From patchwork Mon Oct 14 10:56:36 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tamar Christina X-Patchwork-Id: 1996810 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; dkim=pass (1024-bit key; unprotected) header.d=arm.com header.i=@arm.com header.a=rsa-sha256 header.s=selector1 header.b=LC+AC2Dt; dkim=pass (1024-bit key) header.d=arm.com header.i=@arm.com header.a=rsa-sha256 header.s=selector1 header.b=LC+AC2Dt; dkim-atps=neutral Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=gcc.gnu.org (client-ip=2620:52:3:1:0:246e:9693:128c; helo=server2.sourceware.org; envelope-from=gcc-patches-bounces~incoming=patchwork.ozlabs.org@gcc.gnu.org; receiver=patchwork.ozlabs.org) Received: from server2.sourceware.org (server2.sourceware.org [IPv6:2620:52:3:1:0:246e:9693:128c]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (secp384r1) server-digest SHA384) (No client certificate requested) by legolas.ozlabs.org (Postfix) with ESMTPS id 4XRvNM6RXzz1xvK for ; Mon, 14 Oct 2024 21:58:27 +1100 (AEDT) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 098E1385AE41 for ; Mon, 14 Oct 2024 10:58:26 +0000 (GMT) X-Original-To: gcc-patches@gcc.gnu.org Delivered-To: gcc-patches@gcc.gnu.org Received: from EUR03-AM7-obe.outbound.protection.outlook.com (mail-am7eur03on2062a.outbound.protection.outlook.com [IPv6:2a01:111:f403:260e::62a]) by sourceware.org (Postfix) with ESMTPS id 73B9D385842A for ; Mon, 14 Oct 2024 10:56:56 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 73B9D385842A Authentication-Results: sourceware.org; dmarc=pass (p=none dis=none) header.from=arm.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=arm.com ARC-Filter: OpenARC Filter v1.0.0 sourceware.org 73B9D385842A Authentication-Results: server2.sourceware.org; arc=pass smtp.remote-ip=2a01:111:f403:260e::62a ARC-Seal: i=3; a=rsa-sha256; d=sourceware.org; s=key; t=1728903427; cv=pass; b=CkKwmYn8FQ5Ge7x4LTwKqw2e/z0P3s09RXHE2/+K2jQpjob+NGKBJOOTYQzsEfN4emlSGUZSKfQFpMIeO1IyzXXudWIQjeEDnz+tfxWLNkDxeP+QKxpkjBMTGzMaX3j6Mb+uHXo1VLHtmbUTQVvGLa+BgdIAHzbd+50mhOY4ck8= ARC-Message-Signature: i=3; a=rsa-sha256; d=sourceware.org; s=key; t=1728903427; c=relaxed/simple; bh=diooiiZYUv2fA73Spl8WcBUeGRV6xhfwILGwVZBAwL8=; h=DKIM-Signature:DKIM-Signature:Date:From:To:Subject:Message-ID: MIME-Version; b=METyGgvGSubi/8+RE0Xq6oJzX/js68rwXsX1uBlkuMN/p0k5N7zXQBDeH8hjSVuz4TC+ltZ/KsZn+iW/GdLwIbocs27SaTjVyU09j9mt8PGTU0qtkD2fA6H+rzDaLvP71Gkswfy2Mp9RFR0ciuDqm6dljge/G+OADyzCxLx4Gyc= ARC-Authentication-Results: i=3; server2.sourceware.org ARC-Seal: i=2; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=pass; b=Gbfb37HUs8S6xyIkKIB5xgQesGuQCxmPqPXF4P6LJ37gqUV0rtb3Ab09lL88SEh/WGbndqMdD8LrpXxRkY8fhFklXkmNzxcbKDUO373vuW8gc7Y0S9TJjGPVBRf6nSp0iRvTaH1qfTw3NuJVJhUf2MFh4khVt1AOKzuWgCmZtST3L9gpgGbh+GTM/i4e88gZ34Yr2b5C2+2e1IvpRqxIil3hU7lPdauGt1kKrYq2LdNf+oC3rrkmErh7OLnKnhRnLcTxMTXXBg/zf/l7oSUyxM+GfL8d1Zc6bOKvUiaLdBX0HVnbLyAKKMDZ2AfT4XZGlVxzbCmlyGgDrCfymQulKQ== ARC-Message-Signature: i=2; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector10001; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=TnY7B3gSWuXfLFBItBXqbbqqiUfPzZUCapDVVkTgdWw=; b=Kf7DXnPwzWgUOTuooSdr/VKJsxUvweF2vuzsSKTpaGAvoapFU/UJ3EO2otE4iOcR2GZabxoxjMO8PyNNtox0Nedk4YtG/BaimIv999W3VD3yYGi9YDC3T+PrqlDC1iGa2uaNN6mbKJUd6EHfVPzWtc2R9aB8nz4PYxh+RSYXFNB8NwAoUCrZ8UXcdmc0IFsCkCZ/7GgCNFTD8wu+l2LPyvWzKtZo/XQxxEcknx3bjd8bAA6cJyxhBritr1Fv7pEgrC/j499BeeU1lD7Eeysdyz/I79BJXDCjX1X1qV9XLiUFp9v4eS0UmRgHgNquS/BgCcThskY32tpsXORk7hjNsQ== ARC-Authentication-Results: i=2; mx.microsoft.com 1; spf=pass (sender ip is 63.35.35.123) smtp.rcpttodomain=gcc.gnu.org smtp.mailfrom=arm.com; dmarc=pass (p=none sp=none pct=100) action=none header.from=arm.com; dkim=pass (signature was verified) header.d=arm.com; arc=pass (0 oda=1 ltdi=1 spf=[1,1,smtp.mailfrom=arm.com] dkim=[1,1,header.d=arm.com] dmarc=[1,1,header.from=arm.com]) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=arm.com; s=selector1; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=TnY7B3gSWuXfLFBItBXqbbqqiUfPzZUCapDVVkTgdWw=; b=LC+AC2DtedebvKgBzKhYNpxyrHNGAGVOaP/qBem1IQ1UHhu8cfFcskJ14jkn9Zce8qeYh60+dMfis7Wi6SGx1uLrJzUlmBiXB55bkJ2xFdKASz73z/WC3WneH+wfRRNAOCtrIoVf7nwNhkUFNs3Mi+D0ZcLdPnHawKsFC/r3gLg= Received: