From patchwork Wed Sep 4 13:26:33 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Christophe Lyon X-Patchwork-Id: 1980812 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; dkim=pass (2048-bit key; unprotected) header.d=linaro.org header.i=@linaro.org header.a=rsa-sha256 header.s=google header.b=BRlbcGnB; dkim-atps=neutral Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=gcc.gnu.org (client-ip=2620:52:3:1:0:246e:9693:128c; helo=server2.sourceware.org; envelope-from=gcc-patches-bounces~incoming=patchwork.ozlabs.org@gcc.gnu.org; receiver=patchwork.ozlabs.org) Received: from server2.sourceware.org (server2.sourceware.org [IPv6:2620:52:3:1:0:246e:9693:128c]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (secp384r1) server-digest SHA384) (No client certificate requested) by legolas.ozlabs.org (Postfix) with ESMTPS id 4WzNjg2Xffz1yg3 for ; Wed, 4 Sep 2024 23:33:27 +1000 (AEST) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id DDD883865488 for ; Wed, 4 Sep 2024 13:33:24 +0000 (GMT) X-Original-To: gcc-patches@gcc.gnu.org Delivered-To: gcc-patches@gcc.gnu.org Received: from mail-oo1-xc2e.google.com (mail-oo1-xc2e.google.com [IPv6:2607:f8b0:4864:20::c2e]) by sourceware.org (Postfix) with ESMTPS id F1FA03858C50 for ; Wed, 4 Sep 2024 13:27:38 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org F1FA03858C50 Authentication-Results: sourceware.org; dmarc=pass (p=none dis=none) header.from=linaro.org Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=linaro.org ARC-Filter: OpenARC Filter v1.0.0 sourceware.org F1FA03858C50 Authentication-Results: server2.sourceware.org; arc=none smtp.remote-ip=2607:f8b0:4864:20::c2e ARC-Seal: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1725456465; cv=none; b=J3b4eG6opMHiukvq7sHqW4qtAkqRYsmKJjjzz65olik7CNJWrVLlINY1DgMiIWqfoPLqysVUtmYMftvgsTKWCed0pYQvP0/wVQakFOy2Ua4MrChMddsKhuQoPhYi6CQOapTgMTnvEsVxmBkBTicunO8V9WLjHOoYFzjkulXjDqs= ARC-Message-Signature: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1725456465; c=relaxed/simple; bh=0AgSqBZ2qXFMELCvm8KJAfCtgvtATc9rvhiKZaxbQj0=; h=DKIM-Signature:From:To:Subject:Date:Message-Id:MIME-Version; b=Ywr3HsYoxZTU44Hyl/O0FybXjSMBVaxCA202ri3wWMC8JG0MS+6mxroK2ywqfOEN5lZMONZDUk35LFG43vv9X2h3sNXqDvYLeWpfWHtiSWOSbRnjMlebF3qmsUZP9UZjipxJZk9DhyWB6Yla/YDC+PQtXm415HY74YkJ05kFZ8w= ARC-Authentication-Results: i=1; server2.sourceware.org Received: by mail-oo1-xc2e.google.com with SMTP id 006d021491bc7-5df9343b5b8so4226118eaf.0 for ; Wed, 04 Sep 2024 06:27:38 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1725456458; x=1726061258; darn=gcc.gnu.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=y0fqHo4aQdR9reDiLKZYLcCevm5XQTIE1HpjctExAEs=; b=BRlbcGnBGwyplD8KMjWFsDrZwVwOTbNeoLohRZu9qjKSDxTvv4jb4pHbk2SsJ1I61y yN8fr136V11Bi3X360zpgc0nynX3r4IxjQOWEmL87rMOllOV4gLp6BUW2eX3JkaSlfoB PTh6wDCH/+Y2EcORLGAdrMTq1XplnxTfRB3iPts0t0OKsd2OtTXPL0g4gTYe+hmtmCU/ XSzUwIDdry/lNsQVTgMR8gTdo7w/sDhrcs+CrFLcis6zuFkmtr3eyXKdYdB6DVtKNe/M bpJyjOM/BmJ1/QbjM7BzxSAVWhe/VLK7v8jRWaMMY//ij6he/z/qX9vEvDejbNhsoDR3 Q3+w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1725456458; x=1726061258; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=y0fqHo4aQdR9reDiLKZYLcCevm5XQTIE1HpjctExAEs=; b=YKI8MtzSKxmVMhDSaI6ZeE19WykV1PbcsXf68hPdrCPfM+0yAMvFSKRgTMGSdUG9s2 4FOrTCMOmh4/xBmYsDJSFyGMI5PUUBVaynkH96gCDNtmHpOhGNtAtDXRV9lvMisOuEVR ygXZaPofmVJKASPp0jPmgfSvxOmUZQgs9S2HK+iVgDkO6MS23+/fG83jdLAZa20YBwFZ OII6M09ugJ5JH+RZJM+LeEVyMKFctwkQ4oU2BlQ0ttlYEqRx0NV2L5WcgbuEZ1U5w/cS BU9qRLfWIwO0KaWdy0TTU3OJYuwyPFqo4Vqs+eZEciqvG7qsXk7A/VhaaChz0OTBh6G4 P95w== X-Gm-Message-State: AOJu0YzgzWZW6uWoZi+o4b6w+D+uCtwzGEWy5DegTpeB7/Qpi8aJB0BH VfFAVNjwTQVM9hRQjjiULdFchRmwQAV4JwF09I7OERw5pqzJ9jAjZ/9b7Y5S29I1k6BIf1GgfER LoPWpRA== X-Google-Smtp-Source: AGHT+IEAZrQBwWtleDxM8hyHK11MtSazyfCXJ/WMsO6f5ueLemcuzSd5N/f/wxP8nGD1V4n4uRaGMg== X-Received: by 2002:a05:6820:545:b0:5d5:a343:d135 with SMTP id 006d021491bc7-5dfacddf0a9mr18593950eaf.1.1725456457514; Wed, 04 Sep 2024 06:27:37 -0700 (PDT) Received: from localhost.localdomain ([139.178.84.207]) by smtp.gmail.com with ESMTPSA id 006d021491bc7-5dfa0580692sm2308062eaf.46.2024.09.04.06.27.36 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 04 Sep 2024 06:27:37 -0700 (PDT) From: Christophe Lyon To: gcc-patches@gcc.gnu.org, richard.earnshaw@arm.com, ramanara@nvidia.com Cc: Christophe Lyon Subject: [PATCH v2 19/36] arm: [MVE intrinsics] rework vddup vidup Date: Wed, 4 Sep 2024 13:26:33 +0000 Message-Id: <20240904132650.2720446-20-christophe.lyon@linaro.org> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240904132650.2720446-1-christophe.lyon@linaro.org> References: <20240711214305.3193022-1-christophe.lyon@linaro.org> <20240904132650.2720446-1-christophe.lyon@linaro.org> MIME-Version: 1.0 X-Spam-Status: No, score=-12.6 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, DKIM_VALID_EF, GIT_PATCH_0, RCVD_IN_DNSWL_NONE, SPF_HELO_NONE, SPF_PASS, TXREP, T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org