From patchwork Thu May 18 10:59:12 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Stamatis Markianos-Wright X-Patchwork-Id: 95779 Return-Path: Delivered-To: ouuuleilei@gmail.com Received: by 2002:a59:b0ea:0:b0:3b6:4342:cba0 with SMTP id b10csp403176vqo; Thu, 18 May 2023 04:04:45 -0700 (PDT) X-Google-Smtp-Source: ACHHUZ5U6JU2Jsx6Ym97qZMeg7sgQ42uu7vf9ZI1qgdxpxfp9V3GMdsUG/X2TRWcwdiVc3Tzfm0u X-Received: by 2002:a17:907:5c5:b0:95f:56e8:1c3c with SMTP id wg5-20020a17090705c500b0095f56e81c3cmr41199000ejb.17.1684407885544; Thu, 18 May 2023 04:04:45 -0700 (PDT) Received: from sourceware.org (server2.sourceware.org. [2620:52:3:1:0:246e:9693:128c]) by mx.google.com with ESMTPS id r9-20020a170906a20900b00969f943c8a3si1154538ejy.431.2023.05.18.04.04.44 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 18 May 2023 04:04:45 -0700 (PDT) Received-SPF: pass (google.com: domain of gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org designates 2620:52:3:1:0:246e:9693:128c as permitted sender) client-ip=2620:52:3:1:0:246e:9693:128c; Authentication-Results: mx.google.com; dkim=pass header.i=@gcc.gnu.org header.s=default header.b=nefON0+T; arc=fail (signature failed); spf=pass (google.com: domain of gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org designates 2620:52:3:1:0:246e:9693:128c as permitted sender) smtp.mailfrom="gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org"; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=gnu.org Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id CB31B3894C22 for ; Thu, 18 May 2023 11:01:59 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org CB31B3894C22 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1684407719; bh=+gW9m3SA13vIBdm+64upM0hMHYqy1W9PSNJKoD3WEuo=; h=To:CC:Subject:Date:In-Reply-To:References:List-Id: List-Unsubscribe:List-Archive:List-Post:List-Help:List-Subscribe: From:Reply-To:From; b=nefON0+TualDsOb/cfrWMiG77cPJ9EZYGuO8TFY6Eu0P5vVzFNM45HCfFbKfVfiG1 Xz7Dx1kP67KrPGSPD42eU8F/pTBYVGaXaXc9bRGi+j819TBZUQMpVzFlFoY9NtgN8L D5izjURSNPgq3G3jSH34CD9uvAxFFtwuT64J2cHA= X-Original-To: gcc-patches@gcc.gnu.org Delivered-To: gcc-patches@gcc.gnu.org Received: from EUR04-VI1-obe.outbound.protection.outlook.com (mail-vi1eur04on2089.outbound.protection.outlook.com [40.107.8.89]) by sourceware.org (Postfix) with ESMTPS id BCF8F3889811 for ; Thu, 18 May 2023 11:00:23 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org BCF8F3889811 Received: from DB6PR0601CA0042.eurprd06.prod.outlook.com (2603:10a6:4:17::28) by PAWPR08MB10044.eurprd08.prod.outlook.com (2603:10a6:102:362::16) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.6411.19; Thu, 18 May 2023 10:59:57 +0000 Received: from DBAEUR03FT041.eop-EUR03.prod.protection.outlook.com (2603:10a6:4:17:cafe::28) by DB6PR0601CA0042.outlook.office365.com (2603:10a6:4:17::28) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.6411.17 via Frontend Transport; Thu, 18 May 2023 10:59:57 +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=armh.onmicrosoft.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 DBAEUR03FT041.mail.protection.outlook.com (100.127.142.233) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.6411.19 via Frontend Transport; Thu, 18 May 2023 10:59:57 +0000 Received: ("Tessian outbound 99a3040377ca:v136"); Thu, 18 May 2023 10:59:57 +0000 X-CheckRecipientChecked: true X-CR-MTA-CID: 44bc77309c8bdda4 X-CR-MTA-TID: 64aa7808 Received: from cf304b3c5c61.1 by 64aa7808-outbound-1.mta.getcheckrecipient.com id 51154C51-E7A2-4B58-8034-E2681606F721.1; Thu, 18 May 2023 10:59:51 +0000 Received: from EUR01-HE1-obe.outbound.protection.outlook.com by 64aa7808-outbound-1.mta.getcheckrecipient.com with ESMTPS id cf304b3c5c61.1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384); Thu, 18 May 2023 10:59:51 +0000 ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=bMEq6JZ+OWL4I2UjirY0hswdR48S3lH4Gga7nhnQfTyHnGcekelv8N4xhvV8evG8eD8ZjNZk+hZpEdR+dWojBex1hNLNlrqqUdUvKky51T+OLkPJT/GHb1dLYVUpGrOi8/i27fCOTJ8oUOTMlT5WuAnt7GWb+jMCEh+gJGOmTwMgl+0W9Wg5GanhzzKgMaRivLQ+/IqpxbCPe5MGVO6r6g1yGpRzxInrcQj2nNaTBQSPWol7T38CP2yP5J4yTi/t5jKjhvrLp14fhTQXcghnhEo7z3Gg+RqjLehNXzjvYzP6NY6ArmKXuJ/eJfCBAz3P/h/O+z8gvFaQqNKMnm4nZw== 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=+gW9m3SA13vIBdm+64upM0hMHYqy1W9PSNJKoD3WEuo=; b=Q3ip5qveTndGAXw8V3FU6zMW9jmkkzEl2q8Wlxd1NSznx+jsDIM0gw3DnxdXby534mldKrcZoY+1BhSiqEALqcC/hJ0+yAG5zmqDFHw+Lx2HLCJECzn6vp3efJXwKLQD5POAoeesxG5YUPZcyhE1R5JYkHgIVNQcvzxm373xA7t6bCTAt+xbSE02EX4Dq4kfwtTHZ3fuS5aqdJtxph7rvZZYTi72cG84r5wJ1DNRkdg4vEizq8Pfn1/XMumrx7DcS7Ssv/K3bLW16df2FlCagjMnR9FjsSFNqCkZJxG9Ur9KhrmrN1+bUCQtJkonFxLeoCipNUGlk+/PwLJg/PgiKg== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass (sender ip is 40.67.248.234) smtp.rcpttodomain=gcc.gnu.org smtp.mailfrom=arm.com; dmarc=pass (p=none sp=none pct=100) action=none header.from=arm.com; dkim=none (message not signed); arc=none Received: from AS9PR06CA0320.eurprd06.prod.outlook.com (2603:10a6:20b:45b::33) by AM9PR08MB6180.eurprd08.prod.outlook.com (2603:10a6:20b:2d4::8) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.6411.19; Thu, 18 May 2023 10:59:25 +0000 Received: from AM7EUR03FT003.eop-EUR03.prod.protection.outlook.com (2603:10a6:20b:45b:cafe::80) by AS9PR06CA0320.outlook.office365.com (2603:10a6:20b:45b::33) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.6411.19 via Frontend Transport; Thu, 18 May 2023 10:59:25 +0000 X-MS-Exchange-Authentication-Results: spf=pass (sender IP is 40.67.248.234) smtp.mailfrom=arm.com; dkim=none (message not signed) header.d=none;dmarc=pass action=none header.from=arm.com; Received-SPF: Pass (protection.outlook.com: domain of arm.com designates 40.67.248.234 as permitted sender) receiver=protection.outlook.com; client-ip=40.67.248.234; helo=nebula.arm.com; pr=C Received: from nebula.arm.com (40.67.248.234) by AM7EUR03FT003.mail.protection.outlook.com (100.127.140.227) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.20.6411.19 via Frontend Transport; Thu, 18 May 2023 10:59:25 +0000 Received: from AZ-NEU-EX03.Arm.com (10.251.24.31) by AZ-NEU-EX03.Arm.com (10.251.24.31) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.23; Thu, 18 May 2023 10:59:23 +0000 Received: from e127973.arm.com (10.57.22.31) by mail.arm.com (10.251.24.31) with Microsoft SMTP Server id 15.1.2507.23 via Frontend Transport; Thu, 18 May 2023 10:59:23 +0000 To: CC: , , "Stam Markianos-Wright" Subject: [commited trunk 6/9] arm: Fix MVE header pointer overloads this time (and a bit more tidying) Date: Thu, 18 May 2023 11:59:12 +0100 Message-ID: <20230518105915.1304768-6-stam.markianos-wright@arm.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230518105915.1304768-1-stam.markianos-wright@arm.com> References: <20230518105915.1304768-1-stam.markianos-wright@arm.com> MIME-Version: 1.0 X-EOPAttributedMessage: 1 X-MS-TrafficTypeDiagnostic: AM7EUR03FT003:EE_|AM9PR08MB6180:EE_|DBAEUR03FT041:EE_|PAWPR08MB10044:EE_ X-MS-Office365-Filtering-Correlation-Id: 618a130f-0d6b-4c52-ac96-08db578f04d5 x-checkrecipientrouted: true NoDisclaimer: true X-MS-Exchange-SenderADCheck: 1 X-MS-Exchange-AntiSpam-Relay: 0 X-Microsoft-Antispam-Untrusted: BCL:0; X-Microsoft-Antispam-Message-Info-Original: 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 X-Forefront-Antispam-Report-Untrusted: CIP:40.67.248.234; CTRY:IE; LANG:en; SCL:1; SRV:; IPV:NLI; SFV:NSPM; H:nebula.arm.com; PTR:InfoDomainNonexistent; CAT:NONE; SFS:(13230028)(4636009)(396003)(346002)(136003)(39860400002)(376002)(451199021)(36840700001)(46966006)(40470700004)(186003)(26005)(1076003)(40460700003)(6666004)(7696005)(36756003)(36860700001)(40480700001)(336012)(83380400001)(47076005)(2616005)(426003)(86362001)(82740400003)(82310400005)(81166007)(356005)(478600001)(30864003)(54906003)(5660300002)(4326008)(84970400001)(316002)(41300700001)(6916009)(70206006)(70586007)(8936002)(8676002)(2906002)(36900700001)(559001)(579004)(357404004); DIR:OUT; SFP:1101; X-MS-Exchange-Transport-CrossTenantHeadersStamped: AM9PR08MB6180 X-MS-Exchange-Transport-CrossTenantHeadersStripped: DBAEUR03FT041.eop-EUR03.prod.protection.outlook.com X-MS-PublicTrafficType: Email X-MS-Office365-Filtering-Correlation-Id-Prvs: f5a69cc7-91cd-48c6-7138-08db578ef16d X-Microsoft-Antispam: BCL:0; X-Microsoft-Antispam-Message-Info: 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 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:(13230028)(4636009)(346002)(376002)(136003)(39860400002)(396003)(451199021)(40470700004)(46966006)(36840700001)(1076003)(478600001)(6666004)(84970400001)(47076005)(8676002)(26005)(2906002)(30864003)(7696005)(41300700001)(186003)(6916009)(4326008)(54906003)(70206006)(70586007)(86362001)(2616005)(336012)(426003)(5660300002)(36756003)(8936002)(81166007)(40460700003)(82310400005)(83380400001)(82740400003)(36860700001)(316002)(40480700001)(579004)(559001)(357404004); DIR:OUT; SFP:1101; X-OriginatorOrg: arm.com X-MS-Exchange-CrossTenant-OriginalArrivalTime: 18 May 2023 10:59:57.5952 (UTC) X-MS-Exchange-CrossTenant-Network-Message-Id: 618a130f-0d6b-4c52-ac96-08db578f04d5 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: DBAEUR03FT041.eop-EUR03.prod.protection.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Anonymous X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem X-MS-Exchange-Transport-CrossTenantHeadersStamped: PAWPR08MB10044 X-Spam-Status: No, score=-12.6 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, FORGED_SPF_HELO, GIT_PATCH_0, KAM_DMARC_NONE, KAM_SHORT, RCVD_IN_DNSWL_NONE, RCVD_IN_MSPIKE_H2, SPF_HELO_PASS, SPF_NONE, TXREP, T_SCC_BODY_TEXT_LINE, 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: 2.1.29 Precedence: list List-Id: Gcc-patches mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-Patchwork-Original-From: Stam Markianos-Wright via Gcc-patches From: Stamatis Markianos-Wright Reply-To: Stam Markianos-Wright Errors-To: gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org Sender: "Gcc-patches" X-getmail-retrieved-from-mailbox: =?utf-8?q?INBOX?= X-GMAIL-THRID: =?utf-8?q?1766229683259059929?= X-GMAIL-MSGID: =?utf-8?q?1766229683259059929?