From patchwork Wed Mar 8 10:00:45 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: =?utf-8?q?Martin_Storsj=C3=B6?= X-Patchwork-Id: 2824 Delivered-To: ffmpegpatchwork@gmail.com Received: by 10.103.50.79 with SMTP id y76csp954941vsy; Wed, 8 Mar 2017 02:07:50 -0800 (PST) X-Received: by 10.223.142.201 with SMTP id q67mr4153111wrb.182.1488967670739; Wed, 08 Mar 2017 02:07:50 -0800 (PST) Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id l17si3679671wra.244.2017.03.08.02.07.50; Wed, 08 Mar 2017 02:07:50 -0800 (PST) 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=@martin-st.20150623.gappssmtp.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 408FD6882DD; Wed, 8 Mar 2017 12:07:34 +0200 (EET) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail-lf0-f66.google.com (mail-lf0-f66.google.com [209.85.215.66]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 5F48E68049C for ; Wed, 8 Mar 2017 12:07:33 +0200 (EET) Received: by mail-lf0-f66.google.com with SMTP id g70so1996826lfh.3 for ; Wed, 08 Mar 2017 02:07:46 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=martin-st.20150623.gappssmtp.com; s=20150623; h=from:to:subject:date:message-id:in-reply-to:references; bh=uHa/GjBnB5wsilmUa+8r+yKdcWsShAwUyhRT9tkokAs=; b=CQ7OLngNwb4JK41j7od+gSHzGUEHw5IBlHX0Gm5A9FDoo7TMw3UXnssNiJh0k79x/O iVSEOCmsY6d4U/CyOrQGU6Xfoymd5e+VxrO4mogClKDPI7axsyjMpjoBMOL9cPbKQ7CD R8sbla9eGToo06KYA83E9R7Oqs/CWqeXN1vZMo1uyv837U5+FAY7RYrECNXU3YOKtpA6 2+x69TfIJFEhRkItRRd7C4ShWHa2F858R7ve60QQaEbL5K72+dmSAVeoAx+eYHM1QHTE K2jpvAJTfzOWWfdigLo6UVBo98jE2p+e5/shwzP/27UT2F0lVRMKiNrzA0hvbhs0DF5j BxFg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:subject:date:message-id:in-reply-to :references; bh=uHa/GjBnB5wsilmUa+8r+yKdcWsShAwUyhRT9tkokAs=; b=fSm31DMjG3OU4yS3wKfGw4cRFziFP2r+atIp8DIxTSB7x7svotMZJeNNvaInaOU26W CZDUsvOwrJImtCIxGKJNikrZUg0oew73HjDbJJcc8hd2zRd5KN8JpjbQuAUsO2qx4riQ PLHNnSnlO5PGZ93HW0Ykf9h3UwhT4yTIqyXJgGst2Ltof5E2kOQof4IEDAODH3QgSjw8 0SJ3lAp9rtX5HxnRs2Mb7B6thqX+X5gz2LA/uBjAHc4wkT15RCTYWbhFPFjv42Qr8ydt 40NbBwSc7y68xV6h+BPtV/T7NzmqhlaU6yHCKs58cQq8mK36iKUQM7GWnoYr6ii/EAWb ll2g== X-Gm-Message-State: AMke39knRvucSBNnbMgagbp1JTrSlSWDZC8RiK1pvYS0g7YT5mViJCPW/T/0KX0Ts6EsqA== X-Received: by 10.25.193.194 with SMTP id r185mr1360603lff.158.1488967280499; Wed, 08 Mar 2017 02:01:20 -0800 (PST) Received: from localhost.localdomain ([2001:470:28:852:7d47:68e:13e8:4933]) by smtp.gmail.com with ESMTPSA id m127sm513064lfg.58.2017.03.08.02.01.19 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Wed, 08 Mar 2017 02:01:20 -0800 (PST) From: =?UTF-8?q?Martin=20Storsj=C3=B6?