X-BeenThere: gcc-patches@gcc.gnu.org X-Mailman-Version: 2.1.30 Precedence: list List-Id: Gcc-patches mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: gcc-patches-bounces~incoming=patchwork.ozlabs.org@gcc.gnu.org Implement vddup and vidup using the new MVE builtins framework. We generate better code because we take advantage of the two outputs produced by the v[id]dup instructions. For instance, before: ldr r3, [r0] sub r2, r3, #8 str r2, [r0] mov r2, r3 vddup.u16 q3, r2, #1 now: ldr r2, [r0] vddup.u16 q3, r2, #1 str r2, [r0] 2024-08-21 Christophe Lyon gcc/ * config/arm/arm-mve-builtins-base.cc (class viddup_impl): New. (vddup): New. (vidup): New. * config/arm/arm-mve-builtins-base.def (vddupq): New. (vidupq): New. * config/arm/arm-mve-builtins-base.h (vddupq): New. (vidupq): New. * config/arm/arm_mve.h (vddupq_m): Delete. (vddupq_u8): Delete. (vddupq_u32): Delete. (vddupq_u16): Delete. (vidupq_m): Delete. (vidupq_u8): Delete. (vidupq_u32): Delete. (vidupq_u16): Delete. (vddupq_x_u8): Delete. (vddupq_x_u16): Delete. (vddupq_x_u32): Delete. (vidupq_x_u8): Delete. (vidupq_x_u16): Delete. (vidupq_x_u32): Delete. (vddupq_m_n_u8): Delete. (vddupq_m_n_u32): Delete. (vddupq_m_n_u16): Delete. (vddupq_m_wb_u8): Delete. (vddupq_m_wb_u16): Delete. (vddupq_m_wb_u32): Delete. (vddupq_n_u8): Delete. (vddupq_n_u32): Delete. (vddupq_n_u16): Delete. (vddupq_wb_u8): Delete. (vddupq_wb_u16): Delete. (vddupq_wb_u32): Delete. (vidupq_m_n_u8): Delete. (vidupq_m_n_u32): Delete. (vidupq_m_n_u16): Delete. (vidupq_m_wb_u8): Delete. (vidupq_m_wb_u16): Delete. (vidupq_m_wb_u32): Delete. (vidupq_n_u8): Delete. (vidupq_n_u32): Delete. (vidupq_n_u16): Delete. (vidupq_wb_u8): Delete. (vidupq_wb_u16): Delete. (vidupq_wb_u32): Delete. (vddupq_x_n_u8): Delete. (vddupq_x_n_u16): Delete. (vddupq_x_n_u32): Delete. (vddupq_x_wb_u8): Delete. (vddupq_x_wb_u16): Delete. (vddupq_x_wb_u32): Delete. (vidupq_x_n_u8): Delete. (vidupq_x_n_u16): Delete. (vidupq_x_n_u32): Delete. (vidupq_x_wb_u8): Delete. (vidupq_x_wb_u16): Delete. (vidupq_x_wb_u32): Delete. (__arm_vddupq_m_n_u8): Delete. (__arm_vddupq_m_n_u32): Delete. (__arm_vddupq_m_n_u16): Delete. (__arm_vddupq_m_wb_u8): Delete. (__arm_vddupq_m_wb_u16): Delete. (__arm_vddupq_m_wb_u32): Delete. (__arm_vddupq_n_u8): Delete. (__arm_vddupq_n_u32): Delete. (__arm_vddupq_n_u16): Delete. (__arm_vidupq_m_n_u8): Delete. (__arm_vidupq_m_n_u32): Delete. (__arm_vidupq_m_n_u16): Delete. (__arm_vidupq_n_u8): Delete. (__arm_vidupq_m_wb_u8): Delete. (__arm_vidupq_m_wb_u16): Delete. (__arm_vidupq_m_wb_u32): Delete. (__arm_vidupq_n_u32): Delete. (__arm_vidupq_n_u16): Delete. (__arm_vidupq_wb_u8): Delete. (__arm_vidupq_wb_u16): Delete. (__arm_vidupq_wb_u32): Delete. (__arm_vddupq_wb_u8): Delete. (__arm_vddupq_wb_u16): Delete. (__arm_vddupq_wb_u32): Delete. (__arm_vddupq_x_n_u8): Delete. (__arm_vddupq_x_n_u16): Delete. (__arm_vddupq_x_n_u32): Delete. (__arm_vddupq_x_wb_u8): Delete. (__arm_vddupq_x_wb_u16): Delete. (__arm_vddupq_x_wb_u32): Delete. (__arm_vidupq_x_n_u8): Delete. (__arm_vidupq_x_n_u16): Delete. (__arm_vidupq_x_n_u32): Delete. (__arm_vidupq_x_wb_u8): Delete. (__arm_vidupq_x_wb_u16): Delete. (__arm_vidupq_x_wb_u32): Delete. (__arm_vddupq_m): Delete. (__arm_vddupq_u8): Delete. (__arm_vddupq_u32): Delete. (__arm_vddupq_u16): Delete. (__arm_vidupq_m): Delete. (__arm_vidupq_u8): Delete. (__arm_vidupq_u32): Delete. (__arm_vidupq_u16): Delete. (__arm_vddupq_x_u8): Delete. (__arm_vddupq_x_u16): Delete. (__arm_vddupq_x_u32): Delete. (__arm_vidupq_x_u8): Delete. (__arm_vidupq_x_u16): Delete. (__arm_vidupq_x_u32): Delete. --- gcc/config/arm/arm-mve-builtins-base.cc | 112 ++++ gcc/config/arm/arm-mve-builtins-base.def | 2 + gcc/config/arm/arm-mve-builtins-base.h | 2 + gcc/config/arm/arm_mve.h | 676 ----------------------- 4 files changed, 116 insertions(+), 676 deletions(-) diff --git a/gcc/config/arm/arm-mve-builtins-base.cc b/gcc/config/arm/arm-mve-builtins-base.cc index 89724320d43..3d8bcdabe24 100644 --- a/gcc/config/arm/arm-mve-builtins-base.cc +++ b/gcc/config/arm/arm-mve-builtins-base.cc @@ -30,6 +30,7 @@ #include "basic-block.h" #include "function.h" #include "gimple.h" +#include "emit-rtl.h" #include "arm-mve-builtins.h" #include "arm-mve-builtins-shapes.h" #include "arm-mve-builtins-base.h" @@ -349,6 +350,115 @@ public: } }; +/* Map the vidup / vddup function directly to CODE (UNSPEC, M) where M is the + vector mode associated with type suffix 0. We need this special case + because in MODE_wb the builtins derefrence the first parameter and update + its contents. We also have to insert the two additional parameters needed + by the builtins compared to the intrinsics. */ +class viddup_impl : public function_base +{ +public: + CONSTEXPR viddup_impl (bool inc_dec) + : m_inc_dec (inc_dec) + {} + + /* Increment (true) or decrement (false). */ + bool m_inc_dec; + + unsigned int + call_properties (const function_instance &fi) const override + { + if (fi.mode_suffix_id == MODE_wb) + return CP_WRITE_MEMORY | CP_READ_MEMORY; + else + return 0; + } + + tree + memory_scalar_type (const function_instance &) const override + { + return get_typenode_from_name (UINT32_TYPE); + } + + rtx + expand (function_expander &e) const override + { + machine_mode mode = e.vector_mode (0); + insn_code code; + rtx insns, offset_ptr; + rtx new_offset; + int offset_arg_no; + rtx incr, total_incr; + + if (! e.type_suffix (0).integer_p) + gcc_unreachable (); + + if ((e.mode_suffix_id != MODE_n) + && (e.mode_suffix_id != MODE_wb)) + gcc_unreachable (); + + offset_arg_no = (e.pred == PRED_m) ? 