From patchwork Wed Dec 6 02:45:21 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Feng Wang X-Patchwork-Id: 1872422 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org 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 4SlMHP1TC7z23mf for ; Wed, 6 Dec 2023 13:46:40 +1100 (AEDT) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id D42FC3865C24 for ; Wed, 6 Dec 2023 02:46:37 +0000 (GMT) X-Original-To: gcc-patches@gcc.gnu.org Delivered-To: gcc-patches@gcc.gnu.org Received: from zg8tmja2lje4os4yms4ymjma.icoremail.net (zg8tmja2lje4os4yms4ymjma.icoremail.net [206.189.21.223]) by sourceware.org (Postfix) with ESMTP id 6DA8E3858289 for ; Wed, 6 Dec 2023 02:46:25 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 6DA8E3858289 Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=eswincomputing.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=eswincomputing.com ARC-Filter: OpenARC Filter v1.0.0 sourceware.org 6DA8E3858289 Authentication-Results: server2.sourceware.org; arc=none smtp.remote-ip=206.189.21.223 ARC-Seal: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1701830787; cv=none; b=oFZdNRBHttxuzRiJhC2Z5nL7hP1NQTv/f+vx1SvZtxNBc51zazcS9iBucePZmuUB9Gc1BjTUNbMceBXoAnVq9rs0UczrZkhEkVuKosUNRwjRRF/wHlgrQ0bQ4brM22AJoZbc+/J9l2Lh67NTQcYuC853XuJWxUQmvUNjow2dojc= ARC-Message-Signature: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1701830787; c=relaxed/simple; bh=5pP5svK45dh2kuQ1VBoH1Km7j4+mSssNMrvEWSxgLe0=; h=From:To:Subject:Date:Message-Id; b=IXCyZMCn7m6GN6AW+wJNgmPVpiq7ZR0Vg+xk0qhMOu0K5l2gi4Fe2XGX8n37NAVfH1sPS8g6ysdS4cAjhvJnD5YQ9fML+UXWGbJ9tjSZ97Qn2VrBD6LvxjG3UlM2uKiMZv0DRrxUNRDnowhlFgffqJ3jCPI3UZ3o96SqVvAMHwc= ARC-Authentication-Results: i=1; server2.sourceware.org Received: from localhost.localdomain (unknown [10.12.130.31]) by app2 (Coremail) with SMTP id TQJkCgAnttQ54G9llmIAAA--.5861S4; Wed, 06 Dec 2023 10:45:14 +0800 (CST) From: Feng Wang To: gcc-patches@gcc.gnu.org Cc: kito.cheng@gmail.com, jeffreyalaw@gmail.com, juzhe.zhong@rivai.ai, zhusonghe@eswincomputing.com, panciyan@eswincomputing.com, Feng Wang Subject: [PATCH 1/4] RISC-V: Add crypto vector implied ISA info. Date: Wed, 6 Dec 2023 02:45:21 +0000 Message-Id: <20231206024524.10792-1-wangfeng@eswincomputing.com> X-Mailer: git-send-email 2.17.1 X-CM-TRANSID: TQJkCgAnttQ54G9llmIAAA--.5861S4 X-Coremail-Antispam: 1UD129KBjvdXoW7Gryftw4Dur4DZrWfWr4fGrg_yoWDJFc_Cr WjgFsFqr4DJa95tFyDXr4YgrWrA3yrJ34xG34xtwnF9w1UZrW3Awn8tFs3Jw48ur98J3Zr Ar4fXF1ayr1UtjkaLaAFLSUrUUUUUb8apTn2vfkv8UJUUUU8Yxn0WfASr-VFAUDa7-sFnT 9fnUUIcSsGvfJTRUUUb28FF20E14v26r4j6ryUM7CY07I20VC2zVCF04k26cxKx2IYs7xG 6rWj6s0DM7CIcVAFz4kK6r1j6r18M28lY4IEw2IIxxk0rwA2F7IY1VAKz4vEj48ve4kI8w A2z4x0Y4vE2Ix0cI8IcVAFwI0_tr0E3s1l84ACjcxK6xIIjxv20xvEc7CjxVAFwI0_Gr1j 6F4UJwA2z4x0Y4vEx4A2jsIE14v26rxl6s0DM28EF7xvwVC2z280aVCY1x0267AKxVW0oV Cq3wAS0I0E0xvYzxvE52x082IY62kv0487Mc02F40EFcxC0VAKzVAqx4xG6I80ewAv7VC0 I7IYx2IY67AKxVWUJVWUGwAv7VC2z280aVAFwI0_Jr0_Gr1lOx8S6xCaFVCjc4AY6r1j6r 4UM4x0Y48IcxkI7VAKI48JM4x0x7Aq67IIx4CEVc8vx2IErcIFxwCY02Avz4vE-syl42xK 82IYc2Ij64vIr41l4I8I3I0E4IkC6x0Yz7v_Jr0_Gr1lx2IqxVAqx4xG67AKxVWUJVWUGw C20s026x8GjcxK67AKxVWUGVWUWwC2zVAF1VAY17CE14v26r126r1DMIIYrxkI7VAKI48J MIIF0xvE2Ix0cI8IcVAFwI0_Jr0_JF4lIxAIcVC0I7IYx2IY6xkF7I0E14v26r1j6r4UMI IF0xvE42xK8VAvwI8IcIk0rVWUJVWUCwCI42IY6I8E87Iv67AKxVWUJVW8JwCI42IY6I8E 87Iv6xkF7I0E14v26r1j6r4UYxBIdaVFxhVjvjDU0xZFpf9x0JUdHUDUUUUU= X-CM-SenderInfo: pzdqwwxhqjqvxvzl0uprps33xlqjhudrp/ X-Spam-Status: No, score=-12.5 required=5.0 tests=BAYES_00, GIT_PATCH_0, KAM_DMARC_STATUS, RCVD_IN_MSPIKE_H4, RCVD_IN_MSPIKE_WL, 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 Due to the crypto vector entension is depend on the Vector extension, so the "v" info is added into implied ISA info with the corresponding crypto vector extension. gcc/ChangeLog: * common/config/riscv/riscv-common.cc: Add "v" into implied ISA info. --- gcc/common/config/riscv/riscv-common.cc | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/gcc/common/config/riscv/riscv-common.cc b/gcc/common/config/riscv/riscv-common.cc index 6c210412515..dbb42ca2f1e 100644 --- a/gcc/common/config/riscv/riscv-common.cc +++ b/gcc/common/config/riscv/riscv-common.cc @@ -120,6 +120,15 @@ static const riscv_implied_info_t riscv_implied_info[] = {"zvksc", "zvbc"}, {"zvksg", "zvks"}, {"zvksg", "zvkg"}, + {"zvbb", "zvkb"}, + {"zvbc", "v"}, + {"zvkb", "v"}, + {"zvkg", "v"}, + {"zvkned", "v"}, + {"zvknha", "v"}, + {"zvknhb", "v"}, + {"zvksed", "v"}, + {"zvksh", "v"}, {"zfh", "zfhmin"}, {"zfhmin", "f"}, From patchwork Wed Dec 6 02:45:22 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Feng Wang X-Patchwork-Id: 1872423 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org 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 4SlMHR6wS0z23mf for ; Wed, 6 Dec 2023 13:46:43 +1100 (AEDT) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 06855384770F for ; Wed, 6 Dec 2023 02:46:42 +0000 (GMT) X-Original-To: gcc-patches@gcc.gnu.org Delivered-To: gcc-patches@gcc.gnu.org Received: from zg8tmtyylji0my4xnjqumte4.icoremail.net (zg8tmtyylji0my4xnjqumte4.icoremail.net [162.243.164.118]) by sourceware.org (Postfix) with ESMTP id 393863858020 for ; Wed, 6 Dec 2023 02:46:27 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 393863858020 Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=eswincomputing.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=eswincomputing.com ARC-Filter: OpenARC Filter v1.0.0 sourceware.org 393863858020 Authentication-Results: server2.sourceware.org; arc=none smtp.remote-ip=162.243.164.118 ARC-Seal: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1701830791; cv=none; b=EPIicgxe0tv5/Bo5i7d3d7wsBXJrw8uOSfOV2myfb40P7Osij11Jd+6RB6W392udY+hOcyo8LpRfTOE6KfXK/AiwW7gL3nuBdanG8l6qMkSFcvxmgtmEUrcrdlao02ODifhUD6KRYjso/LXuVxZr+XkNaP2jal7n3GD91vj7dis= ARC-Message-Signature: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1701830791; c=relaxed/simple; bh=TS2A+15oTRGKsz/Exg47tGyyM4GNcAIu2P3B3t5INUw=; h=From:To:Subject:Date:Message-Id; b=XzHnnMr3MUWnPEj4qeSZEjQdVufs7gEbTQg3J6xZ7wlNunutbv2NTi7x36jyBsRaYI3IR9pP7b+FjCoyJ/t20jJjRp6Mj9YJYBl50bac8d4k6F1Yn2IIghuxbjSGRJB79qlh0YMGM8NwWIv5p8F+N/WGNlJpXFjwBSiuzrsCnHY= ARC-Authentication-Results: i=1; server2.sourceware.org Received: from localhost.localdomain (unknown [10.12.130.31]) by app2 (Coremail) with SMTP id TQJkCgAnttQ54G9llmIAAA--.5861S5; Wed, 06 Dec 2023 10:45:17 +0800 (CST) From: Feng Wang To: gcc-patches@gcc.gnu.org Cc: kito.cheng@gmail.com, jeffreyalaw@gmail.com, juzhe.zhong@rivai.ai, zhusonghe@eswincomputing.com, panciyan@eswincomputing.com, Feng Wang Subject: [PATCH 2/4] RISC-V: Add crypto vector builtin function. Date: Wed, 6 Dec 2023 02:45:22 +0000 Message-Id: <20231206024524.10792-2-wangfeng@eswincomputing.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20231206024524.10792-1-wangfeng@eswincomputing.com> References: <20231206024524.10792-1-wangfeng@eswincomputing.com> X-CM-TRANSID: TQJkCgAnttQ54G9llmIAAA--.5861S5 X-Coremail-Antispam: 1UD129KBjvAXoWfAw1xtw4DCr4UGrW5urWrAFb_yoWrGFy7Ko ZIqr4rZF4fWr1xu393uw1fWrykW3Z5ZrsxZ3WFgF98C3Z3AryFk3s2va4UJa42yr42qF1U Aan7uFW7XaykXFn5n29KB7ZKAUJUUUUU529EdanIXcx71UUUUU7v73VFW2AGmfu7bjvjm3 AaLaJ3UjIYCTnIWjp_UUUYA7AC8VAFwI0_Xr0_Wr1l1xkIjI8I6I8E6xAIw20EY4v20xva j40_Wr0E3s1l1IIY67AEw4v_Jr0_Jr4l82xGYIkIc2x26280x7IE14v26r18M28IrcIa0x kI8VCY1x0267AKxVWUCVW8JwA2ocxC64kIII0Yj41l84x0c7CEw4AK67xGY2AK021l84AC jcxK6xIIjxv20xvE14v26w1j6s0DM28EF7xvwVC0I7IYx2IY6xkF7I0E14v26r4UJVWxJr 1l84ACjcxK6I8E87Iv67AKxVW0oVCq3wA2z4x0Y4vEx4A2jsIEc7CjxVAFwI0_GcCE3s1l e2I262IYc4CY6c8Ij28IcVAaY2xG8wAqx4xG64xvF2IEw4CE5I8CrVC2j2WlYx0E2Ix0cI 8IcVAFwI0_Jr0_Jr4lYx0Ex4A2jsIE14v26r1j6r4UMcvjeVCFs4IE7xkEbVWUJVW8JwAC jcxG0xvY0x0EwIxGrwACjI8F5VA0II8E6IAqYI8I648v4I1lc2xSY4AK6svPMxAIw28Icx kI7VAKI48JMxC20s026xCaFVCjc4AY6r1j6r4UMI8I3I0E5I8CrVAFwI0_Jr0_Jr4lx2Iq xVCjr7xvwVAFwI0_JrI_JrWlx4CE17CEb7AF67AKxVWUAVWUtwCIc40Y0x0EwIxGrwCI42 IY6xIIjxv20xvE14v26r1j6r1xMIIF0xvE2Ix0cI8IcVCY1x0267AKxVW8JVWxJwCI42IY 6xAIw20EY4v20xvaj40_Jr0_JF4lIxAIcVC2z280aVAFwI0_Jr0_Gr1lIxAIcVC2z280aV CY1x0267AKxVW8JVW8JrUvcSsGvfC2KfnxnUUI43ZEXa7VUbec_DUUUUU== X-CM-SenderInfo: pzdqwwxhqjqvxvzl0uprps33xlqjhudrp/ X-Spam-Status: No, score=-12.2 required=5.0 tests=BAYES_00, GIT_PATCH_0, KAM_DMARC_STATUS, RCVD_IN_MSPIKE_H4, RCVD_IN_MSPIKE_WL, 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 This patch add the intrinsic funtions of crypto vector based on the intrinsic doc(https://github.com/riscv-non-isa/rvv-intrinsic-doc/blob /eopc/vector-crypto/auto-generated/vector-crypto/intrinsic_funcs.md). Co-Authored by: Songhe Zhu Co-Authored by: Ciyan Pan gcc/ChangeLog: * config/riscv/riscv-vector-builtins-bases.cc (class vandn): Add new function_base for crypto vector. (class bitmanip): Ditto. (class b_reverse):Ditto. (class vwsll): Ditto. (class clmul): Ditto. (class vg_nhab): Ditto. (class crypto_vv):Ditto. (class crypto_vi):Ditto. (class vaeskf2_vsm3c):Ditto. (class vsm3me):Ditto. (BASE): Add BASE declaration for crypto vector. * config/riscv/riscv-vector-builtins-bases.h: Ditto. * config/riscv/riscv-vector-builtins-shapes.cc (struct crypto_vv_def): Add new function_shape for crypto vector. (struct crypto_vi_def): Ditto. (SHAPE): Add SHAPE declaration of crypto vector. * config/riscv/riscv-vector-builtins-shapes.h: Ditto. * config/riscv/riscv-vector-builtins.cc (DEF_RVV_CRYPTO_SEW32_OPS): Add new data struct for crypto vector. (DEF_RVV_CRYPTO_SEW64_OPS): Ditto. (DEF_VECTOR_CRYPTO_FUNCTION): New MACRO define of crypto vector. (registered_function::overloaded_hash): Processing size_t uimm for C overloaded func. (handle_pragma_vector): Add registration for crypto vector. * config/riscv/riscv-vector-builtins.def (vi): Add vi OP_TYPE. * config/riscv/riscv-vector-builtins.h (struct crypto_function_group_info): Add new struct definition for crypto vector. * config/riscv/t-riscv: Add building dependency files. * config/riscv/riscv-vector-crypto-builtins-avail.h: New file to control enable. * config/riscv/riscv-vector-crypto-builtins-functions.def: New file. Definition of crypto vector. * config/riscv/riscv-vector-crypto-builtins-types.def: New file. New type definition for crypto vector. --- .../riscv/riscv-vector-builtins-bases.cc | 259 +++++++++++++++++- .../riscv/riscv-vector-builtins-bases.h | 28 ++ .../riscv/riscv-vector-builtins-shapes.cc | 66 ++++- .../riscv/riscv-vector-builtins-shapes.h | 4 + gcc/config/riscv/riscv-vector-builtins.cc | 152 +++++++++- gcc/config/riscv/riscv-vector-builtins.def | 1 + gcc/config/riscv/riscv-vector-builtins.h | 8 + .../riscv-vector-crypto-builtins-avail.h | 25 ++ ...riscv-vector-crypto-builtins-functions.def | 78 ++++++ .../riscv-vector-crypto-builtins-types.def | 21 ++ gcc/config/riscv/t-riscv | 2 + 11 files changed, 641 insertions(+), 3 deletions(-) create mode 100755 gcc/config/riscv/riscv-vector-crypto-builtins-avail.h create mode 100755 gcc/config/riscv/riscv-vector-crypto-builtins-functions.def create mode 100755 gcc/config/riscv/riscv-vector-crypto-builtins-types.def diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.cc b/gcc/config/riscv/riscv-vector-builtins-bases.cc index d70468542ee..6d52230e9ba 100644 --- a/gcc/config/riscv/riscv-vector-builtins-bases.cc +++ b/gcc/config/riscv/riscv-vector-builtins-bases.cc @@ -2127,6 +2127,207 @@ public: } }; +/* Below implements are vector crypto */ +/* Implements vandn.[vv,vx] */ +class vandn : public function_base +{ +public: + rtx expand (function_expander &e) const override + { + switch (e.op_info->op) + { + case OP_TYPE_vv: + return e.use_exact_insn (code_for_pred_vandn (e.vector_mode ())); + case OP_TYPE_vx: + return e.use_exact_insn (code_for_pred_vandn_scalar (e.vector_mode ())); + default: + gcc_unreachable (); + } + } +}; + +/* Implements vrol/vror/clz/ctz. */ +template +class bitmanip : public function_base +{ +public: + bool apply_tail_policy_p () const override + { + return (CODE == CLZ || CODE == CTZ) ? false : true; + } + bool apply_mask_policy_p () const override + { + return (CODE == CLZ || CODE == CTZ) ? false : true; + } + bool has_merge_operand_p () const override + { + return (CODE == CLZ || CODE == CTZ) ? false : true; + } + + rtx expand (function_expander &e) const override + { + switch (e.op_info->op) + { + case OP_TYPE_v: + case OP_TYPE_vv: + return e.use_exact_insn (code_for_pred_v (CODE, e.vector_mode ())); + case OP_TYPE_vx: + return e.use_exact_insn (code_for_pred_v_scalar (CODE, e.vector_mode ())); + default: + gcc_unreachable (); + } + } +}; + +/* Implements vbrev/vbrev8/vrev8. */ +template +class b_reverse : public function_base +{ +public: + rtx expand (function_expander &e) const override + { + return e.use_exact_insn (code_for_pred_v (UNSPEC, e.vector_mode ())); + } +}; + +class vwsll : public function_base +{ +public: + rtx expand (function_expander &e) const override + { + switch (e.op_info->op) + { + case OP_TYPE_vv: + return e.use_exact_insn (code_for_pred_vwsll (e.vector_mode ())); + case OP_TYPE_vx: + return e.use_exact_insn (code_for_pred_vwsll_scalar (e.vector_mode ())); + default: + gcc_unreachable (); + } + } +}; + +/* Implements clmul */ +template +class clmul : public function_base +{ +public: + rtx expand (function_expander &e) const override + { + switch (e.op_info->op) + { + case OP_TYPE_vv: + return e.use_exact_insn (code_for_pred_vclmul (UNSPEC, e.vector_mode ())); + case OP_TYPE_vx: + return e.use_exact_insn (code_for_pred_vclmul_scalar (UNSPEC, e.vector_mode ())); + default: + gcc_unreachable (); + } + } +}; + +/* Implements vghsh/vsh2ms/vsha2c[hl]. */ +template +class vg_nhab : public function_base +{ +public: + bool apply_mask_policy_p () const override { return false; } + bool use_mask_predication_p () const override { return false; } + bool has_merge_operand_p () const override { return false; } + + rtx expand (function_expander &e) const override + { + return e.use_exact_insn (code_for_pred_v (UNSPEC, e.vector_mode ())); + } +}; + +/* Implements vgmul/vaes*. */ +template +class crypto_vv : public function_base +{ +public: + bool apply_mask_policy_p () const override { return false; } + bool use_mask_predication_p () const override { return false; } + bool has_merge_operand_p () const override { return false; } + + rtx expand (function_expander &e) const override + { + poly_uint64 nunits = 0U; + switch (e.op_info->op) + { + case OP_TYPE_vv: + if (UNSPEC == UNSPEC_VGMUL) + return e.use_exact_insn (code_for_pred_crypto_vv (UNSPEC, UNSPEC, e.vector_mode ())); + else + return e.use_exact_insn (code_for_pred_crypto_vv + (UNSPEC + 1, UNSPEC + 1, e.vector_mode ())); + case OP_TYPE_vs: + /* Calculate the ratio between arg0 and arg1*/ + multiple_p (GET_MODE_BITSIZE (e.arg_mode (0)), + GET_MODE_BITSIZE (e.arg_mode (1)), &nunits); + if (maybe_eq (nunits, 1U)) + return e.use_exact_insn (code_for_pred_crypto_vvx1_scalar + (UNSPEC +2, UNSPEC + 2, e.vector_mode ())); + else if (maybe_eq (nunits, 2U)) + return e.use_exact_insn (code_for_pred_crypto_vvx2_scalar + (UNSPEC + 2, UNSPEC + 2, e.vector_mode ())); + else if (maybe_eq (nunits, 4U)) + return e.use_exact_insn (code_for_pred_crypto_vvx4_scalar + (UNSPEC + 2, UNSPEC + 2, e.vector_mode ())); + else if (maybe_eq (nunits, 8U)) + return e.use_exact_insn (code_for_pred_crypto_vvx8_scalar + (UNSPEC + 2, UNSPEC + 2, e.vector_mode ())); + else + return e.use_exact_insn (code_for_pred_crypto_vvx16_scalar + (UNSPEC + 2, UNSPEC + 2, e.vector_mode ())); + default: + gcc_unreachable (); + } + } +}; + +/* Implements vaeskf1/vsm4k. */ +template +class crypto_vi : public function_base +{ +public: + bool apply_mask_policy_p () const override { return false; } + bool use_mask_predication_p () const override { return false; } + + rtx expand (function_expander &e) const override + { + return e.use_exact_insn (code_for_pred_crypto_vi_scalar (UNSPEC, e.vector_mode ())); + } +}; + +/* Implements vaeskf2/vsm3c. */ +template +class vaeskf2_vsm3c : public function_base +{ +public: + bool apply_mask_policy_p () const override { return false; } + bool use_mask_predication_p () const override { return false; } + bool has_merge_operand_p () const override { return false; } + + rtx expand (function_expander &e) const override + { + return e.use_exact_insn (code_for_pred_vi_nomaskedoff_scalar (UNSPEC, e.vector_mode ())); + } +}; + +/* Implements vsm3me. */ +class vsm3me : public function_base +{ +public: + bool apply_mask_policy_p () const override { return false; } + bool use_mask_predication_p () const override { return false; } + + rtx expand (function_expander &e) const override + { + return e.use_exact_insn (code_for_pred_vsm3me (e.vector_mode ())); + } +}; + static CONSTEXPR const vsetvl vsetvl_obj; static CONSTEXPR const vsetvl vsetvlmax_obj; static CONSTEXPR const loadstore vle_obj; @@ -2384,6 +2585,35 @@ static CONSTEXPR const seg_indexed_store vsuxseg_obj; static CONSTEXPR const seg_indexed_store vsoxseg_obj; static CONSTEXPR const vlsegff vlsegff_obj; +/* Crypto Vector */ +static CONSTEXPR const vandn vandn_obj; +static CONSTEXPR const bitmanip vrol_obj; +static CONSTEXPR const bitmanip vror_obj; +static CONSTEXPR const b_reverse vbrev_obj; +static CONSTEXPR const b_reverse vbrev8_obj; +static CONSTEXPR const b_reverse vrev8_obj; +static CONSTEXPR const bitmanip vclz_obj; +static CONSTEXPR const bitmanip vctz_obj; +static CONSTEXPR const vwsll vwsll_obj; +static CONSTEXPR const clmul vclmul_obj; +static CONSTEXPR const clmul vclmulh_obj; +static CONSTEXPR const vg_nhab vghsh_obj; +static CONSTEXPR const crypto_vv vgmul_obj; +static CONSTEXPR const crypto_vv vaesef_obj; +static CONSTEXPR const crypto_vv vaesem_obj; +static CONSTEXPR const crypto_vv vaesdf_obj; +static CONSTEXPR const crypto_vv vaesdm_obj; +static CONSTEXPR const crypto_vv vaesz_obj; +static CONSTEXPR const crypto_vi vaeskf1_obj; +static CONSTEXPR const vaeskf2_vsm3c vaeskf2_obj; +static CONSTEXPR const vg_nhab vsha2ms_obj; +static CONSTEXPR const vg_nhab vsha2ch_obj; +static CONSTEXPR const vg_nhab vsha2cl_obj; +static CONSTEXPR const crypto_vi vsm4k_obj; +static CONSTEXPR const crypto_vv vsm4r_obj; +static CONSTEXPR const vsm3me vsm3me_obj; +static CONSTEXPR const vaeskf2_vsm3c vsm3c_obj; + /* Declare the function base NAME, pointing it to an instance of class _obj. */ #define BASE(NAME) \ @@ -2645,5 +2875,32 @@ BASE (vloxseg) BASE (vsuxseg) BASE (vsoxseg) BASE (vlsegff) - +/* Crypto vector */ +BASE (vandn) +BASE (vbrev) +BASE (vbrev8) +BASE (vrev8) +BASE (vclz) +BASE (vctz) +BASE (vrol) +BASE (vror) +BASE (vwsll) +BASE (vclmul) +BASE (vclmulh) +BASE (vghsh) +BASE (vgmul) +BASE (vaesef) +BASE (vaesem) +BASE (vaesdf) +BASE (vaesdm) +BASE (vaesz) +BASE (vaeskf1) +BASE (vaeskf2) +BASE (vsha2ms) +BASE (vsha2ch) +BASE (vsha2cl) +BASE (vsm4k) +BASE (vsm4r) +BASE (vsm3me) +BASE (vsm3c) } // end namespace riscv_vector diff --git a/gcc/config/riscv/riscv-vector-builtins-bases.h b/gcc/config/riscv/riscv-vector-builtins-bases.h index 131041ea66f..51b53a3d4a9 100644 --- a/gcc/config/riscv/riscv-vector-builtins-bases.h +++ b/gcc/config/riscv/riscv-vector-builtins-bases.h @@ -280,6 +280,34 @@ extern const function_base *const vloxseg; extern const function_base *const vsuxseg; extern const function_base *const vsoxseg; extern const function_base *const vlsegff; +/* Below function_base are Vectro Crypto*/ +extern const function_base *const vandn; +extern const function_base *const vbrev; +extern const function_base *const vbrev8; +extern const function_base *const vrev8; +extern const function_base *const vclz; +extern const function_base *const vctz; +extern const function_base *const vrol; +extern const function_base *const vror; +extern const function_base *const vwsll; +extern const function_base *const vclmul; +extern const function_base *const vclmulh; +extern const function_base *const vghsh; +extern const function_base *const vgmul; +extern const function_base *const vaesef; +extern const function_base *const vaesem; +extern const function_base *const vaesdf; +extern const function_base *const vaesdm; +extern const function_base *const vaesz; +extern const function_base *const vaeskf1; +extern const function_base *const vaeskf2; +extern const function_base *const vsha2ms; +extern const function_base *const vsha2ch; +extern const function_base *const vsha2cl; +extern const function_base *const vsm4k; +extern const function_base *const vsm4r; +extern const function_base *const vsm3me; +extern const function_base *const vsm3c; } } // end namespace riscv_vector diff --git a/gcc/config/riscv/riscv-vector-builtins-shapes.cc b/gcc/config/riscv/riscv-vector-builtins-shapes.cc index 4a754e0228f..c6a7574c019 100644 --- a/gcc/config/riscv/riscv-vector-builtins-shapes.cc +++ b/gcc/config/riscv/riscv-vector-builtins-shapes.cc @@ -984,6 +984,69 @@ struct seg_fault_load_def : public build_base } }; +/* vghsh/vgmul/vsha2ms/vsha2ch/vsha2cl/vsm3me/vaes* class. */ +struct crypto_vv_def : public build_base +{ + char *get_name (function_builder &b, const function_instance &instance, + bool overloaded_p) const override + { + /* Return nullptr if it can not be overloaded. */ + if (overloaded_p && !instance.base->can_be_overloaded_p (instance.pred)) + return nullptr; + b.append_base_name (instance.base_name); + /* There is no op_type name in vghsh/vgmul/vaesz/vsha2ms/vsha2ch/vsha2cl/ + vsm3me overloaded intrinsic */ + if (!((strcmp (instance.base_name, "vghsh") == 0 + || strcmp (instance.base_name, "vgmul") == 0 + || strcmp (instance.base_name, "vaesz") == 0 + || strcmp (instance.base_name, "vsha2ms") == 0 + || strcmp (instance.base_name, "vsha2ch") == 0 + || strcmp (instance.base_name, "vsha2cl") == 0 + || strcmp (instance.base_name, "vsm3me") == 0) + && overloaded_p)) + b.append_name (operand_suffixes[instance.op_info->op]); + if (!overloaded_p) + { + if (instance.op_info->op == OP_TYPE_vv) + b.append_name (type_suffixes[instance.type.index].vector); + else + { + vector_type_index arg0_type_idx + = instance.op_info->args[1].get_function_type_index + (instance.type.index); + b.append_name (type_suffixes[arg0_type_idx].vector); + vector_type_index ret_type_idx + = instance.op_info->ret.get_function_type_index + (instance.type.index); + b.append_name (type_suffixes[ret_type_idx].vector); + } + } + + b.append_name (predication_suffixes[instance.pred]); + return b.finish_name (); + } +}; + +/* vaeskf1/vaeskf2/vsm4k/vsm3c class. */ +struct crypto_vi_def : public build_base +{ + char *get_name (function_builder &b, const function_instance &instance, + bool overloaded_p) const override + { + /* Return nullptr if it can not be overloaded. */ + if (overloaded_p && !instance.base->can_be_overloaded_p (instance.pred)) + return nullptr; + b.append_base_name (instance.base_name); + if (!overloaded_p) + { + b.append_name (operand_suffixes[instance.op_info->op]); + b.append_name (type_suffixes[instance.type.index].vector); + } + b.append_name (predication_suffixes[instance.pred]); + return b.finish_name (); + } +}; + SHAPE(vsetvl, vsetvl) SHAPE(vsetvl, vsetvlmax) SHAPE(loadstore, loadstore) @@ -1012,5 +1075,6 @@ SHAPE(vlenb, vlenb) SHAPE(seg_loadstore, seg_loadstore) SHAPE(seg_indexed_loadstore, seg_indexed_loadstore) SHAPE(seg_fault_load, seg_fault_load) - +SHAPE(crypto_vv, crypto_vv) +SHAPE(crypto_vi, crypto_vi) } // end namespace riscv_vector diff --git a/gcc/config/riscv/riscv-vector-builtins-shapes.h b/gcc/config/riscv/riscv-vector-builtins-shapes.h index df9884bb572..3bb89b575ac 100644 --- a/gcc/config/riscv/riscv-vector-builtins-shapes.h +++ b/gcc/config/riscv/riscv-vector-builtins-shapes.h @@ -52,6 +52,10 @@ extern const function_shape *const vlenb; extern const function_shape *const seg_loadstore; extern const function_shape *const seg_indexed_loadstore; extern const function_shape *const seg_fault_load; +/* Below function_shape are Vectro Crypto*/ +extern const function_shape *const zvbb_zvbc; +extern const function_shape *const crypto_vv; +extern const function_shape *const crypto_vi; } } // end namespace riscv_vector diff --git a/gcc/config/riscv/riscv-vector-builtins.cc b/gcc/config/riscv/riscv-vector-builtins.cc index 6330a3a41c3..e5e8f0d19ac 100644 --- a/gcc/config/riscv/riscv-vector-builtins.cc +++ b/gcc/config/riscv/riscv-vector-builtins.cc @@ -51,6 +51,7 @@ #include "riscv-vector-builtins.h" #include "riscv-vector-builtins-shapes.h" #include "riscv-vector-builtins-bases.h" +#include "riscv-vector-crypto-builtins-avail.h" using namespace riscv_vector; @@ -521,6 +522,19 @@ static const rvv_type_info tuple_ops[] = { #include "riscv-vector-builtins-types.def" {NUM_VECTOR_TYPES, 0}}; +/* Below types will be registered for vector-crypto intrinsic functions*/ +/* A list of sew32 will be registered for vector-crypto intrinsic functions. */ +static const rvv_type_info crypto_sew32_ops[] = { +#define DEF_RVV_CRYPTO_SEW32_OPS(TYPE, REQUIRE) {VECTOR_TYPE_##TYPE, REQUIRE}, +#include "riscv-vector-crypto-builtins-types.def" + {NUM_VECTOR_TYPES, 0}}; + +/* A list of sew64 will be registered for vector-crypto intrinsic functions. */ +static const rvv_type_info crypto_sew64_ops[] = { +#define DEF_RVV_CRYPTO_SEW64_OPS(TYPE, REQUIRE) {VECTOR_TYPE_##TYPE, REQUIRE}, +#include "riscv-vector-crypto-builtins-types.def" + {NUM_VECTOR_TYPES, 0}}; + static CONSTEXPR const rvv_arg_type_info rvv_arg_type_info_end = rvv_arg_type_info (NUM_BASE_TYPES); @@ -754,6 +768,11 @@ static CONSTEXPR const rvv_arg_type_info v_size_args[] = {rvv_arg_type_info (RVV_BASE_vector), rvv_arg_type_info (RVV_BASE_size), rvv_arg_type_info_end}; +/* A list of args for vector_type func (double demote_type, size_t) function. */ +static CONSTEXPR const rvv_arg_type_info wv_size_args[] + = {rvv_arg_type_info (RVV_BASE_double_trunc_vector), + rvv_arg_type_info (RVV_BASE_size),rvv_arg_type_info_end}; + /* A list of args for vector_type func (vector_type, vector_type, size) * function. */ static CONSTEXPR const rvv_arg_type_info vv_size_args[] @@ -1044,6 +1063,14 @@ static CONSTEXPR const rvv_op_info u_v_ops rvv_arg_type_info (RVV_BASE_vector), /* Return type */ end_args /* Args */}; +/* A static operand information for vector_type func (vector_type) + * function registration. */ +static CONSTEXPR const rvv_op_info u_vv_ops + = {u_ops, /* Types */ + OP_TYPE_v, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vector), /* Return type */ + v_args /* Args */}; + /* A static operand information for unsigned long func (vector_type) * function registration. */ static CONSTEXPR const rvv_op_info b_ulong_m_ops @@ -2174,6 +2201,14 @@ static CONSTEXPR const rvv_op_info u_wvv_ops rvv_arg_type_info (RVV_BASE_vector), /* Return type */ wvv_args /* Args */}; +/* A static operand information for vector_type func (double demote type, size type) + * function registration. */ +static CONSTEXPR const rvv_op_info u_shift_wvx_ops + = {wextu_ops, /* Types */ + OP_TYPE_vx, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vector), /* Return type */ + wv_size_args /* Args */}; + /* A static operand information for vector_type func (double demote type, double * demote scalar_type) function registration. */ static CONSTEXPR const rvv_op_info i_wvx_ops @@ -2604,6 +2639,101 @@ static CONSTEXPR const rvv_op_info all_v_vcreate_lmul4_x2_ops rvv_arg_type_info (RVV_BASE_vlmul_ext_x2), /* Return type */ ext_vcreate_args /* Args */}; +/* A static operand information for vector_type func (vector_type). + Some ins just supports SEW=32, such as crypto vectol Zvkg extension. + * function registration. */ +static CONSTEXPR const rvv_arg_type_info vs_lmul_x2_args[] + = {rvv_arg_type_info (RVV_BASE_vlmul_ext_x2), + rvv_arg_type_info (RVV_BASE_vector), rvv_arg_type_info_end}; + +static CONSTEXPR const rvv_arg_type_info vs_lmul_x4_args[] + = {rvv_arg_type_info (RVV_BASE_vlmul_ext_x4), + rvv_arg_type_info (RVV_BASE_vector), rvv_arg_type_info_end}; + +static CONSTEXPR const rvv_arg_type_info vs_lmul_x8_args[] + = {rvv_arg_type_info (RVV_BASE_vlmul_ext_x8), + rvv_arg_type_info (RVV_BASE_vector), rvv_arg_type_info_end}; + +static CONSTEXPR const rvv_arg_type_info vs_lmul_x16_args[] + = {rvv_arg_type_info (RVV_BASE_vlmul_ext_x16), + rvv_arg_type_info (RVV_BASE_vector), rvv_arg_type_info_end}; + +static CONSTEXPR const rvv_op_info u_vvv_crypto_sew32_ops + = {crypto_sew32_ops, /* Types */ + OP_TYPE_vv, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vector), /* Return type */ + vv_args /* Args */}; + +static CONSTEXPR const rvv_op_info u_vvvv_crypto_sew32_ops + = {crypto_sew32_ops, /* Types */ + OP_TYPE_vv, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vector), /* Return type */ + vvv_args /* Args */}; + +static CONSTEXPR const rvv_op_info u_vvv_size_crypto_sew32_ops + = {crypto_sew32_ops, /* Types */ + OP_TYPE_vi, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vector), /* Return type */ + vv_size_args /* Args */}; + +static CONSTEXPR const rvv_op_info u_vv_size_crypto_sew32_ops + = {crypto_sew32_ops, /* Types */ + OP_TYPE_vi, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vector), /* Return type */ + v_size_args /* Args */}; + +static CONSTEXPR const rvv_op_info u_vvs_crypto_sew32_ops + = {crypto_sew32_ops, /* Types */ + OP_TYPE_vs, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vector), /* Return type */ + vv_args /* Args */}; + +static CONSTEXPR const rvv_op_info u_vvs_crypto_sew32_lmul_x2_ops + = {crypto_sew32_ops, /* Types */ + OP_TYPE_vs, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vlmul_ext_x2), /* Return type */ + vs_lmul_x2_args /* Args */}; + +static CONSTEXPR const rvv_op_info u_vvs_crypto_sew32_lmul_x4_ops + = {crypto_sew32_ops, /* Types */ + OP_TYPE_vs, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vlmul_ext_x4), /* Return type */ + vs_lmul_x4_args /* Args */}; + +static CONSTEXPR const rvv_op_info u_vvs_crypto_sew32_lmul_x8_ops + = {crypto_sew32_ops, /* Types */ + OP_TYPE_vs, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vlmul_ext_x8), /* Return type */ + vs_lmul_x8_args /* Args */}; + +static CONSTEXPR const rvv_op_info u_vvs_crypto_sew32_lmul_x16_ops + = {crypto_sew32_ops, /* Types */ + OP_TYPE_vs, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vlmul_ext_x16), /* Return type */ + vs_lmul_x16_args /* Args */}; + +/* A static operand information for vector_type func (vector_type). + Some ins just supports SEW=64, such as crypto vectol Zvbc extension + vclmul.vv, vclmul.vx. + * function registration. */ +static CONSTEXPR const rvv_op_info u_vvv_crypto_sew64_ops + = {crypto_sew64_ops, /* Types */ + OP_TYPE_vv, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vector), /* Return type */ + vv_args /* Args */}; + +static CONSTEXPR const rvv_op_info u_vvx_crypto_sew64_ops + = {crypto_sew64_ops, /* Types */ + OP_TYPE_vx, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vector), /* Return type */ + vx_args /* Args */}; + +static CONSTEXPR const rvv_op_info u_vvvv_crypto_sew64_ops + = {crypto_sew64_ops, /* Types */ + OP_TYPE_vv, /* Suffix */ + rvv_arg_type_info (RVV_BASE_vector), /* Return type */ + vvv_args /* Args */}; + /* A list of all RVV base function types. */ static CONSTEXPR const function_type_info function_types[] = { #define DEF_RVV_TYPE_INDEX( \ @@ -2689,6 +2819,14 @@ static function_group_info function_groups[] = { #include "riscv-vector-builtins-functions.def" }; +/* A list of all Vector Crypto intrinsic functions. */ +static crypto_function_group_info cryoto_function_groups[] = { +#define DEF_VECTOR_CRYPTO_FUNCTION(NAME, SHAPE, PREDS, OPS_INFO, AVAIL) \ + {#NAME, &bases::NAME, &shapes::SHAPE, PREDS, OPS_INFO,\ + riscv_vector_crypto_avail_ ## AVAIL}, +#include "riscv-vector-crypto-builtins-functions.def" +}; + /* The RVV types, with their built-in "__rvv..._t" name. Allow an index of NUM_VECTOR_TYPES, which always