From patchwork Sat Aug 3 09:50:40 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: uk7b@foxmail.com X-Patchwork-Id: 50879 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:612c:1f5a:b0:489:2eb3:e4c4 with SMTP id jm26csp373481vqb; Sat, 3 Aug 2024 02:51:41 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCX4HiAJFAm++3hwNscBsoVOMpzVWkrAFZjyNRtqy1QpdqGdjAeZu8WsSbJXs1SLBw3afXKMRynoiIUUoB058acAZHDR6ea9SHD3JA== X-Google-Smtp-Source: AGHT+IEJjezlyn8a88N3qIrub1Ek+6OJ5ZPb/9dabwJz99xSQksyDc4szBw+c+flK/fe4bFMWoyN X-Received: by 2002:a05:6512:2353:b0:52e:9ab9:da14 with SMTP id 2adb3069b0e04-530bb381472mr3503077e87.31.1722678700757; Sat, 03 Aug 2024 02:51:40 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1722678700; cv=none; d=google.com; s=arc-20160816; b=pZerLNHFPMiKXxkr11Wayrme1dDOO3U8Z1z31XljdJx2e/0mfPXlps8oLK9uJYQYvt EswSzlncHc1ORKQi5TIFWVNyQN5HhPyZPxxwtSfuQF95lIWwt4gaEkkdJQM3GCJ+ZCoW D6C52Tl/uaSq3GZh1CbX7TZcN+RQntQgcrbthr1xJf/SCO5LBU98QDl1hiAPiyPgWuLl mc1QKF56G3UNg6Q/wBxCwgGwbTFVq7rXIMt/paw2X1yJHob0Wrp3XCRd/NcvS9+7U4mQ xJpk4/U4/qWsEes/LBoO27Qr1+Ey25CvW/f/dRbfWSwYKOd29CGFkOQQ1GygbgpeLSxh 712Q== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:cc:reply-to :list-subscribe:list-help:list-post:list-archive:list-unsubscribe :list-id:precedence:subject:mime-version:references:in-reply-to:date :to:from:message-id:dkim-signature:delivered-to; bh=yJSN866xSOhljufzfIHrOALW5NiUqpM5gdr52LE4eic=; fh=D0bFwGkf4X22/D/bfeDVrXKIx7S6kcXsNzy10j8ORbQ=; b=waB6DEm2iaMH3r/asL8K0+U6u5zK6oroUo+rTyFMEGM11ePYez9FV07FWB18bAyy9z qEMfT0/gH7BPgpuN06+upFooPdouOQqiKELi0tMP8Das/k9ncaio5UlAywlPAriDWeZz 0L6tiw10ec9rKcU3475MOh3SVaUyNStHvcOiF0PeHIyHjxMBgi7o4vnuv3OqFT7oEwW7 dggKg2O2zcl4tu2OCzHJ+xhkW6HRi6+I+mrYPBgRHo3TdeT7h7ceKnFUlX1PGGHGjKmW HnKT+tnmVGV68rhILSQNILCByNG2dGjfApMNPNGD7xCDk3r+iI/Me+HRg93UPnazJenf 00qg==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=neutral (body hash did not verify) header.i=@foxmail.com header.s=s201512 header.b="RJyPig/l"; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=foxmail.com Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id 4fb4d7f45d1cf-5b83c03690asi2032824a12.374.2024.08.03.02.51.40; Sat, 03 Aug 2024 02:51:40 -0700 (PDT) Received-SPF: pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) client-ip=79.124.17.100; Authentication-Results: mx.google.com; dkim=neutral (body hash did not verify) header.i=@foxmail.com header.s=s201512 header.b="RJyPig/l"; spf=pass (google.com: domain of ffmpeg-devel-bounces@ffmpeg.org designates 79.124.17.100 as permitted sender) smtp.mailfrom=ffmpeg-devel-bounces@ffmpeg.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=foxmail.com Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id B551868D911; Sat, 3 Aug 2024 12:51:05 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from out203-205-221-210.mail.qq.com (out203-205-221-210.mail.qq.com [203.205.221.210]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 8ACCB68D882 for ; Sat, 3 Aug 2024 12:50:54 +0300 (EEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=foxmail.com; s=s201512; t=1722678646; bh=79U2LoxY8D3bpDfl6SwiJ4C40p/5N4GZYqPrbfFZ8eY=; h=From:To:Cc:Subject:Date:In-Reply-To:References; b=RJyPig/lIarlZSkUnudFilSQpCPT99tC3b/6gLpd3zaJwlRxtSNAnV8nXJJbwABea KSsd09odUkmPgJa/AtDYhn6J3eiyLt3qAPQAva16dlyvPe42MaQqJrjMEYyDQ9MPAq Llhugbx37QVOszdOSAIjiVRtogsBduz6MTHjQKaw= Received: from localhost.localdomain ([42.86.132.47]) by newxmesmtplogicsvrszb16-1.qq.com (NewEsmtp) with SMTP id CAA3C22C; Sat, 03 Aug 2024 17:50:42 +0800 X-QQ-mid: xmsmtpt1722678645twkqipfoo Message-ID: X-QQ-XMAILINFO: MFWpArBVhhGTs7pMDOfyW5EjHeMs9FKd3FoE5ClZlJZ7J+iYqV7n4gG4CPe/U8 AeGlWQ4BybSdKKstOrf6Yv5Otxxm4b4ZhUkuiB1QF4p3MiBvnzl3KOdqidEkqk5maGSP6MJxRB8E 2N1LeojvgCvgTSgFzvDBn2yPIS6ncE5ZhcKghBP3dey3NJblJ5umb19uT2Qe2BBpmwEGMkAWovm8 kpNSEJm2zVjb0Rs/HksUV/sf/GjzLZelRjdtjE4vlxTCOv0f/Io4UhwGT4ialf8mWwXEB5WUe7UD xL0vVPs0StjhDFi7AZECuepSckC9EDmsrF9LpoKPCO9to4TmpPtBzYbtED4hJeITVtjQR8MBxDG+ SvhJNWZVhYLAEEJxHiaaZthWi1TA1lAUEos28HfUM1mSenlCaqwfeI3P7PVXKpTuUWu/nkgsnuIE 6Kv3zNCHx55gnoNHgrQsYmH7H8/PmgVBm56fEE+wySIQI+LUSRi6xl2qW+wtV6OQlB8+XJ3jaSNf EbYfWvaclEJvlVIEqGO4rldLxjZyVcOnViOftt1n/f1LDAa0xqX5NIEbwI2mv4TKRmvkqzPxoMAg /lgM1safHD33tD3Iq0uVKaQlUMSGd5JFUdNTWODPpn4l6+pvwGpon/lXv8ykkfOinn7qARlcaEoO DA8FNrVmNzQ5Ar6/aKPabWFyFk7bpRMLn5UcLNi3BWGGqjWVDtjdoc+cPrSEJl/1Aya8wk1UE49G Z1k24BWjR7MVcfEq5kpHTFxtRjc+in9n1L7nBbzl9aWTkqO4W06s0yj55lC992plZFCCoYouErAB 2agkN8DCMIUk0waxtUxDwUQDmj/pObK7sZGpgoio0VFpG5rwh6UsfYeg9DdIDK7T1fvBZIBsYImw Vh5w/81yrIkMJCsMJgnlNYfz2BL11rYHpwGs7XgzC70siSIFb0RzQ0EimkSX3xqx9kribkDITFnZ 5UrskNtjI= X-QQ-XMRINFO: NS+P29fieYNw95Bth2bWPxk= From: uk7b@foxmail.com To: ffmpeg-devel@ffmpeg.org Date: Sat, 3 Aug 2024 17:50:40 +0800 X-OQ-MSGID: <20240803095040.3648582-4-uk7b@foxmail.com> X-Mailer: git-send-email 2.46.0 In-Reply-To: <20240803095040.3648582-1-uk7b@foxmail.com> References: <20240803095040.3648582-1-uk7b@foxmail.com> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 4/4] lavc/vp9dsp: R-V V mc tap hv X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: FFmpeg development discussions and patches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: FFmpeg development discussions and patches Cc: sunyuechi Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" X-TUID: KwZpfwW5KiiE From: sunyuechi C908 X60 vp9_avg_8tap_smooth_4hv_8bpp_c : 32.0 28.0 vp9_avg_8tap_smooth_4hv_8bpp_rvv_i32 : 15.0 13.2 vp9_avg_8tap_smooth_8hv_8bpp_c : 98.0 86.2 vp9_avg_8tap_smooth_8hv_8bpp_rvv_i32 : 23.7 21.2 vp9_avg_8tap_smooth_16hv_8bpp_c : 355.7 297.0 vp9_avg_8tap_smooth_16hv_8bpp_rvv_i32 : 47.0 41.5 vp9_avg_8tap_smooth_32hv_8bpp_c : 1272.7 1099.7 vp9_avg_8tap_smooth_32hv_8bpp_rvv_i32 : 134.7 119.7 vp9_avg_8tap_smooth_64hv_8bpp_c : 4937.0 4224.2 vp9_avg_8tap_smooth_64hv_8bpp_rvv_i32 : 528.5 228.5 vp9_put_8tap_smooth_4hv_8bpp_c : 30.2 26.7 vp9_put_8tap_smooth_4hv_8bpp_rvv_i32 : 30.5 12.5 vp9_put_8tap_smooth_8hv_8bpp_c : 91.5 81.2 vp9_put_8tap_smooth_8hv_8bpp_rvv_i32 : 22.7 20.2 vp9_put_8tap_smooth_16hv_8bpp_c : 313.2 277.5 vp9_put_8tap_smooth_16hv_8bpp_rvv_i32 : 45.2 40.2 vp9_put_8tap_smooth_32hv_8bpp_c : 1166.7 1022.2 vp9_put_8tap_smooth_32hv_8bpp_rvv_i32 : 131.7 117.2 vp9_put_8tap_smooth_64hv_8bpp_c : 4560.5 3961.7 vp9_put_8tap_smooth_64hv_8bpp_rvv_i32 : 517.0 223.2 --- libavcodec/riscv/vp9_mc_rvv.S | 70 ++++++++++++++++++++++++++++++++++ libavcodec/riscv/vp9dsp_init.c | 8 ++++ 2 files changed, 78 insertions(+) diff --git a/libavcodec/riscv/vp9_mc_rvv.S b/libavcodec/riscv/vp9_mc_rvv.S index c9fee6a3c5..41034444fa 100644 --- a/libavcodec/riscv/vp9_mc_rvv.S +++ b/libavcodec/riscv/vp9_mc_rvv.S @@ -359,6 +359,72 @@ func ff_\op\()_vp9_8tap_\name\()_\len\()\type\()_rvv\vlen\(), zve32x endfunc .endm +#if __riscv_xlen == 64 +.macro epel_hv_once len, name, op + sub a2, a2, a3 + sub a2, a2, a3 + sub a2, a2, a3 + .irp n,0,2,4,6,8,10,12,14 + epel_load_inc v\n, \len, put, \name, h, 1, t + .endr + addi a4, a4, -1 +1: + addi a4, a4, -1 + epel_load v30, \len, \op, \name, v, 0, s + vse8.v v30, (a0) + vmv.v.v v0, v2 + vmv.v.v v2, v4 + vmv.v.v v4, v6 + vmv.v.v v6, v8 + vmv.v.v v8, v10 + vmv.v.v v10, v12 + vmv.v.v v12, v14 + epel_load v14, \len, put, \name, h, 1, t + add a2, a2, a3 + add a0, a0, a1 + bnez a4, 1b + epel_load v30, \len, \op, \name, v, 0, s + vse8.v v30, (a0) +.endm + +.macro epel_hv op, name, len, vlen +func ff_\op\()_vp9_8tap_\name\()_\len\()hv_rvv\vlen\(), zve32x + lpad 0 + addi sp, sp, -64 + .irp n,0,1,2,3,4,5,6,7 + sd s\n, \n\()<<3(sp) + .endr +.if \len == 64 && \vlen < 256 + addi sp, sp, -48 + .irp n,0,1,2,3,4,5 + sd a\n, \n\()<<3(sp) + .endr +.endif + csrwi vxrm, 0 + epel_filter \name, h, t, a7 + epel_filter \name, v, s, s7 + vsetvlstatic8 \len, a6, 64, m2 + epel_hv_once \len, \name, \op +.if \len == 64 && \vlen < 256 + .irp n,0,1,2,3,4,5 + ld a\n, \n\()<<3(sp) + .endr + addi sp, sp, 48 + addi a0, a0, 32 + addi a2, a2, 32 + epel_filter \name, h, t, a7 + epel_hv_once \len, \name, \op +.endif + .irp n,0,1,2,3,4,5,6,7 + ld s\n, \n\()<<3(sp) + .endr + addi sp, sp, 64 + + ret +endfunc +.endm +#endif + .irp len, 64, 32, 16, 8, 4 copy_avg \len .irp op, put, avg @@ -367,6 +433,10 @@ endfunc epel \len, \op, \name, \type, 128 epel \len, \op, \name, \type, 256 .endr + #if __riscv_xlen == 64 + epel_hv \op, \name, \len, 128 + epel_hv \op, \name, \len, 256 + #endif .endr .endr .endr diff --git a/libavcodec/riscv/vp9dsp_init.c b/libavcodec/riscv/vp9dsp_init.c index d7a1f51d6e..6999e93374 100644 --- a/libavcodec/riscv/vp9dsp_init.c +++ b/libavcodec/riscv/vp9dsp_init.c @@ -119,6 +119,10 @@ static av_cold void vp9dsp_mc_init_riscv(VP9DSPContext *dsp, int bpp) if (flags & AV_CPU_FLAG_RVB_ADDR) { init_subpel2(0, 0, 1, v, put, 128); init_subpel2(1, 0, 1, v, avg, 128); +# if __riscv_xlen == 64 + init_subpel2(0, 1, 1, hv, put, 128); + init_subpel2(1, 1, 1, hv, avg, 128); +# endif } } @@ -129,6 +133,10 @@ static av_cold void vp9dsp_mc_init_riscv(VP9DSPContext *dsp, int bpp) if (flags & AV_CPU_FLAG_RVB_ADDR) { init_subpel2(0, 0, 1, v, put, 256); init_subpel2(1, 0, 1, v, avg, 256); +# if __riscv_xlen == 64 + init_subpel2(0, 1, 1, hv, put, 256); + init_subpel2(1, 1, 1, hv, avg, 256); +# endif } } }