_filter16_inner_rvv##vlen; \
- c->vp8_v_loop_filter8uv_inner = ff_vp8_v_loop_filter8uv_inner_rvv##vlen;
+ c->vp8_v_loop_filter8uv_inner = ff_vp8_v_loop_filter8uv_inner_rvv##vlen; \
+ c->vp8_v_loop_filter16y = ff_vp8_v_loop_filter16_rvv##vlen; \
+ c->vp8_h_loop_filter16y = ff_vp8_h_loop_filter16_rvv##vlen; \
+ c->vp8_v_loop_filter8uv = ff_vp8_v_loop_filter8uv_rvv##vlen;
int flags = av_get_cpu_flags();
diff --git a/libavcodec/riscv/vp8dsp_rvv.S b/libavcodec/riscv/vp8dsp_rvv.S
index ed789ec4fd..98ff389b9a 100644
--- a/libavcodec/riscv/vp8dsp_rvv.S
+++ b/libavcodec/riscv/vp8dsp_rvv.S
@@ -410,6 +410,33 @@ endfunc
vsra.vi v24, v24, 1 // (f1 + 1) >> 1;
vadd.vv v8, v18, v24
vsub.vv v10, v20, v24
+ .else
+ li t5, 27
+ li t3, 9
+ li a7, 18
+ vwmul.vx v2, v11, t5
+ vwmul.vx v6, v11, t3
+ vwmul.vx v4, v11, a7
+ vsetvlstatic16 \len, \vlen
+ li a7, 63
+ vzext.vf2 v14, v15 // p2
+ vzext.vf2 v24, v10 // q2
+ vadd.vx v2, v2, a7
+ vadd.vx v4, v4, a7
+ vadd.vx v6, v6, a7
+ vsra.vi v2, v2, 7 // a0
+ vsra.vi v12, v4, 7 // a1
+ vsra.vi v6, v6, 7 // a2
+ vadd.vv v14, v14, v6 // p2 + a2
+ vsub.vv v22, v24, v6 // q2 - a2
+ vsub.vv v10, v20, v12 // q1 - a1
+ vadd.vv v4, v8, v2 // p0 + a0
+ vsub.vv v6, v16, v2 // q0 - a0
+ vadd.vv v8, v12, v18 // a1 + p1
+ vmax.vx v4, v4, zero
+ vmax.vx v6, v6, zero
+ vmax.vx v14, v14, zero
+ vmax.vx v16, v22, zero
.endif
vmax.vx v8, v8, zero
@@ -430,6 +457,17 @@ endfunc
vsse8.v v6, (a6), \stride, v0.t
vsse8.v v7, (t4), \stride, v0.t
.endif
+ .if !\inner
+ vnclipu.wi v14, v14, 0
+ vnclipu.wi v16, v16, 0
+ .ifc \type,v
+ vse8.v v14, (t0), v0.t
+ vse8.v v16, (t6), v0.t
+ .else
+ vsse8.v v14, (t0), \stride, v0.t
+ vsse8.v v16, (t6), \stride, v0.t
+ .endif
+ .endif
.endif
.endm
@@ -464,6 +502,25 @@ func ff_vp8_v_loop_filter8uv_inner_rvv\vlen, zve32x
filter 8, \vlen, v, 1, 1, a1, a2, a3, a4, a5
ret
endfunc
+
+func ff_vp8_v_loop_filter16_rvv\vlen, zve32x
+ vsetvlstatic8 16, \vlen
+ filter 16, \vlen, v, 1, 0, a0, a1, a2, a3, a4
+ ret
+endfunc
+
+func ff_vp8_h_loop_filter16_rvv\vlen, zve32x
+ vsetvlstatic8 16, \vlen
+ filter 16, \vlen, h, 1, 0, a0, a1, a2, a3, a4
+ ret
+endfunc
+
+func ff_vp8_v_loop_filter8uv_rvv\vlen, zve32x
+ vsetvlstatic8 8, \vlen
+ filter 8, \vlen, v, 1, 0, a0, a2, a3, a4, a5
+ filter 8, \vlen, v, 1, 0, a1, a2, a3, a4, a5
+ ret
+endfunc
.endr
.macro bilin_load_h dst mn
--
2.45.2
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
