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 From patchwork Sat Sep 30 09:01:11 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: 44046 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a20:1204:b0:15d:8365:d4b8 with SMTP id v4csp277803pzf; Sat, 30 Sep 2023 02:01:35 -0700 (PDT) X-Google-Smtp-Source: AGHT+IFXzd5jfgU7DDh0E2Ggu3Ah39QWw/J3VdcKQNICrVbTsntx7AQEALGUjjxSS+QSzbW51av7 X-Received: by 2002:aa7:d703:0:b0:530:bbeb:571 with SMTP id t3-20020aa7d703000000b00530bbeb0571mr6014248edq.36.1696064495420; Sat, 30 Sep 2023 02:01:35 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1696064495; cv=none; d=google.com; s=arc-20160816; b=v3FIpzmSENcS0jpYSFRJ6Fw911cfbe5ABTtu260Jz1zpDdNl9ABcm+A7/1yJ0apvTD tAgN/lnAPyFsZi9slogG7ecOEq3A0NjnvTiGdhQcazwspuwNAtrcp69i/SMlAgpItF4y ZaSEbAEnP/jr2/4fTVlaY/B/0wBgP11Zoa9VpRbHGFBjJFQ5t0unWdfZsA84NQYXmlfJ 0LGU3VMVaBjUAc9wonEnVx4UN1DzQ9Yw2w57N+BtlLkdyUJwkPCKCiw8gxYOp82iWQJG 8er4Vm+r5YUrDFiCuBXKOmtspyo0pu/QM7I2ox5FVE7YLMhkNtXHpCgLOMUN5vRfRDN9 3N5Q== 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:references:in-reply-to:message-id :date:to:from:delivered-to; bh=2ZKpyS3ZNhW0xDAApiudwCijekHXXe6qeeHdTBNqcG0=; fh=YOA8vD9MJZuwZ71F/05pj6KdCjf6jQRmzLS+CATXUQk=; b=ha5PatEa7eCGugbTMRTHT0lEvpXQX8S8iwnZ0dp/sxeh01+iz8vFqcui1oUlNuLyMz /KXuUfxdjw0LDUDfHMum+fTCsh5EJSIu5nNWKj/Vo70brNrFrJAGSZFk6viQAHP8p4nh ZLhYFB5Avnn2MFiI7odTX1iEIwumTabm9V5cTCRc6uOZShR+ZaM5ZeeKYvYFmpGITFNN hwd4UmJf0/S8Q2NxVW40Gr80J5rxMeM9V9WFk43yAfAkQLEhDDgakGwoFNBk/qvBGnEa 0Kpe1f+3fmV+uQu+0lYQX2HnqA1evIW+vz6CDDol1UzvgRcKLgU/Puv/+/QY11l46zT5 LL4g== 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 w11-20020aa7d28b000000b00537707c8524si1329403edq.146.2023.09.30.02.01.35; Sat, 30 Sep 2023 02:01:35 -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 B235968CCC7; Sat, 30 Sep 2023 12:01:21 +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 8DD6768CCB1 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 EEFEEC006C 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 12:01:11 +0300 Message-ID: <20230930090112.376259-2-remi@remlab.net> X-Mailer: git-send-email 2.42.0 In-Reply-To: <20230930090112.376259-1-remi@remlab.net> References: <20230930090112.376259-1-remi@remlab.net> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 2/3] swscale/rgb2rgb: avoid S-regs in 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: o2fawBx2UhxI We can make do with callee-clobbered registers only now. As an added bonus, this makes the code XLEN-independent. --- libswscale/riscv/rgb2rgb.c | 2 -- libswscale/riscv/rgb2rgb_rvv.S | 10 ++-------- 2 files changed, 2 insertions(+), 10 deletions(-) diff --git a/libswscale/riscv/rgb2rgb.c b/libswscale/riscv/rgb2rgb.c index 162a4082b0..565f0b77f1 100644 --- a/libswscale/riscv/rgb2rgb.c +++ b/libswscale/riscv/rgb2rgb.c @@ -55,10 +55,8 @@ av_cold void rgb2rgb_init_riscv(void) shuffle_bytes_1230 = ff_shuffle_bytes_1230_rvv; shuffle_bytes_3012 = ff_shuffle_bytes_3012_rvv; interleaveBytes = ff_interleave_bytes_rvv; -#if (__riscv_xlen == 64) uyvytoyuv422 = ff_uyvytoyuv422_rvv; yuyvtoyuv422 = ff_yuyvtoyuv422_rvv; -#endif } #endif } diff --git a/libswscale/riscv/rgb2rgb_rvv.S b/libswscale/riscv/rgb2rgb_rvv.S index 3e7988ca01..3200370224 100644 --- a/libswscale/riscv/rgb2rgb_rvv.S +++ b/libswscale/riscv/rgb2rgb_rvv.S @@ -100,12 +100,9 @@ func ff_interleave_bytes_rvv, zve32x ret endfunc -#if (__riscv_xlen == 64) .macro yuy2_to_i422p y_shift - addi sp, sp, -16 - sd s0, (sp) addi a4, a4, 1 - lw s0, 16(sp) + lw