From patchwork Mon Mar 25 15:02:29 2024 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: 47437 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a20:c889:b0:1a3:b6bb:3029 with SMTP id hb9csp1247862pzb; Mon, 25 Mar 2024 08:04:54 -0700 (PDT) X-Forwarded-Encrypted: i=2; AJvYcCXb7RKxaaSfnEdBYmWPKFWvw34+By1rza+/yYWBFZFOYqiU0qkt47+1Q6yWUYD51eL2/PP/gUCYVlVDjJ1mE74uO49w2dogUcPK4w== X-Google-Smtp-Source: AGHT+IHapy1mB4aZxiznG9oZAdCaXc57aJvKJoot7IN5grko9Bl2rLuaNqHSQcZVyLVsIq4tiD8L X-Received: by 2002:a17:906:99d0:b0:a47:4293:944a with SMTP id s16-20020a17090699d000b00a474293944amr5094856ejn.3.1711379094452; Mon, 25 Mar 2024 08:04:54 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1711379094; cv=none; d=google.com; s=arc-20160816; b=ziJP5ReJyo1m+XbRKy5EdHejBX6trLW+OvDhrKK/93JGTvEun6GJeC2Kh28JFBXEwa gwGJlhEJeKVO4p59sC2HcZesQz7KFWphjhV5f1NDYyunNSTmeAGuPrTUeikwJDafcSmx QslSaExv55QMHCHSrep5Tat7d3i3p0AKV9q+23Y6MChj/qwRsLO09lQwaMov2bMMF3X5 hdB7ol7Td8FKEU/dHOiPTpgJav0fmVeIobSSdSEVhvsVSpbDh5ocMhNebMK3/U9kBtGk k0c9qcHvQCzeHPAMzbpk73zzSaO17df26V11SV67ENOQ5YT3HAidThEkHwQa5+zxJZx3 PJKg== 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 :message-id:date:to:from:dkim-signature:delivered-to; bh=gzXJ2Y0Jy3Gxgnsz4DEuTzdQk5wBe67YyObgHKO4A78=; fh=DRs4GoYGH1Ee5ERfKSLc+LBtFKtorfi5XrD3r13LPeM=; b=qMZQJsrHQnMJ0Dvv46FLZrkeUy2dGhy0LrPOPwGNz+dUSwI4AjiyGOsMmTsII96x1w TwcfRrK8zIU6lzdwULwY8MULmgGTgap0olCduofl9VM03/sD/HKVSSjov2uBUOnW0szf l9c6S92JPgRQGWJ2eKJEfceovxzhS8a2UTeht4Uuii7pL8zHtMmG+hUlrcrO9bSUV4RQ AvK2iLsFC/9RXv2Ro9eCVSnNnhhI7Eqi8dYeRqKOJTtumIOgA/0MJw07TQtTxawmqYlY prawx4f3Vw4MrLDKfHMjEiPK2QOdNCKCRJ2yQVQWIyFxEd6Estj7QPpRd39V2cVurrPG +I3Q==; dara=google.com ARC-Authentication-Results: i=1; mx.google.com; dkim=neutral (body hash did not verify) header.i=@martin-st.20230601.gappssmtp.com header.s=20230601 header.b=DMkkFc3t; 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 u11-20020a17090617cb00b00a46021ef910si2744762eje.854.2024.03.25.08.04.54; Mon, 25 Mar 2024 08:04:54 -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=@martin-st.20230601.gappssmtp.com header.s=20230601 header.b=DMkkFc3t; 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 B0B2668D471; Mon, 25 Mar 2024 17:03:06 +0200 (EET) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail-lf1-f47.google.com (mail-lf1-f47.google.com [209.85.167.47]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 61DA168D552 for ; Mon, 25 Mar 2024 17:02:50 +0200 (EET) Received: by mail-lf1-f47.google.com with SMTP id 2adb3069b0e04-513edc88d3cso4772733e87.0 for ; Mon, 25 Mar 2024 08:02:50 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=martin-st.20230601.gappssmtp.com; s=20230601; t=1711378969; x=1711983769; darn=ffmpeg.