From patchwork Sat Sep 30 09:01:10 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= X-Patchwork-Id: 44045 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a20:1204:b0:15d:8365:d4b8 with SMTP id v4csp277735pzf; Sat, 30 Sep 2023 02:01:27 -0700 (PDT) X-Google-Smtp-Source: AGHT+IEiHmO9gxs5sznqtoxp5ghLfV4LmY+oRr2DnGMNTUlsjwbDY6yLEn7SCbGtImINFrg0FwtC X-Received: by 2002:a17:907:760f:b0:9b2:b633:ada2 with SMTP id jx15-20020a170907760f00b009b2b633ada2mr5678120ejc.36.1696064487076; Sat, 30 Sep 2023 02:01:27 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1696064487; cv=none; d=google.com; s=arc-20160816; b=CprYO507Kpl7VdSwSzRMtfCsZUa3lnbImtBOqKd03Z1arXl96gSX6COA4mstDAYd9n Ng7dH0ZJ+H7QCpsFTzum7I8lJyex41lDv4oNZk7O/KvtrRBrOchmbdur7tDIi2AoJyGy tLKr4xaC5JH1waE4no6jhLZsTqxfOh8+q5SylHnVE2aawUxR3OLhi4zMJkgdv3U/QQGE qtmfGXt87THk866HRFlqr8cmSS3Wsj/h1xARx1ZsgcSrIdFr6/l0Z/s3dyCdumDU/1JA Ca5LAxvWQOCX2AwAIa3e+JF8W8YwU071IaRLfCenllxQHQhtDyDRjnuj/nboh5g4Eela T4QQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:content-transfer-encoding:reply-to:list-subscribe :list-help:list-post:list-archive:list-unsubscribe:list-id :precedence:subject:mime-version:message-id:date:to:from :delivered-to; bh=8O2hZzDdT7DTJyyXTeUlIPUpKI/L5l8zziWm2t42L/8=; fh=YOA8vD9MJZuwZ71F/05pj6KdCjf6jQRmzLS+CATXUQk=; b=e9VP3wcESwxazchbQJNTqkkcKxg7oHLDhEyF5bATGO/WwCn3WSh0k4oXDQp5VXeOom 2vcX8bxafiFWe3uekXD1ZmJMl6Mc6iMwNIqbnUToAIScTsgueCcU5Qa5Lz0u9in1IG1i U4oe1chR2hwQKmNHRvA8qO9qs3KOFKJUvN5ypeWdMnAN4oOjAUB70NBr/37k68Icv/7U DZkLPB0R3pO6lv3yk3PAI/XblPZYVN0611eHE/KPzXE3FuTi5KqfVTfwvHy9x3VMmZf1 qIObHW4HJHulco3S+7D14eRKfz1p1d3VWyLyJgoU+T7uDEa6inh8TTmTFrxatJ0t7zlo NTVw== ARC-Authentication-Results: i=1; mx.google.com; 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 Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id s18-20020a170906c31200b00991f4e7f49asi16805824ejz.215.2023.09.30.02.01.24; Sat, 30 Sep 2023 02:01:27 -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; 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 Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 7352668CCC2; Sat, 30 Sep 2023 12:01:20 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from ursule.remlab.net (vps-a2bccee9.vps.ovh.net [51.75.19.47]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 8B2FE68CB56 for ; Sat, 30 Sep 2023 12:01:13 +0300 (EEST) Received: from basile.remlab.net (localhost [IPv6:::1]) by ursule.remlab.net (Postfix) with ESMTP id B47EDC006B for ; Sat, 30 Sep 2023 12:01:12 +0300 (EEST) From: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= To: ffmpeg-devel@ffmpeg.org Date: Sat, 30 Sep 2023 12:01:10 +0300 Message-ID: <20230930090112.376259-1-remi@remlab.net> X-Mailer: git-send-email 2.42.0 MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 1/3] swscale/rgb2rgb: rework RISC-V V uyvytoyuv422 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 Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" X-TUID: eHTRJa/ZAf4a This avoids using relatively slow register strides. --- libswscale/riscv/rgb2rgb_rvv.S | 24 +++++++++++------------- 1 file changed, 11 insertions(+), 13 deletions(-) diff --git a/libswscale/riscv/rgb2rgb_rvv.S b/libswscale/riscv/rgb2rgb_rvv.S index 008f098bfe..3e7988ca01 100644 --- a/libswscale/riscv/rgb2rgb_rvv.S +++ b/libswscale/riscv/rgb2rgb_rvv.S @@ -101,34 +101,33 @@ func ff_interleave_bytes_rvv, zve32x endfunc #if (__riscv_xlen == 64) -.macro yuy2_to_i422p v_y0, v_y1, v_u, v_v +.macro yuy2_to_i422p y_shift addi sp, sp, -16 sd s0, (sp) - sd s1, 8(sp) addi a4, a4, 1 lw s0, 16(sp) srai a4, a4, 1 // pixel width -> chroma width - li s1, 2 1: mv t4, a4 mv t3, a3 mv t0, a0 - addi t6, a0, 1 mv t1, a1 mv t2, a2 addi a5, a5, -1 2: vsetvli t5, t4, e8, m1, ta, ma + vlseg2e16.v v16, (t3) sub t4, t4, t5 - vlseg4e8.v v8, (t3) + vnsrl.wi v24, v16, \y_shift // Y0 sh2add t3, t5, t3 - vsse8.v \v_y0, (t0), s1 + vnsrl.wi v25, v18, \y_shift // Y1 + vnsrl.wi v28, v16, 8 - \y_shift // U + vnsrl.wi v30, v18, 8 - \y_shift // V + vsseg2e8.v v24, (t0) sh1add t0, t5, t0 - vsse8.v \v_y1, (t6), s1 - sh1add t6, t5, t6 - vse8.v \v_u, (t1) + vse8.v v28, (t1) add t1, t5, t1 - vse8.v \v_v, (t2) + vse8.v v30, (t2) add t2, t5, t2 bnez t4, 2b @@ -138,17 +137,16 @@ endfunc add a2, a2, a7 bnez a5, 1b - ld s1, 8(sp) ld s0, (sp) addi sp, sp, 16 ret .endm func ff_uyvytoyuv422_rvv, zve32x - yuy2_to_i422p v9, v11, v8, v10 + yuy2_to_i422p 8 endfunc func ff_yuyvtoyuv422_rvv, zve32x - yuy2_to_i422p v8, v10, v9, v11 + yuy2_to_i422p 0 endfunc #endif