1 : 0; + + /* In _wb mode, the start offset is passed via a pointer, + dereference it. */ + if (e.mode_suffix_id == MODE_wb) + { + rtx offset = gen_reg_rtx (SImode); + offset_ptr = e.args[offset_arg_no]; + emit_insn (gen_rtx_SET (offset, gen_rtx_MEM (SImode, offset_ptr))); + e.args[offset_arg_no] = offset; + } + + /* We have to shuffle parameters because the builtin needs additional + arguments: + - the updated "new_offset" + - total increment (incr * number of lanes) */ + new_offset = gen_reg_rtx (SImode); + e.args.quick_insert (offset_arg_no, new_offset); + + incr = e.args[offset_arg_no + 2]; + total_incr = gen_int_mode (INTVAL (incr) + * GET_MODE_NUNITS (e.vector_mode (0)), + SImode); + e.args.quick_push (total_incr); + + /* _wb mode uses the _n builtins and adds code to update the + offset. */ + switch (e.pred) + { + case PRED_none: + /* No predicate. */ + code = m_inc_dec + ? code_for_mve_q_u_insn (VIDUPQ, mode) + : code_for_mve_q_u_insn (VDDUPQ, mode); + insns = e.use_exact_insn (code); + break; + + case PRED_m: + case PRED_x: + /* "m" or "x" predicate. */ + code = m_inc_dec + ? code_for_mve_q_m_wb_u_insn (VIDUPQ_M, mode) + : code_for_mve_q_m_wb_u_insn (VDDUPQ_M, mode); + + if (e.pred == PRED_m) + insns = e.use_cond_insn (code, 0); + else + insns = e.use_pred_x_insn (code); + break; + + default: + gcc_unreachable (); + } + + /* Update offset as appropriate. */ + if (e.mode_suffix_id == MODE_wb) + emit_insn (gen_rtx_SET (gen_rtx_MEM (Pmode, offset_ptr), new_offset)); + + return insns; + } +}; + } /* end anonymous namespace */ namespace arm_mve { @@ -561,7 +671,9 @@ FUNCTION_WITHOUT_N_NO_F (vcvtnq, VCVTNQ) FUNCTION_WITHOUT_N_NO_F (vcvtpq, VCVTPQ) FUNCTION (vcvtbq, vcvtxq_impl, (VCVTBQ_F16_F32, VCVTBQ_M_F16_F32, VCVTBQ_F32_F16, VCVTBQ_M_F32_F16)) FUNCTION (vcvttq, vcvtxq_impl, (VCVTTQ_F16_F32, VCVTTQ_M_F16_F32, VCVTTQ_F32_F16, VCVTTQ_M_F32_F16)) +FUNCTION (vddupq, viddup_impl, (false)) FUNCTION_ONLY_N (vdupq, VDUPQ) +FUNCTION (vidupq, viddup_impl, (true)) FUNCTION_WITH_RTX_M (veorq, XOR, VEORQ) FUNCTION (vfmaq, unspec_mve_function_exact_insn, (-1, -1, VFMAQ_F, -1, -1, VFMAQ_N_F, -1, -1, VFMAQ_M_F, -1, -1, VFMAQ_M_N_F)) FUNCTION (vfmasq, unspec_mve_function_exact_insn, (-1, -1, -1, -1, -1, VFMASQ_N_F, -1, -1, -1, -1, -1, VFMASQ_M_N_F)) diff --git a/gcc/config/arm/arm-mve-builtins-base.def b/gcc/config/arm/arm-mve-builtins-base.def index dd46d882882..ed3048e219a 100644 --- a/gcc/config/arm/arm-mve-builtins-base.def +++ b/gcc/config/arm/arm-mve-builtins-base.def @@ -46,12 +46,14 @@ DEF_MVE_FUNCTION (vctp16q, vctp, none, m_or_none) DEF_MVE_FUNCTION (vctp32q, vctp, none, m_or_none) DEF_MVE_FUNCTION (vctp64q, vctp, none, m_or_none) DEF_MVE_FUNCTION (vctp8q, vctp, none, m_or_none) +DEF_MVE_FUNCTION (vddupq, viddup, all_unsigned, mx_or_none) DEF_MVE_FUNCTION (vdupq, unary_n, all_integer, mx_or_none) DEF_MVE_FUNCTION (veorq, binary, all_integer, mx_or_none) DEF_MVE_FUNCTION (vhaddq, binary_opt_n, all_integer, mx_or_none) DEF_MVE_FUNCTION (vhcaddq_rot270, binary, all_signed, mx_or_none) DEF_MVE_FUNCTION (vhcaddq_rot90, binary, all_signed, mx_or_none) DEF_MVE_FUNCTION (vhsubq, binary_opt_n, all_integer, mx_or_none) +DEF_MVE_FUNCTION (vidupq, viddup, all_unsigned, mx_or_none) DEF_MVE_FUNCTION (vld1q, load, all_integer, none) DEF_MVE_FUNCTION (vmaxaq, binary_maxamina, all_signed, m_or_none) DEF_MVE_FUNCTION (vmaxavq, binary_maxavminav, all_signed, p_or_none) diff --git a/gcc/config/arm/arm-mve-builtins-base.h b/gcc/config/arm/arm-mve-builtins-base.h index 41fcf666b11..526e0f8ee3a 100644 --- a/gcc/config/arm/arm-mve-builtins-base.h +++ b/gcc/config/arm/arm-mve-builtins-base.h @@ -66,6 +66,7 @@ extern const function_base *const vcvtnq; extern const function_base *const vcvtpq; extern const function_base *const vcvtq; extern const function_base *const vcvttq; +extern const function_base *const vddupq; extern const function_base *const vdupq; extern const function_base *const veorq; extern const function_base *const vfmaq; @@ -75,6 +76,7 @@ extern const function_base *const vhaddq; extern const function_base *const vhcaddq_rot270; extern const function_base *const vhcaddq_rot90; extern const function_base *const vhsubq; +extern const function_base *const vidupq; extern const function_base *const vld1q; extern const function_base *const vmaxaq; extern const function_base *const