[FFmpeg-devel] [PATCH v3 2/5] lavc/vp9dsp: R-V V mc bilin h v
uk7b at foxmail.com
uk7b at foxmail.com
Wed May 29 20:15:37 EEST 2024
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 | 60 ++++++++++++++++++++++++++++++++++
libavcodec/riscv/vp9dsp.h | 12 +++----
libavcodec/riscv/vp9dsp_init.c | 21 ++++++++++++
3 files changed, 87 insertions(+), 6 deletions(-)
diff --git a/libavcodec/riscv/vp9_mc_rvv.S b/libavcodec/riscv/vp9_mc_rvv.S
index 7cb38ec94a..9611aba0ed 100644
--- a/libavcodec/riscv/vp9_mc_rvv.S
+++ b/libavcodec/riscv/vp9_mc_rvv.S
@@ -53,6 +53,66 @@ func ff_vp9_avg\len\()_rvv, zve32x
endfunc
.endm
+.macro bilin_load dst, op, type, mn
+.ifc \type,v
+ add t5, a2, a3
+.else
+ 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 op, type, mn
+func ff_\op\()_vp9_bilin_4\type\()_rvv, zve32x
+ vsetvlstatic8 4, t0, 64
+.Lbilin_\type\op:
+.ifc \op,avg
+ csrwi vxrm, 0
+.endif
+ li t4, 8
+ neg t1, \mn
+1:
+ addi a4, a4, -1
+ bilin_load v0, \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
.endr
+
+bilin_h_v put, h, a5
+bilin_h_v avg, h, a5
+bilin_h_v put, v, a6
+bilin_h_v avg, v, a6
+
+.macro func_bilin_h_v len, op, type
+func ff_\op\()_vp9_bilin_\len\()\type\()_rvv, zve32x
+ vsetvlstatic8 \len, t0, 64
+ j .Lbilin_\type\()\op
+endfunc
+.endm
+
+.irp len, 64, 32, 16, 8
+ .irp op, put, avg
+ .irp type, h, v
+ func_bilin_h_v \len, \op, \type
+ .endr
+ .endr
+.endr
diff --git a/libavcodec/riscv/vp9dsp.h b/libavcodec/riscv/vp9dsp.h
index ff8431591c..8fb326dae0 100644
--- a/libavcodec/riscv/vp9dsp.h
+++ b/libavcodec/riscv/vp9dsp.h
@@ -113,27 +113,27 @@ void ff_avg_8tap_##type##_##SIZE##hv_rvv(uint8_t *dst, ptrdiff_t dststride, \
int h, int mx, int my);
#define VP9_BILINEAR_RISCV_RVV_FUNC(SIZE) \
-void ff_put_bilin_##SIZE##h_rvv(uint8_t *dst, ptrdiff_t dststride, \
+void ff_put_vp9_bilin_##SIZE##h_rvv(uint8_t *dst, ptrdiff_t dststride, \
const uint8_t *src, ptrdiff_t srcstride, \
int h, int mx, int my); \
\
-void ff_put_bilin_##SIZE##v_rvv(uint8_t *dst, ptrdiff_t dststride, \
+void ff_put_vp9_bilin_##SIZE##v_rvv(uint8_t *dst, ptrdiff_t dststride, \
const uint8_t *src, ptrdiff_t srcstride, \
int h, int mx, int my); \
\
-void ff_put_bilin_##SIZE##hv_rvv(uint8_t *dst, ptrdiff_t dststride, \
+void ff_put_vp9_bilin_##SIZE##hv_rvv(uint8_t *dst, ptrdiff_t dststride, \
const uint8_t *src, ptrdiff_t srcstride, \
int h, int mx, int my); \
\
