From patchwork Thu Jun 6 18:26:17 2024 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: 49630 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a59:c209:0:b0:460:55fa:d5ed with SMTP id d9csp564765vqo; Thu, 6 Jun 2024 11:26:48 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCWwAH3P+u6oD5zPIC/ndi8J6DPwnURCCbuuJ9XJG5J+ZBKAEZXKoEvVcirbRj86lDhgDY2blaCkr4qxA7qI+gUCqLO1Q0q2mlRcyA== X-Google-Smtp-Source: AGHT+IHY+Gv3niXd16Anp3BnQLvnr3Z/kuPpgN8itSXtB1jX9bjE3wP/gNEzci2uEUuE3m1vzIh0 X-Received: by 2002:a17:907:72d6:b0:a67:7649:3c3b with SMTP id a640c23a62f3a-a6cd5616a97mr34456066b.5.1717698407820; Thu, 06 Jun 2024 11:26:47 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1717698407; cv=none; d=google.com; s=arc-20160816; b=bqAqpfzheRnIeIBfU+D6eWM+qNh9SgP6PSmLkHzeeK9kpZcq8jSg8Z1RXPw1r87a8p a7kC6daWUTHxS5PiX1kpD34NwgFEvRk6TuXjmQwbv7gbg9eZeQ2uRrnfF3EREC0OyXT5 xEjHlD/PTDiaiAnDCqVKrPASNMTUXVrK80jYdd3ma9dT2278z+pXfCdAVPyI4Qg+KbpD 727BVa1aUFd3qNETH1mAHUNk6mjDFmQGo+tYl+Vt5sUEzaUsja5E7RG3wopfvhYYteG2 RwVCh7OQnslxeaYZ7vfzGurxPHh/zOGCtFEmqsNpIYWIto5LFD2sBBYNSl/S4E4znBhx Rs8Q== 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=lPSNJbwilKxDoGqcpgW3EWouJO4LUcPJkAK7YaE7UpM=; fh=YOA8vD9MJZuwZ71F/05pj6KdCjf6jQRmzLS+CATXUQk=; b=Xl670IdhdD3V04uU0gt0R86u4b7ZetYtThKule8pgJcJ3zxuFuHyX/N5NIyAWpsItx bj3gCJJUjyGTIFnRm+K2hQMgHfiXLWqly9y60Dp5PGZPRAumKX427cNFngQBX3xtemKz hRG7pj0Gv311ld0iSleMbs3jqhdfpYvUA/H/Sr3+81fBYMa7SpA0uXza1QSXCmsAmdl8 8/EUoyH0P8q1lZVz3s7kxj/XT3mr63eo1Xzt7GkVM5wcWTsxoMg2107J97lMDaC1A+jG uFocelMtCHarn9qTsJ8OIWa95Tm1ktdoZCWPy5nHfqVYEZnUVlJ7oSVNLRTfyqkm1nox RbMA==; dara=google.com 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 a640c23a62f3a-a6c80596b3asi93073866b.77.2024.06.06.11.26.47; Thu, 06 Jun 2024 11:26:47 -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 CF17C68D71E; Thu, 6 Jun 2024 21:26:28 +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 00A2668D6E2 for ; Thu, 6 Jun 2024 21:26:18 +0300 (EEST) Received: from basile.remlab.net (localhost [IPv6:::1]) by ursule.remlab.net (Postfix) with ESMTP id 5A1D8C02F8 for ; Thu, 6 Jun 2024 21:26:18 +0300 (EEST) From: =?utf-8?q?R=C3=A9mi_Denis-Courmont?= To: ffmpeg-devel@ffmpeg.org Date: Thu, 6 Jun 2024 21:26:17 +0300 Message-ID: <20240606182617.39636-3-remi@remlab.net> X-Mailer: git-send-email 2.45.1 In-Reply-To: <20240606182617.39636-1-remi@remlab.net> References: <20240606182617.39636-1-remi@remlab.net> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 3/3] sws/input: R-V V 32-bit RGB to halved UV 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: O8EPyEmu4hJp T-Head C908: abgr_to_uv_half_8_c: 2.2 abgr_to_uv_half_8_rvv_i32: 3.5 abgr_to_uv_half_128_c: 44.0 abgr_to_uv_half_128_rvv_i32: 13.0 abgr_to_uv_half_1080_c: 245.0 abgr_to_uv_half_1080_rvv_i32: 107.2 abgr_to_uv_half_1920_c: 406.2 abgr_to_uv_half_1920_rvv_i32: 188.7 bgra_to_uv_half_8_c: 2.2 bgra_to_uv_half_8_rvv_i32: 3.5 bgra_to_uv_half_128_c: 26.5 bgra_to_uv_half_128_rvv_i32: 13.0 bgra_to_uv_half_1080_c: 219.7 bgra_to_uv_half_1080_rvv_i32: 107.0 bgra_to_uv_half_1920_c: 406.7 bgra_to_uv_half_1920_rvv_i32: 188.7 SpacemiT X60: abgr_to_uv_half_8_c: 2.2 abgr_to_uv_half_8_rvv_i32: 3.0 abgr_to_uv_half_128_c: 28.2 abgr_to_uv_half_128_rvv_i32: 5.7 abgr_to_uv_half_1080_c: 