from AM0PR02CA0218.eurprd02.prod.outlook.com (2603:10a6:20b:28f::25) by AS8PR08MB6453.eurprd08.prod.outlook.com (2603:10a6:20b:31b::19) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.8048.26; Mon, 14 Oct 2024 10:56:50 +0000 Received: from AM1PEPF000252E0.eurprd07.prod.outlook.com (2603:10a6:20b:28f:cafe::3b) by AM0PR02CA0218.outlook.office365.com (2603:10a6:20b:28f::25) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.8048.27 via Frontend Transport; Mon, 14 Oct 2024 10:56:49 +0000 X-MS-Exchange-Authentication-Results: spf=pass (sender IP is 63.35.35.123) smtp.mailfrom=arm.com; dkim=pass (signature was verified) header.d=arm.com;dmarc=pass action=none header.from=arm.com; Received-SPF: Pass (protection.outlook.com: domain of arm.com designates 63.35.35.123 as permitted sender) receiver=protection.outlook.com; client-ip=63.35.35.123; helo=64aa7808-outbound-1.mta.getcheckrecipient.com; pr=C Received: from 64aa7808-outbound-1.mta.getcheckrecipient.com (63.35.35.123) by AM1PEPF000252E0.mail.protection.outlook.com (10.167.16.58) with Microsoft SMTP Server (version=TLS1_3, cipher=TLS_AES_256_GCM_SHA384) id 15.20.8069.17 via Frontend Transport; Mon, 14 Oct 2024 10:56:48 +0000 Received: ("Tessian outbound de6fe3af73ff:v473"); Mon, 14 Oct 2024 10:56:48 +0000 X-CheckRecipientChecked: true X-CR-MTA-CID: bd62cf6f87da4a1c X-TessianGatewayMetadata: jm4DblG5Nk/ACu1KB/O6h48W9TT1AiEt2Ro7qkf/k4xD8QAHibs08nG/7TDWxKY1liF2zVHbh2VyBEl0G2JmSt16RVR6/vn4xXO3kVoXAZknwEfdfqIXZVMUpFCQBlSNbshuH/U1ggq5glzKr+8gNg== X-CR-MTA-TID: 64aa7808 Received: from Lc151ae719435.1 by 64aa7808-outbound-1.mta.getcheckrecipient.com id 0A2E920B-510E-4D8D-A14F-660514338209.1; Mon, 14 Oct 2024 10:56:41 +0000 Received: from EUR05-VI1-obe.outbound.protection.outlook.com by 64aa7808-outbound-1.mta.getcheckrecipient.com with ESMTPS id Lc151ae719435.1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384); Mon, 14 Oct 2024 10:56:41 +0000 ARC-Seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=ufJZ0xTRxSyID1xZFLK59QWiUp/+DRVE4X37xMiHPvuZCE35iodokw1zfDElhum3l6+QJ3tfnKisRcb0D8LII2QLtYOclwSrl0u+LhT54hq+DJbJzNJA7KFaOYS4GOOkAgrYl3vFTQhrrWTKejQc7Mv2YL0R2vf5fl5NIFAhJP0r5kGgnS2SksgH/hW0Yaw7N3F3kk07YB0PorqUsRft9KFBcQjPpkACLPr4mddmMiIIZvGgubsfteBERKUZprNqYq2xa6LMj9sPJhRvsOSKx01XpQHekQ828CQ1tgVJR7SNBcfMkxl058bzNAYNU/H1U6XW85YA4wR6OgEjfwbSIg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector10001; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=TnY7B3gSWuXfLFBItBXqbbqqiUfPzZUCapDVVkTgdWw=; b=qanZRfPJB6FqDMQk/6GyLJkpWcJUTpCdowCKnoNLNUA3I7ih3rhP9sCSpi/4WD5sCynMfOLrsKYj9zQwi/ETseSx3/JEqs+8Hq89vPj/rD6pfoyISi57u+RN3PD72zWJx+NCrgjIPKJfXlz7DiBH4y3eXabnBa4qWbu0TcBEiCdnuC0ZSCqvQeeNxauqMj9TEgUUXMA4UQbxIWwePqhOmvAcQR2sS7uUJDJw+eEbuMA4M8lIci7N4oYhvTZZBSlLqe4vIxenXOsCbK+Xh8j7A0t/ivKeai263MfR2RewCnsB2Se++7aCGYuad9LoQoCLmQKxR4vkB8hJ9dxXEPf/gw== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=arm.com; dmarc=pass action=none header.from=arm.com; dkim=pass header.d=arm.com; arc=none DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=arm.com; s=selector1; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=TnY7B3gSWuXfLFBItBXqbbqqiUfPzZUCapDVVkTgdWw=; b=LC+AC2DtedebvKgBzKhYNpxyrHNGAGVOaP/qBem1IQ1UHhu8cfFcskJ14jkn9Zce8qeYh60+dMfis7Wi6SGx1uLrJzUlmBiXB55bkJ2xFdKASz73z/WC3WneH+wfRRNAOCtrIoVf7nwNhkUFNs3Mi+D0ZcLdPnHawKsFC/r3gLg= Authentication-Results-Original: dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=arm.com; Received: from VI1PR08MB5325.eurprd08.prod.outlook.com (2603:10a6:803:13e::17) by DU0PR08MB8709.eurprd08.prod.outlook.com (2603:10a6:10:403::22) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.8048.25; Mon, 14 Oct 2024 10:56:37 +0000 Received: from VI1PR08MB5325.eurprd08.prod.outlook.com ([fe80::89dc:c731:362b:7c69]) by VI1PR08MB5325.eurprd08.prod.outlook.com ([fe80::89dc:c731:362b:7c69%7]) with mapi id 15.20.8048.020; Mon, 14 Oct 2024 10:56:37 +0000 Date: Mon, 14 Oct 2024 11:56:36 +0100 From: Tamar Christina To: gcc-patches@gcc.gnu.org Cc: nd@arm.com, rguenther@suse.de Subject: [PATCH 4/4]middle-end: create the longest possible