yields a null tree. */ @@ -4176,7 +4314,9 @@ registered_function::overloaded_hash (const vec &arglist) __riscv_vset(vint8m2_t dest, size_t index, vint8m1_t value); The reason is the same as above. */ if ((instance.base == bases::vget && (i == (len - 1))) - || (instance.base == bases::vset && (i == (len - 2)))) + || ((instance.base == bases::vset + || instance.shape == shapes::crypto_vi) + && (i == (len - 2)))) argument_types.safe_push (size_type_node); /* Vector fixed-point arithmetic instructions requiring argument vxrm. For example: vuint32m4_t __riscv_vaaddu(vuint32m4_t vs2, @@ -4414,6 +4554,16 @@ handle_pragma_vector () function_builder builder; for (unsigned int i = 0; i < ARRAY_SIZE (function_groups); ++i) builder.register_function_group (function_groups[i]); + + /* Since Crypto Vector intrinsic functions are depend on vector extension, + so the registration is placed at last */ + for (unsigned int i = 0; i < ARRAY_SIZE (cryoto_function_groups); ++i) + { + crypto_function_group_info *f = &cryoto_function_groups[i]; + if (f->avail ()) + builder.register_function_group\ + (cryoto_function_groups[i].rvv_function_group_info); + } } /* Return the function decl with RVV function subcode CODE, or error_mark_node diff --git a/gcc/config/riscv/riscv-vector-builtins.def b/gcc/config/riscv/riscv-vector-builtins.def index 6661629aad8..0c3ee3b2986 100644 --- a/gcc/config/riscv/riscv-vector-builtins.def +++ b/gcc/config/riscv/riscv-vector-builtins.def @@ -558,6 +558,7 @@ DEF_RVV_TYPE (vfloat64m8_t, 17, __rvv_float64m8_t, double, RVVM8DF, _f64m8, DEF_RVV_OP_TYPE (vv) DEF_RVV_OP_TYPE (vx) +DEF_RVV_OP_TYPE (vi) DEF_RVV_OP_TYPE (v) DEF_RVV_OP_TYPE (wv) DEF_RVV_OP_TYPE (wx) diff --git a/gcc/config/riscv/riscv-vector-builtins.h b/gcc/config/riscv/riscv-vector-builtins.h index cd8ccab1724..a62e8cb4845 100644 --- a/gcc/config/riscv/riscv-vector-builtins.h +++ b/gcc/config/riscv/riscv-vector-builtins.h @@ -234,6 +234,14 @@ struct function_group_info const rvv_op_info ops_infos; }; +/* Static information about a set of crypto vector functions. */ +struct crypto_function_group_info +{ + struct function_group_info rvv_function_group_info; + /* Whether the function is available. */ + unsigned int (*avail) (void); +}; + class GTY ((user)) function_instance { public: diff --git a/gcc/config/riscv/riscv-vector-crypto-builtins-avail.h b/gcc/config/riscv/riscv-vector-crypto-builtins-avail.h new file mode 100755 index 00000000000..c360c1d794f --- /dev/null +++ b/gcc/config/riscv/riscv-vector-crypto-builtins-avail.h @@ -0,0 +1,25 @@ +#ifndef GCC_RISCV_VECTOR_CRYPTO_BUILTINS_AVAIL_H +#define GCC_RISCV_VECTOR_CRYPTO_BUILTINS_AVAIL_H + +#include "insn-codes.h" +namespace riscv_vector { + +/* Declare an availability predicate for built-in functions. */ +#define AVAIL(NAME, COND) \ + static unsigned int \ + riscv_vector_crypto_avail_##NAME (void) \ + { \ + return (COND); \ + } + +AVAIL (zvbb, TARGET_ZVBB) +AVAIL (zvbc, TARGET_ZVBC) +AVAIL (zvkb_or_zvbb, TARGET_ZVKB || TARGET_ZVBB) +AVAIL (zvkg, TARGET_ZVKG) +AVAIL (zvkned, TARGET_ZVKNED) +AVAIL (zvknha_or_zvknhb, TARGET_ZVKNHA || TARGET_ZVKNHB) +AVAIL (zvknhb, TARGET_ZVKNHB) +AVAIL (zvksed, TARGET_ZVKSED) +AVAIL (zvksh, TARGET_ZVKSH) +} +#endif diff --git a/gcc/config/riscv/riscv-vector-crypto-builtins-functions.def b/gcc/config/riscv/riscv-vector-crypto-builtins-functions.def new file mode 100755 index 00000000000..b7f3f1a053a --- /dev/null +++ b/gcc/config/riscv/riscv-vector-crypto-builtins-functions.def @@ -0,0 +1,78 @@ +#ifndef DEF_VECTOR_CRYPTO_FUNCTION +#define DEF_VECTOR_CRYPTO_FUNCTION(NAME, SHAPE, PREDS, OPS_INFO, AVAIL) +#endif + + +// ZVBB +DEF_VECTOR_CRYPTO_FUNCTION (vandn, alu, full_preds, u_vvv_ops, zvkb_or_zvbb) +DEF_VECTOR_CRYPTO_FUNCTION (vandn, alu, full_preds, u_vvx_ops, zvkb_or_zvbb) +DEF_VECTOR_CRYPTO_FUNCTION (vbrev, alu, full_preds, u_vv_ops, zvbb) +DEF_VECTOR_CRYPTO_FUNCTION (vbrev8, alu, full_preds, u_vv_ops, zvkb_or_zvbb) +DEF_VECTOR_CRYPTO_FUNCTION (vrev8, alu, full_preds, u_vv_ops, zvkb_or_zvbb) +DEF_VECTOR_CRYPTO_FUNCTION (vclz, alu, none_m_preds, u_vv_ops, zvbb) +DEF_VECTOR_CRYPTO_FUNCTION (vctz, alu, none_m_preds, u_vv_ops, zvbb) +DEF_VECTOR_CRYPTO_FUNCTION (vrol, alu, full_preds, u_vvv_ops, zvkb_or_zvbb) +DEF_VECTOR_CRYPTO_FUNCTION (vrol, alu, full_preds, u_shift_vvx_ops, zvkb_or_zvbb) +DEF_VECTOR_CRYPTO_FUNCTION (vror, alu, full_preds, u_vvv_ops, zvkb_or_zvbb) +DEF_VECTOR_CRYPTO_FUNCTION (vror, alu, full_preds, u_shift_vvx_ops, zvkb_or_zvbb) +DEF_VECTOR_CRYPTO_FUNCTION (vwsll, alu, full_preds, u_wvv_ops, zvbb) +DEF_VECTOR_CRYPTO_FUNCTION (vwsll, alu, full_preds, u_shift_wvx_ops, zvbb) +//ZVBC +DEF_VECTOR_CRYPTO_FUNCTION (vclmul, alu, full_preds, u_vvv_crypto_sew64_ops, zvbc) +DEF_VECTOR_CRYPTO_FUNCTION (vclmul, alu, full_preds, u_vvx_crypto_sew64_ops, zvbc) +DEF_VECTOR_CRYPTO_FUNCTION (vclmulh, alu, full_preds, u_vvv_crypto_sew64_ops, zvbc) +DEF_VECTOR_CRYPTO_FUNCTION (vclmulh, alu, full_preds, u_vvx_crypto_sew64_ops, zvbc) +//ZVKG +DEF_VECTOR_CRYPTO_FUNCTION(vghsh, crypto_vv, none_tu_preds, u_vvvv_crypto_sew32_ops, zvkg) +DEF_VECTOR_CRYPTO_FUNCTION(vgmul, crypto_vv, none_tu_preds, u_vvv_crypto_sew32_ops, zvkg) +//ZVKNED +DEF_VECTOR_CRYPTO_FUNCTION (vaesef, crypto_vv, none_tu_preds, u_vvv_crypto_sew32_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesef, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesef, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x2_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesef, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x4_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesef, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x8_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesef, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x16_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesem, crypto_vv, none_tu_preds, u_vvv_crypto_sew32_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesem, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesem, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x2_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesem, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x4_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesem, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x8_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesem, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x16_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesdf, crypto_vv, none_tu_preds, u_vvv_crypto_sew32_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesdf, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesdf, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x2_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesdf, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x4_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesdf, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x8_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesdf, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x16_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesdm, crypto_vv, none_tu_preds, u_vvv_crypto_sew32_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesdm, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesdm, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x2_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesdm, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x4_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesdm, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x8_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesdm, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x16_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesz, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesz, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x2_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesz, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x4_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesz, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x8_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaesz, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x16_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaeskf1, crypto_vi, none_tu_preds, u_vv_size_crypto_sew32_ops, zvkned) +DEF_VECTOR_CRYPTO_FUNCTION (vaeskf2, crypto_vi, none_tu_preds, u_vvv_size_crypto_sew32_ops, zvkned) +//ZVKNHA +DEF_VECTOR_CRYPTO_FUNCTION (vsha2ms, crypto_vv, none_tu_preds, u_vvvv_crypto_sew32_ops, zvknha_or_zvknhb) +DEF_VECTOR_CRYPTO_FUNCTION (vsha2ch, crypto_vv, none_tu_preds, u_vvvv_crypto_sew32_ops, zvknha_or_zvknhb) +DEF_VECTOR_CRYPTO_FUNCTION (vsha2cl, crypto_vv, none_tu_preds, u_vvvv_crypto_sew32_ops, zvknha_or_zvknhb) +//ZVKNHB +DEF_VECTOR_CRYPTO_FUNCTION (vsha2ms, crypto_vv, none_tu_preds, u_vvvv_crypto_sew64_ops, zvknhb) +DEF_VECTOR_CRYPTO_FUNCTION (vsha2ch, crypto_vv, none_tu_preds, u_vvvv_crypto_sew64_ops, zvknhb) +DEF_VECTOR_CRYPTO_FUNCTION (vsha2cl, crypto_vv, none_tu_preds, u_vvvv_crypto_sew64_ops, zvknhb) +//Zvksed +DEF_VECTOR_CRYPTO_FUNCTION (vsm4k, crypto_vi, none_tu_preds, u_vv_size_crypto_sew32_ops, zvksed) +DEF_VECTOR_CRYPTO_FUNCTION (vsm4r, crypto_vv, none_tu_preds, u_vvv_crypto_sew32_ops, zvksed) +DEF_VECTOR_CRYPTO_FUNCTION (vsm4r, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_ops, zvksed) +DEF_VECTOR_CRYPTO_FUNCTION (vsm4r, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x2_ops, zvksed) +DEF_VECTOR_CRYPTO_FUNCTION (vsm4r, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x4_ops, zvksed) +DEF_VECTOR_CRYPTO_FUNCTION (vsm4r, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x8_ops, zvksed) +DEF_VECTOR_CRYPTO_FUNCTION (vsm4r, crypto_vv, none_tu_preds, u_vvs_crypto_sew32_lmul_x16_ops, zvksed) +//Zvksh +DEF_VECTOR_CRYPTO_FUNCTION (vsm3me, crypto_vv, none_tu_preds, u_vvv_crypto_sew32_ops, zvksh) +DEF_VECTOR_CRYPTO_FUNCTION (vsm3c, crypto_vi, none_tu_preds, u_vvv_size_crypto_sew32_ops, zvksh) \ No newline at end of file diff --git a/gcc/config/riscv/riscv-vector-crypto-builtins-types.def b/gcc/config/riscv/riscv-vector-crypto-builtins-types.def new file mode 100755 index 00000000000..f40367ae2c3 --- /dev/null +++ b/gcc/config/riscv/riscv-vector-crypto-builtins-types.def @@ -0,0 +1,21 @@ +#ifndef DEF_RVV_CRYPTO_SEW32_OPS +#define DEF_RVV_CRYPTO_SEW32_OPS(TYPE, REQUIRE) +#endif + +#ifndef DEF_RVV_CRYPTO_SEW64_OPS +#define DEF_RVV_CRYPTO_SEW64_OPS(TYPE, REQUIRE) +#endif + +DEF_RVV_CRYPTO_SEW32_OPS (vuint32mf2_t, RVV_REQUIRE_MIN_VLEN_64) +DEF_RVV_CRYPTO_SEW32_OPS (vuint32m1_t, 0) +DEF_RVV_CRYPTO_SEW32_OPS (vuint32m2_t, 0) +DEF_RVV_CRYPTO_SEW32_OPS (vuint32m4_t, 0) +DEF_RVV_CRYPTO_SEW32_OPS (vuint32m8_t, 0) + +DEF_RVV_CRYPTO_SEW64_OPS (vuint64m1_t, RVV_REQUIRE_ELEN_64) +DEF_RVV_CRYPTO_SEW64_OPS (vuint64m2_t, RVV_REQUIRE_ELEN_64) +DEF_RVV_CRYPTO_SEW64_OPS (vuint64m4_t, RVV_REQUIRE_ELEN_64) +DEF_RVV_CRYPTO_SEW64_OPS (vuint64m8_t, RVV_REQUIRE_ELEN_64) + +#undef DEF_RVV_CRYPTO_SEW32_OPS +#undef DEF_RVV_CRYPTO_SEW64_OPS \ No newline at end of file diff --git a/gcc/config/riscv/t-riscv b/gcc/config/riscv/t-riscv index 3b9686daa58..429d36b6425 100644 --- a/gcc/config/riscv/t-riscv +++ b/gcc/config/riscv/t-riscv @@ -1,6 +1,8 @@ RISCV_BUILTINS_H = $(srcdir)/config/riscv/riscv-vector-builtins.h \ $(srcdir)/config/riscv/riscv-vector-builtins.def \ $(srcdir)/config/riscv/riscv-vector-builtins-functions.def \ + $(srcdir)/config/riscv/riscv-vector-crypto-builtins-avail.h \ + $(srcdir)/config/riscv/riscv-vector-crypto-builtins-functions.def \ riscv-vector-type-indexer.gen.def riscv-builtins.o: $(srcdir)/config/riscv/riscv-builtins.cc $(CONFIG_H) \ From patchwork Wed Dec 6 02:45:23 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Feng Wang X-Patchwork-Id: 1872424 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org Authentication-Results: legolas.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=gcc.gnu.org (client-ip=8.43.85.97; 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 [8.43.85.97]) (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 4SlMHy30n5z23mf for ; Wed, 6 Dec 2023 13:47:10 +1100 (AEDT) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 6B56A3845BEB for ; Wed, 6 Dec 2023 02:47:08 +0000 (GMT) X-Original-To: gcc-patches@gcc.gnu.org Delivered-To: gcc-patches@gcc.gnu.org Received: from azure-sdnproxy.icoremail.net (azure-sdnproxy.icoremail.net [20.231.56.155]) by sourceware.org (Postfix) with ESMTP id 5D361385F009 for ; Wed, 6 Dec 2023 02:46:33 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 5D361385F009 Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=eswincomputing.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=eswincomputing.com ARC-Filter: OpenARC Filter v1.0.0 sourceware.org 5D361385F009 Authentication-Results: server2.sourceware.org; arc=none smtp.remote-ip=20.231.56.155 ARC-Seal: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1701830797; cv=none; b=f/vLgUxXVatv7wOeV8+tQn1bL+4Q3zRYo4MsDS/Yq5rJVt7Q1v5oMgdT7+wttYciQIaOBnpTftnjFHcuWCrWbHiDknJIxj/j81CDOXXHyqIH9W8X/E/1sQZvXHi5wU20TrGzq4m5CYeNaY4wRUM6fn4IvWbJndDpa6KUKTtozUI= ARC-Message-Signature: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1701830797; c=relaxed/simple; bh=mN1HmgTeU9mfvGnLzANIAj1zpqxwfYL9PXJjFYxmGbY=; h=From:To:Subject:Date:Message-Id; b=ZAnHN6rPoXPddieLNbo5wt0ANSRchiHu5gjt8DwgaYmb9OaqZzDXcqhlOehDW4yUHSXjAvKE4CeZ3H21mCVvnpS0t5Gswm8w1jQEk5oNjMvvrrRDn50jumDZvAujkXHQjWAw77MM1tZiyeHOIp27r16tv/dzaLZF+4OIG2yKBLc= ARC-Authentication-Results: i=1; server2.sourceware.org Received: from localhost.localdomain (unknown [10.12.130.31]) by app2 (Coremail) with SMTP id TQJkCgAnttQ54G9llmIAAA--.5861S6; Wed, 06 Dec 2023 10:45:21 +0800 (CST) From: Feng Wang To: gcc-patches@gcc.gnu.org Cc: kito.cheng@gmail.com, jeffreyalaw@gmail.com, juzhe.zhong@rivai.ai, zhusonghe@eswincomputing.com, panciyan@eswincomputing.com, Feng Wang Subject: [PATCH 3/4] RISC-V: Add crypto vector machine descriptions Date: Wed, 6 Dec 2023 02:45:23 +0000 Message-Id: <20231206024524.10792-3-wangfeng@eswincomputing.