235.5 abgr_to_uv_half_1080_rvv_i32: 47.7 abgr_to_uv_half_1920_c: 418.2 abgr_to_uv_half_1920_rvv_i32: 84.0 bgra_to_uv_half_8_c: 2.0 bgra_to_uv_half_8_rvv_i32: 3.0 bgra_to_uv_half_128_c: 23.7 bgra_to_uv_half_128_rvv_i32: 5.7 bgra_to_uv_half_1080_c: 195.5 bgra_to_uv_half_1080_rvv_i32: 47.7 bgra_to_uv_half_1920_c: 346.5 bgra_to_uv_half_1920_rvv_i32: 84.0 --- libswscale/riscv/input.S | 61 ++++++++++++++++++++++++++++++++++++++ libswscale/riscv/swscale.c | 16 +++++++--- 2 files changed, 73 insertions(+), 4 deletions(-) diff --git a/libswscale/riscv/input.S b/libswscale/riscv/input.S index 2d00a5a225..1d7de59c66 100644 --- a/libswscale/riscv/input.S +++ b/libswscale/riscv/input.S @@ -242,6 +242,67 @@ func ff_\chr0\()ToUV_rvv, zve32x ret endfunc + +func ff_\chr1\()ToUV_half_rvv, zve32x + lw t1, 20(a6) # BU + lw t4, 32(a6) # BV + lw t3, 12(a6) # RU + lw t6, 24(a6) # RV + j 1f +endfunc + +func ff_\chr0\()ToUV_half_rvv, zve32x + lw t1, 12(a6) # RU + lw t4, 24(a6) # RV + lw t3, 20(a6) # BU + lw t6, 32(a6) # BV +1: + lw t2, 16(a6) # GU + lw t5, 28(a6) # GV + li a6, 0xff + li a7, (256 << 15) + (1 << (15 - 6)) +2: + vsetvli t0, a5, e32, m4, ta, ma + vlseg2e32.v v0, (a3) + sub a5, a5, t0 + .if \high + vsrl.vi v8, v0, 24 + vsrl.vi v12, v4, 24 + .else + vand.vx v8, v0, a6 + vand.vx v12, v4, a6 + .endif + sh3add a3, t0, a3 + vsrl.vi v16, v0, 8 * (1 + \high) + vsrl.vi v20, v4, 8 * (1 + \high) + vsrl.vi v24, v0, 8 * (2 - \high) + vsrl.vi v28, v4, 8 * (2 - \high) + vand.vx v16, v16, a6 + vand.vx v20, v20, a6 + vand.vx v24, v24, a6 + vand.vx v28, v28, a6 + vadd.vv v8, v8, v12 + vadd.vv v16, v16, v20 + vadd.vv v24, v24, v28 + vmul.vx v0, v8, t1 + vmul.vx v4, v8, t4 + vmacc.vx v0, t2, v16 + vmacc.vx v4, t5, v16 + vmacc.vx v0, t3, v24 + vmacc.vx v4, t6, v24 + vadd.vx v0, v0, a7 + vadd.vx v4, v4, a7 + vsetvli zero, zero, e16, m2, ta, ma + vnsra.wi v0, v0, 15 - 5 + vnsra.wi v2, v4, 15 - 5 + vse16.v v0, (a0) + sh1add a0, t0, a0 + vse16.v v2, (a1) + sh1add a1, t0, a1 + bnez a5, 2b + + ret +endfunc .endm rgba_input rgba32, bgra32, 0 diff --git a/libswscale/riscv/swscale.c b/libswscale/riscv/swscale.c index 76fbf2ca08..ffeb7876bf 100644 --- a/libswscale/riscv/swscale.c +++ b/libswscale/riscv/swscale.c @@ -47,13 +47,17 @@ av_cold void ff_sws_init_swscale_riscv(SwsContext *c) switch (c->srcFormat) { case AV_PIX_FMT_ABGR: c->lumToYV12 = ff_abgr32ToY_rvv; - if (!c->chrSrcHSubSample) + if (c->chrSrcHSubSample) + c->chrToYV12 = ff_abgr32ToUV_half_rvv; + else c->chrToYV12 = ff_abgr32ToUV_rvv; break; case AV_PIX_FMT_ARGB: c->lumToYV12 = ff_argb32ToY_rvv; - if (!c->chrSrcHSubSample) + if (c->chrSrcHSubSample) + c->chrToYV12 = ff_argb32ToUV_half_rvv; + else c->chrToYV12 = ff_argb32ToUV_rvv; break; @@ -67,7 +71,9 @@ av_cold void ff_sws_init_swscale_riscv(SwsContext *c) case AV_PIX_FMT_BGRA: c->lumToYV12 = ff_bgra32ToY_rvv; - if (!c->chrSrcHSubSample) + if (c->chrSrcHSubSample) + c->chrToYV12 = ff_bgra32ToUV_half_rvv; + else c->chrToYV12 = ff_bgra32ToUV_rvv; break; @@ -81,7 +87,9 @@ av_cold void ff_sws_init_swscale_riscv(SwsContext *c) case AV_PIX_FMT_RGBA: c->lumToYV12 = ff_rgba32ToY_rvv; - if (!c->chrSrcHSubSample) + if (c->chrSrcHSubSample) + c->chrToYV12 = ff_rgba32ToUV_half_rvv; + else c->chrToYV12 = ff_rgba32ToUV_rvv; break; }