zero extend chain after overwidening Message-ID: Content-Disposition: inline In-Reply-To: X-ClientProxiedBy: LO4P265CA0060.GBRP265.PROD.OUTLOOK.COM (2603:10a6:600:2af::6) To VI1PR08MB5325.eurprd08.prod.outlook.com (2603:10a6:803:13e::17) MIME-Version: 1.0 X-MS-TrafficTypeDiagnostic: VI1PR08MB5325:EE_|DU0PR08MB8709:EE_|AM1PEPF000252E0:EE_|AS8PR08MB6453:EE_ X-MS-Office365-Filtering-Correlation-Id: e0b28f1d-bfec-4ba2-db58-08dcec3ee713 x-checkrecipientrouted: true NoDisclaimer: true X-MS-Exchange-SenderADCheck: 1 X-MS-Exchange-AntiSpam-Relay: 0 X-Microsoft-Antispam-Untrusted: BCL:0;ARA:13230040|366016|376014|1800799024; X-Microsoft-Antispam-Message-Info-Original: 2sT49ZHedI5orQvm2h23EgjEqOmk+DyetDMomZ5JtBSqh9Ll4usSEoQvPJyH/KWinYoPnOdBE1NyOxWjpp+b01+7UhdAdp5a4xj8DmI9RrohyPglvSR7kTsKb8wY+J4vt7jogy9lmtQNxVWV/UB7zfMrGgAyyI+/uhfwLr74Q2iC3DsSRGtNUojzpXxkqZi6gDz448fuMzqXW/Km9w3I2mCKTicZ6UyvtSlOgREiSBS2vkZ0sHRQUYPXabyShGWhVMH9UxhNzSsFCYjxcjwPDnpYK+5Wf9W1hfoLzQn1suQBdmOqQb+CZslxZlyX9dyr29xROHP8tmCVxs8jZ5/ZG2893WF2KbRQMsqk+JpmwT3Bvs8lJ279/jpSxT5QimaCehkbslZ50Xf33WoUqG/IkYbX4iym5l0rji76FGKpD10qJ4pGiKMsLrrMAyT7alMNrjvypt3icajg0XzjtF+xVatq54OJZNafXaX8vm/TSgSmoLwNMRy6itelA4CMCzytkZ1hsKsrLnBpIagnCBUsoam7isocNMSB36pxUSuTqrM7G0GW4VFI5jFUYJK6eylkP+z+8ECoRrx+PgQ+s55VvblKOB2c8bV13ZBPlgfgr0yUat+JKXss9aOMjQCUBwA9Z/8oTFbD92mQlGKu/gd1yTnNTX4SeCuU9e9TTJgw6yzJ6NyS0XsWEfmO+yiUyDAtm26UicBGmv7tRa+R7RTOcJmsaf/3zILivIN6gWFPtO6fGq2WjWFb+3+xxxEkjwmN5fV7SPtYvTZ1EBHDG2yD49yMmEFTLQoCSci7/VzdmI7xEzzDKcR8wBHJAh+txT8/10d0Rx5bCJlmInt3lE2I5AyfqE+IYjbJZ380QEdVtV0626xwcmSQHk53qQI8lpNtVcZCAGlVdfq1zXp2W+WeVgKgHjk1ovH86urrcy7NJwKRiXq7el07pUVQnslIwLatuD0iqaWUJ2rSFPZ0JauL82Xa9ILnsUN0w+CYDNeOiB/kQ57zpeWDlZCsw5TDPOjwev0lfVBXiANLejOuhUfcPJ2QyqTk7Ayp8KtLoIj0nY4L1xX9ZCbK9ckoO7bYr4BVi7yW5sZdq548hQOAO2LZIxrBJ4P3RVpIOJEUxNw1Eobx3DnUDfIMkzJxyZTryGi1hx6CFwpkNPMcQ6S+RR/+97bKqF/RpxS4aO6qNmm3opKL6YJcrrAiLXoDGY8MxNaP/mpBcHbzXekQPTyDU0sxBF/TWXSVUCw/Dz3sQPZuB1w= X-Forefront-Antispam-Report-Untrusted: CIP:255.255.255.255; CTRY:; LANG:en; SCL:1; SRV:; IPV:NLI; SFV:NSPM; H:VI1PR08MB5325.eurprd08.prod.outlook.com; PTR:; CAT:NONE; SFS:(13230040)(366016)(376014)(1800799024); DIR:OUT; SFP:1101; X-MS-Exchange-Transport-CrossTenantHeadersStamped: DU0PR08MB8709 Original-Authentication-Results: dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=arm.com; X-EOPAttributedMessage: 0 X-MS-Exchange-SkipListedInternetSender: ip=[2603:10a6:803:13e::17]; domain=VI1PR08MB5325.eurprd08.prod.outlook.com X-MS-Exchange-Transport-CrossTenantHeadersStripped: AM1PEPF000252E0.eurprd07.prod.outlook.com X-MS-PublicTrafficType: Email X-MS-Office365-Filtering-Correlation-Id-Prvs: f8c3678f-59e3-4190-7e18-08dcec3ee073 X-Microsoft-Antispam: BCL:0; ARA:13230040|82310400026|36860700013|376014|1800799024|35042699022; X-Microsoft-Antispam-Message-Info: =?utf-8?q?+55To2abqB/UIw1qnW/LRGAXcTUFEXN?= =?utf-8?q?dKVqOu2odLunFxCYcfTqWYjoW0dq1RIDUuq8y1PuzE6vms0KBVbyJ9BnVUNtl9TJ3?= =?utf-8?q?pmQrDxfXrUMJ+p8Kk4nLhGpEnz/Vj0qg9IanSKjud5dHPasvNpV70LGLT7qH89i5A?= =?utf-8?q?AnsJEeobXnBEvbRM2HLRQ6eumEsPr3DaP8KyaaNg1V2BvI7a5l9iuTHKLWiU1aX0R?= =?utf-8?q?gBZsGMcBmSKkJEJd4ru6oGcepFsmzmLKOltXJ7aPkAH3cFu5JT0tQllWtUYsmKOl2?= =?utf-8?q?+F8dPeSmNHxVFpC2Y6ULf5iQvhKQ3NJnFto/Y0z5xkOGxlVnsupIFSHYi9ikLo0In?= =?utf-8?q?Hg07ogfU/dGqDEjXHzOfSY4pWOVmg01GFExwRSqw8RSSI2+dVXTPCeob/0kbp9GJH?= =?utf-8?q?jJp6cvnquN6RiKuAOe05rDdB1iVuSlVSzoRd76yLY+o7cM+HsArDsAvI4+Sxb2KBp?= =?utf-8?q?NvftRkyq09h2LJI6ctcO/aT/+KYXcU9Zf+HexHHwXyMynXzp3H+HSuOSG+qI0RXin?= =?utf-8?q?kEnMEwrapWIANpgkaRxhAFmqXUL59LMq/7KdjsAKSQtFC22YYYTzhhpzNIFhNX5f1?= =?utf-8?q?aSo9wo1ffgedXqsz7/Y19rU//lRH2VHrzcoaf0NTEXc00Mx7uwTGTCHCS//3159ej?= =?utf-8?q?abzjJICghFnNH7i9/YoqowW5CDxINJDw2DvP37tPgWSSsueFjeh10Tl4MDdzkueNu?= =?utf-8?q?adP3Me4IHsEe1gBOu1SDFmpfinsXpaO1ugLYfmdc5Gu5iOWvtzEDbiRDXVvvlBQSK?= =?utf-8?q?dx4ZQioPNU5XqLFOlF++9+kFkPx/XmTLAq0uNADHb2H20VbpTfhhtj4KJgJjIQJAj?= =?utf-8?q?ZoqfzYZh6Kcsb95TX/9ZU3u4SyfOP4d0K83gqQE9VCfr3DRpHbtJjIV9iJWHCtlFU?= =?utf-8?q?G+BO3eRSdgN4QSvNXxnE2viaGifNhqsG+xs+M3wG7WN7+zEZy4WDHy9rf7eQUbB/J?= =?utf-8?q?WrgzEwQcr93JaJGTa24itnlCu+kiN7XrLjhIgCg6RMTrnRZMII0rNUohHe2Mb5wFW?= =?utf-8?q?5gtANxLppOz40EhH6nRVmUlFIx4nduu7f/2OVON/Z37rznrjRp4i1aB8l/4rTIdq8?