From patchwork Thu Nov 14 19:13:19 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Srinath Parvathaneni X-Patchwork-Id: 1195138 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=gcc.gnu.org (client-ip=209.132.180.131; helo=sourceware.org; envelope-from=gcc-patches-return-513476-incoming=patchwork.ozlabs.org@gcc.gnu.org; receiver=) Authentication-Results: ozlabs.org; dmarc=none (p=none dis=none) header.from=arm.com Authentication-Results: ozlabs.org; dkim=pass (1024-bit key; unprotected) header.d=gcc.gnu.org header.i=@gcc.gnu.org header.b="P0oMLQUi"; dkim=fail reason="signature verification failed" (1024-bit key; unprotected) header.d=armh.onmicrosoft.com header.i=@armh.onmicrosoft.com header.b="Xeqjr+de"; dkim=fail reason="signature verification failed" (1024-bit key) header.d=armh.onmicrosoft.com header.i=@armh.onmicrosoft.com header.b="Xeqjr+de"; dkim-atps=neutral Received: from sourceware.org (server1.sourceware.org [209.132.180.131]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 47DWYQ4VTQz9sPc for ; Fri, 15 Nov 2019 06:21:14 +1100 (AEDT) DomainKey-Signature: a=rsa-sha1; c=nofws; d=gcc.gnu.org; h=list-id :list-unsubscribe:list-archive:list-post:list-help:sender:from :to:cc:subject:date:message-id:references:in-reply-to :content-type:mime-version; q=dns; s=default; b=g8Y9+4awSXED9Qkh Ceu7D9aQycNIM8EyKEmCEONlnMEzc8/WFSuPJ9XzZ5OXNTxZwF1LpephkoBxz5Qe /X9YvkMJWwhwVn4C3QMbE0yL+DjJzjNE6UjpMnHPdKpO7ekQPyL6AQm/JnyJUuVU Kzc76lQGJ4br3RYrWYRYMGx+TVI= DKIM-Signature: v=1; a=rsa-sha1; c=relaxed; d=gcc.gnu.org; h=list-id :list-unsubscribe:list-archive:list-post:list-help:sender:from :to:cc:subject:date:message-id:references:in-reply-to :content-type:mime-version; s=default; bh=zpNlcrkvRO9/qUDTCGnAQ9 K55lU=; b=P0oMLQUiv18E41YHOJzsK3y2nD5IzUGYfEKdk6SkFku9dwhuI7/sqQ YMAmAMCsnZ/i3Xbv7kdOIFgBJQYB5KZnLL194/yZtjjgbsak/tXdwrEDHu0Lw3RA 9Ep9lT23RV8yQ7BenCoPDG3N/haPqXESWw+T1eBEcqnQsER5AK8iY= Received: (qmail 43480 invoked by alias); 14 Nov 2019 19:14:58 -0000 Mailing-List: contact gcc-patches-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Id: List-Unsubscribe: List-Archive: List-Post: List-Help: Sender: gcc-patches-owner@gcc.gnu.org Delivered-To: mailing list gcc-patches@gcc.gnu.org Received: (qmail 38634 invoked by uid 89); 14 Nov 2019 19:13:56 -0000 Authentication-Results: sourceware.org; auth=none X-Spam-SWARE-Status: No, score=-21.3 required=5.0 tests=AWL, BAYES_00, GIT_PATCH_0, GIT_PATCH_1, GIT_PATCH_2, GIT_PATCH_3, KAM_LOTSOFHASH, RCVD_IN_DNSWL_NONE, SPF_HELO_PASS, SPF_PASS autolearn=ham version=3.3.1 spammy= X-HELO: EUR01-VE1-obe.outbound.protection.outlook.com Received: from mail-eopbgr140053.outbound.protection.outlook.com (HELO EUR01-VE1-obe.outbound.protection.outlook.com) (40.107.14.53) by sourceware.org (qpsmtpd/0.93/v0.84-503-g423c35a) with ESMTP; Thu, 14 Nov 2019 19:13:32 +0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=armh.onmicrosoft.com; s=selector2-armh-onmicrosoft-com; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=XMDcCWbQBhuFP6QWekeqe5DLUYX989t+O0IZyOxsLUY=; b=Xeqjr+deuConT2R9e4Hqv5mjvVm1ybeKL2n5+ChADt8wNeInxT6Id2Qgh6T6+LxzoeTJ4340xzjmnFrzpPE4WGRvs6euwsyD3SVJ/cQIpsx8+/pPTaoDykg/LXyBnNwZBMW7/Xj1yt3Gdci2PM3OVKpp/bkonsuX5USaph+TtIU= Received: from VI1PR08CA0153.eurprd08.prod.outlook.com (2603:10a6:800:d5::31) by DB6PR0801MB1895.eurprd08.prod.outlook.com (2603:10a6:4:74::17) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.2430.24; Thu, 14 Nov 2019 19:13:28 +0000 Received: from DB5EUR03FT005.eop-EUR03.prod.protection.outlook.com (2a01:111:f400:7e0a::202) by VI1PR08CA0153.outlook.office365.com (2603:10a6:800:d5::31) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.2451.23 via Frontend Transport; Thu, 14 Nov 2019 19:13:28 +0000 Authentication-Results: spf=fail (sender IP is 63.35.35.123) smtp.mailfrom=arm.com; gcc.gnu.org; dkim=pass (signature was verified) header.d=armh.onmicrosoft.com; gcc.gnu.org; dmarc=none action=none header.from=arm.com; Received-SPF: Fail (protection.outlook.com: domain of arm.com does not designate 63.35.35.123 as permitted sender) receiver=protection.outlook.com; client-ip=63.35.35.123; helo=64aa7808-outbound-1.mta.getcheckrecipient.com; Received: from 64aa7808-outbound-1.mta.getcheckrecipient.com (63.35.35.123) by DB5EUR03FT005.mail.protection.outlook.com (10.152.20.122) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.2451.23 via Frontend Transport; Thu, 14 Nov 2019 19:13:28 +0000 Received: ("Tessian outbound 851a1162fca7:v33"); Thu, 14 Nov 2019 19:13:27 +0000 X-CheckRecipientChecked: true X-CR-MTA-CID: 89cecf3a45c86eae X-CR-MTA-TID: 64aa7808 Received: from 26484ad84d47.4 (cr-mta-lb-1.cr-mta-net [104.47.13.56]) by 64aa7808-outbound-1.mta.getcheckrecipient.com id 954DD9C7-4611-430F-ABDD-AC4068831FBC.1; Thu, 14 Nov 2019 19:13:22 +0000 Received: from EUR04-HE1-obe.outbound.protection.outlook.com (mail-he1eur04lp2056.outbound.protection.outlook.com [104.47.13.56]) by 64aa7808-outbound-1.mta.getcheckrecipient.com with ESMTPS id 26484ad84d47.4 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384); Thu, 14 Nov 2019 19:13:22 +0000 ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=LZSvqsCU9h6QeJF96MOVjdr1wlgTGhT6slMWJXHVig6ebq8tZKm/6y4u1ZXVE7yBEyPYk5btnzpDojoNh1vbZ1S6GgRXSm2gX/LnKQ9sNmClYxdRoe85OsZaZwFeB96WWIBHuw8txKaDcvQl7HpEmss87vRyrep2dKuSjA3lFmOMedmJIzIWaIrrQpRHQUlj7XvyGqNNKGEP6du7ciD9mmQKdceXjVvhZYXLVgyzGMvO+40iXCiW84/qbjijeL1VckCOokz+ClsBOqTuf2ocr/Fb6M0SPTvbNlLqHqp0XKgVPi7zKOXQpMtqsPovkKS5e6vdv1wB0EkN0jhRFf+bVw== 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-SenderADCheck; bh=XMDcCWbQBhuFP6QWekeqe5DLUYX989t+O0IZyOxsLUY=; b=cTRBICbyT0fLDa/y+fBA8NjDjPwPlX1vTCGtSv4dl8daV4rPeqosGEn65XX2JqJ8v4E8IWVOW+fOptwMA61POsnFCYPPZS4E/ugEaGTfvfza5VWv+twMwICqpSY1vTdWaOdf8P7RCdflhUpRdD3Y7RRIEYHWMX4LT/Xz/3kTzHzdDaIwMntKwEPMyqOW0xDYIo88L5gx50WhZ5B2YEppQzsEB1N+W4Iq2bPgAPyRHLMIPc8vQHV+acQsOaEHM33t/b3iW3B7D19bqRWXecb5ginX9U7eJBQUm/b9zBdSJ5JrlV9nMEM6deIrZq69LgPQX22+sgOESkA8+ciBfgyckQ== 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=armh.onmicrosoft.com; s=selector2-armh-onmicrosoft-com; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=XMDcCWbQBhuFP6QWekeqe5DLUYX989t+O0IZyOxsLUY=; b=Xeqjr+deuConT2R9e4Hqv5mjvVm1ybeKL2n5+ChADt8wNeInxT6Id2Qgh6T6+LxzoeTJ4340xzjmnFrzpPE4WGRvs6euwsyD3SVJ/cQIpsx8+/pPTaoDykg/LXyBnNwZBMW7/Xj1yt3Gdci2PM3OVKpp/bkonsuX5USaph+TtIU= Received: from DBBPR08MB4775.eurprd08.prod.outlook.com (20.179.46.211) by DBBPR08MB4807.eurprd08.prod.outlook.com (20.179.46.144) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.2430.23; Thu, 14 Nov 2019 19:13:19 +0000 Received: from DBBPR08MB4775.eurprd08.prod.outlook.com ([fe80::1c7c:c72d:2183:12d1]) by DBBPR08MB4775.eurprd08.prod.outlook.com ([fe80::1c7c:c72d:2183:12d1%7]) with mapi id 15.20.2430.028; Thu, 14 Nov 2019 19:13:19 +0000 From: Srinath Parvathaneni To: "gcc-patches@gcc.gnu.org" CC: Richard Earnshaw , Kyrylo Tkachov Subject: [PATCH][ARM][GCC][2/5x]: MVE load intrinsics. Date: Thu, 14 Nov 2019 19:13:19 +0000 Message-ID: References: <157375666998.31400.16652205595246718910.scripted-patch-series@arm.com> In-Reply-To: <157375666998.31400.16652205595246718910.scripted-patch-series@arm.com> Authentication-Results-Original: spf=none (sender IP is ) smtp.mailfrom=Srinath.Parvathaneni@arm.com; X-MS-Exchange-PUrlCount: 1 x-ms-exchange-transport-forked: True x-checkrecipientrouted: true x-ms-oob-tlc-oobclassifiers: OLM:13;OLM:13; X-Forefront-Antispam-Report-Untrusted: SFV:NSPM; SFS:(10009020)(1496009)(4636009)(39860400002)(396003)(366004)(376002)(346002)(136003)(54534003)(199004)(189003)(81156014)(316002)(81166006)(30864003)(2501003)(44832011)(4326008)(74316002)(7696005)(99286004)(478600001)(186003)(11346002)(26005)(54906003)(76176011)(52536014)(5660300002)(446003)(25786009)(71190400001)(71200400001)(33656002)(66946007)(52116002)(305945005)(66556008)(7736002)(66446008)(66476007)(66616009)(64756008)(256004)(5024004)(9686003)(966005)(5640700003)(3846002)(66066001)(6916009)(86362001)(486006)(6506007)(6436002)(14454004)(8936002)(2906002)(6116002)(2351001)(55016002)(8676002)(102836004)(386003)(476003)(6306002)(579004)(559001); DIR:OUT; SFP:1101; SCL:1; SRVR:DBBPR08MB4807; H:DBBPR08MB4775.eurprd08.prod.outlook.com; FPR:; SPF:None; LANG:en; PTR:InfoNoRecords; A:1; MX:1; received-spf: None (protection.outlook.com: arm.com does not designate permitted sender hosts) X-MS-Exchange-SenderADCheck: 1 X-Microsoft-Antispam-Untrusted: BCL:0; X-Microsoft-Antispam-Message-Info-Original: gWeQqGl+/aSJ/hL4vEfD+mJd2eaHMUQ/hV8od6AuxEnTKiAvzWfIh0vMH706KoOhUonpst0U6kjVci990l1vPN/iwJGRDONuLBzZtkZ6jBbekme+T43KvgWDy/JanIe5lKcWAEeSlxTmIF70sTHMvdZZ5/PcqUYIx422vnmdp2pbsQ7zs4J5xx2oXSxoQzIISSasjq5yTJlM2Mis3gncvOxChqhOyJlVr8ihQ/L1+ZTuPXPOBDy+xLNb/yQIzT77MMbkhb7VEa4WOotB0jR/UZHytBdUZjd+1i7rZ9J2EMIJqkskfNwc7EOYS2agn/BbgEDLFjfGQ3erVtSoSQSZ+3pnaxTvMPesM7n9O7NEYcydJvePyWEhXNmpYjZQfhXntR55RODl5+hmactXW2ufKlh847caNwxgOfz09wOf+PEZbQyZyBIst7qb9sIkXrAflTTlvgXeBS5jW+zd+B/DwGbTSyUSQhiVpDhqAvV1FyI= MIME-Version: 1.0 Original-Authentication-Results: spf=none (sender IP is ) smtp.mailfrom=Srinath.Parvathaneni@arm.com; X-MS-Exchange-Transport-CrossTenantHeadersStripped: DB5EUR03FT005.eop-EUR03.prod.protection.outlook.com X-MS-Office365-Filtering-Correlation-Id-Prvs: 82912f8c-d5f4-430a-6561-08d76936b57b X-IsSubscribed: yes Hello, This patch supports the following MVE ACLE load intrinsics. vldrbq_gather_offset_u8, vldrbq_gather_offset_s8, vldrbq_s8, vldrbq_u8, vldrbq_gather_offset_u16, vldrbq_gather_offset_s16, vldrbq_s16, vldrbq_u16, vldrbq_gather_offset_u32, vldrbq_gather_offset_s32, vldrbq_s32, vldrbq_u32, vldrwq_gather_base_s32, vldrwq_gather_base_u32. Please refer to M-profile Vector Extension (MVE) intrinsics [1] for more details. [1] https://developer.arm.com/architectures/instruction-sets/simd-isas/helium/mve-intrinsics Regression tested on arm-none-eabi and found no regressions. Ok for trunk? Thanks, Srinath. gcc/ChangeLog: 2019-11-01 Andre Vieira Mihail Ionescu Srinath Parvathaneni * config/arm/arm-builtins.c (LDRGU_QUALIFIERS): Define builtin qualifier. (LDRGS_QUALIFIERS): Likewise. (LDRS_QUALIFIERS): Likewise. (LDRU_QUALIFIERS): Likewise. (LDRGBS_QUALIFIERS): Likewise. (LDRGBU_QUALIFIERS): Likewise. * config/arm/arm_mve.h (vldrbq_gather_offset_u8): Define macro. (vldrbq_gather_offset_s8): Likewise. (vldrbq_s8): Likewise. (vldrbq_u8): Likewise. (vldrbq_gather_offset_u16): Likewise. (vldrbq_gather_offset_s16): Likewise. (vldrbq_s16): Likewise. (vldrbq_u16): Likewise. (vldrbq_gather_offset_u32): Likewise. (vldrbq_gather_offset_s32): Likewise. (vldrbq_s32): Likewise. (vldrbq_u32): Likewise. (vldrwq_gather_base_s32): Likewise. (vldrwq_gather_base_u32): Likewise. (__arm_vldrbq_gather_offset_u8): Define intrinsic. (__arm_vldrbq_gather_offset_s8): Likewise. (__arm_vldrbq_s8): Likewise. (__arm_vldrbq_u8): Likewise. (__arm_vldrbq_gather_offset_u16): Likewise. (__arm_vldrbq_gather_offset_s16): Likewise. (__arm_vldrbq_s16): Likewise. (__arm_vldrbq_u16): Likewise. (__arm_vldrbq_gather_offset_u32): Likewise. (__arm_vldrbq_gather_offset_s32): Likewise. (__arm_vldrbq_s32): Likewise. (__arm_vldrbq_u32): Likewise. (__arm_vldrwq_gather_base_s32): Likewise. (__arm_vldrwq_gather_base_u32): Likewise. (vldrbq_gather_offset): Define polymorphic variant. * config/arm/arm_mve_builtins.def (LDRGU_QUALIFIERS): Use builtin qualifier. (LDRGS_QUALIFIERS): Likewise. (LDRS_QUALIFIERS): Likewise. (LDRU_QUALIFIERS): Likewise. (LDRGBS_QUALIFIERS): Likewise. (LDRGBU_QUALIFIERS): Likewise. * config/arm/mve.md (VLDRBGOQ): Define iterator. (VLDRBQ): Likewise. (VLDRWGBQ): Likewise. (mve_vldrbq_gather_offset_): Define RTL pattern. (mve_vldrbq_): Likewise. (mve_vldrwq_gather_base_v4si): Likewise. gcc/testsuite/ChangeLog: 2019-11-01 Andre Vieira Mihail Ionescu Srinath Parvathaneni * gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s16.c: New test. * gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s32.c: Likewise. * gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s8.c: Likewise. * gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u16.c: Likewise. * gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u32.c: Likewise. * gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u8.c: Likewise. * gcc.target/arm/mve/intrinsics/vldrbq_s16.c: Likewise. * gcc.target/arm/mve/intrinsics/vldrbq_s32.c: Likewise. * gcc.target/arm/mve/intrinsics/vldrbq_s8.c: Likewise. * gcc.target/arm/mve/intrinsics/vldrbq_u16.c: Likewise. * gcc.target/arm/mve/intrinsics/vldrbq_u32.c: Likewise. * gcc.target/arm/mve/intrinsics/vldrbq_u8.c: Likewise. * gcc.target/arm/mve/intrinsics/vldrwq_gather_base_s32.c: Likewise. * gcc.target/arm/mve/intrinsics/vldrwq_gather_base_u32.c: Likewise. ############### Attachment also inlined for ease of reply ############### diff --git a/gcc/config/arm/arm-builtins.c