From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.16]) by sourceware.org (Postfix) with ESMTPS id 537233858D35 for ; Wed, 15 May 2024 03:30:10 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 537233858D35 Authentication-Results: sourceware.org; dmarc=pass (p=none dis=none) header.from=intel.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=intel.com ARC-Filter: OpenARC Filter v1.0.0 sourceware.org 537233858D35 Authentication-Results: server2.sourceware.org; arc=pass smtp.remote-ip=198.175.65.16 ARC-Seal: i=2; a=rsa-sha256; d=sourceware.org; s=key; t=1715743812; cv=pass; b=HUUk40a28DohcjmU4yUmODY/j7q89WakILTAZt1PRFTr2Dx7DqELRJKU0Uzn8zAep4u3f1DJ9LNiYJa6l177Oj7SFMuob7Y0LE+F8crE+7x0FUvDxsC77uxKj9oPjFxYPS6FQVNMoRW2gv9URQYWqa3AGq98R9/1Bvp8TiADkXY= ARC-Message-Signature: i=2; a=rsa-sha256; d=sourceware.org; s=key; t=1715743812; c=relaxed/simple; bh=R7ClayISpssp+vvBbGnZwnAUy8eichU9fJLVT1tKzVs=; h=DKIM-Signature:From:To:Subject:Date:Message-ID:MIME-Version; b=PAow4wn3rGGrvi77ByZeETyFwistkEPjNhAp3eVXIyFzRdh8q2sCmcTmxTMkyippbjaDdzO6+6wqsZX+AW9dKNoIp2IHt2H9ZjxfbwazWdL4HZ0UIf9VudMtUITVx2yFl1Zxfdu+4ZKSTvOQbQ3CXA80aGHLJiJQ4tt8u/2ZSmU= ARC-Authentication-Results: i=2; server2.sourceware.org DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1715743811; x=1747279811; h=from:to:cc:subject:date:message-id:references: in-reply-to:content-transfer-encoding:mime-version; bh=R7ClayISpssp+vvBbGnZwnAUy8eichU9fJLVT1tKzVs=; b=SXWCXRUCqNQX7rb1yZoAJN29Q3pM8lcnvQ6ByisH4EugZQl9ovw0vnJU OgrbTHDCHvnyMoDZxaEUZ44zv6DSCGwJn73qIsd/Niwe+cHi62Opf826g WGd8eu/JVjynvGiNpNm3BL71zGEOIyd+o+ANQD/kwyrX4Q1LkvYfZ1WcE moTJjY+ADjDQWY+/0kmmA2poNuF51Rt89vLyJ0pR4iYA/LXgi6jKj5BZG DCYWZy/z+DvqJjLhD/T23Yx4Z+16vc1okBQSXZ22nWxASfpEwaSe1PJXi 8OBfa9KdFsAVFYK2sO6d9kZZJtqNlC7lg+wthEBY/RjvzYDoV+mhJ+JVm Q==; X-CSE-ConnectionGUID: 6XD795XISUSsbNVsNa4XNQ== X-CSE-MsgGUID: Wnl28kQSTxit00x7+tAn0g== X-IronPort-AV: E=McAfee;i="6600,9927,11073"; a="11887737" X-IronPort-AV: E=Sophos;i="6.08,160,1712646000"; d="scan'208";a="11887737" Received: from orviesa002.jf.intel.com ([10.64.159.142]) by orvoesa108.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 14 May 2024 20:30:09 -0700 X-CSE-ConnectionGUID: lAAwNQiaQw+L7NEbJZm/mg== X-CSE-MsgGUID: v/z1iz19QEqOFgsRamUQ3g== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.08,160,1712646000"; d="scan'208";a="61731262" Received: from orsmsx601.amr.corp.intel.com ([10.22.229.14]) by orviesa002.jf.intel.com with ESMTP/TLS/AES256-GCM-SHA384; 14 May 2024 20:30:09 -0700 Received: from orsmsx611.amr.corp.intel.com (10.22.229.24) by