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=gXNX4ngYbpvBiCQdO3jp7Iv80HrGuzASFaD7rFPMfJo=; b=DMkkFc3ter4c0G7rGo94hjuy48BAtzgXFPcYPNup85c2bxjnH2tfIgYnEMVS3vKSNl pJgtQlaAGW4l6/pZzmdmp2ERLMFH9ILQHyhS/P1NdsxJPKRcR9HAVh3TI1qIlLS1e93b 768/wikgQHAQ22UxDCulWMQMfCBr5YRbhURgL84ssuj6up3dhghQ//qEqiFMA7/kF5u/ RBPB2WXMRXK6kZMJiuLoI+R+8FaOhq+M2towHWxy/S8LiwAn9fAtqSyTUECjpWoGhzE6 Q+b8yeimAZMXodBVLwnrvK8drbpSwcoZ1GZNcDpnfdFDD6O87e0Qj/p1jTuVezVH8PLJ LS2g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1711378969; x=1711983769; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=gXNX4ngYbpvBiCQdO3jp7Iv80HrGuzASFaD7rFPMfJo=; b=tvKOGJ/DM53S/yYxLRJNtFAZvY3AMlaL9/OJyJNnGI+wnjNh4hdX440wP0KbfoBZj9 hZJPp1r13KdKGzSF2fGAI8ElZBoTCBPgkMrC17LH5sQDrvja9UamsfwhOtoo+79pLYsS zucn4sqQTS+lHflfI8lUciQoZu3I5/aM+349visSVUtbGL3RPo5ad7VWEoTLdK0Aplb1 a23R+dh7IYo5vcxu5W4ENdStlghd23jGGcC/LcgMj4jBjwX/AY011BGNL0HGNbCeVlEp JJu8qq0S0gf+Eh5TfKxAQLlf4Rg1zDPVd2OWRCgwrqcse9xKjEH1M/l2x0DqoQfPXXgd VmsQ== X-Gm-Message-State: AOJu0YwIBWOwz8iGjzxMhXSmRgrwjqzAuWxohp8/ib7Fn/LbYxybGC2v 6kD/ySghEPSC9RYFRvbP0/TrmgRL1296zMRskhN3HxQ3G4hprUhgbiaJJlDnzs3FMZQTazuLidE zJJii X-Received: by 2002:a19:381e:0:b0:513:dcc1:4c35 with SMTP id f30-20020a19381e000000b00513dcc14c35mr3836235lfa.55.1711378969553; Mon, 25 Mar 2024 08:02:49 -0700 (PDT) Received: from localhost (host-114-191.parnet.fi. [77.234.114.191]) by smtp.gmail.com with ESMTPSA id u10-20020ac258ca000000b00513c9ad26e8sm1119054lfo.34.2024.03.25.08.02.49 (version=TLS1 cipher=AES128-SHA bits=128/128); Mon, 25 Mar 2024 08:02:49 -0700 (PDT) From: =?utf-8?q?Martin_Storsj=C3=B6?= To: ffmpeg-devel@ffmpeg.org Date: Mon, 25 Mar 2024 17:02:29 +0200 Message-Id: <20240325150243.59058-8-martin@martin.st> X-Mailer: git-send-email 2.39.3 (Apple Git-146) In-Reply-To: <20240325150243.59058-1-martin@martin.st> References: <20240325150243.59058-1-martin@martin.st> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH 07/21] aarch64: hevc: Implement a neon version of hevc_epel_uni_w_h*_8 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: Logan Lyu , "J . Dekker" Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" X-TUID: 0PeuLhiIB+gY AWS Graviton 3: put_hevc_epel_uni_w_h4_8_c: 97.2 put_hevc_epel_uni_w_h4_8_neon: 41.2 put_hevc_epel_uni_w_h4_8_i8mm: 35.2 put_hevc_epel_uni_w_h6_8_c: 203.7 put_hevc_epel_uni_w_h6_8_neon: 84.7 put_hevc_epel_uni_w_h6_8_i8mm: 74.7 put_hevc_epel_uni_w_h8_8_c: 345.7 put_hevc_epel_uni_w_h8_8_neon: 94.0 put_hevc_epel_uni_w_h8_8_i8mm: 80.7 put_hevc_epel_uni_w_h12_8_c: 768.7 put_hevc_epel_uni_w_h12_8_neon: 196.7 put_hevc_epel_uni_w_h12_8_i8mm: 169.7 