From: uk7b@foxmail.com To: ffmpeg-devel@ffmpeg.org Cc: sunyuechi <sunyuechi@iscas.ac.cn> Subject: [FFmpeg-devel] [PATCH v3 9/9] lavc/vp8dsp: R-V V loop_filter Date: Mon, 6 May 2024 11:38:09 +0800 Message-ID: <tencent_A5074F95D1026348BB7864EE0FEB2DAC8E05@qq.com> (raw) In-Reply-To: <20240506033809.3790245-1-uk7b@foxmail.com> From: sunyuechi <sunyuechi@iscas.ac.cn> C908: vp8_loop_filter8uv_v_c: 745.5 vp8_loop_filter8uv_v_rvv_i32: 467.2 vp8_loop_filter16y_h_c: 674.2 vp8_loop_filter16y_h_rvv_i32: 553.0 vp8_loop_filter16y_v_c: 732.7 vp8_loop_filter16y_v_rvv_i32: 324.5 --- libavcodec/riscv/vp8dsp_init.c | 4 +++ libavcodec/riscv/vp8dsp_rvv.S | 57 ++++++++++++++++++++++++++++++++++ 2 files changed, 61 insertions(+) diff --git a/libavcodec/riscv/vp8dsp_init.c b/libavcodec/riscv/vp8dsp_init.c index 2adff1052a..1bb5aad518 100644 --- a/libavcodec/riscv/vp8dsp_init.c +++ b/libavcodec/riscv/vp8dsp_init.c @@ -129,6 +129,10 @@ av_cold void ff_vp8dsp_init_riscv(VP8DSPContext *c) c->vp8_idct_dc_add4uv = ff_vp8_idct_dc_add4uv_rvv; } + c->vp8_v_loop_filter16y = ff_vp8_v_loop_filter16_rvv; + c->vp8_h_loop_filter16y = ff_vp8_h_loop_filter16_rvv; + c->vp8_v_loop_filter8uv = ff_vp8_v_loop_filter8uv_rvv; + c->vp8_v_loop_filter16y_inner = ff_vp8_v_loop_filter16_inner_rvv; c->vp8_h_loop_filter16y_inner = ff_vp8_h_loop_filter16_inner_rvv; c->vp8_v_loop_filter8uv_inner = ff_vp8_v_loop_filter8uv_inner_rvv; diff --git a/libavcodec/riscv/vp8dsp_rvv.S b/libavcodec/riscv/vp8dsp_rvv.S index 21fa232325..567dc96f76 100644 --- a/libavcodec/riscv/vp8dsp_rvv.S +++ b/libavcodec/riscv/vp8dsp_rvv.S @@ -229,6 +229,33 @@ 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 + 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 @@ -249,6 +276,17 @@ 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 @@ -283,6 +321,25 @@ func ff_vp8_v_loop_filter8uv_inner_rvv, zve32x ret endfunc +func ff_vp8_v_loop_filter16_rvv, zve32x + vsetvlstatic8 16 + filter 16 v 1 0 a0 a1 a2 a3 a4 + ret +endfunc + +func ff_vp8_h_loop_filter16_rvv, zve32x + vsetvlstatic8 16 + filter 16 h 1 0 a0 a1 a2 a3 a4 + ret +endfunc + +func ff_vp8_v_loop_filter8uv_rvv, zve32x + vsetvlstatic8 8 + filter 8 v 1 0 a0 a2 a3 a4 a5 + filter 8 v 1 0 a1 a2 a3 a4 a5 + ret +endfunc + .macro bilin_load dst len type mn .ifc \type,v add t5, a2, a3 -- 2.45.0 _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
prev parent reply other threads:[~2024-05-06 3:39 UTC|newest] Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top [not found] <20240506033809.3790245-1-uk7b@foxmail.com> 2024-05-06 3:38 ` [FFmpeg-devel] [PATCH v3 2/9] lavc/vp8dsp: R-V V put_bilin_h v uk7b 2024-05-06 3:44 ` flow gg 2024-05-07 15:59 ` Rémi Denis-Courmont 2024-05-07 16:07 ` flow gg 2024-05-07 16:10 ` Rémi Denis-Courmont 2024-05-06 3:38 ` [FFmpeg-devel] [PATCH v3 3/9] lavc/vp8dsp: R-V V put_bilin_hv uk7b 2024-05-06 3:38 ` [FFmpeg-devel] [PATCH v3 4/9] lavc/vp8dsp: R-V V put_epel h uk7b 2024-05-06 3:38 ` [FFmpeg-devel] [PATCH v3 5/9] lavc/vp8dsp: R-V V put_epel v uk7b 2024-05-06 3:38 ` [FFmpeg-devel] [PATCH v3 6/9] lavc/vp8dsp: R-V V put_epel hv uk7b 2024-05-06 19:24 ` Rémi Denis-Courmont 2024-05-07 2:27 ` [FFmpeg-devel] [PATCH " uk7b 2024-05-07 2:31 ` [FFmpeg-devel] [PATCH v3 " flow gg 2024-05-06 3:38 ` [FFmpeg-devel] [PATCH v3 7/9] lavc/vp8dsp: R-V V loop_filter_simple uk7b 2024-05-06 3:38 ` [FFmpeg-devel] [PATCH v3 8/9] lavc/vp8dsp: R-V V loop_filter_inner uk7b 2024-05-06 3:38 ` uk7b [this message]
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=tencent_A5074F95D1026348BB7864EE0FEB2DAC8E05@qq.com \ --to=uk7b@foxmail.com \ --cc=ffmpeg-devel@ffmpeg.org \ --cc=sunyuechi@iscas.ac.cn \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: link
Git Inbox Mirror of the ffmpeg-devel mailing list - see https://ffmpeg.org/mailman/listinfo/ffmpeg-devel This inbox may be cloned and mirrored by anyone: git clone --mirror https://master.gitmailbox.com/ffmpegdev/0 ffmpegdev/git/0.git # If you have public-inbox 1.1+ installed, you may # initialize and index your mirror using the following commands: public-inbox-init -V2 ffmpegdev ffmpegdev/ https://master.gitmailbox.com/ffmpegdev \ ffmpegdev@gitmailbox.com public-inbox-index ffmpegdev Example config snippet for mirrors. AGPL code for this site: git clone https://public-inbox.org/public-inbox.git