= Hi all, Previously we had fixed the overloading of scalar arguments to intrinsics with the introduction of a new `__ARM_mve_coerce3` _ Generic association. This allowed users to give types other than int32_t, e.g. int, short, long, etc., which previously would emit a nonsensical error message from the _Generic. Here I adjust that handling slightly and I am also doing the same thing, but for pointer types: (un)signed char* can be now used instead of (u)int8_t* (un)signed short* can be now used instead of (u)int16_t* (un)signed int* and long* can be now used instead of (u)int32_t* (un)signed long long* can be now used instead of (u)int64_t* __fp16* and _Float16* can be now used instead of float16_t* float* can be now used instead of float32_t* This required me to break down the _coerce_ generics for the specific pointer types. On the scalar types, the change in this patch is minor, renaming the _coerce_ generics and passing all scalars through the `__typeof` for consistency with each-other. No test regressions in the GCC testsuite or CMSIS-NN. gcc/ChangeLog: * config/arm/arm_mve.h: (__ARM_mve_typeid): Add more pointer types. (__ARM_mve_coerce1): Remove. (__ARM_mve_coerce2): Remove. (__ARM_mve_coerce3): Remove. (__ARM_mve_coerce_i_scalar): New. (__ARM_mve_coerce_s8_ptr): New. (__ARM_mve_coerce_u8_ptr): New. (__ARM_mve_coerce_s16_ptr): New. (__ARM_mve_coerce_u16_ptr): New. (__ARM_mve_coerce_s32_ptr): New. (__ARM_mve_coerce_u32_ptr): New. (__ARM_mve_coerce_s64_ptr): New. (__ARM_mve_coerce_u64_ptr): New. (__ARM_mve_coerce_f_scalar): New. (__ARM_mve_coerce_f16_ptr): New. (__ARM_mve_coerce_f32_ptr): New. (__arm_vst4q): Change _coerce_ overloads. (__arm_vbicq): Change _coerce_ overloads. (__arm_vld1q): Change _coerce_ overloads. (__arm_vld1q_z): Change _coerce_ overloads. (__arm_vld2q): Change _coerce_ overloads. (__arm_vld4q): Change _coerce_ overloads. (__arm_vldrhq_gather_offset): Change _coerce_ overloads. (__arm_vldrhq_gather_offset_z): Change _coerce_ overloads. (__arm_vldrhq_gather_shifted_offset): Change _coerce_ overloads. (__arm_vldrhq_gather_shifted_offset_z): Change _coerce_ overloads. (__arm_vldrwq_gather_offset): Change _coerce_ overloads. (__arm_vldrwq_gather_offset_z): Change _coerce_ overloads. (__arm_vldrwq_gather_shifted_offset): Change _coerce_ overloads. (__arm_vldrwq_gather_shifted_offset_z): Change _coerce_ overloads. (__arm_vst1q_p): Change _coerce_ overloads. (__arm_vst2q): Change _coerce_ overloads. (__arm_vst1q): Change _coerce_ overloads. (__arm_vstrhq): Change _coerce_ overloads. (__arm_vstrhq_p): Change _coerce_ overloads. (__arm_vstrhq_scatter_offset_p): Change _coerce_ overloads. (__arm_vstrhq_scatter_offset): Change _coerce_ overloads. (__arm_vstrhq_scatter_shifted_offset_p): Change _coerce_ overloads. (__arm_vstrhq_scatter_shifted_offset): Change _coerce_ overloads. (__arm_vstrwq_p): Change _coerce_ overloads. (__arm_vstrwq): Change _coerce_ overloads. (__arm_vstrwq_scatter_offset): Change _coerce_ overloads. (__arm_vstrwq_scatter_offset_p): Change _coerce_ overloads. (__arm_vstrwq_scatter_shifted_offset): Change _coerce_ overloads. (__arm_vstrwq_scatter_shifted_offset_p): Change _coerce_ overloads. (__arm_vsetq_lane): Change _coerce_ overloads. (__arm_vldrbq_gather_offset): Change _coerce_ overloads. (__arm_vdwdupq_x_u8): Change _coerce_ overloads. (__arm_vdwdupq_x_u16): Change _coerce_ overloads. (__arm_vdwdupq_x_u32): Change _coerce_ overloads. (__arm_viwdupq_x_u8): Change _coerce_ overloads. (__arm_viwdupq_x_u16): Change _coerce_ overloads. (__arm_viwdupq_x_u32): Change _coerce_ overloads. (__arm_vidupq_x_u8): Change _coerce_ overloads. (__arm_vddupq_x_u8): Change _coerce_ overloads. (__arm_vidupq_x_u16): Change _coerce_ overloads. (__arm_vddupq_x_u16): Change _coerce_ overloads. (__arm_vidupq_x_u32): Change _coerce_ overloads. (__arm_vddupq_x_u32): Change _coerce_ overloads. (__arm_vldrdq_gather_offset): Change _coerce_ overloads. (__arm_vldrdq_gather_offset_z): Change _coerce_ overloads. (__arm_vldrdq_gather_shifted_offset): Change _coerce_ overloads. (__arm_vldrdq_gather_shifted_offset_z): Change _coerce_ overloads. (__arm_vldrbq_gather_offset_z): Change _coerce_ overloads. (__arm_vidupq_u16): Change _coerce_ overloads. (__arm_vidupq_u32): Change _coerce_ overloads. (__arm_vidupq_u8): Change _coerce_ overloads. (__arm_vddupq_u16): Change _coerce_ overloads. (__arm_vddupq_u32): Change _coerce_ overloads. (__arm_vddupq_u8): Change _coerce_ overloads. (__arm_viwdupq_m): Change _coerce_ overloads. (__arm_viwdupq_u16): Change _coerce_ overloads. (__arm_viwdupq_u32): Change _coerce_ overloads. (__arm_viwdupq_u8): Change _coerce_ overloads. (__arm_vdwdupq_m): Change _coerce_ overloads. (__arm_vdwdupq_u16): Change _coerce_ overloads. (__arm_vdwdupq_u32): Change _coerce_ overloads. (__arm_vdwdupq_u8): Change _coerce_ overloads. (__arm_vstrbq): Change _coerce_ overloads. (__arm_vstrbq_p): Change _coerce_ overloads. (__arm_vstrbq_scatter_offset_p): Change _coerce_ overloads. (__arm_vstrdq_scatter_offset_p): Change _coerce_ overloads. (__arm_vstrdq_scatter_offset): Change _coerce_ overloads. (__arm_vstrdq_scatter_shifted_offset_p): Change _coerce_ overloads. (__arm_vstrdq_scatter_shifted_offset): Change _coerce_ overloads. gcc/testsuite/ChangeLog: * gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-fp.c: Add testcases. * gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-int.c: Add testcases. --- gcc/config/arm/arm_mve.h | 914 +++++++++--------- .../mve_intrinsic_type_overloads-fp.c | 55 +- .../mve_intrinsic_type_overloads-int.c | 74 +- 3 files changed, 577 insertions(+), 466 deletions(-) diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h index 30cec519791..30485e74cdd 100644 --- a/gcc/config/arm/arm_mve.h +++ b/gcc/config/arm/arm_mve.h @@ -10727,16 +10727,29 @@ enum { short: __ARM_mve_type_int_n, \ int: __ARM_mve_type_int_n, \ long: __ARM_mve_type_int_n, \ + long long: __ARM_mve_type_int_n, \ _Float16: __ARM_mve_type_fp_n, \ __fp16: __ARM_mve_type_fp_n, \ float: __ARM_mve_type_fp_n, \ double: __ARM_mve_type_fp_n, \ - long long: __ARM_mve_type_int_n, \ unsigned char: __ARM_mve_type_int_n, \ unsigned short: __ARM_mve_type_int_n, \ unsigned int: __ARM_mve_type_int_n, \ unsigned long: __ARM_mve_type_int_n, \ unsigned long long: __ARM_mve_type_int_n, \ + signed char*: __ARM_mve_type_int8_t_ptr, \ + short*: __ARM_mve_type_int16_t_ptr, \ + int*: __ARM_mve_type_int32_t_ptr, \ + long*: __ARM_mve_type_int32_t_ptr, \ + long long*: __ARM_mve_type_int64_t_ptr, \ + _Float16*: __ARM_mve_type_float16_t_ptr, \ + __fp16*: __ARM_mve_type_float16_t_ptr, \ + float*: __ARM_mve_type_float32_t_ptr, \ + unsigned char*: __ARM_mve_type_uint8_t_ptr, \ + unsigned short*: __ARM_mve_type_uint16_t_ptr, \ + unsigned int*: __ARM_mve_type_uint32_t_ptr, \ + unsigned long*: __ARM_mve_type_uint32_t_ptr, \ + unsigned long long*: __ARM_mve_type_uint64_t_ptr, \ default: __ARM_mve_unsupported_type)) #else #define __ARM_mve_typeid(x) _Generic(x, \ @@ -10795,32 +10808,67 @@ enum { unsigned int: __ARM_mve_type_int_n, \ unsigned long: __ARM_mve_type_int_n, \ unsigned long long: __ARM_mve_type_int_n, \ + signed char*: __ARM_mve_type_int8_t_ptr, \ + short*: __ARM_mve_type_int16_t_ptr, \ + int*: __ARM_mve_type_int32_t_ptr, \ + long*: __ARM_mve_type_int32_t_ptr, \ + long long*: __ARM_mve_type_int64_t_ptr, \ + unsigned char*: __ARM_mve_type_uint8_t_ptr, \ + unsigned short*: __ARM_mve_type_uint16_t_ptr, \ + unsigned int*: __ARM_mve_type_uint32_t_ptr, \ + unsigned long*: __ARM_mve_type_uint32_t_ptr, \ + unsigned long long*: __ARM_mve_type_uint64_t_ptr, \ default: __ARM_mve_unsupported_type)) #endif /* MVE Floating point. */ extern void *__ARM_undef; #define __ARM_mve_coerce(param, type) \ _Generic(param, type: param, default: *(type *)__ARM_undef) -#define __ARM_mve_coerce1(param, type) \ - _Generic(param, type: param, const type: param, default: *(type *)__ARM_undef) -#define __ARM_mve_coerce2(param, type) \ - _Generic(param, type: param, __fp16: param, default: _Generic (param, _Float16: param, float16_t: param, float32_t: param, default: *(type *)__ARM_undef)) -#define __ARM_mve_coerce3(param, type) \ - _Generic(param, type: param, default: _Generic (param, int8_t: param, int16_t: param, int32_t: param, int64_t: param, uint8_t: param, uint16_t: param, uint32_t: param, uint64_t: param, default: *(type *)__ARM_undef)) +#define __ARM_mve_coerce_i_scalar(param, type) \ + _Generic(param, type: param, const type: param, default: _Generic (param, int8_t: param, int16_t: param, int32_t: param, int64_t: param, uint8_t: param, uint16_t: param, uint32_t: param, uint64_t: param, default: *(type *)__ARM_undef)) + +#define __ARM_mve_coerce_s8_ptr(param, type) \ + _Generic(param, type: param, const type: param, default: _Generic (param, signed char*: param, default: *(type *)__ARM_undef)) +#define __ARM_mve_coerce_u8_ptr(param, type) \ + _Generic(param, type: param, const type: param, default: _Generic (param, unsigned char*: param, default: *(type *)__ARM_undef)) + +#define __ARM_mve_coerce_s16_ptr(param, type) \ + _Generic(param, type: param, const type: param, default: _Generic (param, short*: param, default: *(type *)__ARM_undef)) +#define __ARM_mve_coerce_u16_ptr(param, type) \ + _Generic(param, type: param, const type: param, default: _Generic (param, unsigned short*: param, default: *(type *)__ARM_undef)) + +#define __ARM_mve_coerce_s32_ptr(param, type) \ + _Generic(param, type: param, const type: param, default: _Generic (param, int*: param, long*: param, default: *(type *)__ARM_undef)) +#define __ARM_mve_coerce_u32_ptr(param, type) \ + _Generic(param, type: param, const type: param, default: _Generic (param, unsigned int*: param, unsigned long*: param, default: *(type *)__ARM_undef)) + +#define __ARM_mve_coerce_s64_ptr(param, type) \ + _Generic(param, type: param, const type: param, default: _Generic (param, long long*: param, default: *(type *)__ARM_undef)) +#define __ARM_mve_coerce_u64_ptr(param, type) \ + _Generic(param, type: param, const type: param, default: _Generic (param, unsigned long long*: param, default: *(type *)__ARM_undef)) + +#if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */ +#define __ARM_mve_coerce_f_scalar(param, type) \ + _Generic(param, type: param, const type: param, __fp16: param, default: _Generic (param, _Float16: param, float16_t: param, float32_t: param, default: *(type *)__ARM_undef)) +#define __ARM_mve_coerce_f16_ptr(param, type) \ + _Generic(param, type: param, const type: param, default: _Generic (param, __fp16*: param, _Float16*: param, default: *(type *)__ARM_undef)) +#define __ARM_mve_coerce_f32_ptr(param, type) \ + _Generic(param, type: param, const type: param, default: _Generic (param, float*: param, default: *(type *)__ARM_undef)) +#endif #if (__ARM_FEATURE_MVE & 2) /* MVE Floating point. */ #define __arm_vst4q(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_ptr][__ARM_mve_type_int8x16x4_t]: __arm_vst4q_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x4_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x4_t]: __arm_vst4q_s16 (__ARM_mve_coerce(__p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x4_t)), \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x4_t]: __arm_vst4q_s32 (__ARM_mve_coerce(__p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x4_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x4_t]: __arm_vst4q_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x4_t]: __arm_vst4q_u16 (__ARM_mve_coerce(__p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x4_t)), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x4_t]: __arm_vst4q_u32 (__ARM_mve_coerce(__p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x4_t)), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x4_t]: __arm_vst4q_f16 (__ARM_mve_coerce(__p0, float16_t *), __ARM_mve_coerce(__p1, float16x8x4_t)), \ - int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4x4_t]: __arm_vst4q_f32 (__ARM_mve_coerce(__p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x4_t)));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x4_t]: __arm_vst4q_s8 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x4_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x4_t]: __arm_vst4q_s16 (__ARM_mve_coerce_s16_ptr(__p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x4_t)), \ + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x4_t]: __arm_vst4q_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x4_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x4_t]: __arm_vst4q_u8 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x4_t]: __arm_vst4q_u16 (__ARM_mve_coerce_u16_ptr(__p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x4_t)), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x4_t]: __arm_vst4q_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x4_t)), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x4_t]: __arm_vst4q_f16 (__ARM_mve_coerce_f16_ptr(__p0, float16_t *), __ARM_mve_coerce(__p1, float16x8x4_t)), \ + int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4x4_t]: __arm_vst4q_f32 (__ARM_mve_coerce_f32_ptr(__p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x4_t)));}) #define __arm_vcvtbq_f32(p0) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ @@ -10847,10 +10895,10 @@ extern void *__ARM_undef; #define __arm_vbicq(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_int16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce3 (p1, int)), \ - int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce3 (p1, int)), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce3 (p1, int)), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce3 (p1, int)), \ + int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce_i_scalar (__p1, int)), \ + int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce_i_scalar (__p1, int)), \ + int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_i_scalar (__p1, int)), \ + int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_i_scalar (__p1, int)), \ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vbicq_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vbicq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vbicq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \ @@ -11188,236 +11236,236 @@ extern void *__ARM_undef; #define __arm_vld1q(p0) (\ _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_s8 (__ARM_mve_coerce1(p0, int8_t *)), \ - int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_s16 (__ARM_mve_coerce1(p0, int16_t *)), \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_s32 (__ARM_mve_coerce1(p0, int32_t *)), \ - int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_u8 (__ARM_mve_coerce1(p0, uint8_t *)), \ - int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_u16 (__ARM_mve_coerce1(p0, uint16_t *)), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_u32 (__ARM_mve_coerce1(p0, uint32_t *)), \ - int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld1q_f16 (__ARM_mve_coerce1(p0, float16_t *)), \ - int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld1q_f32 (__ARM_mve_coerce1(p0, float32_t *)))) + int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *)), \ + int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *)), \ + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *)), \ + int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *)), \ + int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *)), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *)), \ + int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld1q_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *)), \ + int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld1q_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *)))) #define __arm_vld1q_z(p0,p1) ( \ _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_z_s8 (__ARM_mve_coerce1(p0, int8_t *), p1), \ - int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_z_s16 (__ARM_mve_coerce1(p0, int16_t *), p1), \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_z_s32 (__ARM_mve_coerce1(p0, int32_t *), p1), \ - int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_z_u8 (__ARM_mve_coerce1(p0, uint8_t *), p1), \ - int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), p1), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_z_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1), \ - int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld1q_z_f16 (__ARM_mve_coerce1(p0, float16_t *), p1), \ - int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld1q_z_f32 (__ARM_mve_coerce1(p0, float32_t *), p1))) + int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_z_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), p1), \ + int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_z_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), p1), \ + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_z_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), p1), \ + int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_z_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), p1), \ + int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_z_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), p1), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_z_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), p1), \ + int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld1q_z_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), p1), \ + int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld1q_z_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), p1))) #define __arm_vld2q(p0) ( \ _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld2q_s8 (__ARM_mve_coerce1(p0, int8_t *)), \ - int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld2q_s16 (__ARM_mve_coerce1(p0, int16_t *)), \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld2q_s32 (__ARM_mve_coerce1(p0, int32_t *)), \ - int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld2q_u8 (__ARM_mve_coerce1(p0, uint8_t *)), \ - int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld2q_u16 (__ARM_mve_coerce1(p0, uint16_t *)), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld2q_u32 (__ARM_mve_coerce1(p0, uint32_t *)), \ - int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld2q_f16 (__ARM_mve_coerce1(p0, float16_t *)), \ - int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld2q_f32 (__ARM_mve_coerce1(p0, float32_t *)))) + int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld2q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *)), \ + int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld2q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *)), \ + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld2q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *)), \ + int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld2q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *)), \ + int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld2q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *)), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld2q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *)), \ + int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld2q_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *)), \ + int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld2q_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *)))) #define __arm_vld4q(p0) ( \ _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld4q_s8 (__ARM_mve_coerce1(p0, int8_t *)), \ - int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld4q_s16 (__ARM_mve_coerce1(p0, int16_t *)), \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld4q_s32 (__ARM_mve_coerce1(p0, int32_t *)), \ - int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld4q_u8 (__ARM_mve_coerce1(p0, uint8_t *)), \ - int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld4q_u16 (__ARM_mve_coerce1(p0, uint16_t *)), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld4q_u32 (__ARM_mve_coerce1(p0, uint32_t *)), \ - int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld4q_f16 (__ARM_mve_coerce1(p0, float16_t *)), \ - int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld4q_f32 (__ARM_mve_coerce1(p0, float32_t *)))) + int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld4q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *)), \ + int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld4q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *)), \ + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld4q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *)), \ + int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld4q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *)), \ + int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld4q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *)), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld4q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *)), \ + int (*)[__ARM_mve_type_float16_t_ptr]: __arm_vld4q_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *)), \ + int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vld4q_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *)))) #define __arm_vldrhq_gather_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_f16 (__ARM_mve_coerce1(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t)));}) #define __arm_vldrhq_gather_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_f16 (__ARM_mve_coerce1(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2));}) #define __arm_vldrhq_gather_shifted_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_f16 (__ARM_mve_coerce1(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t)));}) #define __arm_vldrhq_gather_shifted_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_f16 (__ARM_mve_coerce1(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2));}) #define __arm_vldrwq_gather_offset(p0,p1) ( \ _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce1(p0, int32_t *), p1), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1), \ - int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_f32 (__ARM_mve_coerce1(p0, float32_t *), p1))) + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), p1), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), p1), \ + int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), p1))) #define __arm_vldrwq_gather_offset_z(p0,p1,p2) ( \ _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce1(p0, int32_t *), p1, p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1, p2), \ - int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_z_f32 (__ARM_mve_coerce1(p0, float32_t *), p1, p2))) + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), p1, p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), p1, p2), \ + int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_offset_z_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), p1, p2))) #define __arm_vldrwq_gather_shifted_offset(p0,p1) ( \ _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce1(p0, int32_t *), p1), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1), \ - int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_f32 (__ARM_mve_coerce1(p0, float32_t *), p1))) + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), p1), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), p1), \ + int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), p1))) #define __arm_vldrwq_gather_shifted_offset_z(p0,p1,p2) ( \ _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce1(p0, int32_t *), p1, p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1, p2), \ - int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_f32 (__ARM_mve_coerce1(p0, float32_t *), p1, p2))) + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), p1, p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), p1, p2), \ + int (*)[__ARM_mve_type_float32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), p1, p2))) #define __arm_vst1q_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_p_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_p_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_p_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vst1q_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t), p2), \ - int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vst1q_p_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t), p2));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_p_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \ + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_p_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vst1q_p_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t), p2), \ + int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vst1q_p_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t), p2));}) #define __arm_vst2q(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x2_t]: __arm_vst2q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x2_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x2_t]: __arm_vst2q_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x2_t)), \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x2_t]: __arm_vst2q_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x2_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x2_t]: __arm_vst2q_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x2_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x2_t]: __arm_vst2q_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x2_t)), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x2_t]: __arm_vst2q_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x2_t)), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x2_t]: __arm_vst2q_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8x2_t)), \ - int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4x2_t]: __arm_vst2q_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x2_t)));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x2_t]: __arm_vst2q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x2_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x2_t]: __arm_vst2q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x2_t)), \ + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x2_t]: __arm_vst2q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x2_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x2_t]: __arm_vst2q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x2_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x2_t]: __arm_vst2q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x2_t)), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x2_t]: __arm_vst2q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x2_t)), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8x2_t]: __arm_vst2q_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8x2_t)), \ + int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4x2_t]: __arm_vst2q_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4x2_t)));}) #define __arm_vst1q(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vst1q_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t)), \ - int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vst1q_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t)));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \ + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vst1q_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t)), \ + int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vst1q_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t)));}) #define __arm_vstrhq(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vstrhq_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vstrhq_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t)));}) #define __arm_vstrhq_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vstrhq_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t), p2));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_float16x8_t]: __arm_vstrhq_p_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, float16x8_t), p2));}) #define __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_p_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));}) #define __arm_vstrhq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));}) #define __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));}) #define __arm_vstrhq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));}) #define __arm_vstrwq_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_p_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ - int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_p_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t), p2));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ + int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_p_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t), p2));}) #define __arm_vstrwq(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ - int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_f32 (__ARM_mve_coerce(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t)));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ + int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __ARM_mve_coerce(__p1, float32x4_t)));}) #define __arm_vstrhq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));}) #define __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_offset_p_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));}) #define __arm_vstrhq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t)));}) #define __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \ - int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_f16 (__ARM_mve_coerce(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3), \ + int (*)[__ARM_mve_type_float16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_float16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_f16 (__ARM_mve_coerce_f16_ptr(p0, float16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, float16x8_t), p3));}) #define __arm_vstrwq_scatter_base(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \ @@ -11434,44 +11482,44 @@ extern void *__ARM_undef; #define __arm_vstrwq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_s32 (__ARM_mve_coerce(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t)), \ - int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_offset_f32 (__ARM_mve_coerce(__p0, float32_t *), p1, __ARM_mve_coerce(__p2, float32x4_t)));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t)), \ + int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_offset_f32 (__ARM_mve_coerce_f32_ptr(__p0, float32_t *), p1, __ARM_mve_coerce(__p2, float32x4_t)));}) #define __arm_vstrwq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_p_s32 (__ARM_mve_coerce(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_p_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \ - int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_offset_p_f32 (__ARM_mve_coerce(__p0, float32_t *), p1, __ARM_mve_coerce(__p2, float32x4_t), p3));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_p_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_p_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \ + int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_offset_p_f32 (__ARM_mve_coerce_f32_ptr(__p0, float32_t *), p1, __ARM_mve_coerce(__p2, float32x4_t), p3));}) #define __arm_vstrwq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)), \ - int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t)));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)), \ + int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t)));}) #define __arm_vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \ - int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t), p3));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \ + int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t), p3));}) #define __arm_vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \ - int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t), p3));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3), \ + int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t), p3));}) #define __arm_vstrwq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)), \ - int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_f32 (__ARM_mve_coerce(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t)));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)), \ + int (*)[__ARM_mve_type_float32_t_ptr][__ARM_mve_type_float32x4_t]: __arm_vstrwq_scatter_shifted_offset_f32 (__ARM_mve_coerce_f32_ptr(p0, float32_t *), __p1, __ARM_mve_coerce(__p2, float32x4_t)));}) #define __arm_vuninitializedq(p0) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ @@ -11600,16 +11648,16 @@ extern void *__ARM_undef; #define __arm_vsetq_lane(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int8x16_t]: __arm_vsetq_lane_s8 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int8x16_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t]: __arm_vsetq_lane_s16 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int16x8_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vsetq_lane_s32 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int32x4_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int64x2_t]: __arm_vsetq_lane_s64 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int64x2_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint8x16_t]: __arm_vsetq_lane_u8 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vsetq_lane_u16 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vsetq_lane_u32 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint64x2_t]: __arm_vsetq_lane_u64 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint64x2_t), p2), \ - int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vsetq_lane_f16 (__ARM_mve_coerce2(p0, double), __ARM_mve_coerce(__p1, float16x8_t), p2), \ - int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vsetq_lane_f32 (__ARM_mve_coerce2(p0, double), __ARM_mve_coerce(__p1, float32x4_t), p2));}) + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int8x16_t]: __arm_vsetq_lane_s8 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int8x16_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t]: __arm_vsetq_lane_s16 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int16x8_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vsetq_lane_s32 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int32x4_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int64x2_t]: __arm_vsetq_lane_s64 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int64x2_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint8x16_t]: __arm_vsetq_lane_u8 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vsetq_lane_u16 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vsetq_lane_u32 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint64x2_t]: __arm_vsetq_lane_u64 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint64x2_t), p2), \ + int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float16x8_t]: __arm_vsetq_lane_f16 (__ARM_mve_coerce_f_scalar(__p0, double), __ARM_mve_coerce(__p1, float16x8_t), p2), \ + int (*)[__ARM_mve_type_fp_n][__ARM_mve_type_float32x4_t]: __arm_vsetq_lane_f32 (__ARM_mve_coerce_f_scalar(__p0, double), __ARM_mve_coerce(__p1, float32x4_t), p2));}) #else /* MVE Integer. */ @@ -11625,12 +11673,12 @@ extern void *__ARM_undef; #define __arm_vst4q(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x4_t]: __arm_vst4q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x4_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x4_t]: __arm_vst4q_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x4_t)), \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x4_t]: __arm_vst4q_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x4_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x4_t]: __arm_vst4q_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x4_t]: __arm_vst4q_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x4_t)), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x4_t]: __arm_vst4q_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x4_t)));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x4_t]: __arm_vst4q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x4_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x4_t]: __arm_vst4q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x4_t)), \ + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x4_t]: __arm_vst4q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x4_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x4_t]: __arm_vst4q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x4_t]: __arm_vst4q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x4_t)), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x4_t]: __arm_vst4q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x4_t)));}) #define __arm_vornq(p0,p1) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ @@ -11699,10 +11747,10 @@ extern void *__ARM_undef; #define __arm_vbicq(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_int16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce3 (p1, int)), \ - int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce3 (p1, int)), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce3 (p1, int)), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce3 (p1, int)), \ + int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce_i_scalar (__p1, int)), \ + int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce_i_scalar (__p1, int)), \ + int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_i_scalar (__p1, int)), \ + int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vbicq_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_i_scalar (__p1, int)), \ int (*)[__ARM_mve_type_int8x16_t][__ARM_mve_type_int8x16_t]: __arm_vbicq_s8 (__ARM_mve_coerce(__p0, int8x16_t), __ARM_mve_coerce(__p1, int8x16_t)), \ int (*)[__ARM_mve_type_int16x8_t][__ARM_mve_type_int16x8_t]: __arm_vbicq_s16 (__ARM_mve_coerce(__p0, int16x8_t), __ARM_mve_coerce(__p1, int16x8_t)), \ int (*)[__ARM_mve_type_int32x4_t][__ARM_mve_type_int32x4_t]: __arm_vbicq_s32 (__ARM_mve_coerce(__p0, int32x4_t), __ARM_mve_coerce(__p1, int32x4_t)), \ @@ -11789,12 +11837,12 @@ extern void *__ARM_undef; #define __arm_vldrbq_gather_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_s8 (__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_s16 (__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_s32 (__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_u8 (__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_u16 (__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_u32 (__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_s16 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_s32 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_u16 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_u32 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) #define __arm_vstrwq_scatter_base_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \ @@ -11803,144 +11851,144 @@ extern void *__ARM_undef; #define __arm_vld1q(p0) (\ _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_s8 (__ARM_mve_coerce1(p0, int8_t *)), \ - int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_s16 (__ARM_mve_coerce1(p0, int16_t *)), \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_s32 (__ARM_mve_coerce1(p0, int32_t *)), \ - int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_u8 (__ARM_mve_coerce1(p0, uint8_t *)), \ - int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_u16 (__ARM_mve_coerce1(p0, uint16_t *)), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_u32 (__ARM_mve_coerce1(p0, uint32_t *)))) + int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *)), \ + int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *)), \ + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *)), \ + int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *)), \ + int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *)), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *)))) #define __arm_vldrhq_gather_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) #define __arm_vldrhq_gather_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_offset_z_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_offset_z_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) #define __arm_vldrhq_gather_shifted_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) #define __arm_vldrhq_gather_shifted_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_s32 (__ARM_mve_coerce1(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce1(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrhq_gather_shifted_offset_z_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrhq_gather_shifted_offset_z_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) #define __arm_vldrwq_gather_offset(p0,p1) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce1(__p0, int32_t *), p1), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce1(__p0, uint32_t *), p1));}) + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));}) #define __arm_vldrwq_gather_offset_z(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce1(__p0, int32_t *), p1, p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce1(__p0, uint32_t *), p1, p2));}) + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_offset_z_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1, p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_offset_z_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));}) #define __arm_vldrwq_gather_shifted_offset(p0,p1) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce1(__p0, int32_t *), p1), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce1(__p0, uint32_t *), p1));}) + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));}) #define __arm_vldrwq_gather_shifted_offset_z(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce1(__p0, int32_t *), p1, p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce1(__p0, uint32_t *), p1, p2));}) + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1, p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vldrwq_gather_shifted_offset_z_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));}) #define __arm_vst1q(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \ + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) #define __arm_vst1q_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_p_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_p_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_p_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vst1q_p_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vst1q_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \ + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vst1q_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vst1q_p_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vst1q_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vst1q_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) #define __arm_vst2q(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x2_t]: __arm_vst2q_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x2_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x2_t]: __arm_vst2q_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x2_t)), \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x2_t]: __arm_vst2q_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x2_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x2_t]: __arm_vst2q_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x2_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x2_t]: __arm_vst2q_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x2_t)), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x2_t]: __arm_vst2q_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x2_t)));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16x2_t]: __arm_vst2q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16x2_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8x2_t]: __arm_vst2q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8x2_t)), \ + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4x2_t]: __arm_vst2q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4x2_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16x2_t]: __arm_vst2q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16x2_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8x2_t]: __arm_vst2q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8x2_t)), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4x2_t]: __arm_vst2q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4x2_t)));}) #define __arm_vstrhq(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) #define __arm_vstrhq_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrhq_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrhq_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) #define __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) #define __arm_vstrhq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));}) #define __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) #define __arm_vstrhq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));}) #define __arm_vstrwq(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) #define __arm_vstrwq_p(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_p_s32 (__ARM_mve_coerce(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) #define __arm_vstrdq_scatter_base_p(p0,p1,p2,p3) ({ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \ @@ -11955,58 +12003,58 @@ extern void *__ARM_undef; #define __arm_vstrhq_scatter_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));}) #define __arm_vstrhq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) #define __arm_vstrhq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));}) #define __arm_vstrhq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ - int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ - int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ + int (*)[__ARM_mve_type_int16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrhq_scatter_shifted_offset_p_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ + int (*)[__ARM_mve_type_uint16_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrhq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) #define __arm_vstrwq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_s32 (__ARM_mve_coerce(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t)));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t)));}) #define __arm_vstrwq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_p_s32 (__ARM_mve_coerce(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_p_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t), p3));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_offset_p_s32 (__ARM_mve_coerce_s32_ptr(__p0, int32_t *), p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_offset_p_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, __ARM_mve_coerce(__p2, uint32x4_t), p3));}) #define __arm_vstrwq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t)));}) #define __arm_vstrwq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3));}) + int (*)[__ARM_mve_type_int32_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), __p1, __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint32_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrwq_scatter_shifted_offset_p_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), __p1, __ARM_mve_coerce(__p2, uint32x4_t), p3));}) #define __arm_vuninitializedq(p0) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ @@ -12092,29 +12140,29 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vbicq_x_u32 (__ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) #define __arm_vld1q_z(p0,p1) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_z_s8 (__ARM_mve_coerce1(p0, int8_t *), p1), \ - int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_z_s16 (__ARM_mve_coerce1(p0, int16_t *), p1), \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_z_s32 (__ARM_mve_coerce1(p0, int32_t *), p1), \ - int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_z_u8 (__ARM_mve_coerce1(p0, uint8_t *), p1), \ - int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_z_u16 (__ARM_mve_coerce1(p0, uint16_t *), p1), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_z_u32 (__ARM_mve_coerce1(p0, uint32_t *), p1))) + int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld1q_z_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), p1), \ + int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld1q_z_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *), p1), \ + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld1q_z_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *), p1), \ + int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld1q_z_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), p1), \ + int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld1q_z_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *), p1), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld1q_z_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *), p1))) #define __arm_vld2q(p0) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld2q_s8 (__ARM_mve_coerce1(p0, int8_t *)), \ - int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld2q_s16 (__ARM_mve_coerce1(p0, int16_t *)), \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld2q_s32 (__ARM_mve_coerce1(p0, int32_t *)), \ - int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld2q_u8 (__ARM_mve_coerce1(p0, uint8_t *)), \ - int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld2q_u16 (__ARM_mve_coerce1(p0, uint16_t *)), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld2q_u32 (__ARM_mve_coerce1(p0, uint32_t *)))) + int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld2q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *)), \ + int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld2q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *)), \ + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld2q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *)), \ + int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld2q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *)), \ + int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld2q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *)), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld2q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *)))) #define __arm_vld4q(p0) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld4q_s8 (__ARM_mve_coerce1(p0, int8_t *)), \ - int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld4q_s16 (__ARM_mve_coerce1(p0, int16_t *)), \ - int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld4q_s32 (__ARM_mve_coerce1(p0, int32_t *)), \ - int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld4q_u8 (__ARM_mve_coerce1(p0, uint8_t *)), \ - int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld4q_u16 (__ARM_mve_coerce1(p0, uint16_t *)), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld4q_u32 (__ARM_mve_coerce1(p0, uint32_t *)))) + int (*)[__ARM_mve_type_int8_t_ptr]: __arm_vld4q_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *)), \ + int (*)[__ARM_mve_type_int16_t_ptr]: __arm_vld4q_s16 (__ARM_mve_coerce_s16_ptr(p0, int16_t *)), \ + int (*)[__ARM_mve_type_int32_t_ptr]: __arm_vld4q_s32 (__ARM_mve_coerce_s32_ptr(p0, int32_t *)), \ + int (*)[__ARM_mve_type_uint8_t_ptr]: __arm_vld4q_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *)), \ + int (*)[__ARM_mve_type_uint16_t_ptr]: __arm_vld4q_u16 (__ARM_mve_coerce_u16_ptr(p0, uint16_t *)), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vld4q_u32 (__ARM_mve_coerce_u32_ptr(p0, uint32_t *)))) #define __arm_vgetq_lane(p0,p1) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ @@ -12130,14 +12178,14 @@ extern void *__ARM_undef; #define __arm_vsetq_lane(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int8x16_t]: __arm_vsetq_lane_s8 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int8x16_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t]: __arm_vsetq_lane_s16 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int16x8_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vsetq_lane_s32 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int32x4_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int64x2_t]: __arm_vsetq_lane_s64 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, int64x2_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint8x16_t]: __arm_vsetq_lane_u8 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vsetq_lane_u16 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vsetq_lane_u32 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ - int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint64x2_t]: __arm_vsetq_lane_u64 (__ARM_mve_coerce3(p0, int), __ARM_mve_coerce(__p1, uint64x2_t), p2));}) + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int8x16_t]: __arm_vsetq_lane_s8 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int8x16_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int16x8_t]: __arm_vsetq_lane_s16 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int16x8_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int32x4_t]: __arm_vsetq_lane_s32 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int32x4_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_int64x2_t]: __arm_vsetq_lane_s64 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, int64x2_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint8x16_t]: __arm_vsetq_lane_u8 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint16x8_t]: __arm_vsetq_lane_u16 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint32x4_t]: __arm_vsetq_lane_u32 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ + int (*)[__ARM_mve_type_int_n][__ARM_mve_type_uint64x2_t]: __arm_vsetq_lane_u64 (__ARM_mve_coerce_i_scalar(__p0, int), __ARM_mve_coerce(__p1, uint64x2_t), p2));}) #endif /* MVE Integer. */ @@ -12146,62 +12194,62 @@ extern void *__ARM_undef; #define __arm_vdwdupq_x_u8(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u8 ((uint32_t) __p1, p2, p3, p4), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u8 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));}) #define __arm_vdwdupq_x_u16(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u16 ((uint32_t) __p1, p2, p3, p4), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u16 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));}) #define __arm_vdwdupq_x_u32(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_x_n_u32 ((uint32_t) __p1, p2, p3, p4), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_x_wb_u32 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));}) #define __arm_viwdupq_x_u8(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u8 ((uint32_t) __p1, p2, p3, p4), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u8 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));}) #define __arm_viwdupq_x_u16(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u16 ((uint32_t) __p1, p2, p3, p4), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u16 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));}) #define __arm_viwdupq_x_u32(p1,p2,p3,p4) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_x_n_u32 ((uint32_t) __p1, p2, p3, p4), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_x_wb_u32 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));}) #define __arm_vidupq_x_u8(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u8 ((uint32_t) __p1, p2, p3), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u8 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));}) #define __arm_vddupq_x_u8(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u8 ((uint32_t) __p1, p2, p3), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u8 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u8 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));}) #define __arm_vidupq_x_u16(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u16 ((uint32_t) __p1, p2, p3), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u16 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));}) #define __arm_vddupq_x_u16(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u16 ((uint32_t) __p1, p2, p3), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u16 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u16 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));}) #define __arm_vidupq_x_u32(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vidupq_x_n_u32 ((uint32_t) __p1, p2, p3), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_x_wb_u32 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));}) #define __arm_vddupq_x_u32(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p1)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vddupq_x_n_u32 ((uint32_t) __p1, p2, p3), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u32 (__ARM_mve_coerce(__p1, uint32_t *), p2, p3));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_x_wb_u32 (__ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));}) #define __arm_vhcaddq_rot270_x(p1,p2,p3) ({ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ @@ -12234,20 +12282,20 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_base_wb_u64 (p0, p1, __ARM_mve_coerce(__p2, uint64x2_t)));}) #define __arm_vldrdq_gather_offset(p0,p1) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_s64 (__ARM_mve_coerce1(p0, int64_t *), p1), \ - int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_u64 (__ARM_mve_coerce1(p0, uint64_t *), p1))) + int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_s64 (__ARM_mve_coerce_s64_ptr(p0, int64_t *), p1), \ + int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_u64 (__ARM_mve_coerce_u64_ptr(p0, uint64_t *), p1))) #define __arm_vldrdq_gather_offset_z(p0,p1,p2) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_z_s64 (__ARM_mve_coerce1(p0, int64_t *), p1, p2), \ - int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_z_u64 (__ARM_mve_coerce1(p0, uint64_t *), p1, p2))) + int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_offset_z_s64 (__ARM_mve_coerce_s64_ptr(p0, int64_t *), p1, p2), \ + int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_offset_z_u64 (__ARM_mve_coerce_u64_ptr(p0, uint64_t *), p1, p2))) #define __arm_vldrdq_gather_shifted_offset(p0,p1) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_s64 (__ARM_mve_coerce1(p0, int64_t *), p1), \ - int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_u64 (__ARM_mve_coerce1(p0, uint64_t *), p1))) + int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_s64 (__ARM_mve_coerce_s64_ptr(p0, int64_t *), p1), \ + int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_u64 (__ARM_mve_coerce_u64_ptr(p0, uint64_t *), p1))) #define __arm_vldrdq_gather_shifted_offset_z(p0,p1,p2) ( _Generic( (int (*)[__ARM_mve_typeid(p0)])0, \ - int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_s64 (__ARM_mve_coerce1(p0, int64_t *), p1, p2), \ - int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_u64 (__ARM_mve_coerce1(p0, uint64_t *), p1, p2))) + int (*)[__ARM_mve_type_int64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_s64 (__ARM_mve_coerce_s64_ptr(p0, int64_t *), p1, p2), \ + int (*)[__ARM_mve_type_uint64_t_ptr]: __arm_vldrdq_gather_shifted_offset_z_u64 (__ARM_mve_coerce_u64_ptr(p0, uint64_t *), p1, p2))) #define __arm_vadciq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ @@ -12303,12 +12351,12 @@ extern void *__ARM_undef; #define __arm_vldrbq_gather_offset_z(p0,p1,p2) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_z_s8 (__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_z_s16 (__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_z_s32 (__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_z_u8 (__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_z_u16 (__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_z_u32 (__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_z_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_z_s16 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_z_s32 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_z_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_z_u16 