ORSMSX601.amr.corp.intel.com (10.22.229.14) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.35; Tue, 14 May 2024 20:30:08 -0700 Received: from orsmsx610.amr.corp.intel.com (10.22.229.23) by ORSMSX611.amr.corp.intel.com (10.22.229.24) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.35; Tue, 14 May 2024 20:30:08 -0700 Received: from orsedg603.ED.cps.intel.com (10.7.248.4) by orsmsx610.amr.corp.intel.com (10.22.229.23) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.35 via Frontend Transport; Tue, 14 May 2024 20:30:08 -0700 Received: from NAM10-BN7-obe.outbound.protection.outlook.com (104.47.70.100) by edgegateway.intel.com (134.134.137.100) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.1.2507.35; Tue, 14 May 2024 20:30:08 -0700 ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=WYLgsw34sUI3xP/v9Axu/CEFzE3fMJW1Yf4V2VipTMqSyG/SSZfiSthOItJ/ohqCCm+WlP1+ymUuc3umC573ywHZMTUirwTtqZaHoVNto/4fu5CwWWgdde26nLT66L0DqsWf2y+dmUu9tRwGpjwDqFl2ZCT7CcsVV+0QWRS7E3rLFjDUwD7tJn2tRby2mM7lCu0JDhF7vMb1w9SzYo05fEvHq+ORsl1XUbdiXDqgu2VW62EpkXyTYnqOWTqJnW/3cgH/lvP9eAG1dqS1ct8mflw5fycYTe0Pse3jTmi0AvdbP+kEOrFOb5NUBKNR9yj2YrUsZ34fNbNVXH0MjW5nLQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector9901; 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=YovTSAj4pIpMfFXZ8Jz0d5wGP6BQzL3zukBDec/QcAc=; b=RbrOWaXnvVIbrVdicPCJDZPYBAHydg24cm5ACXDsxufWYJFfreOZTlGdLywFYfkSjFTDsVZlyeQIyvZwOBUKWwPqdeIXUyLdsjxLtNM1WLGZ5ZJAUD2i0xX10fxeLAxIS50TB7Glj/SFahmLhGNdGcgogv7rdTBNtpqp6oITlmdFhtuljHRe8MN+h8K0Z4W1Gz1/yK04OOaS5isSmwTlchZ5NsMRkAGN189UKIW9P6eH2Yysd8RbkLFshvJyuGYEWHaiuYF/SAfutsuqiBv0qYmURSRkrNkc8VszgUwJbkHn1MBNqmSYCLozOQd3j8mIMRLs7p6jmulxjwdo8KT/GQ== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=intel.com; dmarc=pass action=none header.from=intel.com; dkim=pass header.d=intel.com; arc=none Received: from SA1PR11MB5946.namprd11.prod.outlook.com (2603:10b6:806:23a::9) by SJ2PR11MB7575.namprd11.prod.outlook.com (2603:10b6:a03:4ce::11) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.7544.55; Wed, 15 May 2024 03:30:05 +0000 Received: from SA1PR11MB5946.namprd11.prod.outlook.com ([fe80::8c88:67b8:7849:aa8c]) by SA1PR11MB5946.namprd11.prod.outlook.com ([fe80::8c88:67b8:7849:aa8c%5]) with mapi id 15.20.7544.052; Wed, 15 May 2024 03:30:05 +0000 From: "Jiang, Haochen" To: "Jiang, Haochen" , "gcc-patches@gcc.gnu.org" CC: "Liu, Hongtao" , "ubizjak@gmail.com" , Jan Hubicka , Richard Biener Subject: RE: [PATCH 0/2] Align tight loops to solve cross cacheline issue Thread-Topic: [PATCH 0/2] Align tight loops to solve