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20231206024524.10792-1-wangfeng@eswincomputing.com> References: <20231206024524.10792-1-wangfeng@eswincomputing.com> X-CM-TRANSID: TQJkCgAnttQ54G9llmIAAA--.5861S6 X-Coremail-Antispam: 1UD129KBjvAXoWftw1UXrWfZF18XFW3Jr1DKFg_yoW5urWxCo WrKr4kAF18WFy09390ka1fGr1kXF43AF1xJayfKr1Yvan8JrZ8trnF9a13Z343trsrXw4D Wr97u3WUXFW8Jw4fn29KB7ZKAUJUUUUU529EdanIXcx71UUUUU7v73VFW2AGmfu7bjvjm3 AaLaJ3UjIYCTnIWjp_UUUYA7AC8VAFwI0_Wr0E3s1l1xkIjI8I6I8E6xAIw20EY4v20xva j40_Wr0E3s1l1IIY67AEw4v_Jr0_Jr4l82xGYIkIc2x26280x7IE14v26r15M28IrcIa0x kI8VCY1x0267AKxVW8JVW5JwA2ocxC64kIII0Yj41l84x0c7CEw4AK67xGY2AK021l84AC jcxK6xIIjxv20xvE14v26w1j6s0DM28EF7xvwVC0I7IYx2IY6xkF7I0E14v26r4UJVWxJr 1l84ACjcxK6I8E87Iv67AKxVW0oVCq3wA2z4x0Y4vEx4A2jsIEc7CjxVAFwI0_GcCE3s1l e2I262IYc4CY6c8Ij28IcVAaY2xG8wAqx4xG64xvF2IEw4CE5I8CrVC2j2WlYx0E2Ix0cI 8IcVAFwI0_Jr0_Jr4lYx0Ex4A2jsIE14v26r1j6r4UMcvjeVCFs4IE7xkEbVWUJVW8JwAC jcxG0xvY0x0EwIxGrwACjI8F5VA0II8E6IAqYI8I648v4I1lc2xSY4AK6svPMxAIw28Icx kI7VAKI48JMxC20s026xCaFVCjc4AY6r1j6r4UMI8I3I0E5I8CrVAFwI0_Jr0_Jr4lx2Iq xVCjr7xvwVAFwI0_JrI_JrWlx4CE17CEb7AF67AKxVWUAVWUtwCIc40Y0x0EwIxGrwCI42 IY6xIIjxv20xvE14v26r1j6r1xMIIF0xvE2Ix0cI8IcVCY1x0267AKxVW8JVWxJwCI42IY 6xAIw20EY4v20xvaj40_Jr0_JF4lIxAIcVC2z280aVAFwI0_Jr0_Gr1lIxAIcVC2z280aV CY1x0267AKxVW8JVW8JrUvcSsGvfC2KfnxnUUI43ZEXa7VUjYiiDUUUUU== X-CM-SenderInfo: pzdqwwxhqjqvxvzl0uprps33xlqjhudrp/ X-Spam-Status: No, score=-12.7 required=5.0 tests=BAYES_00, GIT_PATCH_0, KAM_DMARC_STATUS, RCVD_IN_DNSWL_NONE, RCVD_IN_MSPIKE_H3, RCVD_IN_MSPIKE_WL, 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 This patch add the crypto machine descriptions(vector-crypto.md) and some new iterators which are used by crypto vector ext. Co-Authored by: Songhe Zhu Co-Authored by: Ciyan Pan gcc/ChangeLog: * config/riscv/iterators.md: Add rotate insn name. * config/riscv/riscv.md: Add new insns name for crypto vector. * config/riscv/vector-iterators.md: Add new iterators for crypto vector. * config/riscv/vector.md: Add the corresponding attr for crypto vector. * config/riscv/vector-crypto.md: New file.The machine descriptions for crypto vector. --- gcc/config/riscv/iterators.md | 4 +- gcc/config/riscv/riscv.md | 33 +- gcc/config/riscv/vector-crypto.md | 500 +++++++++++++++++++++++++++ gcc/config/riscv/vector-iterators.md | 41 +++ gcc/config/riscv/vector.md | 49 ++- 5 files changed, 607 insertions(+), 20 deletions(-) create mode 100755 gcc/config/riscv/vector-crypto.md diff --git a/gcc/config/riscv/iterators.md b/gcc/config/riscv/iterators.md index ecf033f2fa7..f332fba7031 100644 --- a/gcc/config/riscv/iterators.md +++ b/gcc/config/riscv/iterators.md @@ -304,7 +304,9 @@ (umax "maxu") (clz "clz") (ctz "ctz") - (popcount "cpop")]) + (popcount "cpop") + (rotate "rol") + (rotatert "ror")]) ;; ------------------------------------------------------------------- ;; Int Iterators. diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md index 935eeb7fd8e..a887f3cd412 100644 --- a/gcc/config/riscv/riscv.md +++ b/gcc/config/riscv/riscv.md @@ -428,6 +428,34 @@ ;; vcompress vector compress instruction ;; vmov whole vector register move ;; vector unknown vector instruction +;; 17. Crypto Vector instructions +;; vandn crypto vector bitwise and-not instructions +;; vbrev crypto vector reverse bits in elements instructions +;; vbrev8 crypto vector reverse bits in bytes instructions +;; vrev8 crypto vector reverse bytes instructions +;; vclz crypto vector count leading Zeros instructions +;; vctz crypto vector count lrailing Zeros instructions +;; vrol crypto vector rotate left instructions +;; vror crypto vector rotate right instructions +;; vwsll crypto vector widening shift left logical instructions +;; vclmul crypto vector carry-less multiply - return low half instructions +;; vclmulh crypto vector carry-less multiply - return high half instructions +;; vghsh crypto vector add-multiply over GHASH Galois-Field instructions +;; vgmul crypto vector multiply over GHASH Galois-Field instrumctions +;; vaesef crypto vector AES final-round encryption instructions +;; vaesem crypto vector AES middle-round encryption instructions +;; vaesdf crypto vector AES final-round decryption instructions +;; vaesdm crypto vector AES middle-round decryption instructions +;; vaeskf1 crypto vector AES-128 Forward KeySchedule generation instructions +;; vaeskf2 crypto vector AES-256 Forward KeySchedule generation instructions +;; vaesz crypto vector AES round zero encryption/decryption instructions +;; vsha2ms crypto vector SHA-2 message schedule instructions +;; vsha2ch crypto vector SHA-2 two rounds of compression instructions +;; vsha2cl crypto vector SHA-2 two rounds of compression instructions +;; vsm4k crypto vector SM4 KeyExpansion instructions +;; vsm4r crypto vector SM4 Rounds instructions +;; vsm3me crypto vector SM3 Message Expansion instructions +;; vsm3c crypto vector SM3 Compression instructions (define_attr "type" "unknown,branch,jump,jalr,ret,call,load,fpload,store,fpstore, mtc,mfc,const,arith,logical,shift,slt,imul,idiv,move,fmove,fadd,fmul, @@ -447,7 +475,9 @@ vired,viwred,vfredu,vfredo,vfwredu,vfwredo, vmalu,vmpop,vmffs,vmsfs,vmiota,vmidx,vimovvx,vimovxv,vfmovvf,vfmovfv, vslideup,vslidedown,vislide1up,vislide1down,vfslide1up,vfslide1down, - vgather,vcompress,vmov,vector" + vgather,vcompress,vmov,vector,vandn,vbrev,vbrev8,vrev8,vclz,vctz,vcpop,vrol,vror,vwsll, + vclmul,vclmulh,vghsh,vgmul,vaesef,vaesem,vaesdf,vaesdm,vaeskf1,vaeskf2,vaesz, + vsha2ms,vsha2ch,vsha2cl,vsm4k,vsm4r,vsm3me,vsm3c" (cond [(eq_attr "got" "load") (const_string "load") ;; If a doubleword move uses these expensive instructions, @@ -3747,6 +3777,7 @@ (include "thead.md") (include "generic-ooo.md") (include "vector.md") +(include "vector-crypto.md") (include "zicond.md") (include "zc.md") (include "corev.md") diff --git a/gcc/config/riscv/vector-crypto.md b/gcc/config/riscv/vector-crypto.md new file mode 100755 index 00000000000..a40ecef4342 --- /dev/null +++ b/gcc/config/riscv/vector-crypto.md @@ -0,0 +1,500 @@ +(define_c_enum "unspec" [ + ;; Zvbb unspecs + UNSPEC_VBREV + UNSPEC_VBREV8 + UNSPEC_VREV8 + UNSPEC_VCLMUL + UNSPEC_VCLMULH + UNSPEC_VGHSH + UNSPEC_VGMUL + UNSPEC_VAESEF + UNSPEC_VAESEFVV + UNSPEC_VAESEFVS + UNSPEC_VAESEM + UNSPEC_VAESEMVV + UNSPEC_VAESEMVS + UNSPEC_VAESDF + UNSPEC_VAESDFVV + UNSPEC_VAESDFVS + UNSPEC_VAESDM + UNSPEC_VAESDMVV + UNSPEC_VAESDMVS + UNSPEC_VAESZ + UNSPEC_VAESZVVNULL + UNSPEC_VAESZVS + UNSPEC_VAESKF1 + UNSPEC_VAESKF2 + UNSPEC_VSHA2MS + UNSPEC_VSHA2CH + UNSPEC_VSHA2CL + UNSPEC_VSM4K + UNSPEC_VSM4R + UNSPEC_VSM4RVV + UNSPEC_VSM4RVS + UNSPEC_VSM3ME + UNSPEC_VSM3C +]) + +(define_int_attr rev [(UNSPEC_VBREV "brev") (UNSPEC_VBREV8 "brev8") (UNSPEC_VREV8 "rev8")]) + +(define_int_attr h [(UNSPEC_VCLMUL "") (UNSPEC_VCLMULH "h")]) + +(define_int_attr vv_ins_name [(UNSPEC_VGMUL "gmul" ) (UNSPEC_VAESEFVV "aesef") + (UNSPEC_VAESEMVV "aesem") (UNSPEC_VAESDFVV "aesdf") + (UNSPEC_VAESDMVV "aesdm") (UNSPEC_VAESEFVS "aesef") + (UNSPEC_VAESEMVS "aesem") (UNSPEC_VAESDFVS "aesdf") + (UNSPEC_VAESDMVS "aesdm") (UNSPEC_VAESZVS "aesz" ) + (UNSPEC_VSM4RVV "sm4r" ) (UNSPEC_VSM4RVS "sm4r" )]) + +(define_int_attr vv_ins1_name [(UNSPEC_VGHSH "ghsh") (UNSPEC_VSHA2MS "sha2ms") + (UNSPEC_VSHA2CH "sha2ch") (UNSPEC_VSHA2CL "sha2cl")]) + +(define_int_attr vi_ins_name [(UNSPEC_VAESKF1 "aeskf1") (UNSPEC_VSM4K "sm4k")]) + +(define_int_attr vi_ins1_name [(UNSPEC_VAESKF2 "aeskf2") (UNSPEC_VSM3C "sm3c")]) + +(define_int_attr ins_type [(UNSPEC_VGMUL "vv") (UNSPEC_VAESEFVV "vv") + (UNSPEC_VAESEMVV "vv") (UNSPEC_VAESDFVV "vv") + (UNSPEC_VAESDMVV "vv") (UNSPEC_VAESEFVS "vs") + (UNSPEC_VAESEMVS "vs") (UNSPEC_VAESDFVS "vs") + (UNSPEC_VAESDMVS "vs") (UNSPEC_VAESZVS "vs") + (UNSPEC_VSM4RVV "vv") (UNSPEC_VSM4RVS "vs")]) + +(define_int_iterator UNSPEC_VRBB8 [UNSPEC_VBREV UNSPEC_VBREV8 UNSPEC_VREV8]) + +(define_int_iterator UNSPEC_CLMUL [UNSPEC_VCLMUL UNSPEC_VCLMULH]) + +(define_int_iterator UNSPEC_CRYPTO_VV [UNSPEC_VGMUL UNSPEC_VAESEFVV UNSPEC_VAESEMVV + UNSPEC_VAESDFVV UNSPEC_VAESDMVV UNSPEC_VAESEFVS + UNSPEC_VAESEMVS UNSPEC_VAESDFVS UNSPEC_VAESDMVS + UNSPEC_VAESZVS UNSPEC_VSM4RVV UNSPEC_VSM4RVS]) + +(define_int_iterator UNSPEC_VGNHAB [UNSPEC_VGHSH UNSPEC_VSHA2MS UNSPEC_VSHA2CH UNSPEC_VSHA2CL]) + +(define_int_iterator UNSPEC_CRYPTO_VI [UNSPEC_VAESKF1 UNSPEC_VSM4K]) + +(define_int_iterator UNSPEC_CRYPTO_VI1 [UNSPEC_VAESKF2 UNSPEC_VSM3C]) + +;; zvbb instructions patterns. +;; vandn.vv vandn.vx vrol.vv vrol.vx +;; vror.vv vror.vx vror.vi +;; vwsll.vv vwsll.vx vwsll.vi + +(define_insn "@pred_vandn" + [(set (match_operand:VI 0 "register_operand" "=vd,vd") + (if_then_else:VI + (unspec: + [(match_operand: 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 5 "vector_length_operand" "rK,rK") + (match_operand 6 "const_int_operand" "i, i") + (match_operand 7 "const_int_operand" "i, i") + (match_operand 8 "const_int_operand" "i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (and:VI + (match_operand:VI 3 "register_operand" "vr,vr") + (not:VI (match_operand:VI 4 "register_operand" "vr,vr"))) + (match_operand:VI 2 "vector_merge_operand" "vu, 0")))] + "TARGET_ZVBB || TARGET_ZVKB" + "vandn.vv\t%0,%3,%4%p1" + [(set_attr "type" "vandn") + (set_attr "mode" "")]) + +(define_insn "@pred_vandn_scalar" + [(set (match_operand:VI 0 "register_operand" "=vd,vd") + (if_then_else:VI + (unspec: + [(match_operand: 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 5 "vector_length_operand" "rK,rK") + (match_operand 6 "const_int_operand" "i, i") + (match_operand 7 "const_int_operand" "i, i") + (match_operand 8 "const_int_operand" "i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (and:VI + (match_operand:VI 3 "register_operand" "vr,vr") + (not: + (match_operand: 4 "register_operand" "r,r"))) + (match_operand:VI 2 "vector_merge_operand" "vu, 0")))] + "TARGET_ZVBB || TARGET_ZVKB" + "vandn.vx\t%0,%3,%4%p1" + [(set_attr "type" "vandn") + (set_attr "mode" "")]) + +(define_insn "@pred_v" + [(set (match_operand:VI 0 "register_operand" "=vd,vd") + (if_then_else:VI + (unspec: + [(match_operand: 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 5 "vector_length_operand" "rK,rK") + (match_operand 6 "const_int_operand" "i, i") + (match_operand 7 "const_int_operand" "i, i") + (match_operand 8 "const_int_operand" "i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (bitmanip_rotate:VI + (match_operand:VI 3 "register_operand" "vr,vr") + (match_operand:VI 4 "register_operand" "vr,vr")) + (match_operand:VI 2 "vector_merge_operand" "vu, 0")))] + "TARGET_ZVBB || TARGET_ZVKB" + "v.vv\t%0,%3,%4%p1" + [(set_attr "type" "v") + (set_attr "mode" "")]) + +(define_insn "@pred_v_scalar" + [(set (match_operand:VI 0 "register_operand" "=vd, vd") + (if_then_else:VI + (unspec: + [(match_operand: 1 "vector_mask_operand" "vmWc1, vmWc1") + (match_operand 5 "vector_length_operand" "rK, rK") + (match_operand 6 "const_int_operand" "i, i") + (match_operand 7 "const_int_operand" "i, i") + (match_operand 8 "const_int_operand" "i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (bitmanip_rotate:VI + (match_operand:VI 3 "register_operand" "vr, vr") + (match_operand 4 "pmode_register_operand" "r, r")) + (match_operand:VI 2 "vector_merge_operand" "vu, 0")))] + "TARGET_ZVBB || TARGET_ZVKB" + "v.vx\t%0,%3,%4%p1" + [(set_attr "type" "v") + (set_attr "mode" "")]) + +(define_insn "*pred_vror_scalar" + [(set (match_operand:VI 0 "register_operand" "=vd, vd") + (if_then_else:VI + (unspec: + [(match_operand: 1 "vector_mask_operand" "vmWc1, vmWc1") + (match_operand 5 "vector_length_operand" "rK, rK") + (match_operand 6 "const_int_operand" "i, i") + (match_operand 7 "const_int_operand" "i, i") + (match_operand 8 "const_int_operand" "i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (rotatert:VI + (match_operand:VI 3 "register_operand" "vr, vr") + (match_operand 4 "const_csr_operand" "K, K")) + (match_operand:VI 2 "vector_merge_operand" "vu, 0")))] + "TARGET_ZVBB || TARGET_ZVKB" + "vror.vi\t%0,%3,%4%p1" + [(set_attr "type" "vror") + (set_attr "mode" "")]) + +(define_insn "@pred_vwsll" + [(set (match_operand:VWEXTI 0 "register_operand" "=&vd") + (if_then_else:VWEXTI + (unspec: + [(match_operand: 1 "vector_mask_operand" "vmWc1") + (match_operand 5 "vector_length_operand" " rK") + (match_operand 6 "const_int_operand" " i") + (match_operand 7 "const_int_operand" " i") + (match_operand 8 "const_int_operand" " i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (ashift:VWEXTI + (zero_extend:VWEXTI + (match_operand: 3 "register_operand" "vr")) + (match_operand: 4 "register_operand" "vr")) + (match_operand:VWEXTI 2 "vector_merge_operand" "0vu")))] + "TARGET_ZVBB" + "vwsll.vv\t%0,%3,%4%p1" + [(set_attr "type" "vwsll") + (set_attr "mode" "")]) + +(define_insn "@pred_vwsll_scalar" + [(set (match_operand:VWEXTI 0 "register_operand" "=&vd") + (if_then_else:VWEXTI + (unspec: + [(match_operand: 1 "vector_mask_operand" "vmWc1") + (match_operand 5 "vector_length_operand" " rK") + (match_operand 6 "const_int_operand" " i") + (match_operand 7 "const_int_operand" " i") + (match_operand 8 "const_int_operand" " i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (ashift:VWEXTI + (zero_extend:VWEXTI + (match_operand: 3 "register_operand" "vr")) + (match_operand: 4 "pmode_reg_or_uimm5_operand" "rK")) + (match_operand:VWEXTI 2 "vector_merge_operand" "0vu")))] + "TARGET_ZVBB" + "vwsll.v%o4\t%0,%3,%4%p1" + [(set_attr "type" "vwsll") + (set_attr "mode" "")]) + +;; vbrev.v vbrev8.v vrev8.v + +(define_insn "@pred_v" + [(set (match_operand:VI 0 "register_operand" "=vd,vd") + (if_then_else:VI + (unspec: + [(match_operand: 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 4 "vector_length_operand" "rK,rK") + (match_operand 5 "const_int_operand" "i, i") + (match_operand 6 "const_int_operand" "i, i") + (match_operand 7 "const_int_operand" "i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (unspec:VI + [(match_operand:VI 3 "register_operand" "vr,vr")]UNSPEC_VRBB8) + (match_operand:VI 2 "vector_merge_operand" "vu, 0")))] + "TARGET_ZVBB || TARGET_ZVKB" + "v.v\t%0,%3%p1" + [(set_attr "type" "v") + (set_attr "mode" "")]) + +;; vclz.v vctz.v + +(define_insn "@pred_v" + [(set (match_operand:VI 0 "register_operand" "=vd") + (clz_ctz_pcnt:VI + (parallel + [(match_operand:VI 2 "register_operand" "vr") + (unspec: + [(match_operand: 1 "vector_mask_operand" "vmWc1") + (match_operand 3 "vector_length_operand" " rK") + (match_operand 4 "const_int_operand" " i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)])))] + "TARGET_ZVBB" + "v.v\t%0,%2%p1" + [(set_attr "type" "v") + (set_attr "mode" "")]) + +;; zvbc instructions patterns. +;; vclmul.vv vclmul.vx +;; vclmulh.vv vclmulh.vx + +(define_insn "@pred_vclmul" + [(set (match_operand:VDI 0 "register_operand" "=vd,vd") + (if_then_else:VDI + (unspec: + [(match_operand: 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 5 "vector_length_operand" "rK,rK") + (match_operand 6 "const_int_operand" "i, i") + (match_operand 7 "const_int_operand" "i, i") + (match_operand 8 "const_int_operand" "i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (unspec:VDI + [(match_operand:VDI 3 "register_operand" "vr,vr") + (match_operand:VDI 4 "register_operand" "vr,vr")]UNSPEC_CLMUL) + (match_operand:VDI 2 "vector_merge_operand" "vu, 0")))] + "TARGET_ZVBC && TARGET_64BIT" + "vclmul.vv\t%0,%3,%4%p1" + [(set_attr "type" "vclmul") + (set_attr "mode" "")]) + +(define_insn "@pred_vclmul_scalar" + [(set (match_operand:VDI 0 "register_operand" "=vd,vd") + (if_then_else:VDI + (unspec: + [(match_operand: 1 "vector_mask_operand" "vmWc1,vmWc1") + (match_operand 5 "vector_length_operand" "rK,rK") + (match_operand 6 "const_int_operand" "i, i") + (match_operand 7 "const_int_operand" "i, i") + (match_operand 8 "const_int_operand" "i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (unspec:VDI + [(match_operand:VDI 3 "register_operand" "vr,vr") + (match_operand: 4 "register_operand" "r,r")]UNSPEC_CLMUL) + (match_operand:VDI 2 "vector_merge_operand" "vu, 0")))] + "TARGET_ZVBC && TARGET_64BIT" + "vclmul.vx\t%0,%3,%4%p1" + [(set_attr "type" "vclmul") + (set_attr "mode" "")]) + +;; zvknh[ab] and zvkg instructions patterns. +;; vsha2ms.vv vsha2ch.vv vsha2cl.vv vghsh.vv + +(define_insn "@pred_v" + [(set (match_operand:VQEXTI 0 "register_operand" "=vd") + (if_then_else:VQEXTI + (unspec: + [(match_operand 4 "vector_length_operand" "rK") + (match_operand 5 "const_int_operand" " i") + (match_operand 6 "const_int_operand" " i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (unspec:VQEXTI + [(match_operand:VQEXTI 1 "register_operand" " 0") + (match_operand:VQEXTI 2 "register_operand" "vr") + (match_operand:VQEXTI 3 "register_operand" "vr")] UNSPEC_VGNHAB) + (match_dup 1)))] + "TARGET_ZVKNHA || TARGET_ZVKNHB || TARGET_ZVKG" + "v.vv\t%0,%2,%3" + [(set_attr "type" "v") + (set_attr "mode" "")]) + +;; zvkned instructions patterns. +;; vgmul.vv vaesz.vs +;; vaesef.[vv,vs] vaesem.[vv,vs] vaesdf.[vv,vs] vaesdm.[vv,vs] +(define_insn "@pred_crypto_vv" + [(set (match_operand:VSI 0 "register_operand" "=vd") + (if_then_else:VSI + (unspec: + [(match_operand 3 "vector_length_operand" "rK") + (match_operand 4 "const_int_operand" " i") + (match_operand 5 "const_int_operand" " i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (unspec:VSI + [(match_operand:VSI 1 "register_operand" " 0") + (match_operand:VSI 2 "register_operand" "vr")] UNSPEC_CRYPTO_VV) + (match_dup 1)))] + "TARGET_ZVKG || TARGET_ZVKNED" + "v.