b/gcc/config/arm/arm-builtins.c index ec88199bb5e7e9c15a346061c70841f3086004ef..02ea297937b18099f33a50c808964d1dd7eac1b3 100644 --- a/gcc/config/arm/arm-builtins.c +++ b/gcc/config/arm/arm-builtins.c @@ -588,6 +588,36 @@ arm_strsbu_qualifiers[SIMD_MAX_BUILTIN_ARGS] qualifier_unsigned}; #define STRSBU_QUALIFIERS (arm_strsbu_qualifiers) +static enum arm_type_qualifiers +arm_ldrgu_qualifiers[SIMD_MAX_BUILTIN_ARGS] + = { qualifier_unsigned, qualifier_pointer, qualifier_unsigned}; +#define LDRGU_QUALIFIERS (arm_ldrgu_qualifiers) + +static enum arm_type_qualifiers +arm_ldrgs_qualifiers[SIMD_MAX_BUILTIN_ARGS] + = { qualifier_none, qualifier_pointer, qualifier_unsigned}; +#define LDRGS_QUALIFIERS (arm_ldrgs_qualifiers) + +static enum arm_type_qualifiers +arm_ldrs_qualifiers[SIMD_MAX_BUILTIN_ARGS] + = { qualifier_none, qualifier_pointer}; +#define LDRS_QUALIFIERS (arm_ldrs_qualifiers) + +static enum arm_type_qualifiers +arm_ldru_qualifiers[SIMD_MAX_BUILTIN_ARGS] + = { qualifier_unsigned, qualifier_pointer}; +#define LDRU_QUALIFIERS (arm_ldru_qualifiers) + +static enum arm_type_qualifiers +arm_ldrgbs_qualifiers[SIMD_MAX_BUILTIN_ARGS] + = { qualifier_none, qualifier_unsigned, qualifier_immediate}; +#define LDRGBS_QUALIFIERS (arm_ldrgbs_qualifiers) + +static enum arm_type_qualifiers +arm_ldrgbu_qualifiers[SIMD_MAX_BUILTIN_ARGS] + = { qualifier_unsigned, qualifier_unsigned, qualifier_immediate}; +#define LDRGBU_QUALIFIERS (arm_ldrgbu_qualifiers) + /* End of Qualifier for MVE builtins. */ /* void ([T element type] *, T, immediate). */ diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h index 3d64033dd23636b041cbd6ecb3eb18c3b9db3aed..c123de1f3d37054b779a9ee908525c242b2bc4ab 100644 --- a/gcc/config/arm/arm_mve.h +++ b/gcc/config/arm/arm_mve.h @@ -1716,6 +1716,20 @@ typedef struct { uint8x16_t val[4]; } uint8x16x4_t; #define vstrbq_scatter_offset_s32( __base, __offset, __value) __arm_vstrbq_scatter_offset_s32( __base, __offset, __value) #define vstrwq_scatter_base_s32(__addr, __offset, __value) __arm_vstrwq_scatter_base_s32(__addr, __offset, __value) #define vstrwq_scatter_base_u32(__addr, __offset, __value) __arm_vstrwq_scatter_base_u32(__addr, __offset, __value) +#define vldrbq_gather_offset_u8(__base, __offset) __arm_vldrbq_gather_offset_u8(__base, __offset) +#define vldrbq_gather_offset_s8(__base, __offset) __arm_vldrbq_gather_offset_s8(__base, __offset) +#define vldrbq_s8(__base) __arm_vldrbq_s8(__base) +#define vldrbq_u8(__base) __arm_vldrbq_u8(__base) +#define vldrbq_gather_offset_u16(__base, __offset) __arm_vldrbq_gather_offset_u16(__base, __offset) +#define vldrbq_gather_offset_s16(__base, __offset) __arm_vldrbq_gather_offset_s16(__base, __offset) +#define vldrbq_s16(__base) __arm_vldrbq_s16(__base) +#define vldrbq_u16(__base) __arm_vldrbq_u16(__base) +#define vldrbq_gather_offset_u32(__base, __offset) __arm_vldrbq_gather_offset_u32(__base, __offset) +#define vldrbq_gather_offset_s32(__base, __offset) __arm_vldrbq_gather_offset_s32(__base, __offset) +#define vldrbq_s32(__base) __arm_vldrbq_s32(__base) +#define vldrbq_u32(__base) __arm_vldrbq_u32(__base) +#define vldrwq_gather_base_s32(__addr, __offset) __arm_vldrwq_gather_base_s32(__addr, __offset) +#define vldrwq_gather_base_u32(__addr, __offset) __arm_vldrwq_gather_base_u32(__addr, __offset) #endif __extension__ extern __inline void @@ -11106,6 +11120,105 @@ __arm_vstrwq_scatter_base_u32 (uint32x4_t __addr, const int __offset, uint32x4_t { __builtin_mve_vstrwq_scatter_base_uv4si (__addr, __offset, __value); } + +__extension__ extern __inline uint8x16_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_gather_offset_u8 (uint8_t const * __base, uint8x16_t __offset) +{ + return __builtin_mve_vldrbq_gather_offset_uv16qi ((__builtin_neon_qi *) __base, __offset); +} + +__extension__ extern __inline int8x16_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_gather_offset_s8 (int8_t const * __base, uint8x16_t __offset) +{ + return __builtin_mve_vldrbq_gather_offset_sv16qi ((__builtin_neon_qi *) __base, __offset); +} + +__extension__ extern __inline int8x16_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_s8 (int8_t const * __base) +{ + return __builtin_mve_vldrbq_sv16qi ((__builtin_neon_qi *) __base); +} + +__extension__ extern __inline uint8x16_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_u8 (uint8_t const * __base) +{ + return __builtin_mve_vldrbq_uv16qi ((__builtin_neon_qi *) __base); +} + +__extension__ extern __inline uint16x8_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_gather_offset_u16 (uint8_t const * __base, uint16x8_t __offset) +{ + return __builtin_mve_vldrbq_gather_offset_uv8hi ((__builtin_neon_qi *) __base, __offset); +} + +__extension__ extern __inline int16x8_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_gather_offset_s16 (int8_t const * __base, uint16x8_t __offset) +{ + return __builtin_mve_vldrbq_gather_offset_sv8hi ((__builtin_neon_qi *) __base, __offset); +} + +__extension__ extern __inline int16x8_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_s16 (int8_t const * __base) +{ + return __builtin_mve_vldrbq_sv8hi ((__builtin_neon_qi *) __base); +} + +__extension__ extern __inline uint16x8_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_u16 (uint8_t const * __base) +{ + return __builtin_mve_vldrbq_uv8hi ((__builtin_neon_qi *) __base); +} + +__extension__ extern __inline uint32x4_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_gather_offset_u32 (uint8_t const * __base, uint32x4_t __offset) +{ + return __builtin_mve_vldrbq_gather_offset_uv4si ((__builtin_neon_qi *) __base, __offset); +} + +__extension__ extern __inline int32x4_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_gather_offset_s32 (int8_t const * __base, uint32x4_t __offset) +{ + return __builtin_mve_vldrbq_gather_offset_sv4si ((__builtin_neon_qi *) __base, __offset); +} + +__extension__ extern __inline int32x4_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_s32 (int8_t const * __base) +{ + return __builtin_mve_vldrbq_sv4si ((__builtin_neon_qi *) __base); +} + +__extension__ extern __inline uint32x4_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_u32 (uint8_t const * __base) +{ + return __builtin_mve_vldrbq_uv4si ((__builtin_neon_qi *) __base); +} + +__extension__ extern __inline int32x4_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrwq_gather_base_s32 (uint32x4_t __addr, const int __offset) +{ + return __builtin_mve_vldrwq_gather_base_sv4si (__addr, __offset); +} + +__extension__ extern __inline uint32x4_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrwq_gather_base_u32 (uint32x4_t __addr, const int __offset) +{ + return __builtin_mve_vldrwq_gather_base_uv4si (__addr, __offset); +} + #if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */ __extension__ extern __inline void @@ -17682,6 +17795,17 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_s32(p0, p1, __ARM_mve_coerce(__p2, int32x4_t)), \ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_u32(p0, p1, __ARM_mve_coerce(__p2, uint32x4_t)));}) +#define vldrbq_gather_offset(p0,p1) __arm_vldrbq_gather_offset(p0,p1) +#define __arm_vldrbq_gather_offset(p0,p1) ({ __typeof(p0) __p0 = (p0); \ + __typeof(p1) __p1 = (p1); \ + _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \ + int (*)[__ARM_mve_type_int8_t_const_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_s8 (__ARM_mve_coerce(__p0, int8_t const *), __ARM_mve_coerce(__p1, uint8x16_t)), \ + int (*)[__ARM_mve_type_int8_t_const_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_s16 (__ARM_mve_coerce(__p0, int8_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_int8_t_const_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_s32 (__ARM_mve_coerce(__p0, int8_t const *), __ARM_mve_coerce(__p1, uint32x4_t)), \ + int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_u8 (__ARM_mve_coerce(__p0, uint8_t const *), __ARM_mve_coerce(__p1, uint8x16_t)), \ + int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_u16 (__ARM_mve_coerce(__p0, uint8_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_u32 (__ARM_mve_coerce(__p0, uint8_t const *), __ARM_mve_coerce(__p1, uint32x4_t)));}) + #endif /* MVE Floating point. */ #ifdef __cplusplus diff --git a/gcc/config/arm/arm_mve_builtins.def b/gcc/config/arm/arm_mve_builtins.def index 149c4115b6167e3f2f0eb43fbdeaa8708ba5d723..60e50767a2ac80a05303e3df8512f2612c8bc8ef 100644 --- a/gcc/config/arm/arm_mve_builtins.def +++ b/gcc/config/arm/arm_mve_builtins.def @@ -691,3 +691,9 @@ VAR3 (STRSS, vstrbq_scatter_offset_s, v16qi, v8hi, v4si) VAR3 (STRSU, vstrbq_scatter_offset_u, v16qi, v8hi, v4si) VAR1 (STRSBS, vstrwq_scatter_base_s, v4si) VAR1 (STRSBU, vstrwq_scatter_base_u, v4si) +VAR3 (LDRGU, vldrbq_gather_offset_u, v16qi, v8hi, v4si) +VAR3 (LDRGS, vldrbq_gather_offset_s, v16qi, v8hi, v4si) +VAR3 (LDRS, vldrbq_s, v16qi, v8hi, v4si) +VAR3 (LDRU, vldrbq_u, v16qi, v8hi, v4si) +VAR1 (LDRGBS, vldrwq_gather_base_s, v4si) +VAR1 (LDRGBU, vldrwq_gather_base_u, v4si) diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md index eb365166e934f32f7695e5354258151202f378c0..7b416f9a4e04f8c02547953d6019787817688a36 100644 --- a/gcc/config/arm/mve.md +++ b/gcc/config/arm/mve.md @@ -192,7 +192,8 @@ VCMULQ_ROT270_M_F VCMULQ_ROT90_M_F VFMAQ_M_F VFMAQ_M_N_F VFMASQ_M_N_F VFMSQ_M_F VMAXNMQ_M_F VMINNMQ_M_F VSUBQ_M_F VSTRWQSB_S VSTRWQSB_U - VSTRBQSO_S VSTRBQSO_U VSTRBQ_S VSTRBQ_U]) + VSTRBQSO_S VSTRBQSO_U VSTRBQ_S VSTRBQ_U VLDRBQGO_S + VLDRBQGO_U VLDRBQ_S VLDRBQ_U VLDRWQGB_S VLDRWQGB_U]) (define_mode_attr MVE_CNVT [(V8HI "V8HF") (V4SI "V4SF") (V8HF "V8HI") (V4SF "V4SI")]) @@ -345,7 +346,9 @@ (VMLALDAVAXQ_P_S "s") (VMLALDAVAXQ_P_U "u") (VMLALDAVAQ_P_S "s") (VMLALDAVAQ_P_U "u") (VSTRWQSB_S "s") (VSTRWQSB_U "u") (VSTRBQSO_S "s") - (VSTRBQSO_U "u") (VSTRBQ_S "s") (VSTRBQ_U "u")]) + (VSTRBQSO_U "u") (VSTRBQ_S "s") (VSTRBQ_U "u") + (VLDRBQGO_S "s") (VLDRBQGO_U "u") (VLDRBQ_S "s") + (VLDRBQ_U "u") (VLDRWQGB_S "s") (VLDRWQGB_U "u")]) (define_int_attr mode1 [(VCTP8Q "8") (VCTP16Q "16") (VCTP32Q "32") (VCTP64Q "64") (VCTP8Q_M "8") (VCTP16Q_M "16") @@ -569,6 +572,9 @@ (define_int_iterator VSTRWSBQ [VSTRWQSB_S VSTRWQSB_U]) (define_int_iterator VSTRBSOQ [VSTRBQSO_S VSTRBQSO_U]) (define_int_iterator VSTRBQ [VSTRBQ_S VSTRBQ_U]) +(define_int_iterator VLDRBGOQ [VLDRBQGO_S VLDRBQGO_U]) +(define_int_iterator VLDRBQ [VLDRBQ_S VLDRBQ_U]) +(define_int_iterator VLDRWGBQ [VLDRWQGB_S VLDRWQGB_U]) (define_insn "*mve_mov" [(set (match_operand:MVE_types 0 "s_register_operand" "=w,w,r,w,w,r,w") @@ -8002,3 +8008,65 @@ return ""; } [(set_attr "length" "4")]) + +;; +;; [vldrbq_gather_offset_s vldrbq_gather_offset_u] +;; +(define_insn "mve_vldrbq_gather_offset_" + [(set (match_operand:MVE_2 0 "s_register_operand" "=&w") + (unspec:MVE_2 [(match_operand: 1 "memory_operand" "Us") + (match_operand:MVE_2 2 "s_register_operand" "w")] + VLDRBGOQ)) + ] + "TARGET_HAVE_MVE" +{ + rtx ops[3]; + ops[0] = operands[0]; + ops[1] = operands[1]; + ops[2] = operands[2]; + if (!strcmp ("","s") && == 8) + output_asm_insn ("vldrb.u8\t%q0, [%m1, %q2]",ops); + else + output_asm_insn ("vldrb.\t%q0, [%m1, %q2]",ops); + return ""; +} + [(set_attr "length" "4")]) + +;; +;; [vldrbq_s vldrbq_u] +;; +(define_insn "mve_vldrbq_" + [(set (match_operand:MVE_2 0 "s_register_operand" "=w") + (unspec:MVE_2 [(match_operand: 1 "memory_operand" "Us")] + VLDRBQ)) + ] + "TARGET_HAVE_MVE" +{ + rtx ops[2]; + int regno = REGNO (operands[0]); + ops[0] = gen_rtx_REG (TImode, regno); + ops[1] = operands[1]; + output_asm_insn ("vldrb.\t%q0, %E1",ops); + return ""; +} + [(set_attr "length" "4")]) + +;; +;; [vldrwq_gather_base_s vldrwq_gather_base_u] +;; +(define_insn "mve_vldrwq_gather_base_v4si" + [(set (match_operand:V4SI 0 "s_register_operand" "=&w") + (unspec:V4SI [(match_operand:V4SI 1 "s_register_operand" "w") + (match_operand:SI 2 "immediate_operand" "i")] + VLDRWGBQ)) + ] + "TARGET_HAVE_MVE" +{ + rtx ops[3]; + ops[0] = operands[0]; + ops[1] = operands[1]; + ops[2] = operands[2]; + output_asm_insn ("vldrw.u32\t%q0, [%q1, %2]",ops); + return ""; +} + [(set_attr "length" "4")]) diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s16.c new file mode 100644 index 0000000000000000000000000000000000000000..f7763b8a1f668e25c5b34ed429dd5dc9a5455676 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s16.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int16x8_t +foo (int8_t const * base, uint16x8_t offset) +{ + return vldrbq_gather_offset_s16 (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.s16" } } */ + +int16x8_t +foo1 (int8_t const * base, uint16x8_t offset) +{ + return vldrbq_gather_offset (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.s16" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s32.c new file mode 100644 index 0000000000000000000000000000000000000000..768a4325beae64496e174f55932554a961cbc886 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s32.