vmaxavq; diff --git a/gcc/config/arm/arm_mve.h b/gcc/config/arm/arm_mve.h index 49c4ea9afee..c3da491b9d1 100644 --- a/gcc/config/arm/arm_mve.h +++ b/gcc/config/arm/arm_mve.h @@ -82,18 +82,10 @@ #define vstrwq_scatter_shifted_offset_p(__base, __offset, __value, __p) __arm_vstrwq_scatter_shifted_offset_p(__base, __offset, __value, __p) #define vstrwq_scatter_shifted_offset(__base, __offset, __value) __arm_vstrwq_scatter_shifted_offset(__base, __offset, __value) #define vuninitializedq(__v) __arm_vuninitializedq(__v) -#define vddupq_m(__inactive, __a, __imm, __p) __arm_vddupq_m(__inactive, __a, __imm, __p) -#define vddupq_u8(__a, __imm) __arm_vddupq_u8(__a, __imm) -#define vddupq_u32(__a, __imm) __arm_vddupq_u32(__a, __imm) -#define vddupq_u16(__a, __imm) __arm_vddupq_u16(__a, __imm) #define vdwdupq_m(__inactive, __a, __b, __imm, __p) __arm_vdwdupq_m(__inactive, __a, __b, __imm, __p) #define vdwdupq_u8(__a, __b, __imm) __arm_vdwdupq_u8(__a, __b, __imm) #define vdwdupq_u32(__a, __b, __imm) __arm_vdwdupq_u32(__a, __b, __imm) #define vdwdupq_u16(__a, __b, __imm) __arm_vdwdupq_u16(__a, __b, __imm) -#define vidupq_m(__inactive, __a, __imm, __p) __arm_vidupq_m(__inactive, __a, __imm, __p) -#define vidupq_u8(__a, __imm) __arm_vidupq_u8(__a, __imm) -#define vidupq_u32(__a, __imm) __arm_vidupq_u32(__a, __imm) -#define vidupq_u16(__a, __imm) __arm_vidupq_u16(__a, __imm) #define viwdupq_m(__inactive, __a, __b, __imm, __p) __arm_viwdupq_m(__inactive, __a, __b, __imm, __p) #define viwdupq_u8(__a, __b, __imm) __arm_viwdupq_u8(__a, __b, __imm) #define viwdupq_u32(__a, __b, __imm) __arm_viwdupq_u32(__a, __b, __imm) @@ -102,15 +94,9 @@ #define vstrdq_scatter_base_wb_p(__addr, __offset, __value, __p) __arm_vstrdq_scatter_base_wb_p(__addr, __offset, __value, __p) #define vstrwq_scatter_base_wb_p(__addr, __offset, __value, __p) __arm_vstrwq_scatter_base_wb_p(__addr, __offset, __value, __p) #define vstrwq_scatter_base_wb(__addr, __offset, __value) __arm_vstrwq_scatter_base_wb(__addr, __offset, __value) -#define vddupq_x_u8(__a, __imm, __p) __arm_vddupq_x_u8(__a, __imm, __p) -#define vddupq_x_u16(__a, __imm, __p) __arm_vddupq_x_u16(__a, __imm, __p) -#define vddupq_x_u32(__a, __imm, __p) __arm_vddupq_x_u32(__a, __imm, __p) #define vdwdupq_x_u8(__a, __b, __imm, __p) __arm_vdwdupq_x_u8(__a, __b, __imm, __p) #define vdwdupq_x_u16(__a, __b, __imm, __p) __arm_vdwdupq_x_u16(__a, __b, __imm, __p) #define vdwdupq_x_u32(__a, __b, __imm, __p) __arm_vdwdupq_x_u32(__a, __b, __imm, __p) -#define vidupq_x_u8(__a, __imm, __p) __arm_vidupq_x_u8(__a, __imm, __p) -#define vidupq_x_u16(__a, __imm, __p) __arm_vidupq_x_u16(__a, __imm, __p) -#define vidupq_x_u32(__a, __imm, __p) __arm_vidupq_x_u32(__a, __imm, __p) #define viwdupq_x_u8(__a, __b, __imm, __p) __arm_viwdupq_x_u8(__a, __b, __imm, __p) #define viwdupq_x_u16(__a, __b, __imm, __p) __arm_viwdupq_x_u16(__a, __b, __imm, __p) #define viwdupq_x_u32(__a, __b, __imm, __p) __arm_viwdupq_x_u32(__a, __b, __imm, __p) @@ -337,18 +323,6 @@ #define vuninitializedq_s64(void) __arm_vuninitializedq_s64(void) #define vuninitializedq_f16(void) __arm_vuninitializedq_f16(void) #define vuninitializedq_f32(void) __arm_vuninitializedq_f32(void) -#define vddupq_m_n_u8(__inactive, __a, __imm, __p) __arm_vddupq_m_n_u8(__inactive, __a, __imm, __p) -#define vddupq_m_n_u32(__inactive, __a, __imm, __p) __arm_vddupq_m_n_u32(__inactive, __a, __imm, __p) -#define vddupq_m_n_u16(__inactive, __a, __imm, __p) __arm_vddupq_m_n_u16(__inactive, __a, __imm, __p) -#define vddupq_m_wb_u8(__inactive, __a, __imm, __p) __arm_vddupq_m_wb_u8(__inactive, __a, __imm, __p) -#define vddupq_m_wb_u16(__inactive, __a, __imm, __p) __arm_vddupq_m_wb_u16(__inactive, __a, __imm, __p) -#define vddupq_m_wb_u32(__inactive, __a, __imm, __p) __arm_vddupq_m_wb_u32(__inactive, __a, __imm, __p) -#define vddupq_n_u8(__a, __imm) __arm_vddupq_n_u8(__a, __imm) -#define vddupq_n_u32(__a, __imm) __arm_vddupq_n_u32(__a, __imm) -#define vddupq_n_u16(__a, __imm) __arm_vddupq_n_u16(__a, __imm) -#define vddupq_wb_u8( __a, __imm) __arm_vddupq_wb_u8( __a, __imm) -#define vddupq_wb_u16( __a, __imm) __arm_vddupq_wb_u16( __a, __imm) -#define vddupq_wb_u32( __a, __imm) __arm_vddupq_wb_u32( __a, __imm) #define vdwdupq_m_n_u8(__inactive, __a, __b, __imm, __p) __arm_vdwdupq_m_n_u8(__inactive, __a, __b, __imm, __p) #define vdwdupq_m_n_u32(__inactive, __a, __b, __imm, __p) __arm_vdwdupq_m_n_u32(__inactive, __a, __b, __imm, __p) #define vdwdupq_m_n_u16(__inactive, __a, __b, __imm, __p) __arm_vdwdupq_m_n_u16(__inactive, __a, __b, __imm, __p) @@ -361,18 +335,6 @@ #define vdwdupq_wb_u8( __a, __b, __imm) __arm_vdwdupq_wb_u8( __a, __b, __imm) #define vdwdupq_wb_u32( __a, __b, __imm) __arm_vdwdupq_wb_u32( __a, __b, __imm) #define vdwdupq_wb_u16( __a, __b, __imm) __arm_vdwdupq_wb_u16( __a, __b, __imm) -#define vidupq_m_n_u8(__inactive, __a, __imm, __p) __arm_vidupq_m_n_u8(__inactive, __a, __imm, __p) -#define