\t%0,%2" + [(set_attr "type" "v") + (set_attr "mode" "")]) + +(define_insn "@pred_crypto_vvx1_scalar" + [(set (match_operand:VSI 0 "register_operand" "=vd") + (if_then_else:VSI + (unspec: + [(match_operand 3 "vector_length_operand" "rK") + (match_operand 4 "const_int_operand" " i") + (match_operand 5 "const_int_operand" " i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (unspec:VSI + [(match_operand:VSI 1 "register_operand" " 0") + (match_operand:VSI 2 "register_operand" "vr")] UNSPEC_CRYPTO_VV) + (match_dup 1)))] + "TARGET_ZVKNED || TARGET_ZVKSED" + "v.\t%0,%2" + [(set_attr "type" "v") + (set_attr "mode" "")]) + +(define_insn "@pred_crypto_vvx2_scalar" + [(set (match_operand: 0 "register_operand" "=vd") + (if_then_else: + (unspec: + [(match_operand 3 "vector_length_operand" "rK") + (match_operand 4 "const_int_operand" " i") + (match_operand 5 "const_int_operand" " i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (unspec: + [(match_operand: 1 "register_operand" " 0") + (match_operand:VLMULX2_SI 2 "register_operand" "vr")] UNSPEC_CRYPTO_VV) + (match_dup 1)))] + "TARGET_ZVKNED || TARGET_ZVKSED" + "v.\t%0,%2" + [(set_attr "type" "v") + (set_attr "mode" "")]) + +(define_insn "@pred_crypto_vvx4_scalar" + [(set (match_operand: 0 "register_operand" "=vd") + (if_then_else: + (unspec: + [(match_operand 3 "vector_length_operand" "rK") + (match_operand 4 "const_int_operand" " i") + (match_operand 5 "const_int_operand" " i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (unspec: + [(match_operand: 1 "register_operand" " 0") + (match_operand:VLMULX4_SI 2 "register_operand" "vr")] UNSPEC_CRYPTO_VV) + (match_dup 1)))] + "TARGET_ZVKNED || TARGET_ZVKSED" + "v.\t%0,%2" + [(set_attr "type" "v") + (set_attr "mode" "")]) + +(define_insn "@pred_crypto_vvx8_scalar" + [(set (match_operand: 0 "register_operand" "=vd") + (if_then_else: + (unspec: + [(match_operand 3 "vector_length_operand" "rK") + (match_operand 4 "const_int_operand" " i") + (match_operand 5 "const_int_operand" " i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (unspec: + [(match_operand: 1 "register_operand" " 0") + (match_operand:VLMULX8_SI 2 "register_operand" "vr")] UNSPEC_CRYPTO_VV) + (match_dup 1)))] + "TARGET_ZVKNED || TARGET_ZVKSED" + "v.\t%0,%2" + [(set_attr "type" "v") + (set_attr "mode" "")]) + +(define_insn "@pred_crypto_vvx16_scalar" + [(set (match_operand: 0 "register_operand" "=vd") + (if_then_else: + (unspec: + [(match_operand 3 "vector_length_operand" "rK") + (match_operand 4 "const_int_operand" " i") + (match_operand 5 "const_int_operand" " i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (unspec: + [(match_operand: 1 "register_operand" " 0") + (match_operand:VLMULX16_SI 2 "register_operand" "vr")] UNSPEC_CRYPTO_VV) + (match_dup 1)))] + "TARGET_ZVKNED || TARGET_ZVKSED" + "v.\t%0,%2" + [(set_attr "type" "v") + (set_attr "mode" "")]) + +;; vaeskf1.vi vsm4k.vi +(define_insn "@pred_crypto_vi_scalar" + [(set (match_operand:VSI 0 "register_operand" "=vd, vd") + (if_then_else:VSI + (unspec: + [(match_operand 4 "vector_length_operand" "rK, rK") + (match_operand 5 "const_int_operand" " i, i") + (match_operand 6 "const_int_operand" " i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (unspec:VSI + [(match_operand:VSI 2 "register_operand" "vr, vr") + (match_operand: 3 "const_int_operand" " i, i")] UNSPEC_CRYPTO_VI) + (match_operand:VSI 1 "vector_merge_operand" "vu, 0")))] + "TARGET_ZVKNED || TARGET_ZVKSED" + "v.vi\t%0,%2,%3" + [(set_attr "type" "v") + (set_attr "mode" "")]) + +;; vaeskf2.vi vsm3c.vi +(define_insn "@pred_vi_nomaskedoff_scalar" + [(set (match_operand:VSI 0 "register_operand" "=vd") + (if_then_else:VSI + (unspec: + [(match_operand 4 "vector_length_operand" "rK") + (match_operand 5 "const_int_operand" " i") + (match_operand 6 "const_int_operand" " i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (unspec:VSI + [(match_operand:VSI 1 "register_operand" "0") + (match_operand:VSI 2 "register_operand" "vr") + (match_operand: 3 "const_int_operand" " i")] UNSPEC_CRYPTO_VI1) + (match_dup 1)))] + "TARGET_ZVKNED || TARGET_ZVKSH" + "v.vi\t%0,%2,%3" + [(set_attr "type" "v") + (set_attr "mode" "")]) + +;; zvksh instructions patterns. +;; vsm3me.vv + +(define_insn "@pred_vsm3me" + [(set (match_operand:VSI 0 "register_operand" "=vd, vd") + (if_then_else:VSI + (unspec: + [(match_operand 4 "vector_length_operand" "rK, rK") + (match_operand 5 "const_int_operand" " i, i") + (match_operand 6 "const_int_operand" " i, i") + (reg:SI VL_REGNUM) + (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE) + (unspec:VSI + [(match_operand:VSI 2 "register_operand" "vr, vr") + (match_operand:VSI 3 "register_operand" "vr, vr")] UNSPEC_VSM3ME) + (match_operand:VSI 1 "vector_merge_operand" "vu, 0")))] + "TARGET_ZVKSH" + "vsm3me.vv\t%0,%2,%3" + [(set_attr "type" "vsm3me") + (set_attr "mode" "")]) \ No newline at end of file diff --git a/gcc/config/riscv/vector-iterators.md b/gcc/config/riscv/vector-iterators.md index 56080ed1f5f..1b16b476035 100644 --- a/gcc/config/riscv/vector-iterators.md +++ b/gcc/config/riscv/vector-iterators.md @@ -3916,3 +3916,44 @@ (V1024BI "riscv_vector::vls_mode_valid_p (V1024BImode) && TARGET_MIN_VLEN >= 1024") (V2048BI "riscv_vector::vls_mode_valid_p (V2048BImode) && TARGET_MIN_VLEN >= 2048") (V4096BI "riscv_vector::vls_mode_valid_p (V4096BImode) && TARGET_MIN_VLEN >= 4096")]) + +(define_mode_iterator VSI [ + RVVM8SI RVVM4SI RVVM2SI RVVM1SI (RVVMF2SI "TARGET_MIN_VLEN > 32") +]) + +(define_mode_iterator VLMULX2_SI [ + RVVM4SI RVVM2SI RVVM1SI (RVVMF2SI "TARGET_MIN_VLEN > 32") +]) + +(define_mode_iterator VLMULX4_SI [ + RVVM2SI RVVM1SI (RVVMF2SI "TARGET_MIN_VLEN > 32") +]) + +(define_mode_iterator VLMULX8_SI [ + RVVM1SI (RVVMF2SI "TARGET_MIN_VLEN > 32") +]) + +(define_mode_iterator VLMULX16_SI [ + (RVVMF2SI "TARGET_MIN_VLEN > 32") +]) + +(define_mode_attr VSIX2 [ + (RVVM8SI "RVVM8SI") (RVVM4SI "RVVM8SI") (RVVM2SI "RVVM4SI") (RVVM1SI "RVVM2SI") (RVVMF2SI "RVVM1SI") +]) + +(define_mode_attr VSIX4 [ + (RVVM2SI "RVVM8SI") (RVVM1SI "RVVM4SI") (RVVMF2SI "RVVM2SI") +]) + +(define_mode_attr VSIX8 [ + (RVVM1SI "RVVM8SI") (RVVMF2SI "RVVM4SI") +]) + +(define_mode_attr VSIX16 [ + (RVVMF2SI "RVVM8SI") +]) + +(define_mode_iterator VDI [ + (RVVM8DI "TARGET_VECTOR_ELEN_64") (RVVM4DI "TARGET_VECTOR_ELEN_64") + (RVVM2DI "TARGET_VECTOR_ELEN_64") (RVVM1DI "TARGET_VECTOR_ELEN_64") +]) \ No newline at end of file diff --git a/gcc/config/riscv/vector.md b/gcc/config/riscv/vector.md index ba9c9e5a9b6..36cb7510ec6 100644 --- a/gcc/config/riscv/vector.md +++ b/gcc/config/riscv/vector.md @@ -52,7 +52,9 @@ vmalu,vmpop,vmffs,vmsfs,vmiota,vmidx,vimovvx,vimovxv,vfmovvf,vfmovfv,\ vslideup,vslidedown,vislide1up,vislide1down,vfslide1up,vfslide1down,\ vgather,vcompress,vlsegde,vssegte,vlsegds,vssegts,vlsegdux,vlsegdox,\ - vssegtux,vssegtox,vlsegdff") + vssegtux,vssegtox,vlsegdff,vandn,vbrev,vbrev8,vrev8,vclz,vctz,vrol,\ + vror,vwsll,vclmul,vclmulh,vghsh,vgmul,vaesef,vaesem,vaesdf,vaesdm,\ + vaeskf1,vaeskf2,vaesz,vsha2ms,vsha2ch,vsha2cl,vsm4k,vsm4r,vsm3me,vsm3c") (const_string "true")] (const_string "false"))) @@ -74,7 +76,9 @@ vmalu,vmpop,vmffs,vmsfs,vmiota,vmidx,vimovxv,vfmovfv,\ vslideup,vslidedown,vislide1up,vislide1down,vfslide1up,vfslide1down,\ vgather,vcompress,vlsegde,vssegte,vlsegds,vssegts,vlsegdux,vlsegdox,\ - vssegtux,vssegtox,vlsegdff") + vssegtux,vssegtox,vlsegdff,vandn,vbrev,vbrev8,vrev8,vclz,vctz,vrol,\ + vror,vwsll,vclmul,vclmulh,vghsh,vgmul,vaesef,vaesem,vaesdf,vaesdm,\ + vaeskf1,vaeskf2,vaesz,vsha2ms,vsha2ch,vsha2cl,vsm4k,vsm4r,vsm3me,vsm3c") (const_string "true")] (const_string "false"))) @@ -698,10 +702,12 @@ vfwcvtftoi,vfwcvtftof,vfncvtitof,vfncvtftoi,vfncvtftof,vfclass,\ vired,viwred,vfredu,vfredo,vfwredu,vfwredo,vimovxv,vfmovfv,\ vslideup,vslidedown,vislide1up,vislide1down,vfslide1up,vfslide1down,\ - vgather,vldff,viwmuladd,vfwmuladd,vlsegde,vlsegds,vlsegdux,vlsegdox,vlsegdff") + vgather,vldff,viwmuladd,vfwmuladd,vlsegde,vlsegds,vlsegdux,vlsegdox,vlsegdff,\ + vandn,vbrev,vbrev8,vrev8,vrol,vror,vwsll,vclmul,vclmulh") (const_int 2) - (eq_attr "type" "vimerge,vfmerge,vcompress") + (eq_attr "type" "vimerge,vfmerge,vcompress,vghsh,vgmul,vaesef,vaesem,vaesdf,vaesdm,\ + vaeskf1,vaeskf2,vaesz,vsha2ms,vsha2ch,vsha2cl,vsm4k,vsm4r,vsm3me,vsm3c") (const_int 1) (eq_attr "type" "vimuladd,vfmuladd") @@ -740,7 +746,8 @@ vstox,vext,vmsfs,vmiota,vfsqrt,vfrecp,vfcvtitof,vldff,\ vfcvtftoi,vfwcvtitof,vfwcvtftoi,vfwcvtftof,vfncvtitof,\ vfncvtftoi,vfncvtftof,vfclass,vimovxv,vfmovfv,vcompress,\ - vlsegde,vssegts,vssegtux,vssegtox,vlsegdff") + vlsegde,vssegts,vssegtux,vssegtox,vlsegdff,vbrev,vbrev8,vrev8,\ + vghsh,vaeskf1,vaeskf2,vsha2ms,vsha2ch,vsha2cl,vsm4k,vsm3me,vsm3c") (const_int 4) ;; If operands[3] of "vlds" is not vector mode, it is pred_broadcast. @@ -755,13 +762,15 @@ vsshift,vnclip,vfalu,vfmul,vfminmax,vfdiv,vfwalu,vfwmul,\ vfsgnj,vfmerge,vired,viwred,vfredu,vfredo,vfwredu,vfwredo,\ vslideup,vslidedown,vislide1up,vislide1down,vfslide1up,vfslide1down,\ - vgather,viwmuladd,vfwmuladd,vlsegds,vlsegdux,vlsegdox") + vgather,viwmuladd,vfwmuladd,vlsegds,vlsegdux,vlsegdox,vandn,vrol,\ + vror,vwsll,vclmul,vclmulh") (const_int 5) (eq_attr "type" "vicmp,vimuladd,vfcmp,vfmuladd") (const_int 6) - (eq_attr "type" "vmpop,vmffs,vmidx,vssegte") + (eq_attr "type" "vmpop,vmffs,vmidx,vssegte,vclz,vctz,vgmul,vaesef,vaesem,vaesdf,vaesdm,\ + vaesz,vsm4r") (const_int 3)] (const_int INVALID_ATTRIBUTE))) @@ -770,7 +779,8 @@ (cond [(eq_attr "type" "vlde,vimov,vfmov,vext,vmiota,vfsqrt,vfrecp,\ vfcvtitof,vfcvtftoi,vfwcvtitof,vfwcvtftoi,vfwcvtftof,\ vfncvtitof,vfncvtftoi,vfncvtftof,vfclass,vimovxv,vfmovfv,\ - vcompress,vldff,vlsegde,vlsegdff") + vcompress,vldff,vlsegde,vlsegdff,vbrev,vbrev8,vrev8,vghsh,\ + vaeskf1,vaeskf2,vsha2ms,vsha2ch,vsha2cl,vsm4k,vsm3me,vsm3c") (symbol_ref "riscv_vector::get_ta(operands[5])") ;; If operands[3] of "vlds" is not vector mode, it is pred_broadcast. @@ -786,13 +796,13 @@ vfwalu,vfwmul,vfsgnj,vfmerge,vired,viwred,vfredu,\ vfredo,vfwredu,vfwredo,vslideup,vslidedown,vislide1up,\ vislide1down,vfslide1up,vfslide1down,vgather,viwmuladd,vfwmuladd,\ - vlsegds,vlsegdux,vlsegdox") + vlsegds,vlsegdux,vlsegdox,vandn,vrol,vror,vwsll,vclmul,vclmulh") (symbol_ref "riscv_vector::get_ta(operands[6])") (eq_attr "type" "vimuladd,vfmuladd") (symbol_ref "riscv_vector::get_ta(operands[7])") - (eq_attr "type" "vmidx") + (eq_attr "type" "vmidx,vgmul,vaesef,vaesem,vaesdf,vaesdm,vaesz,vsm4r") (symbol_ref "riscv_vector::get_ta(operands[4])")] (const_int INVALID_ATTRIBUTE))) @@ -800,7 +810,7 @@ (define_attr "ma" "" (cond [(eq_attr "type" "vlde,vext,vmiota,vfsqrt,vfrecp,vfcvtitof,vfcvtftoi,\ vfwcvtitof,vfwcvtftoi,vfwcvtftof,vfncvtitof,vfncvtftoi,\ - vfncvtftof,vfclass,vldff,vlsegde,vlsegdff") + vfncvtftof,vfclass,vldff,vlsegde,vlsegdff,vbrev,vbrev8,vrev8") (symbol_ref "riscv_vector::get_ma(operands[6])") ;; If operands[3] of "vlds" is not vector mode, it is pred_broadcast. @@ -815,7 +825,8 @@ vnclip,vicmp,vfalu,vfmul,vfminmax,vfdiv,\ vfwalu,vfwmul,vfsgnj,vfcmp,vslideup,vslidedown,\ vislide1up,vislide1down,vfslide1up,vfslide1down,vgather,\ - viwmuladd,vfwmuladd,vlsegds,vlsegdux,vlsegdox") + viwmuladd,vfwmuladd,vlsegds,vlsegdux,vlsegdox,vandn,vrol,\ + vror,vwsll,vclmul,vclmulh") (symbol_ref "riscv_vector::get_ma(operands[7])") (eq_attr "type" "vimuladd,vfmuladd") @@ -831,9 +842,10 @@ vfsqrt,vfrecp,vfmerge,vfcvtitof,vfcvtftoi,vfwcvtitof,\ vfwcvtftoi,vfwcvtftof,vfncvtitof,vfncvtftoi,vfncvtftof,\ vfclass,vired,viwred,vfredu,vfredo,vfwredu,vfwredo,\ - vimovxv,vfmovfv,vlsegde,vlsegdff") + vimovxv,vfmovfv,vlsegde,vlsegdff,vbrev,vbrev8,vrev8") (const_int 7) - (eq_attr "type" "vldm,vstm,vmalu,vmalu") + (eq_attr "type" "vldm,vstm,vmalu,vmalu,vgmul,vaesef,vaesem,vaesdf,vaesdm,vaesz,\ + vsm4r") (const_int 5) ;; If operands[3] of "vlds" is not vector mode, it is pred_broadcast. @@ -848,18 +860,19 @@ vnclip,vicmp,vfalu,vfmul,vfminmax,vfdiv,vfwalu,vfwmul,\ vfsgnj,vfcmp,vslideup,vslidedown,vislide1up,\ vislide1down,vfslide1up,vfslide1down,vgather,viwmuladd,vfwmuladd,\ - vlsegds,vlsegdux,vlsegdox") + vlsegds,vlsegdux,vlsegdox,vandn,vrol,vror,vwsll") (const_int 8) - (eq_attr "type" "vstux,vstox,vssegts,vssegtux,vssegtox") + (eq_attr "type" "vstux,vstox,vssegts,vssegtux,vssegtox,vclmul,vclmulh") (const_int 5) (eq_attr "type" "vimuladd,vfmuladd") (const_int 9) - (eq_attr "type" "vmsfs,vmidx,vcompress") + (eq_attr "type" "vmsfs,vmidx,vcompress,vghsh,vaeskf1,vaeskf2,vsha2ms,vsha2ch,vsha2cl,\ + vsm4k,vsm3me,vsm3c") (const_int 6) - (eq_attr "type" "vmpop,vmffs,vssegte") + (eq_attr "type" "vmpop,vmffs,vssegte,vclz,vctz") (const_int 4)] (const_int INVALID_ATTRIBUTE))) From patchwork Wed Dec 6 02:45:24 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Feng Wang X-Patchwork-Id: 1872425 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@legolas.ozlabs.org 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 4SlMJ158kDz23mf for ; Wed, 6 Dec 2023 13:47:13 +1100 (AEDT) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id A4B4C3845BCB for ; Wed, 6 Dec 2023 02:47:11 +0000 (GMT) X-Original-To: gcc-patches@gcc.gnu.org Delivered-To: gcc-patches@gcc.gnu.org Received: from zg8tmja2lje4os4yms4ymjma.icoremail.net (zg8tmja2lje4os4yms4ymjma.icoremail.net [206.189.21.223]) by sourceware.org (Postfix) with ESMTP id 0836B384772B for ; Wed, 6 Dec 2023 02:46:35 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 0836B384772B Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=eswincomputing.com Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=eswincomputing.com ARC-Filter: OpenARC Filter v1.0.0 sourceware.org 0836B384772B Authentication-Results: server2.sourceware.org; arc=none smtp.remote-ip=206.189.21.223 ARC-Seal: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1701830803; cv=none; b=iNNSMr3EY9hkIo0X0d3zPgtgyuWIYIGNPHdgSVPLkg8yjigthNX2ATh1qwdq3WkFzpTdUq8DvraLBBbD0KwbVcKD9455loZVvzbAgsWW95Q8Q1ABeVXaq5LdWdMNr1pCModhnL4LVpv98Y3LB/vPKvuzFvWIuuKTupJB6TfzLOQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1701830803; c=relaxed/simple; bh=IhuKrEGxmj21mjjOXg8sSU0M8o59tbjjh3WAWeCMNdI=; h=From:To:Subject:Date:Message-Id; b=gDAtPrUKNzKgDpaOs/reqOGFcAdGYQOe94UFkD66omoitwBYoHqV6GSZyz3Eiafqjz3WYYhpmhu/z5dsehogYCcU/hRmM6cuKHUxz5mX5Oka2XJ0IzNBUFpKl5pm1xebkyZP1ZPPlL4nkwKTLIug6LoPSkYeN5wMvJOWx3ovcBs= ARC-Authentication-Results: i=1; server2.sourceware.org Received: from localhost.localdomain (unknown [10.12.130.31]) by app2 (Coremail) with SMTP id TQJkCgAnttQ54G9llmIAAA--.5861S7; Wed, 06 Dec 2023 10:45:26 +0800 (CST) From: Feng Wang To: gcc-patches@gcc.gnu.org Cc: kito.cheng@gmail.com, jeffreyalaw@gmail.com, juzhe.zhong@rivai.ai, zhusonghe@eswincomputing.com, panciyan@eswincomputing.com, Feng Wang Subject: [PATCH 4/4] RISC-V: Add crypto vector api-testing cases. Date: Wed, 6 Dec 2023 02:45:24 +0000 Message-Id: <20231206024524.10792-4-wangfeng@eswincomputing.