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int32x4_t +foo (int8_t const * base, uint32x4_t offset) +{ + return vldrbq_gather_offset_s32 (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.s32" } } */ + +int32x4_t +foo1 (int8_t const * base, uint32x4_t offset) +{ + return vldrbq_gather_offset (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.s32" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s8.c new file mode 100644 index 0000000000000000000000000000000000000000..4c52b5a009507bf68b6bd83699cd78e85b291572 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s8.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int8x16_t +foo (int8_t const * base, uint8x16_t offset) +{ + return vldrbq_gather_offset_s8 (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u8" } } */ + +int8x16_t +foo1 (int8_t const * base, uint8x16_t offset) +{ + return vldrbq_gather_offset (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u8" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u16.c new file mode 100644 index 0000000000000000000000000000000000000000..44b310add69aa8e7b74cf2c501013b136d5da041 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u16.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint16x8_t +foo (uint8_t const * base, uint16x8_t offset) +{ + return vldrbq_gather_offset_u16 (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u16" } } */ + +uint16x8_t +foo1 (uint8_t const * base, uint16x8_t offset) +{ + return vldrbq_gather_offset (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u16" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u32.c new file mode 100644 index 0000000000000000000000000000000000000000..8415ea701327b2a296e1e28e37537045b69ff6a9 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u32.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint32x4_t +foo (uint8_t const * base, uint32x4_t offset) +{ + return vldrbq_gather_offset_u32 (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u32" } } */ + +uint32x4_t +foo1 (uint8_t const * base, uint32x4_t offset) +{ + return vldrbq_gather_offset (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u32" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u8.c new file mode 100644 index 0000000000000000000000000000000000000000..9fbe1aa419d572ffad9b319d3ad24d9ac913b7e6 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u8.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint8x16_t +foo (uint8_t const * base, uint8x16_t offset) +{ + return vldrbq_gather_offset_u8 (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u8" } } */ + +uint8x16_t +foo1 (uint8_t const * base, uint8x16_t offset) +{ + return vldrbq_gather_offset (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u8" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s16.c new file mode 100644 index 0000000000000000000000000000000000000000..a63c7367e9ae24b78f4819aea95e6e5d0ec85891 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s16.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int16x8_t +foo (int8_t const * base) +{ + return vldrbq_s16 (base); +} + +/* { dg-final { scan-assembler "vldrb.s16" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s32.c new file mode 100644 index 0000000000000000000000000000000000000000..040c58d44c5e6bf09ad61d13c44f53dfd987e8e4 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s32.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int32x4_t +foo (int8_t const * base) +{ + return vldrbq_s32 (base); +} + +/* { dg-final { scan-assembler "vldrb.s32" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s8.c new file mode 100644 index 0000000000000000000000000000000000000000..e5cc3deb79b909a19cbbcafe9213c91b67ac337a --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s8.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int8x16_t +foo (int8_t const * base) +{ + return vldrbq_s8 (base); +} + +/* { dg-final { scan-assembler "vldrb.s8" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u16.c new file mode 100644 index 0000000000000000000000000000000000000000..7dedbde6eeae066fdc04e9d6fb6fe626af4580db --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u16.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint16x8_t +foo (uint8_t const * base) +{ + return vldrbq_u16 (base); +} + +/* { dg-final { scan-assembler "vldrb.u16" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u32.c new file mode 100644 index 0000000000000000000000000000000000000000..3c3ec6c4ffe6b014bf58d0b7c2a2d501ddf8301b --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u32.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint32x4_t +foo (uint8_t const * base) +{ + return vldrbq_u32 (base); +} + +/* { dg-final { scan-assembler "vldrb.u32" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u8.c new file mode 100644 index 0000000000000000000000000000000000000000..5328d99bab94d62bd032d4da3509cd2c55a7841a --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u8.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint8x16_t +foo (uint8_t const * base) +{ + return vldrbq_u8 (base); +} + +/* { dg-final { scan-assembler "vldrb.u8" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_s32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_s32.c new file mode 100644 index 0000000000000000000000000000000000000000..14831a91b65900d040f74b90c592bc195af42874 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_s32.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int32x4_t +foo (uint32x4_t addr) +{ + return vldrwq_gather_base_s32 (addr, 4); +} + +/* { dg-final { scan-assembler "vldrw.u32" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_u32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_u32.c new file mode 100644 index 0000000000000000000000000000000000000000..7753ea6a7c9ec83b90f3e723683c156b20617e23 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_u32.