put_hevc_epel_uni_w_h16_8_c: 1313.0 put_hevc_epel_uni_w_h16_8_neon: 290.7 put_hevc_epel_uni_w_h16_8_i8mm: 238.0 put_hevc_epel_uni_w_h24_8_c: 2877.5 put_hevc_epel_uni_w_h24_8_neon: 650.0 put_hevc_epel_uni_w_h24_8_i8mm: 512.0 put_hevc_epel_uni_w_h32_8_c: 5113.5 put_hevc_epel_uni_w_h32_8_neon: 1129.5 put_hevc_epel_uni_w_h32_8_i8mm: 739.2 put_hevc_epel_uni_w_h48_8_c: 11757.0 put_hevc_epel_uni_w_h48_8_neon: 2518.7 put_hevc_epel_uni_w_h48_8_i8mm: 1688.5 put_hevc_epel_uni_w_h64_8_c: 20478.0 put_hevc_epel_uni_w_h64_8_neon: 4411.7 put_hevc_epel_uni_w_h64_8_i8mm: 2884.0 --- libavcodec/aarch64/hevcdsp_epel_neon.S | 326 +++++++++++++++++++++- libavcodec/aarch64/hevcdsp_init_aarch64.c | 6 + 2 files changed, 319 insertions(+), 13 deletions(-) diff --git a/libavcodec/aarch64/hevcdsp_epel_neon.S b/libavcodec/aarch64/hevcdsp_epel_neon.S index 419e83529a..0e49491a81 100644 --- a/libavcodec/aarch64/hevcdsp_epel_neon.S +++ b/libavcodec/aarch64/hevcdsp_epel_neon.S @@ -1520,6 +1520,319 @@ function ff_hevc_put_hevc_epel_h32_8_neon, export=1 ret endfunc +.macro EPEL_UNI_W_H_HEADER elems=4s + ldr x12, [sp] + sub x2, x2, #1 + movrel x9, epel_filters + add x9, x9, x12, lsl #2 + ld1r {v28.4s}, [x9] + mov w10, #-6 + sub w10, w10, w5 + dup v30.\elems, w6 + dup v31.4s, w10 + dup v29.4s, w7 +.endm + +function ff_hevc_put_hevc_epel_uni_w_h4_8_neon, export=1 + EPEL_UNI_W_H_HEADER 4h + sxtl v0.8h, v28.8b +1: + ld1 {v4.8b}, [x2], x3 + subs w4, w4, #1 + uxtl v4.8h, v4.8b + ext v5.16b, v4.16b, v4.16b, #2 + ext v6.16b, v4.16b, v4.16b, #4 + ext v7.16b, v4.16b, v4.16b, #6 + mul v16.4h, v4.4h, v0.h[0] + mla v16.4h, v5.4h, v0.h[1] + mla v16.4h, v6.4h, v0.h[2] + mla v16.4h, v7.4h, v0.h[3] + smull v16.4s, v16.4h, v30.4h + sqrshl v16.4s, v16.4s, v31.4s + sqadd v16.4s, v16.4s, v29.4s + sqxtn v16.4h, v16.4s + sqxtun v16.8b, v16.8h + str s16, [x0] + add x0, x0, x1 + b.hi 1b + ret +endfunc + +function ff_hevc_put_hevc_epel_uni_w_h6_8_neon, export=1 + EPEL_UNI_W_H_HEADER 8h + sub x1, x1, #4 + sxtl v0.8h, v28.8b +1: + ld1 {v3.8b, v4.8b}, [x2], x3 + subs w4, w4, #1 + uxtl v3.8h, v3.8b + uxtl v4.8h, v4.8b + ext v5.16b, v3.16b, v4.16b, #2 + ext v6.16b, v3.16b, v4.16b, #4 + ext v7.16b, v3.16b, v4.16b, #6 + mul v16.8h, v3.8h, v0.h[0] + mla v16.8h, v5.8h, v0.h[1] + mla v16.8h, v6.8h, v0.h[2] + mla v16.8h, v7.8h, v0.h[3] + smull v17.4s, v16.4h, v30.4h + smull2 v18.4s, v16.8h, v30.8h + sqrshl v17.4s, v17.4s, v31.4s + sqrshl v18.4s, v18.4s, v31.4s + sqadd v17.4s, v17.4s, v29.4s + sqadd v18.4s, v18.4s, v29.4s + sqxtn v16.4h, v17.4s + sqxtn2 v16.8h, v18.4s + sqxtun v16.8b, v16.8h + str s16, [x0], #4 + st1 {v16.h}[2], [x0], x1 + b.hi 1b + ret +endfunc + +function ff_hevc_put_hevc_epel_uni_w_h8_8_neon, export=1 + EPEL_UNI_W_H_HEADER 8h + sxtl v0.8h, v28.8b +1: + ld1 {v3.8b, v4.8b}, [x2], x3 + subs w4, w4, #1 + uxtl v3.8h, v3.8b + uxtl v4.8h, v4.8b + ext v5.16b, v3.16b, v4.16b, #2 + ext v6.16b, v3.16b, v4.16b, #4 + ext v7.16b, v3.16b, v4.16b, #6 + mul v16.8h, v3.8h, v0.h[0] + mla v16.8h, v5.8h, v0.h[1] + mla v16.8h, v6.8h, v0.h[2] + mla v16.8h, v7.8h, v0.h[3] + smull v17.4s, v16.4h, v30.4h + smull2 v18.4s, v16.8h, v30.8h + sqrshl v17.4s, v17.4s, v31.4s + sqrshl v18.4s, v18.4s, v31.4s + sqadd v17.4s, v17.4s, v29.4s + sqadd v18.4s, v18.4s, v29.4s + sqxtn v16.4h, v17.4s + sqxtn2 v16.8h, v18.4s + sqxtun v16.8b, v16.8h + st1 {v16.8b}, [x0], x1 + b.hi 1b + ret +endfunc + +function ff_hevc_put_hevc_epel_uni_w_h12_8_neon, export=1 + EPEL_UNI_W_H_HEADER 8h + sxtl v0.8h, v28.8b +1: + ld1 {v3.8b, v4.8b}, [x2], x3 + subs w4, w4, #1 + uxtl v3.8h, v3.8b + uxtl v4.8h, v4.8b + ext v5.16b, v3.16b, v4.16b, #2 + ext v6.16b, v3.16b, v4.16b, #4 + ext v7.16b, v3.16b, v4.16b, #6 + ext v20.16b, v4.16b, v4.16b, #2 + ext v21.16b, v4.16b, v4.16b, #4 + ext v22.16b, v4.16b, v4.16b, #6 + mul v16.8h, v3.8h, v0.h[0] + mla v16.8h, v5.8h, v0.h[1] + mla v16.8h, v6.8h, v0.h[2] + mla v16.8h, v7.8h, v0.h[3] + mul v17.4h, v4.4h, v0.h[0] + mla v17.4h, v20.4h, v0.h[1] + mla v17.4h, v21.4h, v0.h[2] + mla v17.4h, v22.4h, v0.h[3] + smull v18.4s, v16.4h, v30.4h + smull2 v19.4s, v16.8h, v30.8h + smull v20.4s, v17.4h, v30.4h + sqrshl v18.4s, v18.4s, v31.4s + sqrshl v19.4s, v19.4s, v31.4s + sqrshl v20.4s, v20.4s, v31.4s + sqadd v18.4s, v18.4s, v29.4s + sqadd v19.4s, v19.4s, v29.4s + sqadd v20.4s, v20.4s, v29.4s + sqxtn v16.4h, v18.4s + sqxtn2 v16.8h, v19.4s + sqxtn v17.4h, v20.4s + sqxtun v16.8b, v16.8h + sqxtun v17.8b, v17.8h + str d16, [x0] + str s17, [x0, #8] + add x0, x0, x1 + b.hi 1b + ret +endfunc + +function ff_hevc_put_hevc_epel_uni_w_h16_8_neon, export=1 + EPEL_UNI_W_H_HEADER 8h + sxtl v0.8h, v28.8b +1: + ld1 {v1.8b, v2.8b, v3.8b}, [x2], x3 + subs w4, w4, #1 + uxtl v1.8h, v1.8b + uxtl v2.8h, v2.8b + uxtl v3.8h, v3.8b + ext v5.16b, v1.16b, v2.16b, #2 + ext v6.16b, v1.16b, v2.16b, #4 + ext v7.16b, v1.16b, v2.16b, #6 + ext v20.16b, v2.16b, v3.16b, #2 + ext v21.16b, v2.16b, v3.16b, #4 + ext v22.16b, v2.16b, v3.16b, #6 + mul v16.8h, v1.8h, v0.h[0] + mla v16.8h, v5.8h, v0.h[1] + mla v16.8h, v6.8h, v0.h[2] + mla v16.8h, v7.8h, v0.h[3] + mul v17.8h, v2.8h, v0.h[0] + mla v17.8h, v20.8h, v0.h[1] + mla v17.8h, v21.8h, v0.h[2] + mla v17.8h, v22.8h, v0.h[3] + smull v18.4s, v16.4h, v30.4h + smull2 v19.4s, v16.8h, v30.8h + smull v20.4s, v17.4h, v30.4h + smull2 v21.4s, v17.8h, v30.8h + sqrshl v18.4s, v18.4s, v31.4s + sqrshl v19.4s, v19.4s, v31.4s + sqrshl