cross cacheline issue Thread-Index: AQHapnSlOu3a17nnOkSQTVB74I0KgLGXoxeg Date: Wed, 15 May 2024 03:30:05 +0000 Message-ID: References: <20240515030429.2575440-1-haochen.jiang@intel.com> In-Reply-To: <20240515030429.2575440-1-haochen.jiang@intel.com> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: authentication-results: dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=intel.com; x-ms-publictraffictype: Email x-ms-traffictypediagnostic: SA1PR11MB5946:EE_|SJ2PR11MB7575:EE_ x-ms-office365-filtering-correlation-id: 536caaee-563c-4080-864c-08dc748f5015 x-ms-exchange-senderadcheck: 1 x-ms-exchange-antispam-relay: 0 x-microsoft-antispam: BCL:0;ARA:13230031|1800799015|366007|376005|38070700009; x-microsoft-antispam-message-info: =?us-ascii?Q?RCLeM02jpDxTpj02a4EELtL78I4sqOhiTn+8IcQ2rebD/nrTcLli6f8QlGLG?= =?us-ascii?Q?QHy/RKTgQrYrRFhhhkBB5qgrM7HTeeOnUGhOQyvdwu2ySrWau/Zj5+0DmsJ0?= =?us-ascii?Q?bf7q0n9wGSO3hiZJ+4aP/C7IUJevlpQIORvY1j3bh7hDZS/5JVdwnvf9HWVg?= =?us-ascii?Q?UQn7VPiTrDK0x58lS91606iuHUlatTpwnP9G+YtfENa5hZ1v1T22zzTMcgGb?= =?us-ascii?Q?0FNvfBeZcR4gxQLpNMuFJD49TWHXsbU2Sbgh6O5KGvLbATRcW0nuhA0STB5n?= =?us-ascii?Q?Er6MfIG1K+fKW3+lNDAEwDeLNh3dEkn4EU7GZgql+mC/Ad0VfKQd1sONpm2r?= =?us-ascii?Q?1r68CvdSgpXPy3h2Vl51dMu4BBmfWMAmphnpMR2VgGjVRxTzJ0XaojFYuHVZ?= =?us-ascii?Q?p6NdEnizSXsfZaqLD5orfUXj88ddUNBxjkH3nMIpbSmLoIvpGNXgtTCsEl6O?= =?us-ascii?Q?OcqxAU71gpKN2hcay2+JBn3MIxh3mVWlQW1KOiJ41CppTqAv3YemJ2TPNP9e?= =?us-ascii?Q?LhV/ZFNC+53iX9CPUgSpkCFxJdIwbfnFzkruVG9vDDQ5lkPKGj8O0qcZmpP7?= =?us-ascii?Q?hkrGz/WzVATdBh1dr2fFUYxYXvU2jzbGrrklMsS5zkaiBnZ4MhYsI8OYWGD4?= =?us-ascii?Q?EpIT14SSRjTh445iahOUvSqR6N6jAa0x0p9FapsN0dVUFejQQkBqOT1ERnLz?= =?us-ascii?Q?dJE67GMMGbaheRynSZyP6Tn36CLd70MeSuoU6pz3WXvqmInWODBt25JYpull?= =?us-ascii?Q?fKNA9pZDZJUmEZaJmzMWPO2riX3Bz/Nw5I80nqTS/s19C9w/thIHSB7Jaz0p?= =?us-ascii?Q?nrfYqfxY6G0UOLUNCWWLW/Lg8umZu4nFTgrmyxoMab37MIsnFWnnnvMtXi4t?= =?us-ascii?Q?87shoiKrKARJCyXbJqz/6JPB1RJNwWrTAK8Y20xVsqyGqW1KgpGeYGM0taox?= =?us-ascii?Q?OGe0MtIYr4T/t1/xwhudnHq+wYZlxGCjapQDvhFRaOPHJr+aoxAZAUzfsuoh?= =?us-ascii?Q?cGWwNLZGMFJVJJV1Dwg96XMF+OEC/wDYvILUD+MlatGQY/uBwkD25CMpHL3z?= =?us-ascii?Q?wOVf4eP2CMSsAvz0QkSz+E1snCfLsvTAZjagJFwb8NlFWTgCihvJl2lKKnM8?= =?us-ascii?Q?m5HgsFVXHAyng3Wn9TgliZFh5+0PKvX/ILhpE7GyiBLfTwb0gyNs0PVd5e5C?= =?us-ascii?Q?oOPQx3Plc2Y76ynB0lMcJTj51uKl21CCMe6ZY/zMV6GrMzb72lyuxaXl+So8?= =?us-ascii?Q?EZVv1BWj4YK/thfx9tJGJ6vFj7yoNrAJz+iuyg9YcN+XbYP5GKApbPWJTzpi?= =?us-ascii?Q?6I4H1rmsJLi60WWfiqM6SFYmRCM4UbB9swLakOzrBNg1sw=3D=3D?