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20231206024524.10792-1-wangfeng@eswincomputing.com> References: <20231206024524.10792-1-wangfeng@eswincomputing.com> X-CM-TRANSID: TQJkCgAnttQ54G9llmIAAA--.5861S7 X-Coremail-Antispam: 1UD129KBjvAXoWkXw1fJF48Zr4UKw4fZFyftFb_yoWDtrykGo Z09r1rGa1fWr1fZr1Duw4UK3WFq3W8trsxGrn5KrZ2k3WkZw1FkFsFgF1UCFnxKr4qva98 CrnavFWxt3y2krWfn29KB7ZKAUJUUUUU529EdanIXcx71UUUUU7v73VFW2AGmfu7bjvjm3 AaLaJ3UjIYCTnIWjp_UUUYO7AC8VAFwI0_Wr0E3s1l1xkIjI8I6I8E6xAIw20EY4v20xva j40_Wr0E3s1l1IIY67AEw4v_Jr0_Jr4l82xGYIkIc2x26280x7IE14v26r1rM28IrcIa0x kI8VCY1x0267AKxVW5JVCq3wA2ocxC64kIII0Yj41l84x0c7CEw4AK67xGY2AK021l84AC jcxK6xIIjxv20xvE14v26w1j6s0DM28EF7xvwVC0I7IYx2IY6xkF7I0E14v26r4UJVWxJr 1l84ACjcxK6I8E87Iv67AKxVW0oVCq3wA2z4x0Y4vEx4A2jsIEc7CjxVAFwI0_GcCE3s1l e2I262IYc4CY6c8Ij28IcVAaY2xG8wAqx4xG64xvF2IEw4CE5I8CrVC2j2WlYx0E2Ix0cI 8IcVAFwI0_Jr0_Jr4lYx0Ex4A2jsIE14v26r1j6r4UMcvjeVCFs4IE7xkEbVWUJVW8JwAC jI8F5VA0II8E6IAqYI8I648v4I1lc2xSY4AK6svPMxC20s026xCaFVCjc4AY6r1j6r4UMI 8I3I0E5I8CrVAFwI0_Jr0_Jr4lx2IqxVCjr7xvwVAFwI0_JrI_JrWlx4CE17CEb7AF67AK xVWUAVWUtwCI42IY6xIIjxv20xvE14v26r1j6r1xMIIF0xvE2Ix0cI8IcVCY1x0267AKxV W8JVWxJwCI42IY6xAIw20EY4v20xvaj40_Jr0_JF4lIxAIcVC2z280aVAFwI0_Jr0_Gr1l IxAIcVC2z280aVCY1x0267AKxVW8JVW8JrUvcSsGvfC2KfnxnUUI43ZEXa7VUbJ73DUUUU U== X-CM-SenderInfo: pzdqwwxhqjqvxvzl0uprps33xlqjhudrp/ X-Spam-Status: No, score=-12.5 required=5.0 tests=BAYES_00, GIT_PATCH_0, KAM_DMARC_STATUS, KAM_SHORT, RCVD_IN_MSPIKE_H4, RCVD_IN_MSPIKE_WL, 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 This patch add crypto vector api-testing cases based on https://github.com/riscv-non-isa/rvv-intrinsic-doc/blob/ eopc/vector-crypto/auto-generated/vector-crypto gcc/testsuite/ChangeLog: * gcc.target/riscv/zvk/zvbb/vandn.c: New test. * gcc.target/riscv/zvk/zvbb/vandn_overloaded.c: New test. * gcc.target/riscv/zvk/zvbb/vbrev.c: New test. * gcc.target/riscv/zvk/zvbb/vbrev8.c: New test. * gcc.target/riscv/zvk/zvbb/vbrev8_overloaded.c: New test. * gcc.target/riscv/zvk/zvbb/vbrev_overloaded.c: New test. * gcc.target/riscv/zvk/zvbb/vclz.c: New test. * gcc.target/riscv/zvk/zvbb/vclz_overloaded.c: New test. * gcc.target/riscv/zvk/zvbb/vctz.c: New test. * gcc.target/riscv/zvk/zvbb/vctz_overloaded.c: New test. * gcc.target/riscv/zvk/zvbb/vrev8.c: New test. * gcc.target/riscv/zvk/zvbb/vrev8_overloaded.c: New test. * gcc.target/riscv/zvk/zvbb/vrol.c: New test. * gcc.target/riscv/zvk/zvbb/vrol_overloaded.c: New test. * gcc.target/riscv/zvk/zvbb/vror.c: New test. * gcc.target/riscv/zvk/zvbb/vror_overloaded.c: New test. * gcc.target/riscv/zvk/zvbb/vwsll.c: New test. * gcc.target/riscv/zvk/zvbb/vwsll_overloaded.c: New test. * gcc.target/riscv/zvk/zvbb/zvkb.c: New test. * gcc.target/riscv/zvk/zvbc/vclmul.c: New test. * gcc.target/riscv/zvk/zvbc/vclmul_overloaded.c: New test. * gcc.target/riscv/zvk/zvbc/vclmulh.c: New test. * gcc.target/riscv/zvk/zvbc/vclmulh_overloaded.c: New test. * gcc.target/riscv/zvk/zvk.exp: New test. * gcc.target/riscv/zvk/zvkg/vghsh.c: New test. * gcc.target/riscv/zvk/zvkg/vghsh_overloaded.c: New test. * gcc.target/riscv/zvk/zvkg/vgmul.c: New test. * gcc.target/riscv/zvk/zvkg/vgmul_overloaded.c: New test. * gcc.target/riscv/zvk/zvkned/vaesdf.c: New test. * gcc.target/riscv/zvk/zvkned/vaesdf_overloaded.c: New test. * gcc.target/riscv/zvk/zvkned/vaesdm.c: New test. * gcc.target/riscv/zvk/zvkned/vaesdm_overloaded.c: New test. * gcc.target/riscv/zvk/zvkned/vaesef.c: New test. * gcc.target/riscv/zvk/zvkned/vaesef_overloaded.c: New test. * gcc.target/riscv/zvk/zvkned/vaesem.c: New test. * gcc.target/riscv/zvk/zvkned/vaesem_overloaded.c: New test. * gcc.target/riscv/zvk/zvkned/vaeskf1.c: New test. * gcc.target/riscv/zvk/zvkned/vaeskf1_overloaded.c: New test. * gcc.target/riscv/zvk/zvkned/vaeskf2.c: New test. * gcc.target/riscv/zvk/zvkned/vaeskf2_overloaded.c: New test. * gcc.target/riscv/zvk/zvkned/vaesz.c: New test. * gcc.target/riscv/zvk/zvkned/vaesz_overloaded.c: New test. * gcc.target/riscv/zvk/zvknha/vsha2ch.c: New test. * gcc.target/riscv/zvk/zvknha/vsha2ch_overloaded.c: New test. * gcc.target/riscv/zvk/zvknha/vsha2cl.c: New test. * gcc.target/riscv/zvk/zvknha/vsha2cl_overloaded.c: New test. * gcc.target/riscv/zvk/zvknha/vsha2ms.c: New test. * gcc.target/riscv/zvk/zvknha/vsha2ms_overloaded.c: New test. * gcc.target/riscv/zvk/zvknhb/vsha2ch.c: New test. * gcc.target/riscv/zvk/zvknhb/vsha2ch_overloaded.c: New test. * gcc.target/riscv/zvk/zvknhb/vsha2cl.c: New test. * gcc.target/riscv/zvk/zvknhb/vsha2cl_overloaded.c: New test. * gcc.target/riscv/zvk/zvknhb/vsha2ms.c: New test. * gcc.target/riscv/zvk/zvknhb/vsha2ms_overloaded.c: New test. * gcc.target/riscv/zvk/zvksed/vsm4k.c: New test. * gcc.target/riscv/zvk/zvksed/vsm4k_overloaded.c: New test. * gcc.target/riscv/zvk/zvksed/vsm4r.c: New test. * gcc.target/riscv/zvk/zvksed/vsm4r_overloaded.c: New test. * gcc.target/riscv/zvk/zvksh/vsm3c.c: New test. * gcc.target/riscv/zvk/zvksh/vsm3c_overloaded.c: New test. * gcc.target/riscv/zvk/zvksh/vsm3me.c: New test. * gcc.target/riscv/zvk/zvksh/vsm3me_overloaded.c: New test. * gcc.target/riscv/zvkb.c: New test. --- .../gcc.target/riscv/zvk/zvbb/vandn.c | 172 +++++++++++++++ .../riscv/zvk/zvbb/vandn_overloaded.c | 172 +++++++++++++++ .../gcc.target/riscv/zvk/zvbb/vbrev.c | 170 ++++++++++++++ .../gcc.target/riscv/zvk/zvbb/vbrev8.c | 170 ++++++++++++++ .../riscv/zvk/zvbb/vbrev8_overloaded.c | 170 ++++++++++++++ .../riscv/zvk/zvbb/vbrev_overloaded.c | 170 ++++++++++++++ .../gcc.target/riscv/zvk/zvbb/vclz.c | 187 ++++++++++++++++ .../riscv/zvk/zvbb/vclz_overloaded.c | 187 ++++++++++++++++ .../gcc.target/riscv/zvk/zvbb/vctz.c | 187 ++++++++++++++++ .../riscv/zvk/zvbb/vctz_overloaded.c | 188 ++++++++++++++++ .../gcc.target/riscv/zvk/zvbb/vrev8.c | 170 ++++++++++++++ .../riscv/zvk/zvbb/vrev8_overloaded.c | 170 ++++++++++++++ .../gcc.target/riscv/zvk/zvbb/vrol.c | 172 +++++++++++++++ .../riscv/zvk/zvbb/vrol_overloaded.c | 172 +++++++++++++++ .../gcc.target/riscv/zvk/zvbb/vror.c | 172 +++++++++++++++ .../riscv/zvk/zvbb/vror_overloaded.c | 172 +++++++++++++++ .../gcc.target/riscv/zvk/zvbb/vwsll.c | 164 ++++++++++++++ .../riscv/zvk/zvbb/vwsll_overloaded.c | 165 ++++++++++++++ .../gcc.target/riscv/zvk/zvbb/zvkb.c | 48 ++++ .../gcc.target/riscv/zvk/zvbc/vclmul.c | 208 ++++++++++++++++++ .../riscv/zvk/zvbc/vclmul_overloaded.c | 208 ++++++++++++++++++ .../gcc.target/riscv/zvk/zvbc/vclmulh.c | 208 ++++++++++++++++++ .../riscv/zvk/zvbc/vclmulh_overloaded.c | 208 ++++++++++++++++++ gcc/testsuite/gcc.target/riscv/zvk/zvk.exp | 54 +++++ .../gcc.target/riscv/zvk/zvkg/vghsh.c | 51 +++++ .../riscv/zvk/zvkg/vghsh_overloaded.c | 51 +++++ .../gcc.target/riscv/zvk/zvkg/vgmul.c | 51 +++++ .../riscv/zvk/zvkg/vgmul_overloaded.c | 51 +++++ .../gcc.target/riscv/zvk/zvkned/vaesdf.c | 169 ++++++++++++++ .../riscv/zvk/zvkned/vaesdf_overloaded.c | 169 ++++++++++++++ .../gcc.target/riscv/zvk/zvkned/vaesdm.c | 170 ++++++++++++++ .../riscv/zvk/zvkned/vaesdm_overloaded.c | 170 ++++++++++++++ .../gcc.target/riscv/zvk/zvkned/vaesef.c | 170 ++++++++++++++ .../riscv/zvk/zvkned/vaesef_overloaded.c | 170 ++++++++++++++ .../gcc.target/riscv/zvk/zvkned/vaesem.c | 170 ++++++++++++++ .../riscv/zvk/zvkned/vaesem_overloaded.c | 170 ++++++++++++++ .../gcc.target/riscv/zvk/zvkned/vaeskf1.c | 50 +++++ .../riscv/zvk/zvkned/vaeskf1_overloaded.c | 50 +++++ .../gcc.target/riscv/zvk/zvkned/vaeskf2.c | 50 +++++ .../riscv/zvk/zvkned/vaeskf2_overloaded.c | 50 +++++ .../gcc.target/riscv/zvk/zvkned/vaesz.c | 130 +++++++++++ .../riscv/zvk/zvkned/vaesz_overloaded.c | 130 +++++++++++ .../gcc.target/riscv/zvk/zvknha/vsha2ch.c | 51 +++++ .../riscv/zvk/zvknha/vsha2ch_overloaded.c | 51 +++++ .../gcc.target/riscv/zvk/zvknha/vsha2cl.c | 51 +++++ .../riscv/zvk/zvknha/vsha2cl_overloaded.c | 51 +++++ .../gcc.target/riscv/zvk/zvknha/vsha2ms.c | 51 +++++ .../riscv/zvk/zvknha/vsha2ms_overloaded.c | 51 +++++ .../gcc.target/riscv/zvk/zvknhb/vsha2ch.c | 83 +++++++ .../riscv/zvk/zvknhb/vsha2ch_overloaded.c | 83 +++++++ .../gcc.target/riscv/zvk/zvknhb/vsha2cl.c | 83 +++++++ .../riscv/zvk/zvknhb/vsha2cl_overloaded.c | 83 +++++++ .../gcc.target/riscv/zvk/zvknhb/vsha2ms.c | 83 +++++++ .../riscv/zvk/zvknhb/vsha2ms_overloaded.c | 83 +++++++ .../gcc.target/riscv/zvk/zvksed/vsm4k.c | 50 +++++ .../riscv/zvk/zvksed/vsm4k_overloaded.c | 50 +++++ .../gcc.target/riscv/zvk/zvksed/vsm4r.c | 170 ++++++++++++++ .../riscv/zvk/zvksed/vsm4r_overloaded.c | 170 ++++++++++++++ .../gcc.target/riscv/zvk/zvksh/vsm3c.c | 51 +++++ .../riscv/zvk/zvksh/vsm3c_overloaded.c | 51 +++++ .../gcc.target/riscv/zvk/zvksh/vsm3me.c | 51 +++++ .../riscv/zvk/zvksh/vsm3me_overloaded.c | 51 +++++ gcc/testsuite/gcc.target/riscv/zvkb.c | 13 ++ 63 files changed, 7547 insertions(+) create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vandn.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vandn_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev8.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev8_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vclz.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vclz_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vctz.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vctz_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrev8.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrev8_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrol.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrol_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vror.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vror_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vwsll.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/vwsll_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbb/zvkb.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmul.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmul_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmulh.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmulh_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvk.exp create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkg/vghsh.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkg/vghsh_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkg/vgmul.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkg/vgmul_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdf.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdf_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdm.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdm_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesef.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesef_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesem.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesem_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf1.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf1_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf2.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf2_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesz.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesz_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4k.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4k_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4r.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4r_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3c.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3c_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3me.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3me_overloaded.c create mode 100644 gcc/testsuite/gcc.target/riscv/zvkb.c diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vandn.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vandn.c new file mode 100644 index 00000000000..d3462ea114c --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vandn.c @@ -0,0 +1,172 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -Wno-psabi" } */ +#include + +vuint8mf8_t test_vandn_vv_u8mf8(vuint8mf8_t vs2, vuint8mf8_t vs1, size_t vl) { + return __riscv_vandn_vv_u8mf8(vs2, vs1, vl); +} + +vuint8mf8_t test_vandn_vx_u8mf8(vuint8mf8_t vs2, uint8_t rs1, size_t vl) { + return __riscv_vandn_vx_u8mf8(vs2, rs1, vl); +} + +vuint16mf4_t test_vandn_vv_u16mf4(vuint16mf4_t vs2, vuint16mf4_t vs1, size_t vl) { + return __riscv_vandn_vv_u16mf4(vs2, vs1, vl); +} + +vuint16mf4_t test_vandn_vx_u16mf4(vuint16mf4_t vs2, uint16_t rs1, size_t vl) { + return __riscv_vandn_vx_u16mf4(vs2, rs1, vl); +} + +vuint32m1_t test_vandn_vv_u32m1(vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vandn_vv_u32m1(vs2, vs1, vl); +} + +vuint32m1_t test_vandn_vx_u32m1(vuint32m1_t vs2, uint32_t rs1, size_t vl) { + return __riscv_vandn_vx_u32m1(vs2, rs1, vl); +} + +vuint64m2_t test_vandn_vv_u64m2(vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vandn_vv_u64m2(vs2, vs1, vl); +} + +vuint64m2_t test_vandn_vx_u64m2(vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vandn_vx_u64m2(vs2, rs1, vl); +} + +vuint8mf4_t test_vandn_vv_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, vuint8mf4_t vs1, size_t vl) { + return __riscv_vandn_vv_u8mf4_m(mask, vs2, vs1, vl); +} + +vuint8mf4_t test_vandn_vx_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, uint8_t rs1, size_t vl) { + return __riscv_vandn_vx_u8mf4_m(mask, vs2, rs1, vl); +} + +vuint16mf2_t test_vandn_vv_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vandn_vv_u16mf2_m(mask, vs2, vs1, vl); +} + +vuint16mf2_t test_vandn_vx_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, uint16_t rs1, size_t vl) { + return __riscv_vandn_vx_u16mf2_m(mask, vs2, rs1, vl); +} + +vuint32m2_t test_vandn_vv_u32m2_m(vbool16_t mask, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vandn_vv_u32m2_m(mask, vs2, vs1, vl); +} + +vuint32m2_t test_vandn_vx_u32m2_m(vbool16_t mask, vuint32m2_t vs2, uint32_t rs1, size_t vl) { + return __riscv_vandn_vx_u32m2_m(mask, vs2, rs1, vl); +} + +vuint64m4_t test_vandn_vv_u64m4_m(vbool16_t mask, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vandn_vv_u64m4_m(mask, vs2, vs1, vl); +} + +vuint64m4_t test_vandn_vx_u64m4_m(vbool16_t mask, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vandn_vx_u64m4_m(mask, vs2, rs1, vl); +} + +vuint8mf2_t test_vandn_vv_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, vuint8mf2_t vs1, size_t vl) { + return __riscv_vandn_vv_u8mf2_tu(maskedoff, vs2, vs1, vl); +} + +vuint8mf2_t test_vandn_vx_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, uint8_t rs1, size_t vl) { + return __riscv_vandn_vx_u8mf2_tu(maskedoff, vs2, rs1, vl); +} + +vuint16mf2_t test_vandn_vv_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vandn_vv_u16mf2_tu(maskedoff, vs2, vs1, vl); +} + +vuint16mf2_t test_vandn_vx_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, uint16_t rs1, size_t vl) { + return __riscv_vandn_vx_u16mf2_tu(maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vandn_vv_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vandn_vv_u32m1_tu(maskedoff, vs2, vs1, vl); +} + +vuint32m1_t test_vandn_vx_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, uint32_t rs1, size_t vl) { + return __riscv_vandn_vx_u32m1_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vandn_vv_u64m4_tu(vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vandn_vv_u64m4_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vandn_vx_u64m4_tu(vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vandn_vx_u64m4_tu(maskedoff, vs2, rs1, vl); +} + +vuint8m1_t test_vandn_vv_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, vuint8m1_t vs1, size_t vl) { + return __riscv_vandn_vv_u8m1_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint8m1_t test_vandn_vx_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, uint8_t rs1, size_t vl) { + return __riscv_vandn_vx_u8m1_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vandn_vv_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, vuint16m2_t vs1, size_t vl) { + return __riscv_vandn_vv_u16m2_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m2_t test_vandn_vx_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, uint16_t rs1, size_t vl) { + return __riscv_vandn_vx_u16m2_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m4_t test_vandn_vv_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vandn_vv_u32m4_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint32m4_t test_vandn_vx_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, uint32_t rs1, size_t vl) { + return __riscv_vandn_vx_u32m4_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vandn_vv_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vandn_vv_u64m4_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vandn_vx_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vandn_vx_u64m4_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint8m8_t test_vandn_vv_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vandn_vv_u8m8_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint8m8_t test_vandn_vx_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, uint8_t rs1, size_t vl) { + return __riscv_vandn_vx_u8m8_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vandn_vv_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, vuint16m2_t vs1, size_t vl) { + return __riscv_vandn_vv_u16m2_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m2_t test_vandn_vx_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, uint16_t rs1, size_t vl) { + return __riscv_vandn_vx_u16m2_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m2_t test_vandn_vx_u32m2_mu(vbool16_t mask, vuint32m2_t maskedoff, vuint32m2_t vs2, uint32_t rs1, size_t vl) { + return __riscv_vandn_vx_u32m2_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m4_t test_vandn_vv_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vandn_vv_u32m4_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vandn_vv_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vandn_vv_u64m8_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vandn_vx_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vandn_vx_u64m8_mu(mask, maskedoff, vs2, rs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vandn\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]} 20 } } */ +/* { dg-final { scan-assembler-times {vandn\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t} 12 } } */ +/* { dg-final { scan-assembler-times {vandn\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]} 20 } } */ +/* { dg-final { scan-assembler-times {vandn\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]+,\s*v0.t} 12 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vandn_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vandn_overloaded.c new file mode 100644 index 00000000000..25113efb0d2 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vandn_overloaded.c @@ -0,0 +1,172 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O2 -Wno-psabi" } */ +#include + +vuint8mf8_t test_vandn_vv_u8mf8(vuint8mf8_t vs2, vuint8mf8_t vs1, size_t vl) { + return __riscv_vandn(vs2, vs1, vl); +} + +vuint8mf8_t test_vandn_vx_u8mf8(vuint8mf8_t vs2, uint8_t rs1, size_t vl) { + return __riscv_vandn(vs2, rs1, vl); +} + +vuint16mf4_t test_vandn_vv_u16mf4(vuint16mf4_t vs2, vuint16mf4_t vs1, size_t vl) { + return __riscv_vandn(vs2, vs1, vl); +} + +vuint16mf4_t test_vandn_vx_u16mf4(vuint16mf4_t vs2, uint16_t rs1, size_t vl) { + return __riscv_vandn(vs2, rs1, vl); +} + +vuint32m1_t test_vandn_vv_u32m1(vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vandn(vs2, vs1, vl); +} + +vuint32m1_t test_vandn_vx_u32m1(vuint32m1_t vs2, uint32_t rs1, size_t vl) { + return __riscv_vandn(vs2, rs1, vl); +} + +vuint64m2_t test_vandn_vv_u64m2(vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vandn(vs2, vs1, vl); +} + +vuint64m2_t test_vandn_vx_u64m2(vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vandn(vs2, rs1, vl); +} + +vuint8mf4_t test_vandn_vv_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, vuint8mf4_t vs1, size_t vl) { + return __riscv_vandn(mask, vs2, vs1, vl); +} + +vuint8mf4_t test_vandn_vx_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, uint8_t rs1, size_t vl) { + return __riscv_vandn(mask, vs2, rs1, vl); +} + +vuint16mf2_t test_vandn_vv_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vandn(mask, vs2, vs1, vl); +} + +vuint16mf2_t test_vandn_vx_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, uint16_t rs1, size_t vl) { + return __riscv_vandn(mask, vs2, rs1, vl); +} + +vuint32m2_t test_vandn_vv_u32m2_m(vbool16_t mask, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vandn(mask, vs2, vs1, vl); +} + +vuint32m2_t test_vandn_vx_u32m2_m(vbool16_t mask, vuint32m2_t vs2, uint32_t rs1, size_t vl) { + return __riscv_vandn(mask, vs2, rs1, vl); +} + +vuint64m4_t test_vandn_vv_u64m4_m(vbool16_t mask, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vandn(mask, vs2, vs1, vl); +} + +vuint64m4_t test_vandn_vx_u64m4_m(vbool16_t mask, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vandn(mask, vs2, rs1, vl); +} + +vuint8mf2_t test_vandn_vv_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, vuint8mf2_t vs1, size_t vl) { + return __riscv_vandn_tu(maskedoff, vs2, vs1, vl); +} + +vuint8mf2_t test_vandn_vx_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, uint8_t rs1, size_t vl) { + return __riscv_vandn_tu(maskedoff, vs2, rs1, vl); +} + +vuint16mf2_t test_vandn_vv_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vandn_tu(maskedoff, vs2, vs1, vl); +} + +vuint16mf2_t test_vandn_vx_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, uint16_t rs1, size_t vl) { + return __riscv_vandn_tu(maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vandn_vv_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vandn_tu(maskedoff, vs2, vs1, vl); +} + +vuint32m1_t test_vandn_vx_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, uint32_t rs1, size_t vl) { + return __riscv_vandn_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vandn_vv_u64m4_tu(vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vandn_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vandn_vx_u64m4_tu(vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vandn_tu(maskedoff, vs2, rs1, vl); +} + +vuint8m1_t test_vandn_vv_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, vuint8m1_t vs1, size_t vl) { + return __riscv_vandn_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint8m1_t test_vandn_vx_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, uint8_t rs1, size_t vl) { + return __riscv_vandn_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vandn_vv_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, vuint16m2_t vs1, size_t vl) { + return __riscv_vandn_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m2_t test_vandn_vx_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, uint16_t rs1, size_t vl) { + return __riscv_vandn_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m4_t test_vandn_vv_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vandn_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint32m4_t test_vandn_vx_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, uint32_t rs1, size_t vl) { + return __riscv_vandn_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vandn_vv_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vandn_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vandn_vx_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vandn_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint8m8_t test_vandn_vv_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vandn_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint8m8_t test_vandn_vx_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, uint8_t rs1, size_t vl) { + return __riscv_vandn_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vandn_vv_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, vuint16m2_t vs1, size_t vl) { + return __riscv_vandn_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m2_t test_vandn_vx_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, uint16_t rs1, size_t vl) { + return __riscv_vandn_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m2_t test_vandn_vx_u32m2_mu(vbool16_t mask, vuint32m2_t maskedoff, vuint32m2_t vs2, uint32_t rs1, size_t vl) { + return __riscv_vandn_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m4_t test_vandn_vv_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vandn_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vandn_vv_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vandn_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vandn_vx_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vandn_mu(mask, maskedoff, vs2, rs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vandn\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]} 20 } } */ +/* { dg-final { scan-assembler-times {vandn\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t} 12 } } */ +/* { dg-final { scan-assembler-times {vandn\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]} 20 } } */ +/* { dg-final { scan-assembler-times {vandn\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]+,\s*v0.t} 12 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev.c new file mode 100644 index 00000000000..23b3b2f2f62 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O3 -Wno-psabi" } */ +#include + +vuint8mf8_t test_vbrev_v_u8mf8(vuint8mf8_t vs2, size_t vl) { + return __riscv_vbrev_v_u8mf8(vs2, vl); +} + +vuint8m8_t test_vbrev_v_u8m8(vuint8m8_t vs2, size_t vl) { + return __riscv_vbrev_v_u8m8(vs2, vl); +} + +vuint16mf4_t test_vbrev_v_u16mf4(vuint16mf4_t vs2, size_t vl) { + return __riscv_vbrev_v_u16mf4(vs2, vl); +} + +vuint16m4_t test_vbrev_v_u16m4(vuint16m4_t vs2, size_t vl) { + return __riscv_vbrev_v_u16m4(vs2, vl); +} + +vuint32m1_t test_vbrev_v_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u32m1(vs2, vl); +} + +vuint32m2_t test_vbrev_v_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vbrev_v_u32m2(vs2, vl); +} + +vuint64m1_t test_vbrev_v_u64m1(vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u64m1(vs2, vl); +} + +vuint64m2_t test_vbrev_v_u64m2(vuint64m2_t vs2, size_t vl) { + return __riscv_vbrev_v_u64m2(vs2, vl); +} + +vuint8mf4_t test_vbrev_v_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, size_t vl) { + return __riscv_vbrev_v_u8mf4_m(mask, vs2, vl); +} + +vuint8m4_t test_vbrev_v_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t vl) { + return __riscv_vbrev_v_u8m4_m(mask, vs2, vl); +} + +vuint16mf2_t test_vbrev_v_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, size_t vl) { + return __riscv_vbrev_v_u16mf2_m(mask, vs2, vl); +} + +vuint16m1_t test_vbrev_v_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u16m1_m(mask, vs2, vl); +} + +vuint32m1_t test_vbrev_v_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u32m1_m(mask, vs2, vl); +} + +vuint32m2_t test_vbrev_v_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t vl) { + return __riscv_vbrev_v_u32m2_m(mask, vs2, vl); +} + +vuint64m1_t test_vbrev_v_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u64m1_m(mask, vs2, vl); +} + +vuint64m4_t test_vbrev_v_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t vl) { + return __riscv_vbrev_v_u64m4_m(mask, vs2, vl); +} + +vuint8mf2_t test_vbrev_v_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, size_t vl) { + return __riscv_vbrev_v_u8mf2_tu(maskedoff, vs2, vl); +} + +vuint8m2_t test_vbrev_v_u8m2_tu(vuint8m2_t maskedoff, vuint8m2_t vs2, size_t vl) { + return __riscv_vbrev_v_u8m2_tu(maskedoff, vs2, vl); +} + +vuint16mf2_t test_vbrev_v_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t vl) { + return __riscv_vbrev_v_u16mf2_tu(maskedoff, vs2, vl); +} + +vuint16m2_t test_vbrev_v_u16m2_tu(vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vbrev_v_u16m2_tu(maskedoff, vs2, vl); +} + +vuint32m1_t test_vbrev_v_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u32m1_tu(maskedoff, vs2, vl); +} + +vuint32m1_t test_vbrev_v_u32m1_tum(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u32m1_tum(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vbrev_v_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u64m1_tum(mask, maskedoff, vs2, vl); +} + +vuint64m4_t test_vbrev_v_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t vl) { + return __riscv_vbrev_v_u64m4_tum(mask, maskedoff, vs2, vl); +} + +vuint8m1_t test_vbrev_v_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u8m1_tumu(mask, maskedoff, vs2, vl); +} + +vuint8m8_t test_vbrev_v_u8m8_tumu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, size_t vl) { + return __riscv_vbrev_v_u8m8_tumu(mask, maskedoff, vs2, vl); +} + +vuint16mf2_t test_vbrev_v_u16mf2_tumu(vbool32_t mask, vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t vl) { + return __riscv_vbrev_v_u16mf2_tumu(mask, maskedoff, vs2, vl); +} + +vuint16m2_t test_vbrev_v_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vbrev_v_u16m2_tumu(mask, maskedoff, vs2, vl); +} + +vuint32m1_t test_vbrev_v_u32m1_tumu(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u32m1_tumu(mask, maskedoff, vs2, vl); +} + +vuint32m4_t test_vbrev_v_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vbrev_v_u32m4_tumu(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vbrev_v_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u64m1_tumu(mask, maskedoff, vs2, vl); +} + +vuint64m4_t test_vbrev_v_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t vl) { + return __riscv_vbrev_v_u64m4_tumu(mask, maskedoff, vs2, vl); +} + +vuint8m1_t test_vbrev_v_u8m1_mu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u8m1_mu(mask, maskedoff, vs2, vl); +} + +vuint8m8_t test_vbrev_v_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, size_t vl) { + return __riscv_vbrev_v_u8m8_mu(mask, maskedoff, vs2, vl); +} + +vuint16m1_t test_vbrev_v_u16m1_mu(vbool16_t mask, vuint16m1_t maskedoff, vuint16m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u16m1_mu(mask, maskedoff, vs2, vl); +} + +vuint16m2_t test_vbrev_v_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vbrev_v_u16m2_mu(mask, maskedoff, vs2, vl); +} + +vuint32m2_t test_vbrev_v_u32m2_mu(vbool16_t mask, vuint32m2_t maskedoff, vuint32m2_t vs2, size_t vl) { + return __riscv_vbrev_v_u32m2_mu(mask, maskedoff, vs2, vl); +} + +vuint32m4_t test_vbrev_v_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vbrev_v_u32m4_mu(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vbrev_v_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev_v_u64m1_mu(mask, maskedoff, vs2, vl); +} + +vuint64m8_t test_vbrev_v_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, size_t vl) { + return __riscv_vbrev_v_u64m8_mu(mask, maskedoff, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vbrev\.v\s+v[0-9]+,\s*v[0-9]} 40 } } */ +/* { dg-final { scan-assembler-times {vbrev\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0.t} 27 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev8.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev8.c new file mode 100644 index 00000000000..abfeadce941 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev8.