From patchwork Mon Jul 25 11:17:08 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Hubert Mazur X-Patchwork-Id: 36958 Delivered-To: ffmpegpatchwork2@gmail.com Received: by 2002:a05:6a21:1649:b0:8b:613a:194d with SMTP id no9csp1972626pzb; Mon, 25 Jul 2022 04:17:27 -0700 (PDT) X-Google-Smtp-Source: AGRyM1v5Iga1o3KhVcDTgH6w7MhgGEoIrLnPGT9OwF5KbDP4EBXp0Jem8ed5yHCjZZ3s9imTEyaj X-Received: by 2002:a05:6402:4247:b0:43c:12a7:6bf4 with SMTP id g7-20020a056402424700b0043c12a76bf4mr2645246edb.374.1658747846848; Mon, 25 Jul 2022 04:17:26 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1658747846; cv=none; d=google.com; s=arc-20160816; b=vt1HIrQy6q7Y17RcrPwCbSJ07Cah1RMLY1/eJxldXMIhHb6EiI7d9mQkHEQJI8tqxC jLyzvIpyyh9rLvKn/aiqCZwqxsNvrtyt9KGqYIUMVxxB0X3EzZXeFtUw4/jNikTezcUR hhy9tBKTu0hAxJNNnjVki4fkl8reknX8Lj+Xu/oKQTaS6eUlxzNoRCwEcV+0L7DlovVT eh7wqvRjPYxkS6yEnywT0gmpJUTnzOTygtyZQszN0i7OeEnvTaxYgWSQ2Yv+G0jlN5VB 95c4b8N+pVV4Ph5G4yReChtjYv/BuaD5dwGUkRIaxUqX4/EGHkeQZE3NFp2+OK5WTPYb ZTbA== 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=b3CzhxOPSyg5B3f42JCBAJIY69vE3zZsM1WG9Iv7Das=; b=fVwNYjmmaGy79wQ1OSoUTIDdyaMsLjcPbgpQwJme3dQ/oHQInpWks31VmycNt2g9kI xNj0tHz++OYyXuSeRJa7Hi06hS7EujP1AnY25r2vZpFroiEIp8IJnWXRVPwY8N2M18cv HL3KEk7wIS4FlTwtf3Wi7RbsJPOhncvGjogyPGnSz6LR6Qg4WSXov0cykMpnju6Saifq dCCsherntanW6ZgHo49hBATXW52c2cCM0fBtKWvHwH9QdeixOE29j3cubb2KX/IbkYdV 4JFdjpfQuEXAyV5VW5xCy0NRvagDcsWQBF3bw9ZkAN98ilJKUmVENkDPsTN8cyjReXBk NlIQ== ARC-Authentication-Results: i=1; mx.google.com; dkim=neutral (body hash did not verify) header.i=@semihalf.com header.s=google header.b="A6P0/VHR"; 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; dmarc=fail (p=QUARANTINE sp=QUARANTINE dis=NONE) header.from=semihalf.com Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org. [79.124.17.100]) by mx.google.com with ESMTP id g2-20020a50d0c2000000b0043ba51a84f4si12677374edf.198.2022.07.25.04.17.26; Mon, 25 Jul 2022 04:17:26 -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=@semihalf.com header.s=google header.b="A6P0/VHR"; 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; dmarc=fail (p=QUARANTINE sp=QUARANTINE dis=NONE) header.from=semihalf.com Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 85E5D68B7B8; Mon, 25 Jul 2022 14:17:24 +0300 (EEST) X-Original-To: ffmpeg-devel@ffmpeg.org Delivered-To: ffmpeg-devel@ffmpeg.org Received: from mail-lf1-f45.google.com (mail-lf1-f45.google.com [209.85.167.45]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 4636F68B6D3 for ; Mon, 25 Jul 2022 14:17:18 +0300 (EEST) Received: by mail-lf1-f45.google.com with SMTP id w15so9458360lft.11 for ; Mon, 25 Jul 2022 04:17:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=semihalf.com; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=oIli6ZqA+IR8pzOB+J6uWmohsC25/bWwbEVc6IIcLoU=; b=A6P0/VHR7bYUKWEpmteQWkC/JtXo3TfVAUScWvtAq4duqVaL6R17U25zWQHGuHbWnQ ACv4l9adlEiladUWSfyXTYsWISeZX/+m2JNKwj1QPHNTti5Y3rNpXwPg9lLPORCcfGmw nP38G6DuwGgH/YcbYXpCPfTaZuT5U1oSaRN8jtM2HWiD2CklPDzbi+fzxFGY7oOjSc1+ w+//Mu0PaBWs15B1j6wwAdD+QSSrr5qCdKgVlLU4WIB6BDphGKxJfPscEg/kohImMGKh bWtSB7Wj9FgzUXvJeu+7eHPxW7dGiOt5KYcLSR/Bs39IaYpSOnSiDiF3GMURTzNLZKiV XGOA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=oIli6ZqA+IR8pzOB+J6uWmohsC25/bWwbEVc6IIcLoU=; b=IOCIWKncKP7j1wUo3gv0EDAhSMaWB0mvgedyU8nfWVfx65NRxrP06b12QAO/9U/tXi qqlmwubaTupSTHUiaUPYdp/Ma9xJR9z5dvl4Fvc7mnNaaWdt0n385tZp5Vg4JZh4c9EZ 4djqN0ugngnfGK5aE0AxngK0oUyDDTAKJRSSwsvwws1egtKbXdn/Tpf/smoJEglBEdSq 80ixim0xK9Pf+REaZ75gS3lO6zNXoClJkhKwkIb8bYN6NxVPtbSEzvWRpfYdP1j+ieHz mNsW0JU5Vxf0e1OtkQDKgZsuSuolp11TFewHV08V3FzJetN4Jv7znVKDqLyp0TcJjlV4 VdPw== X-Gm-Message-State: AJIora9pYfq+9POfmNmd6Z27RoxnGpqyRfCoqKq1V5l7bfyVAG/N8Uq2 7ehude//NIfJpDVM3co4FGxcaJeu1clMzQ== X-Received: by 2002:ac2:4295:0:b0:48a:23be:ac87 with SMTP id m21-20020ac24295000000b0048a23beac87mr4261035lfh.662.1658747837259; Mon, 25 Jul 2022 04:17:17 -0700 (PDT) Received: from hum-HP-ProBook-440-G7.wifi.semihalf.net ([83.142.187.84]) by smtp.gmail.com with ESMTPSA id t17-20020a05651c205100b0025df5f38da8sm1529480ljo.119.2022.07.25.04.17.16 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 25 Jul 2022 04:17:16 -0700 (PDT) From: Hubert Mazur To: ffmpeg-devel@ffmpeg.org Date: Mon, 25 Jul 2022 13:17:08 +0200 Message-Id: <20220725111708.44992-1-hum@semihalf.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20220715080228.686736-4-hum@semihalf.com> References: <20220715080228.686736-4-hum@semihalf.com> MIME-Version: 1.0 Subject: [FFmpeg-devel] [PATCH] lavc/aarch64: Add neon implementation for pix_abs16_y2 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: gjb@semihalf.com, upstream@semihalf.com, jswinney@amazon.com, Hubert Mazur , martin@martin.st, mw@semihalf.com, spop@amazon.com Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" X-TUID: lVho7ih20JyK Provide optimized implementation of pix_abs16_y2 function for arm64. Performance comparison tests are shown below. pix_abs_0_2_c: 308.5 pix_abs_0_2_neon: 39.2 Benchmarks and tests run with checkasm tool on AWS Graviton 3. Signed-off-by: Hubert Mazur --- libavcodec/aarch64/me_cmp_init_aarch64.c | 3 + libavcodec/aarch64/me_cmp_neon.S | 73 ++++++++++++++++++++++++ 2 files changed, 76 insertions(+) diff --git a/libavcodec/aarch64/me_cmp_init_aarch64.c b/libavcodec/aarch64/me_cmp_init_aarch64.c index 72a2062e7e..07d62cc1e5 100644 --- a/libavcodec/aarch64/me_cmp_init_aarch64.c +++ b/libavcodec/aarch64/me_cmp_init_aarch64.c @@ -29,6 +29,8 @@ int ff_pix_abs16_xy2_neon(MpegEncContext *s, uint8_t *blk1, uint8_t *blk2, ptrdiff_t stride, int h); int ff_pix_abs16_x2_neon(MpegEncContext *v, uint8_t *pix1, uint8_t *pix2, ptrdiff_t stride, int h); +int ff_pix_abs16_y2_neon(MpegEncContext *v, uint8_t *pix1, uint8_t *pix2, + ptrdiff_t stride, int h); int sse16_neon(MpegEncContext *v, uint8_t *pix1, uint8_t *pix2, ptrdiff_t stride, int h); @@ -42,6 +44,7 @@ av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx) if (have_neon(cpu_flags)) { c->pix_abs[0][0] = ff_pix_abs16_neon; c->pix_abs[0][1] = ff_pix_abs16_x2_neon; + c->pix_abs[0][2] = ff_pix_abs16_y2_neon; c->pix_abs[0][3] = ff_pix_abs16_xy2_neon; c->sad[0] = ff_pix_abs16_neon; diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S index 3336d88848..6e392e9066 100644 --- a/libavcodec/aarch64/me_cmp_neon.S +++ b/libavcodec/aarch64/me_cmp_neon.S @@ -417,3 +417,76 @@ function sse4_neon, export=1 ret endfunc + +function ff_pix_abs16_y2_neon, export=1 + // x0 unused + // x1 uint8_t *pix1 + // x2 uint8_t *pix2 + // x3 ptrdiff_t stride + // x4 int h + + // initialize buffers + movi d18, #0 + add x5, x2, x3 // pix2 + stride + cmp w4, #4 + b.lt 2f + +// make 4 iterations at once +1: + + // abs(pix1[0], avg2(pix2[0], pix2[0 + stride])) + // avg2(a, b) = (((a) + (b) + 1) >> 1) + // abs(x) = (x < 0 ? (-x) : (x)) + + ld1 {v1.16b}, [x2], x3 // Load pix2 for first iteration + ld1 {v2.16b}, [x5], x3 // Load pix3 for first iteration + urhadd v30.16b, v1.16b, v2.16b // Rounding halving add, first iteration + ld1 {v0.16b}, [x1], x3 // Load pix1 for first iteration + uabdl v29.8h, v0.8b, v30.8b // Absolute difference of lower half, first iteration + ld1 {v4.16b}, [x2], x3 // Load pix2 for second iteration + uabdl2 v28.8h, v0.16b, v30.16b // Absolute difference of upper half, first iteration + ld1 {v5.16b}, [x5], x3 // Load pix3 for second iteartion + ld1 {v3.16b}, [x1], x3 // Load pix1 for second iteration + urhadd v27.16b, v4.16b, v5.16b // Rounding halving add, second iteration + uabal v29.8h, v3.8b, v27.8b // Absolute difference of lower half for second iteration + ld1 {v7.16b}, [x2], x3 // Load pix2 for third iteration + uabal2 v28.8h, v3.16b, v27.16b // Absolute difference of upper half for second iteration + ld1 {v20.16b}, [x5], x3 // Load pix3 for third iteration + urhadd v26.16b, v7.16b, v20.16b // Rounding halving add, third iteration + ld1 {v6.16b}, [x1], x3 // Load pix1 for third iteration + uabal v29.8h, v6.8b, v26.8b // Absolute difference of lower half for third iteration + ld1 {v22.16b}, [x2], x3 // Load pix2 for fourth iteration + uabal2 v28.8h, v6.16b, v26.16b // Absolute difference of upper half for third iteration + ld1 {v23.16b}, [x5], x3 // Load pix3 for fourth iteration + urhadd v25.16b, v22.16b, v23.16b // Rounding halving add + ld1 {v21.16b}, [x1], x3 // Load pix1 for fourth iteration + uabal v29.8h, v21.8b, v25.8b // Absolute difference of lower half for fourth iteration + uabal2 v28.8h, v21.16b, v25.16b // Absolute difference of upper half for fourth iteration + + add v29.8h, v29.8h, v28.8h // Add vectors together + sub w4, w4, #4 // h-= 4 + uaddlv s16, v29.8h // Add up vector values + cmp w4, #4 + add d18, d18, d16 + b.ge 1b + cbz w4, 3f + +// iterate by one +2: + + ld1 {v1.16b}, [x2], x3 // Load pix2 + ld1 {v2.16b}, [x5], x3 // Load pix3 + urhadd v30.16b, v1.16b, v2.16b // Rounding halving add + ld1 {v0.16b}, [x1], x3 // Load pix1 + uabd v30.16b, v30.16b, v30.16b + + uaddlv h17, v30.16b + subs w4, w4, #1 + add d18, d18, d17 + b.ne 2b + +3: + fmov w0, s18 + + ret +endfunc