vidupq_m_n_u32(__inactive, __a, __imm, __p) __arm_vidupq_m_n_u32(__inactive, __a, __imm, __p) -#define vidupq_m_n_u16(__inactive, __a, __imm, __p) __arm_vidupq_m_n_u16(__inactive, __a, __imm, __p) -#define vidupq_m_wb_u8(__inactive, __a, __imm, __p) __arm_vidupq_m_wb_u8(__inactive, __a, __imm, __p) -#define vidupq_m_wb_u16(__inactive, __a, __imm, __p) __arm_vidupq_m_wb_u16(__inactive, __a, __imm, __p) -#define vidupq_m_wb_u32(__inactive, __a, __imm, __p) __arm_vidupq_m_wb_u32(__inactive, __a, __imm, __p) -#define vidupq_n_u8(__a, __imm) __arm_vidupq_n_u8(__a, __imm) -#define vidupq_n_u32(__a, __imm) __arm_vidupq_n_u32(__a, __imm) -#define vidupq_n_u16(__a, __imm) __arm_vidupq_n_u16(__a, __imm) -#define vidupq_wb_u8( __a, __imm) __arm_vidupq_wb_u8( __a, __imm) -#define vidupq_wb_u16( __a, __imm) __arm_vidupq_wb_u16( __a, __imm) -#define vidupq_wb_u32( __a, __imm) __arm_vidupq_wb_u32( __a, __imm) #define viwdupq_m_n_u8(__inactive, __a, __b, __imm, __p) __arm_viwdupq_m_n_u8(__inactive, __a, __b, __imm, __p) #define viwdupq_m_n_u32(__inactive, __a, __b, __imm, __p) __arm_viwdupq_m_n_u32(__inactive, __a, __b, __imm, __p) #define viwdupq_m_n_u16(__inactive, __a, __b, __imm, __p) __arm_viwdupq_m_n_u16(__inactive, __a, __b, __imm, __p) @@ -405,24 +367,12 @@ #define vstrwq_scatter_base_wb_s32(__addr, __offset, __value) __arm_vstrwq_scatter_base_wb_s32(__addr, __offset, __value) #define vstrwq_scatter_base_wb_u32(__addr, __offset, __value) __arm_vstrwq_scatter_base_wb_u32(__addr, __offset, __value) #define vstrwq_scatter_base_wb_f32(__addr, __offset, __value) __arm_vstrwq_scatter_base_wb_f32(__addr, __offset, __value) -#define vddupq_x_n_u8(__a, __imm, __p) __arm_vddupq_x_n_u8(__a, __imm, __p) -#define vddupq_x_n_u16(__a, __imm, __p) __arm_vddupq_x_n_u16(__a, __imm, __p) -#define vddupq_x_n_u32(__a, __imm, __p) __arm_vddupq_x_n_u32(__a, __imm, __p) -#define vddupq_x_wb_u8(__a, __imm, __p) __arm_vddupq_x_wb_u8(__a, __imm, __p) -#define vddupq_x_wb_u16(__a, __imm, __p) __arm_vddupq_x_wb_u16(__a, __imm, __p) -#define vddupq_x_wb_u32(__a, __imm, __p) __arm_vddupq_x_wb_u32(__a, __imm, __p) #define vdwdupq_x_n_u8(__a, __b, __imm, __p) __arm_vdwdupq_x_n_u8(__a, __b, __imm, __p) #define vdwdupq_x_n_u16(__a, __b, __imm, __p) __arm_vdwdupq_x_n_u16(__a, __b, __imm, __p) #define vdwdupq_x_n_u32(__a, __b, __imm, __p) __arm_vdwdupq_x_n_u32(__a, __b, __imm, __p) #define vdwdupq_x_wb_u8(__a, __b, __imm, __p) __arm_vdwdupq_x_wb_u8(__a, __b, __imm, __p) #define vdwdupq_x_wb_u16(__a, __b, __imm, __p) __arm_vdwdupq_x_wb_u16(__a, __b, __imm, __p) #define vdwdupq_x_wb_u32(__a, __b, __imm, __p) __arm_vdwdupq_x_wb_u32(__a, __b, __imm, __p) -#define vidupq_x_n_u8(__a, __imm, __p) __arm_vidupq_x_n_u8(__a, __imm, __p) -#define vidupq_x_n_u16(__a, __imm, __p) __arm_vidupq_x_n_u16(__a, __imm, __p) -#define vidupq_x_n_u32(__a, __imm, __p) __arm_vidupq_x_n_u32(__a, __imm, __p) -#define vidupq_x_wb_u8(__a, __imm, __p) __arm_vidupq_x_wb_u8(__a, __imm, __p) -#define vidupq_x_wb_u16(__a, __imm, __p) __arm_vidupq_x_wb_u16(__a, __imm, __p) -#define vidupq_x_wb_u32(__a, __imm, __p) __arm_vidupq_x_wb_u32(__a, __imm, __p) #define viwdupq_x_n_u8(__a, __b, __imm, __p) __arm_viwdupq_x_n_u8(__a, __b, __imm, __p) #define viwdupq_x_n_u16(__a, __b, __imm, __p) __arm_viwdupq_x_n_u16(__a, __b, __imm, __p) #define viwdupq_x_n_u32(__a, __b, __imm, __p) __arm_viwdupq_x_n_u32(__a, __b, __imm, __p) @@ -1722,75 +1672,6 @@ __arm_vstrwq_scatter_shifted_offset_u32 (uint32_t * __base, uint32x4_t __offset, __builtin_mve_vstrwq_scatter_shifted_offset_uv4si ((__builtin_neon_si *) __base, __offset, __value); } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_m_n_u8 (uint8x16_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __builtin_mve_vddupq_m_n_uv16qi (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_m_n_u32 (uint32x4_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __builtin_mve_vddupq_m_n_uv4si (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_m_n_u16 (uint16x8_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __builtin_mve_vddupq_m_n_uv8hi (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_m_wb_u8 (uint8x16_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p) -{ - uint8x16_t __res = __builtin_mve_vddupq_m_n_uv16qi (__inactive, * __a, __imm, __p); - *__a -= __imm * 16u; - return __res; -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_m_wb_u16 (uint16x8_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p) -{ - uint16x8_t __res = __builtin_mve_vddupq_m_n_uv8hi (__inactive, *__a, __imm, __p); - *__a -= __imm * 8u; - return __res; -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_m_wb_u32 (uint32x4_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p) -{ - uint32x4_t __res = __builtin_mve_vddupq_m_n_uv4si (__inactive, *__a, __imm, __p); - *__a -= __imm * 4u; - return __res; -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_n_u8 (uint32_t __a, const int __imm) -{ - return __builtin_mve_vddupq_n_uv16qi (__a, __imm); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_n_u32 (uint32_t __a, const int __imm) -{ - return __builtin_mve_vddupq_n_uv4si (__a, __imm); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_n_u16 (uint32_t __a, const int __imm) -{ - return __builtin_mve_vddupq_n_uv8hi (__a, __imm); -} - __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_m_n_u8 (uint8x16_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) @@ -1899,129 +1780,6 @@ __arm_vdwdupq_wb_u16 (uint32_t * __a, uint32_t __b, const int __imm) return __res; } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_m_n_u8 (uint8x16_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __builtin_mve_vidupq_m_n_uv16qi (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_m_n_u32 (uint32x4_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __builtin_mve_vidupq_m_n_uv4si (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_m_n_u16 (uint16x8_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __builtin_mve_vidupq_m_n_uv8hi (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_n_u8 (uint32_t __a, const int __imm) -{ - return __builtin_mve_vidupq_n_uv16qi (__a, __imm); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_m_wb_u8 (uint8x16_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p) -{ - uint8x16_t __res = __builtin_mve_vidupq_m_n_uv16qi (__inactive, *__a, __imm, __p); - *__a += __imm * 16u; - return __res; -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_m_wb_u16 (uint16x8_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p) -{ - uint16x8_t __res = __builtin_mve_vidupq_m_n_uv8hi (__inactive, *__a, __imm, __p); - *__a += __imm * 8u; - return __res; -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_m_wb_u32 (uint32x4_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p) -{ - uint32x4_t __res = __builtin_mve_vidupq_m_n_uv4si (__inactive, *__a, __imm, __p); - *__a += __imm * 4u; - return __res; -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_n_u32 (uint32_t __a, const int __imm) -{ - return __builtin_mve_vidupq_n_uv4si (__a, __imm); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_n_u16 (uint32_t __a, const int __imm) -{ - return __builtin_mve_vidupq_n_uv8hi (__a, __imm); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_wb_u8 (uint32_t * __a, const int __imm) -{ - uint8x16_t __res = __builtin_mve_vidupq_n_uv16qi (*__a, __imm); - *__a += __imm * 16u; - return __res; -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_wb_u16 (uint32_t * __a, const int __imm) -{ - uint16x8_t __res = __builtin_mve_vidupq_n_uv8hi (*__a, __imm); - *__a += __imm * 8u; - return __res; -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_wb_u32 (uint32_t * __a, const int __imm) -{ - uint32x4_t __res = __builtin_mve_vidupq_n_uv4si (*__a, __imm); - *__a += __imm * 4u; - return __res; -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_wb_u8 (uint32_t * __a, const int __imm) -{ - uint8x16_t __res = __builtin_mve_vddupq_n_uv16qi (*__a, __imm); - *__a -= __imm * 16u; - return __res; -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_wb_u16 (uint32_t * __a, const int __imm) -{ - uint16x8_t __res = __builtin_mve_vddupq_n_uv8hi (*__a, __imm); - *__a -= __imm * 8u; - return __res; -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_wb_u32 (uint32_t * __a, const int __imm) -{ - uint32x4_t __res = __builtin_mve_vddupq_n_uv4si (*__a, __imm); - *__a -= __imm * 4u; - return __res; -} - __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_m_n_u8 (uint8x16_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) @@ -2267,57 +2025,6 @@ __arm_vstrwq_scatter_base_wb_u32 (uint32x4_t * __addr, const int __offset, uint3 *__addr = __builtin_mve_vstrwq_scatter_base_wb_uv4si (*__addr, __offset, __value); } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_x_n_u8 (uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __builtin_mve_vddupq_m_n_uv16qi (__arm_vuninitializedq_u8 (), __a, __imm, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_x_n_u16 (uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __builtin_mve_vddupq_m_n_uv8hi (__arm_vuninitializedq_u16 (), __a, __imm, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_x_n_u32 (uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __builtin_mve_vddupq_m_n_uv4si (__arm_vuninitializedq_u32 (), __a, __imm, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_x_wb_u8 (uint32_t *__a, const int __imm, mve_pred16_t __p) -{ - uint8x16_t __arg1 = __arm_vuninitializedq_u8 (); - uint8x16_t __res = __builtin_mve_vddupq_m_n_uv16qi (__arg1, * __a, __imm, __p); - *__a -= __imm * 16u; - return __res; -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_x_wb_u16 (uint32_t *__a, const int __imm, mve_pred16_t __p) -{ - uint16x8_t __arg1 = __arm_vuninitializedq_u16 (); - uint16x8_t __res = __builtin_mve_vddupq_m_n_uv8hi (__arg1, *__a, __imm, __p); - *__a -= __imm * 8u; - return __res; -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_x_wb_u32 (uint32_t *__a, const int __imm, mve_pred16_t __p) -{ - uint32x4_t __arg1 = __arm_vuninitializedq_u32 (); - uint32x4_t __res = __builtin_mve_vddupq_m_n_uv4si (__arg1, *__a, __imm, __p); - *__a -= __imm * 4u; - return __res; -} - __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_x_n_u8 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) @@ -2375,57 +2082,6 @@ __arm_vdwdupq_x_wb_u32 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16 return __res; } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_x_n_u8 (uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __builtin_mve_vidupq_m_n_uv16qi (__arm_vuninitializedq_u8 (), __a, __imm, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_x_n_u16 (uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __builtin_mve_vidupq_m_n_uv8hi (__arm_vuninitializedq_u16 (), __a, __imm, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_x_n_u32 (uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __builtin_mve_vidupq_m_n_uv4si (__arm_vuninitializedq_u32 (), __a, __imm, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_x_wb_u8 (uint32_t *__a, const int __imm, mve_pred16_t __p) -{ - uint8x16_t __arg1 = __arm_vuninitializedq_u8 (); - uint8x16_t __res = __builtin_mve_vidupq_m_n_uv16qi (__arg1, *__a, __imm, __p); - *__a += __imm * 16u; - return __res; -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_x_wb_u16 (uint32_t *__a, const int __imm, mve_pred16_t __p) -{ - uint16x8_t __arg1 = __arm_vuninitializedq_u16 (); - uint16x8_t __res = __builtin_mve_vidupq_m_n_uv8hi (__arg1, *__a, __imm, __p); - *__a += __imm * 8u; - return __res; -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_x_wb_u32 (uint32_t *__a, const int __imm, mve_pred16_t __p) -{ - uint32x4_t __arg1 = __arm_vuninitializedq_u32 (); - uint32x4_t __res = __builtin_mve_vidupq_m_n_uv4si (__arg1, *__a, __imm, __p); - *__a += __imm * 4u; - return __res; -} - __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_x_n_u8 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) @@ -4475,69 +4131,6 @@ __arm_vstrwq_scatter_shifted_offset (uint32_t * __base, uint32x4_t __offset, uin __arm_vstrwq_scatter_shifted_offset_u32 (__base, __offset, __value); } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_m (uint8x16_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vddupq_m_n_u8 (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_m (uint32x4_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vddupq_m_n_u32 (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_m (uint16x8_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vddupq_m_n_u16 (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_m (uint8x16_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vddupq_m_wb_u8 (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_m (uint16x8_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vddupq_m_wb_u16 (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_m (uint32x4_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vddupq_m_wb_u32 (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_u8 (uint32_t __a, const int __imm) -{ - return __arm_vddupq_n_u8 (__a, __imm); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_u32 (uint32_t __a, const int __imm) -{ - return __arm_vddupq_n_u32 (__a, __imm); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_u16 (uint32_t __a, const int __imm) -{ - return __arm_vddupq_n_u16 (__a, __imm); -} - __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_m (uint8x16_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) @@ -4622,111 +4215,6 @@ __arm_vdwdupq_u16 (uint32_t * __a, uint32_t __b, const int __imm) return __arm_vdwdupq_wb_u16 (__a, __b, __imm); } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_m (uint8x16_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vidupq_m_n_u8 (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_m (uint32x4_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vidupq_m_n_u32 (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_m (uint16x8_t __inactive, uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vidupq_m_n_u16 (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_u8 (uint32_t __a, const int __imm) -{ - return __arm_vidupq_n_u8 (__a, __imm); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_m (uint8x16_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vidupq_m_wb_u8 (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_m (uint16x8_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vidupq_m_wb_u16 (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_m (uint32x4_t __inactive, uint32_t * __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vidupq_m_wb_u32 (__inactive, __a, __imm, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_u32 (uint32_t __a, const int __imm) -{ - return __arm_vidupq_n_u32 (__a, __imm); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_u16 (uint32_t __a, const int __imm) -{ - return __arm_vidupq_n_u16 (__a, __imm); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_u8 (uint32_t * __a, const int __imm) -{ - return __arm_vidupq_wb_u8 (__a, __imm); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_u16 (uint32_t * __a, const int __imm) -{ - return __arm_vidupq_wb_u16 (__a, __imm); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_u32 (uint32_t * __a, const int __imm) -{ - return __arm_vidupq_wb_u32 (__a, __imm); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_u8 (uint32_t * __a, const int __imm) -{ - return __arm_vddupq_wb_u8 (__a, __imm); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_u16 (uint32_t * __a, const int __imm) -{ - return __arm_vddupq_wb_u16 (__a, __imm); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_u32 (uint32_t * __a, const int __imm) -{ - return __arm_vddupq_wb_u32 (__a, __imm); -} - __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_m (uint8x16_t __inactive, uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) @@ -4867,48 +4355,6 @@ __arm_vstrwq_scatter_base_wb (uint32x4_t * __addr, const int __offset, uint32x4_ __arm_vstrwq_scatter_base_wb_u32 (__addr, __offset, __value); } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_x_u8 (uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vddupq_x_n_u8 (__a, __imm, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_x_u16 (uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vddupq_x_n_u16 (__a, __imm, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_x_u32 (uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vddupq_x_n_u32 (__a, __imm, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_x_u8 (uint32_t *__a, const int __imm, mve_pred16_t __p) -{ - return __arm_vddupq_x_wb_u8 (__a, __imm, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_x_u16 (uint32_t *__a, const int __imm, mve_pred16_t __p) -{ - return __arm_vddupq_x_wb_u16 (__a, __imm, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vddupq_x_u32 (uint32_t *__a, const int __imm, mve_pred16_t __p) -{ - return __arm_vddupq_x_wb_u32 (__a, __imm, __p); -} - __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_vdwdupq_x_u8 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) @@ -4951,48 +4397,6 @@ __arm_vdwdupq_x_u32 (uint32_t *__a, uint32_t __b, const int __imm, mve_pred16_t return __arm_vdwdupq_x_wb_u32 (__a, __b, __imm, __p); } -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_x_u8 (uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vidupq_x_n_u8 (__a, __imm, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_x_u16 (uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vidupq_x_n_u16 (__a, __imm, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_x_u32 (uint32_t __a, const int __imm, mve_pred16_t __p) -{ - return __arm_vidupq_x_n_u32 (__a, __imm, __p); -} - -__extension__ extern __inline uint8x16_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_x_u8 (uint32_t *__a, const int __imm, mve_pred16_t __p) -{ - return __arm_vidupq_x_wb_u8 (__a, __imm, __p); -} - -__extension__ extern __inline uint16x8_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_x_u16 (uint32_t *__a, const int __imm, mve_pred16_t __p) -{ - return __arm_vidupq_x_wb_u16 (__a, __imm, __p); -} - -__extension__ extern __inline uint32x4_t -__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) -__arm_vidupq_x_u32 (uint32_t *__a, const int __imm, mve_pred16_t __p) -{ - return __arm_vidupq_x_wb_u32 (__a, __imm, __p); -} - __extension__ extern __inline uint8x16_t __attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) __arm_viwdupq_x_u8 (uint32_t __a, uint32_t __b, const int __imm, mve_pred16_t __p) @@ -6773,36 +6177,6 @@ extern void *__ARM_undef; 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_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_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_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_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_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_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_u32_ptr(__p1, uint32_t *), p2, p3));}) - #define __arm_vadciq(p0,p1,p2) ({ __typeof(p0) __p0 = (p0); \ __typeof(p1) __p1 = (p1); \ _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \ @@ -6905,56 +6279,6 @@ extern void *__ARM_undef; 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); \ - _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \ - 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_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); \ - _Generic( (int (*)[__ARM_mve_typeid(__p0)][__ARM_mve_typeid(__p1)])0, \ - 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_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_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_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_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_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_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_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, \