-void ff_avg_bilin_##SIZE##h_rvv(uint8_t *dst, ptrdiff_t dststride, \
+void ff_avg_vp9_bilin_##SIZE##h_rvv(uint8_t *dst, ptrdiff_t dststride, \
const uint8_t *src, ptrdiff_t srcstride, \
int h, int mx, int my); \
\
-void ff_avg_bilin_##SIZE##v_rvv(uint8_t *dst, ptrdiff_t dststride, \
+void ff_avg_vp9_bilin_##SIZE##v_rvv(uint8_t *dst, ptrdiff_t dststride, \
const uint8_t *src, ptrdiff_t srcstride, \
int h, int mx, int my); \
\
-void ff_avg_bilin_##SIZE##hv_rvv(uint8_t *dst, ptrdiff_t dststride, \
+void ff_avg_vp9_bilin_##SIZE##hv_rvv(uint8_t *dst, ptrdiff_t dststride, \
const uint8_t *src, ptrdiff_t srcstride, \
int h, int mx, int my);
diff --git a/libavcodec/riscv/vp9dsp_init.c b/libavcodec/riscv/vp9dsp_init.c
index 454dcd963f..9606d8545f 100644
--- a/libavcodec/riscv/vp9dsp_init.c
+++ b/libavcodec/riscv/vp9dsp_init.c
@@ -63,6 +63,27 @@ static av_cold void vp9dsp_mc_init_riscv(VP9DSPContext *dsp, int bpp)
init_fpel(3, 8);
init_fpel(4, 4);
+ dsp->mc[0][FILTER_BILINEAR ][0][0][1] = ff_put_vp9_bilin_64v_rvv;
+ dsp->mc[0][FILTER_BILINEAR ][0][1][0] = ff_put_vp9_bilin_64h_rvv;
+ dsp->mc[0][FILTER_BILINEAR ][1][0][1] = ff_avg_vp9_bilin_64v_rvv;
+ dsp->mc[0][FILTER_BILINEAR ][1][1][0] = ff_avg_vp9_bilin_64h_rvv;
+ dsp->mc[1][FILTER_BILINEAR ][0][0][1] = ff_put_vp9_bilin_32v_rvv;
+ dsp->mc[1][FILTER_BILINEAR ][0][1][0] = ff_put_vp9_bilin_32h_rvv;
+ dsp->mc[1][FILTER_BILINEAR ][1][0][1] = ff_avg_vp9_bilin_32v_rvv;
+ dsp->mc[1][FILTER_BILINEAR ][1][1][0] = ff_avg_vp9_bilin_32h_rvv;
+ dsp->mc[2][FILTER_BILINEAR ][0][0][1] = ff_put_vp9_bilin_16v_rvv;
+ dsp->mc[2][FILTER_BILINEAR ][0][1][0] = ff_put_vp9_bilin_16h_rvv;
+ dsp->mc[2][FILTER_BILINEAR ][1][0][1] = ff_avg_vp9_bilin_16v_rvv;
+ dsp->mc[2][FILTER_BILINEAR ][1][1][0] = ff_avg_vp9_bilin_16h_rvv;
+ dsp->mc[3][FILTER_BILINEAR ][0][0][1] = ff_put_vp9_bilin_8v_rvv;
+ dsp->mc[3][FILTER_BILINEAR ][0][1][0] = ff_put_vp9_bilin_8h_rvv;
+ dsp->mc[3][FILTER_BILINEAR ][1][0][1] = ff_avg_vp9_bilin_8v_rvv;
+ dsp->mc[3][FILTER_BILINEAR ][1][1][0] = ff_avg_vp9_bilin_8h_rvv;
+ dsp->mc[4][FILTER_BILINEAR ][0][0][1] = ff_put_vp9_bilin_4v_rvv;
+ dsp->mc[4][FILTER_BILINEAR ][0][1][0] = ff_put_vp9_bilin_4h_rvv;
+ dsp->mc[4][FILTER_BILINEAR ][1][0][1] = ff_avg_vp9_bilin_4v_rvv;
+ dsp->mc[4][FILTER_BILINEAR ][1][1][0] = ff_avg_vp9_bilin_4h_rvv;
+
#undef init_fpel
}
#endif
--
2.45.1
More information about the ffmpeg-devel
mailing list