= =?utf-8?q?Sswelirgg9PM/LLy1QEWhYVGILmwr51VNHXJebddV86IvleGCF/E5smr5++z+iL6m?= =?utf-8?q?hnNglQtDk6reiZ2iLdgBT/AtNr0WW+0SKMWWpMs0fhtuAI6Z7iUY4grEqmRKtw6sW?= =?utf-8?q?lx76N9gy1P1kjsDu8RRTgAGdtHSCXFLMzyzdEwQmL5ksSX56l712j0jTDea7boKnK?= =?utf-8?q?jcbNKguSNMwtegHiGfcgAA8XC4TICSdCE8Q=3D=3D?= X-Forefront-Antispam-Report: CIP:63.35.35.123; CTRY:IE; LANG:en; SCL:1; SRV:; IPV:CAL; SFV:NSPM; H:64aa7808-outbound-1.mta.getcheckrecipient.com; PTR:ec2-63-35-35-123.eu-west-1.compute.amazonaws.com; CAT:NONE; SFS:(13230040)(82310400026)(36860700013)(376014)(1800799024)(35042699022); DIR:OUT; SFP:1101; X-OriginatorOrg: arm.com X-MS-Exchange-CrossTenant-OriginalArrivalTime: 14 Oct 2024 10:56:48.8108 (UTC) X-MS-Exchange-CrossTenant-Network-Message-Id: e0b28f1d-bfec-4ba2-db58-08dcec3ee713 X-MS-Exchange-CrossTenant-Id: f34e5979-57d9-4aaa-ad4d-b122a662184d X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=f34e5979-57d9-4aaa-ad4d-b122a662184d; Ip=[63.35.35.123]; Helo=[64aa7808-outbound-1.mta.getcheckrecipient.com] X-MS-Exchange-CrossTenant-AuthSource: AM1PEPF000252E0.eurprd07.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Anonymous X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem X-MS-Exchange-Transport-CrossTenantHeadersStamped: AS8PR08MB6453 X-Spam-Status: No, score=-11.7 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, DKIM_VALID_EF, FORGED_SPF_HELO, GIT_PATCH_0, KAM_LOTSOFHASH, KAM_SHORT, SCC_5_SHORT_WORD_LINES, SPF_HELO_PASS, SPF_NONE, TXREP, UNPARSEABLE_RELAY autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org X-BeenThere: gcc-patches@gcc.gnu.org X-Mailman-Version: 2.1.30 Precedence: list List-Id: Gcc-patches mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: gcc-patches-bounces~incoming=patchwork.ozlabs.org@gcc.gnu.org Hi All, Consider loops such as: void test9(unsigned char *x, long long *y, int n, unsigned char k) { for(int i = 0; i < n; i++) { y[i] = k + x[i]; } } where today we generate: .L5: ldr q29, [x5], 16 add x4, x4, 128 uaddl v1.8h, v29.8b, v30.8b uaddl2 v29.8h, v29.16b, v30.16b zip1 v2.8h, v1.8h, v31.8h zip1 v0.8h, v29.8h, v31.8h zip2 v1.8h, v1.8h, v31.8h zip2 v29.8h, v29.8h, v31.8h sxtl v25.2d, v2.2s sxtl v28.2d, v0.2s sxtl v27.2d, v1.2s sxtl v26.2d, v29.2s sxtl2 v2.2d, v2.4s sxtl2 v0.2d, v0.4s sxtl2 v1.2d, v1.4s sxtl2 v29.2d, v29.4s stp q25, q2, [x4, -128] stp q27, q1, [x4, -96] stp q28, q0, [x4, -64] stp q26, q29, [x4, -32] cmp x5, x6 bne .L5 Note how the zero extend from short to long is half way the chain transformed into a sign extend. There are two problems with this: 1. sign extends are typically slower than zero extends on many uArches. 2. it prevents vectorizable_conversion from attempting to do a single step promotion. These sign extend happen due to the varous range reduction optimizations and patterns we have, such as multiplication widening, etc. My first attempt to fix this was just updating the patterns to when the original source is a zero extend, to not add the intermediate sign extend. However this behavior happens in many other places, some of it and as new patterns get added the problem can be re-introduced. Instead I have added a new pattern vect_recog_zero_extend_chain_pattern that attempts to simplify and extend an existing zero extend over multiple conversions statements. As an example, T3 a = (T3)(signed T2)(unsigned T1)x where bitsize T3 > T2 > T1 gets transformed into T3 a = (T3)(signed T2)(unsigned T2)x. The final cast to signed it kept so the types in the tree still match. It will be correctly elided later on. This represenation is the most optimal as vectorizable_conversion is already able to decompose a long promotion into multiple steps if the target does not support it in a single step. More importantly it allows us to do proper costing and support such conversions like (double)x, where bitsize(x) < int in an efficient manner. To do this I have used Ranger's on-demand analysis to perform the check to see if an extension can be removed and extended to zero extend. The reason for this is that the vectorizer introduces several patterns that are not in the IL, but also lots of widening IFNs for which handling in a switch wouldn't be very future proof. I did try to do it without Ranger, but ranger had two benefits: 1. It simplified the handling of the IL changes the vectorizer introduces, and makes it future proof. 