v20.4s, v20.4s, v31.4s + sqrshl v21.4s, v21.4s, v31.4s + sqadd v18.4s, v18.4s, v29.4s + sqadd v19.4s, v19.4s, v29.4s + sqadd v20.4s, v20.4s, v29.4s + sqadd v21.4s, v21.4s, v29.4s + sqxtn v16.4h, v18.4s + sqxtn2 v16.8h, v19.4s + sqxtn v17.4h, v20.4s + sqxtn2 v17.8h, v21.4s + sqxtun v16.8b, v16.8h + sqxtun v17.8b, v17.8h + st1 {v16.8b, v17.8b}, [x0], x1 + b.hi 1b + ret +endfunc + +function ff_hevc_put_hevc_epel_uni_w_h24_8_neon, export=1 + EPEL_UNI_W_H_HEADER 8h + sxtl v0.8h, v28.8b +1: + ld1 {v1.8b, v2.8b, v3.8b, v4.8b}, [x2], x3 + subs w4, w4, #1 + uxtl v1.8h, v1.8b + uxtl v2.8h, v2.8b + uxtl v3.8h, v3.8b + uxtl v4.8h, v4.8b + ext v5.16b, v1.16b, v2.16b, #2 + ext v6.16b, v1.16b, v2.16b, #4 + ext v7.16b, v1.16b, v2.16b, #6 + ext v20.16b, v2.16b, v3.16b, #2 + ext v21.16b, v2.16b, v3.16b, #4 + ext v22.16b, v2.16b, v3.16b, #6 + ext v23.16b, v3.16b, v4.16b, #2 + ext v24.16b, v3.16b, v4.16b, #4 + ext v25.16b, v3.16b, v4.16b, #6 + mul v16.8h, v1.8h, v0.h[0] + mla v16.8h, v5.8h, v0.h[1] + mla v16.8h, v6.8h, v0.h[2] + mla v16.8h, v7.8h, v0.h[3] + mul v17.8h, v2.8h, v0.h[0] + mla v17.8h, v20.8h, v0.h[1] + mla v17.8h, v21.8h, v0.h[2] + mla v17.8h, v22.8h, v0.h[3] + mul v18.8h, v3.8h, v0.h[0] + mla v18.8h, v23.8h, v0.h[1] + mla v18.8h, v24.8h, v0.h[2] + mla v18.8h, v25.8h, v0.h[3] + smull v20.4s, v16.4h, v30.4h + smull2 v21.4s, v16.8h, v30.8h + smull v22.4s, v17.4h, v30.4h + smull2 v23.4s, v17.8h, v30.8h + smull v24.4s, v18.4h, v30.4h + smull2 v25.4s, v18.8h, v30.8h + sqrshl v20.4s, v20.4s, v31.4s + sqrshl v21.4s, v21.4s, v31.4s + sqrshl v22.4s, v22.4s, v31.4s + sqrshl v23.4s, v23.4s, v31.4s + sqrshl v24.4s, v24.4s, v31.4s + sqrshl v25.4s, v25.4s, v31.4s + sqadd v20.4s, v20.4s, v29.4s + sqadd v21.4s, v21.4s, v29.4s + sqadd v22.4s, v22.4s, v29.4s + sqadd v23.4s, v23.4s, v29.4s + sqadd v24.4s, v24.4s, v29.4s + sqadd v25.4s, v25.4s, v29.4s + sqxtn v16.4h, v20.4s + sqxtn2 v16.8h, v21.4s + sqxtn v17.4h, v22.4s + sqxtn2 v17.8h, v23.4s + sqxtn v18.4h, v24.4s + sqxtn2 v18.8h, v25.4s + sqxtun v16.8b, v16.8h + sqxtun v17.8b, v17.8h + sqxtun v18.8b, v18.8h + st1 {v16.8b, v17.8b, v18.8b}, [x0], x1 + b.hi 1b + ret +endfunc + +function ff_hevc_put_hevc_epel_uni_w_h32_8_neon, export=1 + EPEL_UNI_W_H_HEADER 8h + ldr w10, [sp, #16] // width + ld1 {v1.8b}, [x2], #8 + sub x3, x3, w10, uxtw // decrement src stride + mov w11, w10 // original width + sub x3, x3, #8 // decrement src stride + sub x1, x1, w10, uxtw // decrement dst stride + sxtl v0.8h, v28.8b + uxtl v1.8h, v1.8b +1: + ld1 {v2.8b, v3.8b}, [x2], #16 + subs w10, w10, #16 // width + uxtl v2.8h, v2.8b + uxtl v3.8h, v3.8b + ext v5.16b, v1.16b, v2.16b, #2 + ext v6.16b, v1.16b, v2.16b, #4 + ext