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint32x4_t +foo (uint32x4_t addr) +{ + return vldrwq_gather_base_u32 (addr, 4); +} + +/* { dg-final { scan-assembler "vldrw.u32" } } */ diff --git a/gcc/config/arm/arm-builtins.c b/gcc/config/arm/arm-builtins.c index ec88199bb5e7e9c15a346061c70841f3086004ef..02ea297937b18099f33a50c808964d1dd7eac1b3 100644 --- a/gcc/config/arm/arm-builtins.c +++ b/gcc/config/arm/arm-builtins.c @@ -588,6 +588,36 @@ arm_strsbu_qualifiers[SIMD_MAX_BUILTIN_ARGS] qualifier_unsigned}; #define STRSBU_QUALIFIERS (arm_strsbu_qualifiers) +static enum arm_type_qualifiers +arm_ldrgu_qualifiers[SIMD_MAX_BUILTIN_ARGS] + = { qualifier_unsigned, qualifier_pointer, qualifier_unsigned}; +#define LDRGU_QUALIFIERS (arm_ldrgu_qualifiers) + +static enum arm_type_qualifiers +arm_ldrgs_qualifiers[SIMD_MAX_BUILTIN_ARGS] + = { qualifier_none, qualifier_pointer, qualifier_unsigned}; +#define LDRGS_QUALIFIERS (arm_ldrgs_qualifiers) + +static enum arm_type_qualifiers +arm_ldrs_qualifiers[SIMD_MAX_BUILTIN_ARGS] + = { qualifier_none, qualifier_pointer}; +#define LDRS_QUALIFIERS (arm_ldrs_qualifiers) + +static enum arm_type_qualifiers +arm_ldru_qualifiers[SIMD_MAX_BUILTIN_ARGS] + = { qualifier_unsigned, qualifier_pointer}; +#define LDRU_QUALIFIERS (arm_ldru_qualifiers) + +static enum arm_type_qualifiers +arm_ldrgbs_qualifiers[SIMD_MAX_BUILTIN_ARGS] + = { qualifier_none, qualifier_unsigned, qualifier_immediate}; +#define LDRGBS_QUALIFIERS (arm_ldrgbs_qualifiers) + +static enum arm_type_qualifiers +arm_ldrgbu_qualifiers[SIMD_MAX_BUILTIN_ARGS] + = { qualifier_unsigned, qualifier_unsigned, qualifier_immediate}; +#define LDRGBU_QUALIFIERS (arm_ldrgbu_qualifiers) + /* End of Qualifier for MVE builtins. */ /* void ([T element type] *, T, immediate). */ diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h index 3d64033dd23636b041cbd6ecb3eb18c3b9db3aed..c123de1f3d37054b779a9ee908525c242b2bc4ab 100644 --- a/gcc/config/arm/arm_mve.h +++ b/gcc/config/arm/arm_mve.h @@ -1716,6 +1716,20 @@ typedef struct { uint8x16_t val[4]; } uint8x16x4_t; #define vstrbq_scatter_offset_s32( __base, __offset, __value) __arm_vstrbq_scatter_offset_s32( __base, __offset, __value) #define vstrwq_scatter_base_s32(__addr, __offset, __value) __arm_vstrwq_scatter_base_s32(__addr, __offset, __value) #define vstrwq_scatter_base_u32(__addr, __offset, __value) __arm_vstrwq_scatter_base_u32(__addr, __offset, __value) +#define vldrbq_gather_offset_u8(__base, __offset) __arm_vldrbq_gather_offset_u8(__base, __offset) +#define vldrbq_gather_offset_s8(__base, __offset) __arm_vldrbq_gather_offset_s8(__base, __offset) +#define vldrbq_s8(__base) __arm_vldrbq_s8(__base) +#define vldrbq_u8(__base) __arm_vldrbq_u8(__base) +#define vldrbq_gather_offset_u16(__base, __offset) __arm_vldrbq_gather_offset_u16(__base, __offset) +#define vldrbq_gather_offset_s16(__base, __offset) __arm_vldrbq_gather_offset_s16(__base, __offset) +#define vldrbq_s16(__base) __arm_vldrbq_s16(__base) +#define vldrbq_u16(__base) __arm_vldrbq_u16(__base) +#define vldrbq_gather_offset_u32(__base, __offset) __arm_vldrbq_gather_offset_u32(__base, __offset) +#define vldrbq_gather_offset_s32(__base, __offset) __arm_vldrbq_gather_offset_s32(__base, __offset) +#define vldrbq_s32(__base) __arm_vldrbq_s32(__base) +#define vldrbq_u32(__base) __arm_vldrbq_u32(__base) +#define vldrwq_gather_base_s32(__addr, __offset) __arm_vldrwq_gather_base_s32(__addr, __offset) +#define vldrwq_gather_base_u32(__addr, __offset) __arm_vldrwq_gather_base_u32(__addr, __offset) #endif __extension__ extern __inline void @@ -11106,6 +11120,105 @@ __arm_vstrwq_scatter_base_u32 (uint32x4_t __addr, const int __offset, uint32x4_t { __builtin_mve_vstrwq_scatter_base_uv4si (__addr, __offset, __value); } + +__extension__ extern __inline uint8x16_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_gather_offset_u8 (uint8_t const * __base, uint8x16_t __offset) +{ + return __builtin_mve_vldrbq_gather_offset_uv16qi ((__builtin_neon_qi *) __base, __offset); +} + +__extension__ extern __inline int8x16_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_gather_offset_s8 (int8_t const * __base, uint8x16_t __offset) +{ + return __builtin_mve_vldrbq_gather_offset_sv16qi ((__builtin_neon_qi *) __base, __offset); +} + +__extension__ extern __inline int8x16_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_s8 (int8_t const * __base) +{ + return __builtin_mve_vldrbq_sv16qi ((__builtin_neon_qi *) __base); +} + +__extension__ extern __inline uint8x16_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_u8 (uint8_t const * __base) +{ + return __builtin_mve_vldrbq_uv16qi ((__builtin_neon_qi *) __base); +} + +__extension__ extern __inline uint16x8_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_gather_offset_u16 (uint8_t const * __base, uint16x8_t __offset) +{ + return __builtin_mve_vldrbq_gather_offset_uv8hi ((__builtin_neon_qi *) __base, __offset); +} + +__extension__ extern __inline int16x8_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_gather_offset_s16 (int8_t const * __base, uint16x8_t __offset) +{ + return __builtin_mve_vldrbq_gather_offset_sv8hi ((__builtin_neon_qi *) __base, __offset); +} + +__extension__ extern __inline int16x8_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_s16 (int8_t const * __base) +{ + return __builtin_mve_vldrbq_sv8hi ((__builtin_neon_qi *) __base); +} + +__extension__ extern __inline uint16x8_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_u16 (uint8_t const * __base) +{ + return __builtin_mve_vldrbq_uv8hi ((__builtin_neon_qi *) __base); +} + +__extension__ extern __inline uint32x4_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_gather_offset_u32 (uint8_t const * __base, uint32x4_t __offset) +{ + return __builtin_mve_vldrbq_gather_offset_uv4si ((__builtin_neon_qi *) __base, __offset); +} + +__extension__ extern __inline int32x4_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_gather_offset_s32 (int8_t const * __base, uint32x4_t __offset) +{ + return __builtin_mve_vldrbq_gather_offset_sv4si ((__builtin_neon_qi *) __base, __offset); +} + +__extension__ extern __inline int32x4_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_s32 (int8_t const * __base) +{ + return __builtin_mve_vldrbq_sv4si ((__builtin_neon_qi *) __base); +} + +__extension__ extern __inline uint32x4_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrbq_u32 (uint8_t const * __base) +{ + return __builtin_mve_vldrbq_uv4si ((__builtin_neon_qi *) __base); +} + +__extension__ extern __inline int32x4_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrwq_gather_base_s32 (uint32x4_t __addr, const int __offset) +{ + return __builtin_mve_vldrwq_gather_base_sv4si (__addr, __offset); +} + +__extension__ extern __inline uint32x4_t +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__arm_vldrwq_gather_base_u32 (uint32x4_t __addr, const int __offset) +{ + return __builtin_mve_vldrwq_gather_base_uv4si (__addr, __offset); +} + #if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */ __extension__ extern __inline void @@ -17682,6 +17795,17 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_base_s32(p0, p1, __ARM_mve_coerce(__p2, int32x4_t)), \ int (*)[__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_base_u32(p0, p1, __ARM_mve_coerce(__p2, uint32x4_t)));}) +#define vldrbq_gather_offset(p0,p1) __arm_vldrbq_gather_offset(p0,p1) +#define __arm_vldrbq_gather_offset(p0,p1) ({ __typeof(p0) __p0 = (p0); \ + __typeof(p1) __p1 = (p1); \ + _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \ + int (*)[__ARM_mve_type_int8_t_const_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_s8 (__ARM_mve_coerce(__p0, int8_t const *), __ARM_mve_coerce(__p1, uint8x16_t)), \ + int (*)[__ARM_mve_type_int8_t_const_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_s16 (__ARM_mve_coerce(__p0, int8_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_int8_t_const_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_s32 (__ARM_mve_coerce(__p0, int8_t const *), __ARM_mve_coerce(__p1, uint32x4_t)), \ + int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_u8 (__ARM_mve_coerce(__p0, uint8_t const *), __ARM_mve_coerce(__p1, uint8x16_t)), \ + int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_u16 (__ARM_mve_coerce(__p0, uint8_t const *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint8_t_const_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_u32 (__ARM_mve_coerce(__p0, uint8_t const *), __ARM_mve_coerce(__p1, uint32x4_t)));}) + #endif /* MVE Floating point. */ #ifdef __cplusplus diff --git a/gcc/config/arm/arm_mve_builtins.def b/gcc/config/arm/arm_mve_builtins.def index 149c4115b6167e3f2f0eb43fbdeaa8708ba5d723..60e50767a2ac80a05303e3df8512f2612c8bc8ef 100644 --- a/gcc/config/arm/arm_mve_builtins.def +++ b/gcc/config/arm/arm_mve_builtins.def @@ -691,3 +691,9 @@ VAR3 (STRSS, vstrbq_scatter_offset_s, v16qi, v8hi, v4si) VAR3 (STRSU, vstrbq_scatter_offset_u, v16qi, v8hi, v4si) VAR1 (STRSBS, vstrwq_scatter_base_s, v4si) VAR1 (STRSBU, vstrwq_scatter_base_u, v4si) +VAR3 (LDRGU, vldrbq_gather_offset_u, v16qi, v8hi, v4si) +VAR3 (LDRGS, vldrbq_gather_offset_s, v16qi, v8hi, v4si) +VAR3 (LDRS, vldrbq_s, v16qi, v8hi, v4si) +VAR3 (LDRU, vldrbq_u, v16qi, v8hi, v4si) +VAR1 (LDRGBS, vldrwq_gather_base_s, v4si) +VAR1 (LDRGBU, vldrwq_gather_base_u, v4si) diff --git a/gcc/config/arm/mve.md b/gcc/config/arm/mve.md index eb365166e934f32f7695e5354258151202f378c0..7b416f9a4e04f8c02547953d6019787817688a36 100644 --- a/gcc/config/arm/mve.md +++ b/gcc/config/arm/mve.md @@ -192,7 +192,8 @@ VCMULQ_ROT270_M_F VCMULQ_ROT90_M_F VFMAQ_M_F VFMAQ_M_N_F VFMASQ_M_N_F VFMSQ_M_F VMAXNMQ_M_F VMINNMQ_M_F VSUBQ_M_F VSTRWQSB_S VSTRWQSB_U - VSTRBQSO_S VSTRBQSO_U VSTRBQ_S VSTRBQ_U]) + VSTRBQSO_S VSTRBQSO_U VSTRBQ_S VSTRBQ_U VLDRBQGO_S + VLDRBQGO_U VLDRBQ_S VLDRBQ_U VLDRWQGB_S VLDRWQGB_U]) (define_mode_attr MVE_CNVT [(V8HI "V8HF") (V4SI "V4SF") (V8HF "V8HI") (V4SF "V4SI")]) @@ -345,7 +346,9 @@ (VMLALDAVAXQ_P_S "s") (VMLALDAVAXQ_P_U "u") (VMLALDAVAQ_P_S "s") (VMLALDAVAQ_P_U "u") (VSTRWQSB_S "s") (VSTRWQSB_U "u") (VSTRBQSO_S "s") - (VSTRBQSO_U "u") (VSTRBQ_S "s") (VSTRBQ_U "u")]) + (VSTRBQSO_U "u") (VSTRBQ_S "s") (VSTRBQ_U "u") + (VLDRBQGO_S "s") (VLDRBQGO_U "u") (VLDRBQ_S "s") + (VLDRBQ_U "u") (VLDRWQGB_S "s") (VLDRWQGB_U "u")]) (define_int_attr mode1 [(VCTP8Q "8") (VCTP16Q "16") (VCTP32Q "32") (VCTP64Q "64") (VCTP8Q_M "8") (VCTP16Q_M "16") @@ -569,6 +572,9 @@ (define_int_iterator VSTRWSBQ [VSTRWQSB_S VSTRWQSB_U]) (define_int_iterator VSTRBSOQ [VSTRBQSO_S VSTRBQSO_U]) (define_int_iterator VSTRBQ [VSTRBQ_S VSTRBQ_U]) +(define_int_iterator VLDRBGOQ [VLDRBQGO_S VLDRBQGO_U]) +(define_int_iterator VLDRBQ [VLDRBQ_S VLDRBQ_U]) +(define_int_iterator VLDRWGBQ [VLDRWQGB_S VLDRWQGB_U]) (define_insn "*mve_mov" [(set (match_operand:MVE_types 0 "s_register_operand" "=w,w,r,w,w,r,w") @@ -8002,3 +8008,65 @@ return ""; } [(set_attr "length" "4")]) + +;; +;; [vldrbq_gather_offset_s vldrbq_gather_offset_u] +;; +(define_insn "mve_vldrbq_gather_offset_" + [(set (match_operand:MVE_2 0 "s_register_operand" "=&w") + (unspec:MVE_2 [(match_operand: 1 "memory_operand" "Us") + (match_operand:MVE_2 2 "s_register_operand" "w")] + VLDRBGOQ)) + ] + "TARGET_HAVE_MVE" +{ + rtx ops[3]; + ops[0] = operands[0]; + ops[1] = operands[1]; + ops[2] = operands[2]; + if (!strcmp ("","s") && == 8) + output_asm_insn ("vldrb.u8\t%q0, [%m1, %q2]",ops); + else + output_asm_insn ("vldrb.\t%q0, [%m1, %q2]",ops); + return ""; +} + [(set_attr "length" "4")]) + +;; +;; [vldrbq_s vldrbq_u] +;; +(define_insn "mve_vldrbq_" + [(set (match_operand:MVE_2 0 "s_register_operand" "=w") + (unspec:MVE_2 [(match_operand: 1 "memory_operand" "Us")] + VLDRBQ)) + ] + "TARGET_HAVE_MVE" +{ + rtx ops[2]; + int regno = REGNO (operands[0]); + ops[0] = gen_rtx_REG (TImode, regno); + ops[1] = operands[1]; + output_asm_insn ("vldrb.\t%q0, %E1",ops); + return ""; +} + [(set_attr "length" "4")]) + +;; +;; [vldrwq_gather_base_s vldrwq_gather_base_u] +;; +(define_insn "mve_vldrwq_gather_base_v4si" + [(set (match_operand:V4SI 0 "s_register_operand" "=&w") + (unspec:V4SI [(match_operand:V4SI 1 "s_register_operand" "w") + (match_operand:SI 2 "immediate_operand" "i")] + VLDRWGBQ)) + ] + "TARGET_HAVE_MVE" +{ + rtx ops[3]; + ops[0] = operands[0]; + ops[1] = operands[1]; + ops[2] = operands[2]; + output_asm_insn ("vldrw.u32\t%q0, [%q1, %2]",ops); + return ""; +} + [(set_attr "length" "4")]) diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s16.c new file mode 100644 index 0000000000000000000000000000000000000000..f7763b8a1f668e25c5b34ed429dd5dc9a5455676 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s16.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int16x8_t +foo (int8_t const * base, uint16x8_t offset) +{ + return vldrbq_gather_offset_s16 (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.s16" } } */ + +int16x8_t +foo1 (int8_t const * base, uint16x8_t offset) +{ + return vldrbq_gather_offset (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.s16" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s32.c new file mode 100644 index 0000000000000000000000000000000000000000..768a4325beae64496e174f55932554a961cbc886 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s32.