From e1a01b1e0a365935868d7825d53c7cc64e2c1787 Mon Sep 17 00:00:00 2001 From: sunyuechi Date: Fri, 23 Feb 2024 22:35:23 +0800 Subject: [PATCH 3/3] lavc/vp8dsp: R-V V put_bilin_hv C908: vp8_put_bilin4_hv_c: 567.7 vp8_put_bilin4_hv_rvv_i32: 255.7 vp8_put_bilin8_hv_c: 2169.5 vp8_put_bilin8_hv_rvv_i32: 528.7 vp8_put_bilin16_hv_c: 4777.5 vp8_put_bilin16_hv_rvv_i32: 587.7 --- libavcodec/riscv/vp8dsp_init.c | 13 +++++++++++++ libavcodec/riscv/vp8dsp_rvv.S | 35 ++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) diff --git a/libavcodec/riscv/vp8dsp_init.c b/libavcodec/riscv/vp8dsp_init.c index 10e1498d01..02dbda979e 100644 --- a/libavcodec/riscv/vp8dsp_init.c +++ b/libavcodec/riscv/vp8dsp_init.c @@ -65,6 +65,19 @@ 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 } diff --git a/libavcodec/riscv/vp8dsp_rvv.S b/libavcodec/riscv/vp8dsp_rvv.S index a58c197ba1..9d4ffed255 100644 --- a/libavcodec/riscv/vp8dsp_rvv.S +++ b/libavcodec/riscv/vp8dsp_rvv.S @@ -188,3 +188,38 @@ func ff_put_vp8_bilin4_v_rvv, zve32x vsetivli zero, 4, e8, mf4, ta, ma put_vp8_bilin_v endfunc + +.macro put_vp8_bilin_hv len + li t3, 8 + sub t1, t3, a5 + sub t2, t3, a6 + li t4, 4 + li t5, 1 + bilin_h_load v4, \len + add a2, a2, a3 +1: + addi a4, a4, -1 + vwmulu.vx v20, v4, t2 + bilin_h_load v4, \len + 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 +.endm + +func ff_put_vp8_bilin16_hv_rvv, zve32x + put_vp8_bilin_hv 16 +endfunc + +func ff_put_vp8_bilin8_hv_rvv, zve32x + put_vp8_bilin_hv 8 +endfunc + +func ff_put_vp8_bilin4_hv_rvv, zve32x + put_vp8_bilin_hv 4 +endfunc -- 2.43.2