v7.16b, v1.16b, v2.16b, #6 + ext v20.16b, v2.16b, v3.16b, #2 + ext v21.16b, v2.16b, v3.16b, #4 + ext v22.16b, v2.16b, v3.16b, #6 + mul v16.8h, v1.8h, v0.h[0] + mla v16.8h, v5.8h, v0.h[1] + mla v16.8h, v6.8h, v0.h[2] + mla v16.8h, v7.8h, v0.h[3] + mul v17.8h, v2.8h, v0.h[0] + mla v17.8h, v20.8h, v0.h[1] + mla v17.8h, v21.8h, v0.h[2] + mla v17.8h, v22.8h, v0.h[3] + smull v18.4s, v16.4h, v30.4h + smull2 v19.4s, v16.8h, v30.8h + smull v20.4s, v17.4h, v30.4h + smull2 v21.4s, v17.8h, v30.8h + sqrshl v18.4s, v18.4s, v31.4s + sqrshl v19.4s, v19.4s, v31.4s + sqrshl v20.4s, v20.4s, v31.4s + sqrshl v21.4s, v21.4s, v31.4s + sqadd v18.4s, v18.4s, v29.4s + sqadd v19.4s, v19.4s, v29.4s + sqadd v20.4s, v20.4s, v29.4s + sqadd v21.4s, v21.4s, v29.4s + sqxtn v16.4h, v18.4s + sqxtn2 v16.8h, v19.4s + sqxtn v17.4h, v20.4s + sqxtn2 v17.8h, v21.4s + sqxtun v16.8b, v16.8h + sqxtun v17.8b, v17.8h + st1 {v16.8b, v17.8b}, [x0], #16 + mov v1.16b, v3.16b + b.gt 1b + subs w4, w4, #1 // height + add x2, x2, x3 + b.le 9f + ld1 {v1.8b}, [x2], #8 + mov w10, w11 + add x0, x0, x1 + uxtl v1.8h, v1.8b + b 1b +9: + ret +endfunc + + #if HAVE_I8MM ENABLE_I8MM function ff_hevc_put_hevc_epel_h4_8_neon_i8mm, export=1 @@ -2410,19 +2723,6 @@ function ff_hevc_put_hevc_epel_uni_hv64_8_neon_i8mm, export=1 ret endfunc -.macro EPEL_UNI_W_H_HEADER - ldr x12, [sp] - sub x2, x2, #1 - movrel x9, epel_filters - add x9, x9, x12, lsl #2 - ld1r {v28.4s}, [x9] - mov w10, #-6 - sub w10, w10, w5 - dup v30.4s, w6 - dup v31.4s, w10 - dup v29.4s, w7 -.endm - function ff_hevc_put_hevc_epel_uni_w_h4_8_neon_i8mm, export=1 EPEL_UNI_W_H_HEADER diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c index ece911b8d4..be24737c9c 100644 --- a/libavcodec/aarch64/hevcdsp_init_aarch64.c +++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c @@ -235,6 +235,11 @@ NEON8_FNPROTO(epel_hv, (int16_t *dst, const uint8_t *src, ptrdiff_t srcstride, int height, intptr_t mx, intptr_t my, int width), _i8mm); +NEON8_FNPROTO(epel_uni_w_h, (uint8_t *_dst, ptrdiff_t _dststride, + const uint8_t *_src, ptrdiff_t _srcstride, + int height, int denom, int wx, int ox, + intptr_t mx, intptr_t my, int width),); + NEON8_FNPROTO(epel_uni_w_h, (uint8_t *_dst, ptrdiff_t _dststride, const uint8_t *_src, ptrdiff_t _srcstride, int height, int denom, int wx, int ox, @@ -400,6 +405,7 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth) NEON8_FNASSIGN_PARTIAL_4(c->put_hevc_qpel_uni_w, 1, 0, qpel_uni_w_v,); NEON8_FNASSIGN_SHARED_32(c->put_hevc_epel, 0, 1, epel_h,); + NEON8_FNASSIGN_SHARED_32(c->put_hevc_epel_uni_w, 0, 1, epel_uni_w_h,); if (have_i8mm(cpu_flags)) { NEON8_FNASSIGN(c->put_hevc_epel, 0, 1, epel_h, _i8mm);