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int32x4_t +foo (int8_t const * base, uint32x4_t offset) +{ + return vldrbq_gather_offset_s32 (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.s32" } } */ + +int32x4_t +foo1 (int8_t const * base, uint32x4_t offset) +{ + return vldrbq_gather_offset (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.s32" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s8.c new file mode 100644 index 0000000000000000000000000000000000000000..4c52b5a009507bf68b6bd83699cd78e85b291572 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_s8.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int8x16_t +foo (int8_t const * base, uint8x16_t offset) +{ + return vldrbq_gather_offset_s8 (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u8" } } */ + +int8x16_t +foo1 (int8_t const * base, uint8x16_t offset) +{ + return vldrbq_gather_offset (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u8" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u16.c new file mode 100644 index 0000000000000000000000000000000000000000..44b310add69aa8e7b74cf2c501013b136d5da041 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u16.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint16x8_t +foo (uint8_t const * base, uint16x8_t offset) +{ + return vldrbq_gather_offset_u16 (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u16" } } */ + +uint16x8_t +foo1 (uint8_t const * base, uint16x8_t offset) +{ + return vldrbq_gather_offset (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u16" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u32.c new file mode 100644 index 0000000000000000000000000000000000000000..8415ea701327b2a296e1e28e37537045b69ff6a9 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u32.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint32x4_t +foo (uint8_t const * base, uint32x4_t offset) +{ + return vldrbq_gather_offset_u32 (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u32" } } */ + +uint32x4_t +foo1 (uint8_t const * base, uint32x4_t offset) +{ + return vldrbq_gather_offset (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u32" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u8.c new file mode 100644 index 0000000000000000000000000000000000000000..9fbe1aa419d572ffad9b319d3ad24d9ac913b7e6 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_gather_offset_u8.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint8x16_t +foo (uint8_t const * base, uint8x16_t offset) +{ + return vldrbq_gather_offset_u8 (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u8" } } */ + +uint8x16_t +foo1 (uint8_t const * base, uint8x16_t offset) +{ + return vldrbq_gather_offset (base, offset); +} + +/* { dg-final { scan-assembler "vldrb.u8" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s16.c new file mode 100644 index 0000000000000000000000000000000000000000..a63c7367e9ae24b78f4819aea95e6e5d0ec85891 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s16.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int16x8_t +foo (int8_t const * base) +{ + return vldrbq_s16 (base); +} + +/* { dg-final { scan-assembler "vldrb.s16" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s32.c new file mode 100644 index 0000000000000000000000000000000000000000..040c58d44c5e6bf09ad61d13c44f53dfd987e8e4 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s32.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int32x4_t +foo (int8_t const * base) +{ + return vldrbq_s32 (base); +} + +/* { dg-final { scan-assembler "vldrb.s32" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s8.c new file mode 100644 index 0000000000000000000000000000000000000000..e5cc3deb79b909a19cbbcafe9213c91b67ac337a --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_s8.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int8x16_t +foo (int8_t const * base) +{ + return vldrbq_s8 (base); +} + +/* { dg-final { scan-assembler "vldrb.s8" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u16.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u16.c new file mode 100644 index 0000000000000000000000000000000000000000..7dedbde6eeae066fdc04e9d6fb6fe626af4580db --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u16.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint16x8_t +foo (uint8_t const * base) +{ + return vldrbq_u16 (base); +} + +/* { dg-final { scan-assembler "vldrb.u16" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u32.c new file mode 100644 index 0000000000000000000000000000000000000000..3c3ec6c4ffe6b014bf58d0b7c2a2d501ddf8301b --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u32.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint32x4_t +foo (uint8_t const * base) +{ + return vldrbq_u32 (base); +} + +/* { dg-final { scan-assembler "vldrb.u32" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u8.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u8.c new file mode 100644 index 0000000000000000000000000000000000000000..5328d99bab94d62bd032d4da3509cd2c55a7841a --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrbq_u8.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint8x16_t +foo (uint8_t const * base) +{ + return vldrbq_u8 (base); +} + +/* { dg-final { scan-assembler "vldrb.u8" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_s32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_s32.c new file mode 100644 index 0000000000000000000000000000000000000000..14831a91b65900d040f74b90c592bc195af42874 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_s32.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +int32x4_t +foo (uint32x4_t addr) +{ + return vldrwq_gather_base_s32 (addr, 4); +} + +/* { dg-final { scan-assembler "vldrw.u32" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_u32.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_u32.c new file mode 100644 index 0000000000000000000000000000000000000000..7753ea6a7c9ec83b90f3e723683c156b20617e23 --- /dev/null +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/vldrwq_gather_base_u32.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-march=armv8.1-m.main+mve -mfloat-abi=hard -O2" } */ +/* { dg-skip-if "Skip if not auto" {*-*-*} {"-mfpu=*"} {"-mfpu=auto"} } */ + +#include "arm_mve.h" + +uint32x4_t +foo (uint32x4_t addr) +{ + return vldrwq_gather_base_u32 (addr, 4); +} + +/* { dg-final { scan-assembler "vldrw.u32" } } */