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_z_u32 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) #define __arm_vhcaddq_rot270_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ @@ -12364,12 +12412,12 @@ extern void *__ARM_undef; #define __arm_vldrbq_gather_offset(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_s8(__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_s16(__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_s32(__ARM_mve_coerce1(p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_u8(__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_u16(__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_u32(__ARM_mve_coerce1(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_s8(__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_s16(__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_s32(__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vldrbq_gather_offset_u8(__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vldrbq_gather_offset_u16(__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vldrbq_gather_offset_u32(__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) #define __arm_vidupq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ @@ -12377,9 +12425,9 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vidupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), (uint32_t) __p1, p2, p3), \ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vidupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), (uint32_t) __p1, p2, p3), \ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vidupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), (uint32_t) __p1, p2, p3), \ - int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3));}) + int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3), \ + int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3), \ + int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));}) #define __arm_vddupq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ @@ -12387,89 +12435,89 @@ extern void *__ARM_undef; int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vddupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), (uint32_t) __p1, p2, p3), \ int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vddupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), (uint32_t) __p1, p2, p3), \ int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vddupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), (uint32_t) __p1, p2, p3), \ - int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3));}) + int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3), \ + int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3), \ + int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3));}) #define __arm_vidupq_u16(p0,p1) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u16 ((uint32_t) __p0, p1), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u16 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));}) #define __arm_vidupq_u32(p0,p1) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u32 ((uint32_t) __p0, p1), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));}) #define __arm_vidupq_u8(p0,p1) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vidupq_n_u8 ((uint32_t) __p0, p1), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vidupq_wb_u8 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));}) #define __arm_vddupq_u16(p0,p1) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u16 ((uint32_t) __p0, p1), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u16 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));}) #define __arm_vddupq_u32(p0,p1) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u32 ((uint32_t) __p0, p1), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));}) #define __arm_vddupq_u8(p0,p1) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ int (*)[__ARM_mve_type_int_n]: __arm_vddupq_n_u8 ((uint32_t) __p0, p1), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1));}) + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vddupq_wb_u8 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1));}) #define __arm_viwdupq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_viwdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce3(p1, int), p2, p3, p4), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_viwdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce3(p1, int), p2, p3, p4), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_viwdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce3(p1, int), p2, p3, p4), \ - int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));}) + int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_viwdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce_i_scalar(__p1, int), p2, p3, p4), \ + int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_viwdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_i_scalar(__p1, int), p2, p3, p4), \ + int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_viwdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_i_scalar(__p1, int), p2, p3, p4), \ + int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4), \ + int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4), \ + int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));}) #define __arm_viwdupq_u16(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ - int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u16 (__ARM_mve_coerce3(p0, int), p1, (const int) p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1, (const int) p2));}) + int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u16 (__ARM_mve_coerce_i_scalar(__p0, int), p1, (const int) p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u16 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, (const int) p2));}) #define __arm_viwdupq_u32(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ - int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u32 (__ARM_mve_coerce3(p0, int), p1, p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));}) + int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u32 (__ARM_mve_coerce_i_scalar(__p0, int), p1, p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));}) #define __arm_viwdupq_u8(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ - int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u8 (__ARM_mve_coerce3(p0, int), p1, p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));}) + int (*)[__ARM_mve_type_int_n]: __arm_viwdupq_n_u8 (__ARM_mve_coerce_i_scalar(__p0, int), p1, p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_viwdupq_wb_u8 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));}) #define __arm_vdwdupq_m(p0,p1,p2,p3,p4) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vdwdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce3(p1, int), p2, p3, p4), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vdwdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce3(p1, int), p2, p3, p4), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vdwdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce3(p1, int), p2, p3, p4), \ - int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4), \ - int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4), \ - int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce(__p1, uint32_t *), p2, p3, p4));}) + int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_int_n]: __arm_vdwdupq_m_n_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce_i_scalar(__p1, int), p2, p3, p4), \ + int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_int_n]: __arm_vdwdupq_m_n_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_i_scalar(__p1, int), p2, p3, p4), \ + int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_int_n]: __arm_vdwdupq_m_n_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_i_scalar(__p1, int), p2, p3, p4), \ + int (*)[__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u8 (__ARM_mve_coerce(__p0, uint8x16_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4), \ + int (*)[__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u16 (__ARM_mve_coerce(__p0, uint16x8_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4), \ + int (*)[__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_m_wb_u32 (__ARM_mve_coerce(__p0, uint32x4_t), __ARM_mve_coerce_u32_ptr(__p1, uint32_t *), p2, p3, p4));}) #define __arm_vdwdupq_u16(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ - int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u16 (__ARM_mve_coerce3(p0, int), p1, p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u16 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));}) + int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u16 (__ARM_mve_coerce_i_scalar(__p0, int), p1, p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u16 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));}) #define __arm_vdwdupq_u32(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ - int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u32 (__ARM_mve_coerce3(p0, int), p1, p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u32 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));}) + int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u32 (__ARM_mve_coerce_i_scalar(__p0, int), p1, p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u32 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));}) #define __arm_vdwdupq_u8(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ - int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u8 (__ARM_mve_coerce3(p0, int), p1, p2), \ - int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u8 (__ARM_mve_coerce(__p0, uint32_t *), p1, p2));}) + int (*)[__ARM_mve_type_int_n]: __arm_vdwdupq_n_u8 (__ARM_mve_coerce_i_scalar(__p0, int), p1, p2), \ + int (*)[__ARM_mve_type_uint32_t_ptr]: __arm_vdwdupq_wb_u8 (__ARM_mve_coerce_u32_ptr(__p0, uint32_t *), p1, p2));}) #define __arm_vshlcq_m(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)])0, \ @@ -12514,22 +12562,22 @@ extern void *__ARM_undef; #define __arm_vstrbq(p0,p1) ({ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(p0)][__ARM_mve_typeid(__p1)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vstrbq_s8 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrbq_s16 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int16x8_t)), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrbq_s32 (__ARM_mve_coerce(p0, int8_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_u8 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_u16 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_u32 (__ARM_mve_coerce(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vstrbq_s8 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t)), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrbq_s16 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int16x8_t)), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrbq_s32 (__ARM_mve_coerce_s8_ptr(p0, int8_t *), __ARM_mve_coerce(__p1, int32x4_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_u8 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_u16 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_u32 (__ARM_mve_coerce_u8_ptr(p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t)));}) #define __arm_vstrbq_p(p0,p1,p2) ({ __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_ptr][__ARM_mve_type_int8x16_t]: __arm_vstrbq_p_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrbq_p_s16 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrbq_p_s32 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_p_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_p_u16 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_p_u32 