= x-forefront-antispam-report: CIP:255.255.255.255;CTRY:;LANG:en;SCL:1;SRV:;IPV:NLI;SFV:NSPM;H:SA1PR11MB5946.namprd11.prod.outlook.com;PTR:;CAT:NONE;SFS:(13230031)(1800799015)(366007)(376005)(38070700009);DIR:OUT;SFP:1101; x-ms-exchange-antispam-messagedata-chunkcount: 1 x-ms-exchange-antispam-messagedata-0: =?us-ascii?Q?+y6puq75e5PQpBLHkShH+wZb7pHY+/z8G+aNGQQ3GVFtXTU2xpM2qL/E/fRt?= =?us-ascii?Q?MqmAzVephqduHSe+//Bcgr3+jAggukhjNP0gPxKzB8t3ZTtreAF+xeLquJ1P?= =?us-ascii?Q?R7h3sz5EXiFMltNnjwAlDZ+vA5ESyOZO1erqbEHDB3q31LuSBhRLgPuWBCfN?= =?us-ascii?Q?YCKKIsRairq8NBpR3d0QOsL+SAXt3jOal/W/zaBm09h+GlCInHUiO0AZzVVY?= =?us-ascii?Q?KjX9zwzodfh+T3CFwkCskgnUrb3TYv2E4gXQ/UnNiMpj+jwNHfjh4VGQxhye?= =?us-ascii?Q?EkRF6kRrSqpIAZqEwL919PTxG1M71KIL7Fn3u0FN8v5p2XhaaBduGS+fq9ze?= =?us-ascii?Q?wDMpCJjDAzVKKcrZ2DqOHiz4x82gACHsKgimk60VunWHjUPi4OFHd2qhmsav?= =?us-ascii?Q?Ad4V2dEzow1ZYRmOKAKr6x8HolS96kcN0SN3TSr3HZm6JBac8YNnGS6YYtpu?= =?us-ascii?Q?XNb/4CnLWuPjkmJmwzK3ISydqW6RBqFHniNJv0vasfTuOttJIpyc4pTPM5nt?= =?us-ascii?Q?C7l4mdiUzZ9GVlhjIyon9J7M9U71VwI6B+jlnbXjw88KGRTGns+yQ9dU6UV8?= =?us-ascii?Q?as/RKBMJz7r2+lCSZCQTSlWX6hgYxCE5YkUs9JezRhnxKxKCXtEyRFYCS7Kh?= =?us-ascii?Q?vQ5k7PvFvBCOVezm5+sI/9zFKpPE7ikQFO7/1XuUSSYbg9trUe7TnUtNP7JA?= =?us-ascii?Q?7Ky4SckkDZMWAtoh9zkZ4LMHjlmPgIcMPck53FVLgK/xsw3mbiqnFnS6l8Kt?= =?us-ascii?Q?4q0iIQq20+BoRAcfB1TdjEJrSBJ2rTaxBJk3PhiAyD4P2mu02Xb2+0iNcBT/?= =?us-ascii?Q?DofzdaDvKldgJwhRVQjjKN7jq9oFt0EhfCpPMd4u9U81+n9AIAy+9ixs8rPj?= =?us-ascii?Q?GWknkb7WdQJXfm4O5qb+4dHyskhCBWO5jwrysv4qwj/z/doEtsxUI1Wane6b?= =?us-ascii?Q?axwCKxYVa0RcQZwhZ4dqwQv0IR4wVBvs0ogTOftJlQVvQu2yvmjnS1oYc08Y?= =?us-ascii?Q?AA7nTlFYzxvQU8Ebj/mfhQwC+PM50FK9emAh5FIk/Oo+wamU7uyf3p4fYzBr?= =?us-ascii?Q?utVC9bNPVwc8YlaT87kctf9a8acHdKgiAQzL6BBvIa/JR+5VXWbddL1ifWlj?= =?us-ascii?Q?wAeOiR2hgpoDUcdKJgF9yKRbmALego7PA95Q7v5crexw5wYzMe3Z1w0HhaQD?= =?us-ascii?Q?jNq2t5qy4M9UgLrPVNrjGnGi8mxGiW0tJzUFiBEU8KCww7vQ8VMTPVuTto/Q?= =?us-ascii?Q?KDE0zZ74ZxvdRZBGxLJTc0elUdm8z/9Ak74Y1fg7uZDwW6jgzZd78gAEGKhH?= =?us-ascii?Q?N76iY5Wmq0S02GNGzW6GnPC9rKu4cfSt0DpOWAwNA840bmZw/QcLRExXzSuW?= =?us-ascii?Q?q9cDLZ6GRAF0doY+h7yEr+OGiMbdWVzV5ojiHVQ+knk554WjtlWbELG717Hs?= =?us-ascii?Q?VpnWpp3Nzel+GAoUIghc0xUD7ip5eAwG6inKnUwJtEdkeMI4yh8Givq9pu70?= =?us-ascii?Q?zPNJ9aYfW0Y9oJ/iYZrvRfVWzDYgCLItS/O6byE0fDnHxCxLxgW0bxaEewC+?= =?us-ascii?Q?aRUSG83PkdXMpJeYJcvnc2NfXXdcQKks/Xe0wPdA?= Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-AuthSource: SA1PR11MB5946.namprd11.prod.outlook.com X-MS-Exchange-CrossTenant-Network-Message-Id: 536caaee-563c-4080-864c-08dc748f5015 X-MS-Exchange-CrossTenant-originalarrivaltime: 15 May 2024 03:30:05.2080 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: 46c98d88-e344-4ed4-8496-4ed7712e255d X-MS-Exchange-CrossTenant-mailboxtype: HOSTED X-MS-Exchange-CrossTenant-userprincipalname: tpbuWNTyiWigcVSWNk+PdwxGq+N5Vyp+8WXuLcMejJm3aoFsLiu6HGmu4/kD+YQA2rXr7OPCQmZmvffjyvDLqA== X-MS-Exchange-Transport-CrossTenantHeadersStamped: SJ2PR11MB7575 X-OriginatorOrg: intel.com X-Spam-Status: No, score=-5.3 required=5.0 tests=BAYES_00,DKIMWL_WL_HIGH,DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,SPF_HELO_NONE,SPF_NONE,TXREP autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org List-Id: Also cc Honza and Richard since we touched generic tune. Thx, Haochen > -----Original Message----- > From: Haochen Jiang > Sent: Wednesday, May 15, 2024 11:04 AM > To: gcc-patches@gcc.gnu.org > Cc: Liu, Hongtao ; ubizjak@gmail.com > Subject: [PATCH 0/2] Align tight loops to solve cross cacheline issue >=20 > Hi all, >=20 > Recently, we have encountered several random performance regressions in > benchmarks commit to commit. It is caused by cross cacheline issue for ti= ght > loops. >=20 > We are trying to solve the issue by two patches. One is adjusting the loo= p > alignment for generic tune, the other is aligning tight and hot loops mor= e > aggressively. >=20 > For SPECINT, we get a 0.85% improvement overall in rates, under option > -O2 -march=3Dx86-64-v3 -mtune=3Dgeneric on Emerald Rapids. >=20 > BenchMarks EMR Rates > 500.perlbench_r -1.21% > 502.gcc_r 0.78% > 505.mcf_r 0.00% > 520.omnetpp_r 0.41% > 523.xalancbmk_r 1.33% > 525.x264_r 2.83% > 531.deepsjeng_r 1.11% > 541.leela_r 0.00% > 548.exchange2_r 2.36% > 557.xz_r 0.98% > Geomean-int 0.85% >=20 > Side effect is that we get a 1.40% increase in codesize. >=20 > BenchMarks EMR Codesize > 500.perlbench_r 0.70% > 502.gcc_r 0.67% > 505.mcf_r 3.26% > 520.omnetpp_r 0.31% > 523.xalancbmk_r 1.15% > 525.x264_r 1.11% > 531.deepsjeng_r 1.40% > 541.leela_r 1.31% > 548.exchange2_r 3.06% > 557.xz_r 1.04% > Geomean-int 1.40% >=20 > Bootstrapped and regtested on x86_64-pc-linux-gnu. >=20 > After we committed into trunk for a month, if there isn't any unexpected > happen. We planned to backport it to GCC14.2. >=20 > Thx, > Haochen >=20 > Haochen Jiang (1): > Adjust generic loop alignment from 16:11:8 to 16 for Intel processors >=20 > liuhongt (1): > Align tight&hot loop without considering max skipping bytes. >=20 > gcc/config/i386/i386.cc | 148 ++++++++++++++++++++++++++++++- > gcc/config/i386/i386.md | 10 ++- > gcc/config/i386/x86-tune-costs.h | 2 +- > 3 files changed, 154 insertions(+), 6 deletions(-) >=20 > -- > 2.31.1