From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 86845 invoked by alias); 4 May 2016 15:20:47 -0000 Mailing-List: contact gcc-patches-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Id: List-Archive: List-Post: List-Help: Sender: gcc-patches-owner@gcc.gnu.org Received: (qmail 86831 invoked by uid 89); 4 May 2016 15:20:47 -0000 Authentication-Results: sourceware.org; auth=none X-Virus-Found: No X-Spam-SWARE-Status: No, score=-1.8 required=5.0 tests=AWL,BAYES_00,SPF_PASS autolearn=ham version=3.3.2 spammy=Hx-languages-length:1199, H*MI:eurprd08, fewer, claim X-HELO: eu-smtp-delivery-143.mimecast.com Received: from eu-smtp-delivery-143.mimecast.com (HELO eu-smtp-delivery-143.mimecast.com) (207.82.80.143) by sourceware.org (qpsmtpd/0.93/v0.84-503-g423c35a) with ESMTP; Wed, 04 May 2016 15:20:36 +0000 Received: from emea01-db3-obe.outbound.protection.outlook.com (mail-db3lrp0082.outbound.protection.outlook.com [213.199.154.82]) (Using TLS) by eu-smtp-1.mimecast.com with ESMTP id uk-mta-18-TdFv_gFYR_-5yBjx5qkhaw-1; Wed, 04 May 2016 16:20:30 +0100 Received: from AM3PR08MB0088.eurprd08.prod.outlook.com (10.160.211.18) by AM4PR08MB1234.eurprd08.prod.outlook.com (10.167.92.136) with Microsoft SMTP Server (TLS) id 15.1.485.9; Wed, 4 May 2016 15:20:28 +0000 Received: from AM3PR08MB0088.eurprd08.prod.outlook.com ([fe80::1dc3:4a21:6709:b267]) by AM3PR08MB0088.eurprd08.prod.outlook.com ([fe80::1dc3:4a21:6709:b267%16]) with mapi id 15.01.0485.011; Wed, 4 May 2016 15:20:28 +0000 From: Wilco Dijkstra To: "bschmidt@redhat.com" CC: "gcc-patches@gcc.gnu.org" , Ramana Radhakrishnan , nd , Richard Biener , "ebotcazou@adacore.com" , "dje.gcc@gmail.com" , "law@redhat.com" , "segher@kernel.crashing.org" Subject: Re: Enabling -frename-registers? Date: Wed, 04 May 2016 15:20:00 -0000 Message-ID: x-ms-office365-filtering-correlation-id: 1b622b99-9a7b-4597-ca82-08d3742fa027 x-microsoft-exchange-diagnostics: 1;AM4PR08MB1234;5:43jiS9LAY5nk2ymiScpRzBjRqWANmNGpkhrkc+Yy3J0E9ou6b8Nh1A8rsKxvD/4dLWDD0j7ejYm8xRwfXm9qJ7Ze5LMLFCE7ADFpEvF3iHYIYJL4hBKC6UV9OuRkvdAYRserQ5rzjQJ+HGtBpVbpiw==;24:nEwZvXEKXbkNsyvuOi2fXhk8XG+9NvDyzocKGcNNyxGkEKTba+RLZMTtxFn3QkRcX2zaE5WDwFVYYGUdXkICvCAlZpNesD7RrIHNzPp3zbU=;7:2zpb3yn6jO+xUIYGZKNbAOp+EDk6ROfJyGxE0ex7v8Js6cY0PM6Ue0zQNYr+tEnS97ZZYlvAgxVVO9jMPLkwyx80tBfSyQKzhQ5+hWNaoFivA3c6nKmO6INIBpA7YpV4ORBzx3x5uzjKyP+gwwzpuSB6ndXCkROP5xyUx53XHviz0mGlAAH59H74lufU8+CN;20:1+IN1q1VHQW8ZTxDT+0FssLcd+JOMuAop0+gxZFnyraK/ng7QNVSWmi9KBDBI4cdzKnVAldzEEml3OfjNItTgVBiYsc0F/ssGetSj1Zu6e3QNjhwOTGPxBvYx2tOCQ5FXHZbqGBTdPILGHCyj/OeWTJIakV/wOCiG/InzD3NLJI= x-microsoft-antispam: UriScan:;BCL:0;PCL:0;RULEID:;SRVR:AM4PR08MB1234; nodisclaimer: True x-microsoft-antispam-prvs: x-exchange-antispam-report-test: UriScan:; x-exchange-antispam-report-cfa-test: BCL:0;PCL:0;RULEID:(9101521098)(9101528026)(601004)(2401047)(8121501046)(5005006)(3002001)(10201501046)(6055026);SRVR:AM4PR08MB1234;BCL:0;PCL:0;RULEID:;SRVR:AM4PR08MB1234; x-forefront-prvs: 093290AD39 x-forefront-antispam-report: SFV:NSPM;SFS:(10009020)(6009001)(24454002)(377454003)(6116002)(102836003)(586003)(3846002)(76576001)(2906002)(5004730100002)(189998001)(4326007)(5250100002)(2501003)(66066001)(8936002)(74316001)(110136002)(1220700001)(2900100001)(1730700002)(33656002)(5002640100001)(5008740100001)(81166005)(5003600100002)(86362001)(3660700001)(5640700001)(92566002)(54356999)(2351001)(11100500001)(87936001)(106116001)(9686002)(3280700002)(50986999);DIR:OUT;SFP:1101;SCL:1;SRVR:AM4PR08MB1234;H:AM3PR08MB0088.eurprd08.prod.outlook.com;FPR:;SPF:None;MLV:sfv;LANG:en; spamdiagnosticoutput: 1:23 spamdiagnosticmetadata: NSPM MIME-Version: 1.0 X-OriginatorOrg: arm.com X-MS-Exchange-CrossTenant-originalarrivaltime: 04 May 2016 15:20:28.6587 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: f34e5979-57d9-4aaa-ad4d-b122a662184d X-MS-Exchange-Transport-CrossTenantHeadersStamped: AM4PR08MB1234 X-MC-Unique: TdFv_gFYR_-5yBjx5qkhaw-1 Content-Type: text/plain; charset=WINDOWS-1252 Content-Transfer-Encoding: quoted-printable X-SW-Source: 2016-05/txt/msg00306.txt.bz2 Bernd Schmidt wrote: > On 05/04/2016 03:25 PM, Ramana Radhakrishnan wrote: >> On ARM / AArch32 I haven't seen any performance data yet - the one place= we are concerned=20 >> about the impact is on Thumb2 code size as regrename may end up inadvert= ently putting more=20 >> things in high registers.=20 > > In theory at least arm_preferred_rename_class is designed to make the op= posite happen. Bernd=20=20 I do not see that working unfortunately - Thumb-2 codesize increases by a f= ew percent even with -Os. This is primarily due to replacing a low register with IP, which often chan= ges a 16-bit instruction like: movs r2, #8 into a 32-bit one: mov ip, #8 This will also affect other targets with multiple instruction sizes. So I t= hink it should check the=20 size of the new instruction patterns and only accept a rename if it is not = larger (certainly with -Os). Also when people claim they can't see any benefit, did they check the codes= ize difference on SPEC2006? On AArch64 codesize reduced uniformly due to fewer moves (and in a few case= s significantly so). I expect that to be true for other RISC targets. Simply put, reduced codesize at no = performance loss =3D gain. Wilco