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int8x16_t]: __arm_vstrbq_p_s8 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, int8x16_t), p2), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int16x8_t]: __arm_vstrbq_p_s16 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, int16x8_t), p2), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_int32x4_t]: __arm_vstrbq_p_s32 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, int32x4_t), p2), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_p_u8 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), p2), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_p_u16 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), p2), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_p_u32 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), p2));}) #define __arm_vstrdq_scatter_base(p0,p1,p2) ({ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p2)])0, \ @@ -12545,47 +12593,47 @@ extern void *__ARM_undef; __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vstrbq_scatter_offset_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrbq_scatter_offset_s16 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrbq_scatter_offset_s32 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_scatter_offset_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_scatter_offset_u16 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_scatter_offset_u32 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vstrbq_scatter_offset_s8 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, int8x16_t)), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrbq_scatter_offset_s16 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t)), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrbq_scatter_offset_s32 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_scatter_offset_u8 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_scatter_offset_u16 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t)), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_scatter_offset_u32 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t)));}) #define __arm_vstrbq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vstrbq_scatter_offset_p_s8 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrbq_scatter_offset_p_s16 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ - int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrbq_scatter_offset_p_s32 (__ARM_mve_coerce(__p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_scatter_offset_p_u8 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_scatter_offset_p_u16 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ - int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_scatter_offset_p_u32 (__ARM_mve_coerce(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_int8x16_t]: __arm_vstrbq_scatter_offset_p_s8 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, int8x16_t), p3), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_int16x8_t]: __arm_vstrbq_scatter_offset_p_s16 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, int16x8_t), p3), \ + int (*)[__ARM_mve_type_int8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_int32x4_t]: __arm_vstrbq_scatter_offset_p_s32 (__ARM_mve_coerce_s8_ptr(__p0, int8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, int32x4_t), p3), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint8x16_t][__ARM_mve_type_uint8x16_t]: __arm_vstrbq_scatter_offset_p_u8 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint8x16_t), __ARM_mve_coerce(__p2, uint8x16_t), p3), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint16x8_t][__ARM_mve_type_uint16x8_t]: __arm_vstrbq_scatter_offset_p_u16 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint16x8_t), __ARM_mve_coerce(__p2, uint16x8_t), p3), \ + int (*)[__ARM_mve_type_uint8_t_ptr][__ARM_mve_type_uint32x4_t][__ARM_mve_type_uint32x4_t]: __arm_vstrbq_scatter_offset_p_u32 (__ARM_mve_coerce_u8_ptr(__p0, uint8_t *), __ARM_mve_coerce(__p1, uint32x4_t), __ARM_mve_coerce(__p2, uint32x4_t), p3));}) #define __arm_vstrdq_scatter_offset_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_offset_p_s64 (__ARM_mve_coerce(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \ - int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_offset_p_u64 (__ARM_mve_coerce(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));}) + int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_offset_p_s64 (__ARM_mve_coerce_s64_ptr(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \ + int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_offset_p_u64 (__ARM_mve_coerce_u64_ptr(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));}) #define __arm_vstrdq_scatter_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_offset_s64 (__ARM_mve_coerce(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t)), \ - int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_offset_u64 (__ARM_mve_coerce(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t)));}) + int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_offset_s64 (__ARM_mve_coerce_s64_ptr(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t)), \ + int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_offset_u64 (__ARM_mve_coerce_u64_ptr(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t)));}) #define __arm_vstrdq_scatter_shifted_offset_p(p0,p1,p2,p3) ({ __typeof(p0) __p0 = (p0); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_shifted_offset_p_s64 (__ARM_mve_coerce(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \ - int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_shifted_offset_p_u64 (__ARM_mve_coerce(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));}) + int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_shifted_offset_p_s64 (__ARM_mve_coerce_s64_ptr(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t), p3), \ + int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_shifted_offset_p_u64 (__ARM_mve_coerce_u64_ptr(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t), p3));}) #define __arm_vstrdq_scatter_shifted_offset(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ __typeof(p2) __p2 = (p2); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p2)])0, \ - int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_shifted_offset_s64 (__ARM_mve_coerce(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t)), \ - int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_shifted_offset_u64 (__ARM_mve_coerce(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t)));}) + int (*)[__ARM_mve_type_int64_t_ptr][__ARM_mve_type_int64x2_t]: __arm_vstrdq_scatter_shifted_offset_s64 (__ARM_mve_coerce_s64_ptr(__p0, int64_t *), p1, __ARM_mve_coerce(__p2, int64x2_t)), \ + int (*)[__ARM_mve_type_uint64_t_ptr][__ARM_mve_type_uint64x2_t]: __arm_vstrdq_scatter_shifted_offset_u64 (__ARM_mve_coerce_u64_ptr(__p0, uint64_t *), p1, __ARM_mve_coerce(__p2, uint64x2_t)));}) #endif /* __cplusplus */ #endif /* __ARM_FEATURE_MVE */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-fp.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-fp.c index a2787a47859..a1e786ecd9f 100644 --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-fp.c +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-fp.c @@ -1,6 +1,7 @@ /* { dg-require-effective-target arm_v8_1m_mve_fp_ok } */ /* { dg-add-options arm_v8_1m_mve_fp } */ -/* { dg-additional-options "-O2 -Wno-pedantic -Wno-long-long" } */ +/* { dg-additional-options "-O2 -Wno-pedantic -Wno-long-long -Wno-incompatible-pointer-types" { target c } } */ +/* { dg-additional-options "-O2 -Wno-pedantic -Wno-long-long -fpermissive" { target c++ } } */ #include "arm_mve.h" float f1; @@ -10,35 +11,14 @@ float32_t f4; __fp16 f5; _Float16 f6; -int i1; -short i2; -long i3; -long long i4; -int8_t i5; -int16_t i6; -int32_t i7; -int64_t i8; - float16x8_t floatvec; -int16x8_t intvec; -void test(void) +/* Test a few different supported ways of passing a scalar int value. +The intrinsic vmulq was chosen arbitrarily, but it is representative of +all intrinsics that take a non-const scalar value. */ +void +test_scalars (void) { - /* Test a few different supported ways of passing an int value. The - intrinsic vmulq was chosen arbitrarily, but it is representative of - all intrinsics that take a non-const scalar value. */ - intvec = vmulq(intvec, 2); - intvec = vmulq(intvec, (int32_t) 2); - intvec = vmulq(intvec, (short) 2); - intvec = vmulq(intvec, i1); - intvec = vmulq(intvec, i2); - intvec = vmulq(intvec, i3); - intvec = vmulq(intvec, i4); - intvec = vmulq(intvec, i5); - intvec = vmulq(intvec, i6); - intvec = vmulq(intvec, i7); - intvec = vmulq(intvec, i8); - /* Test a few different supported ways of passing a float value. */ floatvec = vmulq(floatvec, 0.5); floatvec = vmulq(floatvec, 0.5f); @@ -53,4 +33,25 @@ void test(void) floatvec = vmulq(floatvec, (_Float16) 0.15); } +/* Next, test a number of valid pointer overloads. */ +void +foo11 (__fp16 * addr, float16x8_t value) +{ + vst1q (addr, value); +} + +#ifndef __cplusplus +void +foo12 (_Float16 * addr, float16x8_t value) +{ + vst1q (addr, value); +} +#endif + +void +foo13 (float * addr, float32x4_t value) +{ + vst1q (addr, value); +} + /* { dg-final { scan-assembler-not "__ARM_undef" } } */ diff --git a/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-int.c b/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-int.c index 7b88f462e17..7947dc024bc 100644 --- a/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-int.c +++ b/gcc/testsuite/gcc.target/arm/mve/intrinsics/mve_intrinsic_type_overloads-int.c @@ -1,7 +1,7 @@ /* { dg-require-effective-target arm_v8_1m_mve_ok } */ /* { dg-add-options arm_v8_1m_mve } */ -/* { dg-additional-options "-O2 -Wno-pedantic -Wno-long-long" } */ - +/* { dg-additional-options "-O2 -Wno-pedantic -Wno-long-long -Wno-incompatible-pointer-types" { target c } } */ +/* { dg-additional-options "-O2 -Wno-pedantic -Wno-long-long -fpermissive" { target c++ } } */ #include "arm_mve.h" int i1; @@ -15,11 +15,12 @@ int64_t i8; int16x8_t intvec; -void test(void) +/* Test a few different supported ways of passing a scalar int value. +The intrinsic vmulq was chosen arbitrarily, but it is representative of +all intrinsics that take a non-const scalar value. */ +void +test_scalars (void) { - /* Test a few different supported ways of passing an int value. The - intrinsic vmulq was chosen arbitrarily, but it is representative of - all intrinsics that take a non-const scalar value. */ intvec = vmulq(intvec, 2); intvec = vmulq(intvec, (int32_t) 2); intvec = vmulq(intvec, (short) 2); @@ -33,4 +34,65 @@ void test(void) intvec = vmulq(intvec, i8); } +/* Next, test a number of valid pointer overloads. */ +void +foo1 (signed char * addr, int8x16_t value) +{ + vst1q (addr, value); +} + +void +foo2 (short * addr, int16x8_t value) +{ + vst1q (addr, value); +} + +void +foo3 (int * addr, int32x4_t value) +{ + vst1q (addr, value); /* { dg-warning "invalid conversion" "" { target c++ } } */ +} + +void +foo4 (long * addr, int32x4_t value) +{ + vst1q (addr, value); +} + +void +foo5 (long long * addr, uint64x2_t value) +{ + vldrdq_gather_offset (addr, value); +} + +void +foo6 (unsigned char * addr, uint8x16_t value) +{ + vst1q (addr, value); +} + +void +foo7 (unsigned short * addr, uint16x8_t value) +{ + vst1q (addr, value); +} + +void +foo8 (unsigned int * addr, uint32x4_t value) +{ + vst1q (addr, value); /* { dg-warning "invalid conversion" "" { target c++ } } */ +} + +void +foo9 (unsigned long * addr, uint32x4_t value) +{ + vst1q (addr, value); +} + +void +foo10 (unsigned long long * addr, uint64x2_t value) +{ + vldrdq_gather_offset (addr, value); +} + /* { dg-final { scan-assembler-not "__ARM_undef" } } */