2. Ranger has the advantage of doing the transformation in cases where it knows that the top bits of the value is zero. Which we wouldn't be able to tell by looking purely at statements. 3. Ranger simplified the handling of corner cases. Without it the handling was quite complex and I wasn't very confident in it's correctness. So I think ranger is the right way to go here... With these changes the above now generates: .L5: add x4, x4, 128 ldr q26, [x5], 16 uaddl v2.8h, v26.8b, v31.8b uaddl2 v26.8h, v26.16b, v31.16b tbl v4.16b, {v2.16b}, v30.16b tbl v3.16b, {v2.16b}, v29.16b tbl v24.16b, {v2.16b}, v28.16b tbl v1.16b, {v26.16b}, v30.16b tbl v0.16b, {v26.16b}, v29.16b tbl v25.16b, {v26.16b}, v28.16b tbl v2.16b, {v2.16b}, v27.16b tbl v26.16b, {v26.16b}, v27.16b stp q4, q3, [x4, -128] stp q1, q0, [x4, -64] stp q24, q2, [x4, -96] stp q25, q26, [x4, -32] cmp x5, x6 bne .L5 I have also seen similar improvements in codegen on Arm and x86_64, especially with AVX512. Bootstrapped Regtested on aarch64-none-linux-gnu, arm-none-linux-gnueabihf, x86_64-pc-linux-gnu -m32, -m64 and no issues. Hopefully Ok for master? Thanks, Tamar gcc/ChangeLog: * tree-vect-patterns.cc (vect_recog_zero_extend_chain_pattern): New. gcc/testsuite/ChangeLog: * gcc.dg/vect/bb-slp-pattern-1.c: Update tests. * gcc.dg/vect/slp-widen-mult-half.c: Likewise. * gcc.dg/vect/vect-over-widen-10.c: Likewise. * gcc.dg/vect/vect-over-widen-12.c: Likewise. * gcc.dg/vect/vect-over-widen-14.c: Likewise. * gcc.dg/vect/vect-over-widen-16.c: Likewise. * gcc.dg/vect/vect-over-widen-6.c: Likewise. * gcc.dg/vect/vect-over-widen-8.c: Likewise. * gcc.dg/vect/vect-widen-mult-u16.c: Likewise. * gcc.dg/vect/vect-widen-mult-u8-s16-s32.c: Likewise. * lib/target-supports.exp (check_effective_target_vect_widen_mult_hi_to_si_pattern, check_effective_target_vect_widen_mult_si_to_di_pattern): Enable AArch64. * gcc.target/aarch64/vect-tbl-zero-extend_2.c: New test. --- -- diff --git a/gcc/testsuite/gcc.dg/vect/bb-slp-pattern-1.c b/gcc/testsuite/gcc.dg/vect/bb-slp-pattern-1.c index 5ae99225273ca5f915f60ecba3a5aaedebe46e96..627de78af4e48581575beda97bf2a0708ac091cb 100644 --- a/gcc/testsuite/gcc.dg/vect/bb-slp-pattern-1.c +++ b/gcc/testsuite/gcc.dg/vect/bb-slp-pattern-1.c @@ -52,4 +52,4 @@ int main (void) /* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "slp2" { target { vect_widen_mult_hi_to_si || vect_unpack } } } } */ /* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 8 "slp2" { target vect_widen_mult_hi_to_si_pattern } } } */ -/* { dg-final { scan-tree-dump-times "pattern recognized" 8 "slp2" { target vect_widen_mult_hi_to_si_pattern } } } */ +/* { dg-final { scan-tree-dump-times "widen_mult pattern recognized" 8 "slp2" { target vect_widen_mult_hi_to_si_pattern } } } */ diff --git a/gcc/testsuite/gcc.dg/vect/slp-widen-mult-half.c b/gcc/testsuite/gcc.dg/vect/slp-widen-mult-half.c index b69ade338862cda4f44f5206d195eef1cb5e8d36..aecc085a51c93e0e7bed122df0a77a0a099ad6ef 100644 --- a/gcc/testsuite/gcc.dg/vect/slp-widen-mult-half.c +++ b/gcc/testsuite/gcc.dg/vect/slp-widen-mult-half.c @@ -52,5 +52,5 @@ int main (void) /* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_widen_mult_hi_to_si } } } */ /* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 2 "vect" { target vect_widen_mult_hi_to_si } } } */ /* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */ -/* { dg-final { scan-tree-dump-times "pattern recognized" 2 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */ +/* { dg-final { scan-tree-dump-times "pattern recognized" 4 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */ diff --git a/gcc/testsuite/gcc.dg/vect/vect-over-widen-10.c b/gcc/testsuite/gcc.dg/vect/vect-over-widen-10.c index f0140e4ef6d70cd61aa7dbb3ba39b1da142a79b2..bd798fae7e8136975d488206cfef9e39fac2bfea 100644 --- a/gcc/testsuite/gcc.dg/vect/vect-over-widen-10.c +++ b/gcc/testsuite/gcc.dg/vect/vect-over-widen-10.c @@ -11,7 +11,7 @@ #include "vect-over-widen-9.c" -/* { dg-final { scan-tree-dump {Splitting statement} "vect" } } */ +/* { dg-final { scan-tree-dump {Splitting pattern statement} "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* \+ } "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* >> 1} "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* >> 2} "vect" } } */ diff --git a/gcc/testsuite/gcc.dg/vect/vect-over-widen-12.c b/gcc/testsuite/gcc.dg/vect/vect-over-widen-12.c index ddb3bd8c0d378f0138c8cc7f9c6ea3300744b8a8..8c0544e35c29de60e76759f4ed13206278c72925 100644 --- a/gcc/testsuite/gcc.dg/vect/vect-over-widen-12.c +++ b/gcc/testsuite/gcc.dg/vect/vect-over-widen-12.c @@ -11,7 +11,7 @@ #include "vect-over-widen-11.c" -/* { dg-final { scan-tree-dump {Splitting statement} "vect" } } */ +/* { dg-final { scan-tree-dump {Splitting pattern statement} "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* \+ } "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* >> 1} "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* >> 2} "vect" } } */ diff --git a/gcc/testsuite/gcc.dg/vect/vect-over-widen-14.c b/gcc/testsuite/gcc.dg/vect/vect-over-widen-14.c index dfa09f5d2cafe329e6d57b5cc681786cc2c7d215..1fe0305c1c4f61d05864ef97789726a1dc6ec8b1 100644 --- a/gcc/testsuite/gcc.dg/vect/vect-over-widen-14.c +++ b/gcc/testsuite/gcc.dg/vect/vect-over-widen-14.c @@ -11,7 +11,7 @@ #include "vect-over-widen-13.c" -/* { dg-final { scan-tree-dump {Splitting statement} "vect" } } */ +/* { dg-final { scan-tree-dump {Splitting pattern statement} "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* \+} "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* >> 1} "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_cast_forwprop_pattern: detected:[^\n]* = \(unsigned char\)} "vect" } } */ diff --git a/gcc/testsuite/gcc.dg/vect/vect-over-widen-16.c b/gcc/testsuite/gcc.dg/vect/vect-over-widen-16.c index 4584c586da1e6f13e8c8de4c1291cea0141ebab5..4ecdadf7a035a4f83b1767a063a1b0f47bdd543d 100644 --- a/gcc/testsuite/gcc.dg/vect/vect-over-widen-16.c +++ b/gcc/testsuite/gcc.dg/vect/vect-over-widen-16.c @@ -11,7 +11,7 @@ #include "vect-over-widen-15.c" -/* { dg-final { scan-tree-dump {Splitting statement} "vect" } } */ +/* { dg-final { scan-tree-dump {Splitting pattern statement} "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* \+} "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* >> 1} "vect" } } */ /* { dg-final { scan-tree-dump-not {vect_recog_cast_forwprop_pattern: detected} "vect" } } */ diff --git a/gcc/testsuite/gcc.dg/vect/vect-over-widen-6.c b/gcc/testsuite/gcc.dg/vect/vect-over-widen-6.c index bda92c965e080dd3f48ec42b6bea16e79d9416cd..6b8c3dfa2c89ce04d7673607ef2d2f14a14eb32f 100644 --- a/gcc/testsuite/gcc.dg/vect/vect-over-widen-6.c +++ b/gcc/testsuite/gcc.dg/vect/vect-over-widen-6.c @@ -9,7 +9,7 @@ #include "vect-over-widen-5.c" -/* { dg-final { scan-tree-dump {Splitting statement} "vect" } } */ +/* { dg-final { scan-tree-dump {Splitting pattern statement} "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* \+ } "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* >> 1} "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_cast_forwprop_pattern: detected:[^\n]* \(unsigned char\)} "vect" } } */ diff --git a/gcc/testsuite/gcc.dg/vect/vect-over-widen-8.c b/gcc/testsuite/gcc.dg/vect/vect-over-widen-8.c index 553c0712a79a1d19195dbdab7cbd6fa330685bea..1cf725ff4b7f151097192db1a0b65173c4c83b19 100644 --- a/gcc/testsuite/gcc.dg/vect/vect-over-widen-8.c +++ b/gcc/testsuite/gcc.dg/vect/vect-over-widen-8.c @@ -12,7 +12,7 @@ #include "vect-over-widen-7.c" -/* { dg-final { scan-tree-dump {Splitting statement} "vect" } } */ +/* { dg-final { scan-tree-dump {Splitting pattern statement} "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* \+ } "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_over_widening_pattern: detected:[^\n]* >> 2} "vect" } } */ /* { dg-final { scan-tree-dump {vect_recog_cast_forwprop_pattern: detected:[^\n]* \(unsigned char\)} "vect" } } */ diff --git a/gcc/testsuite/gcc.dg/vect/vect-widen-mult-u16.c b/gcc/testsuite/gcc.dg/vect/vect-widen-mult-u16.c index 