t6, (sp) srai a4, a4, 1 // pixel width -> chroma width 1: mv t4, a4 @@ -131,14 +128,12 @@ endfunc add t2, t5, t2 bnez t4, 2b - add a3, a3, s0 + add a3, a3, t6 add a0, a0, a6 add a1, a1, a7 add a2, a2, a7 bnez a5, 1b - ld s0, (sp) - addi sp, sp, 16 ret .endm @@ -149,4 +144,3 @@ endfunc func ff_yuyvtoyuv422_rvv, zve32x yuy2_to_i422p 0 endfunc -#endif From patchwork Sat Sep 30 09:01:12 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: 44047 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a20:1204:b0:15d:8365:d4b8 with SMTP id v4csp277887pzf; Sat, 30 Sep 2023 02:01:44 -0700 (PDT) X-Google-Smtp-Source: AGHT+IFFyTd4PREL0fXwTsOdJpADxZTCHtGcCmndH83YRwFDAhGE0UFYRjg0PJg6YbTu2vVxYfaD X-Received: by 2002:a05:6402:40cf:b0:531:14c4:ae30 with SMTP id z15-20020a05640240cf00b0053114c4ae30mr5612189edb.0.1696064504106; Sat, 30 Sep 2023 02:01:44 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1696064504; cv=none; d=google.com; s=arc-20160816; b=yyAmSukX+8Q8qJiH/+H1zjKWd/JlPuplvu0MgrUQt2aPwRFztMr/69llc+hCuoFDoi q8PknuThXFAraMQA6Mb8qlzwLmI9R77BL1rTgWMCcfgKtYEte5H153z7tYhWoJym4CI9 V5LXm1JF3XXJozIA7sD4IfgZ6lNyLtA/du+8u5i80WRBVuLcpwzR6wq5UEcpc9u8XSB3 OC8ZwxpE4xZq/4cjTYfFtgzO8eIPjo6CFYUgn4cbGjBQKb2YmWCtLUWv6SuDkXLgE47/ FFKN0zpuZ1xBTbb7ZKQQZAxzq5MdCp/4Qd3bY/rHGrgox5/lKSiA5rK150hMPxeerL+O kkQQ== 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:references:in-reply-to:message-id :date:to:from:delivered-to; bh=lxiaIHLscuXBJSdnp5YM6eAa02XWFa+T1WR9jVIgmig=; fh=YOA8vD9MJZuwZ71F/05pj6KdCjf6jQRmzLS+CATXUQk=; b=vCAiDHcICNod5cI77u4oVN+a3yvcaZwwbl8oIFRBdYRk+ESTzgfGxadfnRYTHWQuKG Vmas9BcLVJhdyL3c8uLurmJNqon6HQ5LuevrHF/DfC8CyyYYQgwqz7VIVsDeWlLm4KpR WPcGKjtxLohubvAAjwZQGJZmZGzsbzDoyscme6IuuS2qh0+55uJmHlG3bH4lyjbVuMXw SzCTdiIkxt6mioN8agWDKzTCfYNNJ5PuuqDy3e1e3crPfkbXcMrabHba0Q56hIasu9Jb MFusNTAO0OdGE+5u1m6NSFnskCJ2v4zssPaV4N3FwKOCKYUlRizNU/ENqeE21+2TKpye oCwg== 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 bd28-20020a056402207c00b00533cae6dce0si8030213edb.624.2023.09.30.02.01.43; Sat, 30 Sep 2023 02:01:44 -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 BA3AC68CCCB; Sat, 30 Sep 2023 12:01:22 +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 94BD868CCB2 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 358C5C018F for ; Sat, 30 Sep 2023 12:01:13 +0300 (EEST) From: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= To: ffmpeg-devel@ffmpeg.org Date: Sat, 30 Sep 2023 12:01:12 +0300 Message-ID: <20230930090112.376259-3-remi@remlab.net> X-Mailer: git-send-email 2.42.0 In-Reply-To: <20230930090112.376259-1-remi@remlab.net> References: <20230930090112.376259-1-remi@remlab.net> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 3/3] swscale/rgb2rgb: unroll 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: 2Nrghd/Q9YkN --- libswscale/riscv/rgb2rgb_rvv.S | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/libswscale/riscv/rgb2rgb_rvv.S b/libswscale/riscv/rgb2rgb_rvv.S index 3200370224..ff02eba9bf 100644 --- a/libswscale/riscv/rgb2rgb_rvv.S +++ b/libswscale/riscv/rgb2rgb_rvv.S @@ -112,14 +112,14 @@ endfunc mv t2, a2 addi a5, a5, -1 2: - vsetvli t5, t4, e8, m1, ta, ma + vsetvli t5, t4, e8, m2, ta, ma vlseg2e16.v v16, (t3) sub t4, t4, t5 vnsrl.wi v24, v16, \y_shift // Y0 sh2add t3, t5, t3 - vnsrl.wi v25, v18, \y_shift // Y1 + vnsrl.wi v26, v20, \y_shift // Y1 vnsrl.wi v28, v16, 8 - \y_shift // U - vnsrl.wi v30, v18, 8 - \y_shift // V + vnsrl.wi v30, v20, 8 - \y_shift // V vsseg2e8.v v24, (t0) sh1add t0, t5, t0 vse8.v v28, (t1)