= To: ffmpeg-devel@ffmpeg.org Date: Wed, 8 Mar 2017 12:00:45 +0200 Message-Id: <1488967274-8143-5-git-send-email-martin@martin.st> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1488967274-8143-1-git-send-email-martin@martin.st> References: <1488967274-8143-1-git-send-email-martin@martin.st> Subject: [FFmpeg-devel] [PATCH 05/34] arm: vp9itxfm: Move the load_add_store macro out from the itxfm16 pass2 function X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.20 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 MIME-Version: 1.0 Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" This allows reusing the macro for a separate implementation of the pass2 function. This is cherrypicked from libav commit 47b3c2c18d1897f3c753ba0cec4b2d7aa24526af. --- libavcodec/arm/vp9itxfm_neon.S | 72 +++++++++++++++++++++--------------------- 1 file changed, 36 insertions(+), 36 deletions(-) diff --git a/libavcodec/arm/vp9itxfm_neon.S b/libavcodec/arm/vp9itxfm_neon.S index 328bb01..682a82e 100644 --- a/libavcodec/arm/vp9itxfm_neon.S +++ b/libavcodec/arm/vp9itxfm_neon.S @@ -657,6 +657,42 @@ function iadst16 bx lr endfunc +.macro load_add_store coef0, coef1, coef2, coef3 + vrshr.s16 \coef0, \coef0, #6 + vrshr.s16 \coef1, \coef1, #6 + + vld1.32 {d4[]}, [r0,:32], r1 + vld1.32 {d4[1]}, [r3,:32], r1 + vrshr.s16 \coef2, \coef2, #6 + vrshr.s16 \coef3, \coef3, #6 + vld1.32 {d5[]}, [r0,:32], r1 + vld1.32 {d5[1]}, [r3,:32], r1 + vaddw.u8 \coef0, \coef0, d4 + vld1.32 {d6[]}, [r0,:32], r1 + vld1.32 {d6[1]}, [r3,:32], r1 + vaddw.u8 \coef1, \coef1, d5 + vld1.32 {d7[]}, [r0,:32], r1 + vld1.32 {d7[1]}, [r3,:32], r1 + + vqmovun.s16 d4, \coef0 + vqmovun.s16 d5, \coef1 + sub r0, r0, r1, lsl #2 + sub r3, r3, r1, lsl #2 + vaddw.u8 \coef2, \coef2, d6 + vaddw.u8 \coef3, \coef3, d7 + vst1.32 {d4[0]}, [r0,:32], r1 + vst1.32 {d4[1]}, [r3,:32], r1 + vqmovun.s16 d6, \coef2 + vst1.32 {d5[0]}, [r0,:32], r1 + vst1.32 {d5[1]}, [r3,:32], r1 + vqmovun.s16 d7, \coef3 + + vst1.32 {d6[0]}, [r0,:32], r1 + vst1.32 {d6[1]}, [r3,:32], r1 + vst1.32 {d7[0]}, [r0,:32], r1 + vst1.32 {d7[1]}, [r3,:32], r1 +.endm + .macro itxfm16_1d_funcs txfm @ Read a vertical 4x16 slice out of a 16x16 matrix, do a transform on it, @ transpose into a horizontal 16x4 slice and store. @@ -739,44 +775,8 @@ function \txfm\()16_1d_4x16_pass2_neon lsl r1, r1, #1 bl \txfm\()16 -.macro load_add_store coef0, coef1, coef2, coef3 - vrshr.s16 \coef0, \coef0, #6 - vrshr.s16 \coef1, \coef1, #6 - - vld1.32 {d4[]}, [r0,:32], r1 - vld1.32 {d4[1]}, [r3,:32], r1 - vrshr.s16 \coef2, \coef2, #6 - vrshr.s16 \coef3, \coef3, #6 - vld1.32 {d5[]}, [r0,:32], r1 - vld1.32 {d5[1]}, [r3,:32], r1 - vaddw.u8 \coef0, \coef0, d4 - vld1.32 {d6[]}, [r0,:32], r1 - vld1.32 {d6[1]}, [r3,:32], r1 - vaddw.u8 \coef1, \coef1, d5 - vld1.32 {d7[]}, [r0,:32], r1 - vld1.32 {d7[1]}, [r3,:32], r1 - - vqmovun.s16 d4, \coef0 - vqmovun.s16 d5, \coef1 - sub r0, r0, r1, lsl #2 - sub r3, r3, r1, lsl #2 - vaddw.u8 \coef2, \coef2, d6 - vaddw.u8 \coef3, \coef3, d7 - vst1.32 {d4[0]}, [r0,:32], r1 - vst1.32 {d4[1]}, [r3,:32], r1 - vqmovun.s16 d6, \coef2 - vst1.32 {d5[0]}, [r0,:32], r1 - vst1.32 {d5[1]}, [r3,:32], r1 - vqmovun.s16 d7, \coef3 - - vst1.32 {d6[0]}, [r0,:32], r1 - vst1.32 {d6[1]}, [r3,:32], r1 - vst1.32 {d7[0]}, [r0,:32], r1 - vst1.32 {d7[1]}, [r3,:32], r1 -.endm load_add_store q8, q9, q10, q11 load_add_store q12, q13, q14, q15 -.purgem load_add_store pop {pc} endfunc