258d253f401459d448d1ae86f56b0c97815d5b61..b5018f855a72534b4d64d2dc2b7ab2ac0deb674b 100644 --- a/gcc/testsuite/gcc.dg/vect/vect-widen-mult-u16.c +++ b/gcc/testsuite/gcc.dg/vect/vect-widen-mult-u16.c @@ -47,5 +47,5 @@ int main (void) /* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_widen_mult_hi_to_si || vect_unpack } } } } */ /* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 1 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */ -/* { dg-final { scan-tree-dump-times "pattern recognized" 1 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */ +/* { dg-final { scan-tree-dump-times "widen_mult pattern recognized" 1 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */ diff --git a/gcc/testsuite/gcc.dg/vect/vect-widen-mult-u8-s16-s32.c b/gcc/testsuite/gcc.dg/vect/vect-widen-mult-u8-s16-s32.c index 3baafca7b548124ae5c48fdf3c2f07c319155967..ab523ca77652e1f1533889fda9c0eb31c987ffe9 100644 --- a/gcc/testsuite/gcc.dg/vect/vect-widen-mult-u8-s16-s32.c +++ b/gcc/testsuite/gcc.dg/vect/vect-widen-mult-u8-s16-s32.c @@ -47,5 +47,5 @@ int main (void) /* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_widen_mult_hi_to_si || vect_unpack } } } } */ /* { dg-final { scan-tree-dump-times "vect_recog_widen_mult_pattern: detected" 1 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */ -/* { dg-final { scan-tree-dump-times "pattern recognized" 1 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */ +/* { dg-final { scan-tree-dump-times "widen_mult pattern recognized" 1 "vect" { target vect_widen_mult_hi_to_si_pattern } } } */ diff --git a/gcc/testsuite/gcc.target/aarch64/vect-tbl-zero-extend_2.c b/gcc/testsuite/gcc.target/aarch64/vect-tbl-zero-extend_2.c new file mode 100644 index 0000000000000000000000000000000000000000..1577eacd9dbbb52274d9f86c77406555b7726482 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/vect-tbl-zero-extend_2.c @@ -0,0 +1,33 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-O3 -std=c99 -march=armv8-a" } */ + +void test6(unsigned char *x, double *y, int n) { + for(int i = 0; i < (n & -8); i++) { + y[i] += x[i]; + } +} + +void test7(unsigned char *x, double *y, int n, unsigned char k) { + for(int i = 0; i < (n & -8); i++) { + y[i] += k * x[i]; + } +} + +void test8(unsigned char *x, double *y, int n, unsigned char k) { + for(int i = 0; i < (n & -8); i++) { + y[i] = k + x[i]; + } +} + +void test9(unsigned char *x, long long *y, int n, unsigned char k) { + for(int i = 0; i < (n & -8); i++) { + y[i] = k + x[i]; + } +} + +/* { dg-final { scan-assembler-times {\tuxtl} 1 } } */ +/* { dg-final { scan-assembler-not {\tuxtl2} } } */ +/* { dg-final { scan-assembler-not {\tzip1} } } */ +/* { dg-final { scan-assembler-not {\tzip2} } } */ +/* { dg-final { scan-assembler-times {\ttbl} 44 } } */ +/* { dg-final { scan-assembler-times {\.LC[0-9]+:} 12 } } */ diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp index d113a08dff7b2a8ab5bdfe24386d271bff255afc..feae1b8fcf8cd7ab56a8c76c0cd3034c0a828724 100644 --- a/gcc/testsuite/lib/target-supports.exp +++ b/gcc/testsuite/lib/target-supports.exp @@ -8240,6 +8240,7 @@ proc check_effective_target_vect_widen_mult_hi_to_si_pattern { } { return [check_cached_effective_target_indexed vect_widen_mult_hi_to_si_pattern { expr { [istarget powerpc*-*-*] || [istarget ia64-*-*] + || [istarget aarch64*-*-*] || [istarget loongarch*-*-*] || [istarget i?86-*-*] || [istarget x86_64-*-*] || ([is-effective-target arm_neon] @@ -8259,6 +8260,7 @@ proc check_effective_target_vect_widen_mult_si_to_di_pattern { } { expr { [istarget ia64-*-*] || [istarget i?86-*-*] || [istarget x86_64-*-*] || [istarget loongarch*-*-*] + || [istarget aarch64*-*-*] || ([istarget s390*-*-*] && [check_effective_target_s390_vx]) }}] } diff --git a/gcc/tree-vect-patterns.cc b/gcc/tree-vect-patterns.cc index 9bf8526ac995c6c2678b25f5df4316aec41333e0..74c7269a3ab15cba1ee2ef0556d25afda851f7f0 100644 --- a/gcc/tree-vect-patterns.cc +++ b/gcc/tree-vect-patterns.cc @@ -5524,6 +5524,122 @@ vect_recog_mixed_size_cond_pattern (vec_info *vinfo, return pattern_stmt; } +/* Function vect_recog_zero_extend_chain_pattern + + Try to find the following pattern: + + type x_t; + TYPE a_T, b_T, c_T; + loop: + S1 a_T = (b_T)(c_T)x_t; + + where type 'TYPE' is an integral type which has different size + from 'type' and c_T is a zero extend or a sign extend on a value whose top + bit is known to be zero. a_T can be signed or unsigned. + + Input: + + * STMT_VINFO: The stmt from which the pattern search begins. + + Output: + + * TYPE_OUT: The type of the output of this pattern. + + * Return value: A new stmt that will be used to replace the pattern. + This replaces multiple chained extensions with the longest possible + chain or zero extends and a final convert to the required sign. + + S1 a_T = (a_T)(unsigned a_T)x_t; */ + +static gimple * +vect_recog_zero_extend_chain_pattern (vec_info *vinfo, + stmt_vec_info stmt_vinfo, tree *type_out) +{ + gimple *last_stmt = STMT_VINFO_STMT (vect_stmt_to_vectorize (stmt_vinfo)); + + if (!is_gimple_assign (last_stmt)) + return NULL; + + tree_code code = gimple_assign_rhs_code (last_stmt); + tree lhs = gimple_assign_lhs (last_stmt); + tree rhs = gimple_assign_rhs1 (last_stmt); + tree lhs_type = TREE_TYPE (lhs); + tree rhs_type = TREE_TYPE (rhs); + + if ((code != FLOAT_EXPR && code != NOP_EXPR) + || TYPE_UNSIGNED (lhs_type) + || TREE_CODE (rhs_type) != INTEGER_TYPE + || TREE_CODE (rhs) != SSA_NAME + || STMT_VINFO_DEF_TYPE (stmt_vinfo) != vect_internal_def) + return NULL; + + /* Check to see if it's safe to extend the zero extend to the new type. + In general this is safe if the rhs1 type is unsigned or if we know that + the top bits are zero, this can happen due to all the widening operations + we have. For instance a widening addition will have top bits zero. */ + if (!TYPE_UNSIGNED (rhs_type)) + { + wide_int wcst = get_nonzero_bits (rhs); + if (wi::neg_p (wcst) || wi::clz (wcst) == 0) + return NULL; + } + + tree cvt_type = unsigned_type_for (lhs_type); + + tree cvt_vectype = get_vectype_for_scalar_type (vinfo, cvt_type); + if (!cvt_vectype || !VECTOR_TYPE_P (cvt_vectype)) + return NULL; + + tree out_vectype = get_vectype_for_scalar_type (vinfo, lhs_type); + if (!out_vectype || !VECTOR_TYPE_P (out_vectype)) + return NULL; + + stmt_vec_info irhs; + + gimple_ranger ranger; + + /* Dig through any existing conversions to see if we can extend the zero + extend chain across multiple converts. */ + while ((irhs = vect_get_internal_def (vinfo, rhs))) + { + gimple *g_irhs = STMT_VINFO_STMT (irhs); + if (!is_gimple_assign (g_irhs) + || gimple_assign_rhs_code (g_irhs) != NOP_EXPR) + break; + + /* See if we can consume the next conversion as well. To do this it's + best to use Ranger as it can see through the intermediate IL that the + vectorizer creates throughout pattern matching. */ + int_range_max r; + ranger.range_of_stmt (r, g_irhs); + wide_int nz = r.get_nonzero_bits (); + if (wi::neg_p (nz) || wi::clz (nz) == 0) + break; + + rhs = gimple_assign_rhs1 (g_irhs); + } + + /* If the result is a no-op, or we've jumped over a truncate of sort, or if + nothing would change materially just leave it alone. */ + if (TYPE_PRECISION (lhs_type) <= TYPE_PRECISION (TREE_TYPE (rhs)) + || (code == FLOAT_EXPR && rhs == gimple_assign_rhs1 (last_stmt))) + return NULL; + + vect_pattern_detected ("vect_recog_zero_extend_chain_pattern", last_stmt); + + tree cast_var = vect_recog_temp_ssa_var (cvt_type, NULL); + gimple *pattern_stmt = NULL; + pattern_stmt = gimple_build_assign (cast_var, NOP_EXPR, rhs); + append_pattern_def_seq (vinfo, stmt_vinfo, pattern_stmt, cvt_vectype); + + tree cvt_var = vect_recog_temp_ssa_var (lhs_type, NULL); + pattern_stmt = gimple_build_assign (cvt_var, code, cast_var); + + *type_out = out_vectype; + + return pattern_stmt; +} + /* Helper function of vect_recog_bool_pattern. Called recursively, return true if bool VAR can and should be optimized that way. Assume it shouldn't @@ -7509,6 +7625,7 @@ static vect_recog_func vect_vect_recog_func_ptrs[] = { { vect_recog_widen_minus_pattern, "widen_minus" }, { vect_recog_widen_abd_pattern, "widen_abd" }, /* These must come after the double widening ones. */ + { vect_recog_zero_extend_chain_pattern, "zero_extend_chain" }, }; /* Mark statements that are involved in a pattern. */