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O3 -Wno-psabi" } */ +#include + +vuint8mf8_t test_vbrev8_v_u8mf8(vuint8mf8_t vs2, size_t vl) { + return __riscv_vbrev8_v_u8mf8(vs2, vl); +} + +vuint8m8_t test_vbrev8_v_u8m8(vuint8m8_t vs2, size_t vl) { + return __riscv_vbrev8_v_u8m8(vs2, vl); +} + +vuint16mf4_t test_vbrev8_v_u16mf4(vuint16mf4_t vs2, size_t vl) { + return __riscv_vbrev8_v_u16mf4(vs2, vl); +} + +vuint16m4_t test_vbrev8_v_u16m4(vuint16m4_t vs2, size_t vl) { + return __riscv_vbrev8_v_u16m4(vs2, vl); +} + +vuint32m1_t test_vbrev8_v_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u32m1(vs2, vl); +} + +vuint32m2_t test_vbrev8_v_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vbrev8_v_u32m2(vs2, vl); +} + +vuint64m1_t test_vbrev8_v_u64m1(vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u64m1(vs2, vl); +} + +vuint64m2_t test_vbrev8_v_u64m2(vuint64m2_t vs2, size_t vl) { + return __riscv_vbrev8_v_u64m2(vs2, vl); +} + +vuint8mf4_t test_vbrev8_v_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, size_t vl) { + return __riscv_vbrev8_v_u8mf4_m(mask, vs2, vl); +} + +vuint8m4_t test_vbrev8_v_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t vl) { + return __riscv_vbrev8_v_u8m4_m(mask, vs2, vl); +} + +vuint16mf2_t test_vbrev8_v_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, size_t vl) { + return __riscv_vbrev8_v_u16mf2_m(mask, vs2, vl); +} + +vuint16m1_t test_vbrev8_v_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u16m1_m(mask, vs2, vl); +} + +vuint32m1_t test_vbrev8_v_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u32m1_m(mask, vs2, vl); +} + +vuint32m2_t test_vbrev8_v_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t vl) { + return __riscv_vbrev8_v_u32m2_m(mask, vs2, vl); +} + +vuint64m1_t test_vbrev8_v_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u64m1_m(mask, vs2, vl); +} + +vuint64m4_t test_vbrev8_v_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t vl) { + return __riscv_vbrev8_v_u64m4_m(mask, vs2, vl); +} + +vuint8mf2_t test_vbrev8_v_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, size_t vl) { + return __riscv_vbrev8_v_u8mf2_tu(maskedoff, vs2, vl); +} + +vuint8m2_t test_vbrev8_v_u8m2_tu(vuint8m2_t maskedoff, vuint8m2_t vs2, size_t vl) { + return __riscv_vbrev8_v_u8m2_tu(maskedoff, vs2, vl); +} + +vuint16mf2_t test_vbrev8_v_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t vl) { + return __riscv_vbrev8_v_u16mf2_tu(maskedoff, vs2, vl); +} + +vuint16m2_t test_vbrev8_v_u16m2_tu(vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vbrev8_v_u16m2_tu(maskedoff, vs2, vl); +} + +vuint32m1_t test_vbrev8_v_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u32m1_tu(maskedoff, vs2, vl); +} + +vuint32m1_t test_vbrev8_v_u32m1_tum(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u32m1_tum(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vbrev8_v_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u64m1_tum(mask, maskedoff, vs2, vl); +} + +vuint64m4_t test_vbrev8_v_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t vl) { + return __riscv_vbrev8_v_u64m4_tum(mask, maskedoff, vs2, vl); +} + +vuint8m1_t test_vbrev8_v_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u8m1_tumu(mask, maskedoff, vs2, vl); +} + +vuint8m8_t test_vbrev8_v_u8m8_tumu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, size_t vl) { + return __riscv_vbrev8_v_u8m8_tumu(mask, maskedoff, vs2, vl); +} + +vuint16mf2_t test_vbrev8_v_u16mf2_tumu(vbool32_t mask, vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t vl) { + return __riscv_vbrev8_v_u16mf2_tumu(mask, maskedoff, vs2, vl); +} + +vuint16m2_t test_vbrev8_v_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vbrev8_v_u16m2_tumu(mask, maskedoff, vs2, vl); +} + +vuint32m1_t test_vbrev8_v_u32m1_tumu(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u32m1_tumu(mask, maskedoff, vs2, vl); +} + +vuint32m4_t test_vbrev8_v_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vbrev8_v_u32m4_tumu(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vbrev8_v_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u64m1_tumu(mask, maskedoff, vs2, vl); +} + +vuint64m4_t test_vbrev8_v_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t vl) { + return __riscv_vbrev8_v_u64m4_tumu(mask, maskedoff, vs2, vl); +} + +vuint8m1_t test_vbrev8_v_u8m1_mu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u8m1_mu(mask, maskedoff, vs2, vl); +} + +vuint8m8_t test_vbrev8_v_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, size_t vl) { + return __riscv_vbrev8_v_u8m8_mu(mask, maskedoff, vs2, vl); +} + +vuint16m1_t test_vbrev8_v_u16m1_mu(vbool16_t mask, vuint16m1_t maskedoff, vuint16m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u16m1_mu(mask, maskedoff, vs2, vl); +} + +vuint16m2_t test_vbrev8_v_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vbrev8_v_u16m2_mu(mask, maskedoff, vs2, vl); +} + +vuint32m2_t test_vbrev8_v_u32m2_mu(vbool16_t mask, vuint32m2_t maskedoff, vuint32m2_t vs2, size_t vl) { + return __riscv_vbrev8_v_u32m2_mu(mask, maskedoff, vs2, vl); +} + +vuint32m4_t test_vbrev8_v_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vbrev8_v_u32m4_mu(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vbrev8_v_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev8_v_u64m1_mu(mask, maskedoff, vs2, vl); +} + +vuint64m8_t test_vbrev8_v_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, size_t vl) { + return __riscv_vbrev8_v_u64m8_mu(mask, maskedoff, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vbrev8\.v\s+v[0-9]+,\s*v[0-9]} 40 } } */ +/* { dg-final { scan-assembler-times {vbrev8\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0.t} 27 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev8_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev8_overloaded.c new file mode 100644 index 00000000000..8a578fd19cb --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev8_overloaded.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O2 -Wno-psabi" } */ +#include + +vuint8mf8_t test_vbrev8_v_u8mf8(vuint8mf8_t vs2, size_t vl) { + return __riscv_vbrev8(vs2, vl); +} + +vuint8m8_t test_vbrev8_v_u8m8(vuint8m8_t vs2, size_t vl) { + return __riscv_vbrev8(vs2, vl); +} + +vuint16mf4_t test_vbrev8_v_u16mf4(vuint16mf4_t vs2, size_t vl) { + return __riscv_vbrev8(vs2, vl); +} + +vuint16m4_t test_vbrev8_v_u16m4(vuint16m4_t vs2, size_t vl) { + return __riscv_vbrev8(vs2, vl); +} + +vuint32m1_t test_vbrev8_v_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev8(vs2, vl); +} + +vuint32m2_t test_vbrev8_v_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vbrev8(vs2, vl); +} + +vuint64m1_t test_vbrev8_v_u64m1(vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev8(vs2, vl); +} + +vuint64m2_t test_vbrev8_v_u64m2(vuint64m2_t vs2, size_t vl) { + return __riscv_vbrev8(vs2, vl); +} + +vuint8mf4_t test_vbrev8_v_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, size_t vl) { + return __riscv_vbrev8(mask, vs2, vl); +} + +vuint8m4_t test_vbrev8_v_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t vl) { + return __riscv_vbrev8(mask, vs2, vl); +} + +vuint16mf2_t test_vbrev8_v_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, size_t vl) { + return __riscv_vbrev8(mask, vs2, vl); +} + +vuint16m1_t test_vbrev8_v_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t vl) { + return __riscv_vbrev8(mask, vs2, vl); +} + +vuint32m1_t test_vbrev8_v_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev8(mask, vs2, vl); +} + +vuint32m2_t test_vbrev8_v_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t vl) { + return __riscv_vbrev8(mask, vs2, vl); +} + +vuint64m1_t test_vbrev8_v_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev8(mask, vs2, vl); +} + +vuint64m4_t test_vbrev8_v_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t vl) { + return __riscv_vbrev8(mask, vs2, vl); +} + +vuint8mf2_t test_vbrev8_v_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, size_t vl) { + return __riscv_vbrev8_tu(maskedoff, vs2, vl); +} + +vuint8m2_t test_vbrev8_v_u8m2_tu(vuint8m2_t maskedoff, vuint8m2_t vs2, size_t vl) { + return __riscv_vbrev8_tu(maskedoff, vs2, vl); +} + +vuint16mf2_t test_vbrev8_v_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t vl) { + return __riscv_vbrev8_tu(maskedoff, vs2, vl); +} + +vuint16m2_t test_vbrev8_v_u16m2_tu(vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vbrev8_tu(maskedoff, vs2, vl); +} + +vuint32m1_t test_vbrev8_v_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev8_tu(maskedoff, vs2, vl); +} + +vuint32m1_t test_vbrev8_v_u32m1_tum(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev8_tum(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vbrev8_v_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev8_tum(mask, maskedoff, vs2, vl); +} + +vuint64m4_t test_vbrev8_v_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t vl) { + return __riscv_vbrev8_tum(mask, maskedoff, vs2, vl); +} + +vuint8m1_t test_vbrev8_v_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, size_t vl) { + return __riscv_vbrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint8m8_t test_vbrev8_v_u8m8_tumu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, size_t vl) { + return __riscv_vbrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint16mf2_t test_vbrev8_v_u16mf2_tumu(vbool32_t mask, vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t vl) { + return __riscv_vbrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint16m2_t test_vbrev8_v_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vbrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint32m1_t test_vbrev8_v_u32m1_tumu(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint32m4_t test_vbrev8_v_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vbrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vbrev8_v_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint64m4_t test_vbrev8_v_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t vl) { + return __riscv_vbrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint8m1_t test_vbrev8_v_u8m1_mu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, size_t vl) { + return __riscv_vbrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint8m8_t test_vbrev8_v_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, size_t vl) { + return __riscv_vbrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint16m1_t test_vbrev8_v_u16m1_mu(vbool16_t mask, vuint16m1_t maskedoff, vuint16m1_t vs2, size_t vl) { + return __riscv_vbrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint16m2_t test_vbrev8_v_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vbrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint32m2_t test_vbrev8_v_u32m2_mu(vbool16_t mask, vuint32m2_t maskedoff, vuint32m2_t vs2, size_t vl) { + return __riscv_vbrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint32m4_t test_vbrev8_v_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vbrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vbrev8_v_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint64m8_t test_vbrev8_v_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, size_t vl) { + return __riscv_vbrev8_mu(mask, maskedoff, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vbrev8\.v\s+v[0-9]+,\s*v[0-9]} 40 } } */ +/* { dg-final { scan-assembler-times {vbrev8\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0.t} 27 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev_overloaded.c new file mode 100644 index 00000000000..ae22a1ea15a --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vbrev_overloaded.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O2 -Wno-psabi" } */ +#include + +vuint8mf8_t test_vbrev_v_u8mf8(vuint8mf8_t vs2, size_t vl) { + return __riscv_vbrev(vs2, vl); +} + +vuint8m8_t test_vbrev_v_u8m8(vuint8m8_t vs2, size_t vl) { + return __riscv_vbrev(vs2, vl); +} + +vuint16mf4_t test_vbrev_v_u16mf4(vuint16mf4_t vs2, size_t vl) { + return __riscv_vbrev(vs2, vl); +} + +vuint16m4_t test_vbrev_v_u16m4(vuint16m4_t vs2, size_t vl) { + return __riscv_vbrev(vs2, vl); +} + +vuint32m1_t test_vbrev_v_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev(vs2, vl); +} + +vuint32m2_t test_vbrev_v_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vbrev(vs2, vl); +} + +vuint64m1_t test_vbrev_v_u64m1(vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev(vs2, vl); +} + +vuint64m2_t test_vbrev_v_u64m2(vuint64m2_t vs2, size_t vl) { + return __riscv_vbrev(vs2, vl); +} + +vuint8mf4_t test_vbrev_v_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, size_t vl) { + return __riscv_vbrev(mask, vs2, vl); +} + +vuint8m4_t test_vbrev_v_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t vl) { + return __riscv_vbrev(mask, vs2, vl); +} + +vuint16mf2_t test_vbrev_v_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, size_t vl) { + return __riscv_vbrev(mask, vs2, vl); +} + +vuint16m1_t test_vbrev_v_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t vl) { + return __riscv_vbrev(mask, vs2, vl); +} + +vuint32m1_t test_vbrev_v_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev(mask, vs2, vl); +} + +vuint32m2_t test_vbrev_v_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t vl) { + return __riscv_vbrev(mask, vs2, vl); +} + +vuint64m1_t test_vbrev_v_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev(mask, vs2, vl); +} + +vuint64m4_t test_vbrev_v_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t vl) { + return __riscv_vbrev(mask, vs2, vl); +} + +vuint8mf2_t test_vbrev_v_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, size_t vl) { + return __riscv_vbrev_tu(maskedoff, vs2, vl); +} + +vuint8m2_t test_vbrev_v_u8m2_tu(vuint8m2_t maskedoff, vuint8m2_t vs2, size_t vl) { + return __riscv_vbrev_tu(maskedoff, vs2, vl); +} + +vuint16mf2_t test_vbrev_v_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t vl) { + return __riscv_vbrev_tu(maskedoff, vs2, vl); +} + +vuint16m2_t test_vbrev_v_u16m2_tu(vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vbrev_tu(maskedoff, vs2, vl); +} + +vuint32m1_t test_vbrev_v_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev_tu(maskedoff, vs2, vl); +} + +vuint32m1_t test_vbrev_v_u32m1_tum(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev_tum(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vbrev_v_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev_tum(mask, maskedoff, vs2, vl); +} + +vuint64m4_t test_vbrev_v_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t vl) { + return __riscv_vbrev_tum(mask, maskedoff, vs2, vl); +} + +vuint8m1_t test_vbrev_v_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, size_t vl) { + return __riscv_vbrev_tumu(mask, maskedoff, vs2, vl); +} + +vuint8m8_t test_vbrev_v_u8m8_tumu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, size_t vl) { + return __riscv_vbrev_tumu(mask, maskedoff, vs2, vl); +} + +vuint16mf2_t test_vbrev_v_u16mf2_tumu(vbool32_t mask, vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t vl) { + return __riscv_vbrev_tumu(mask, maskedoff, vs2, vl); +} + +vuint16m2_t test_vbrev_v_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vbrev_tumu(mask, maskedoff, vs2, vl); +} + +vuint32m1_t test_vbrev_v_u32m1_tumu(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vbrev_tumu(mask, maskedoff, vs2, vl); +} + +vuint32m4_t test_vbrev_v_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vbrev_tumu(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vbrev_v_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev_tumu(mask, maskedoff, vs2, vl); +} + +vuint64m4_t test_vbrev_v_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t vl) { + return __riscv_vbrev_tumu(mask, maskedoff, vs2, vl); +} + +vuint8m1_t test_vbrev_v_u8m1_mu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, size_t vl) { + return __riscv_vbrev_mu(mask, maskedoff, vs2, vl); +} + +vuint8m8_t test_vbrev_v_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, size_t vl) { + return __riscv_vbrev_mu(mask, maskedoff, vs2, vl); +} + +vuint16m1_t test_vbrev_v_u16m1_mu(vbool16_t mask, vuint16m1_t maskedoff, vuint16m1_t vs2, size_t vl) { + return __riscv_vbrev_mu(mask, maskedoff, vs2, vl); +} + +vuint16m2_t test_vbrev_v_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vbrev_mu(mask, maskedoff, vs2, vl); +} + +vuint32m2_t test_vbrev_v_u32m2_mu(vbool16_t mask, vuint32m2_t maskedoff, vuint32m2_t vs2, size_t vl) { + return __riscv_vbrev_mu(mask, maskedoff, vs2, vl); +} + +vuint32m4_t test_vbrev_v_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vbrev_mu(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vbrev_v_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vbrev_mu(mask, maskedoff, vs2, vl); +} + +vuint64m8_t test_vbrev_v_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, size_t vl) { + return __riscv_vbrev_mu(mask, maskedoff, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vbrev\.v\s+v[0-9]+,\s*v[0-9]} 40 } } */ +/* { dg-final { scan-assembler-times {vbrev\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0.t} 27 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vclz.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vclz.c new file mode 100644 index 00000000000..df19efd3c7d --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vclz.c @@ -0,0 +1,187 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O3 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint8mf8_t test_vclz_v_u8mf8(vuint8mf8_t vs2, size_t vl) { + return __riscv_vclz_v_u8mf8(vs2, vl); +} + +vuint8mf4_t test_vclz_v_u8mf4(vuint8mf4_t vs2, size_t vl) { + return __riscv_vclz_v_u8mf4(vs2, vl); +} + +vuint8mf2_t test_vclz_v_u8mf2(vuint8mf2_t vs2, size_t vl) { + return __riscv_vclz_v_u8mf2(vs2, vl); +} + +vuint8m1_t test_vclz_v_u8m1(vuint8m1_t vs2, size_t vl) { + return __riscv_vclz_v_u8m1(vs2, vl); +} + +vuint8m2_t test_vclz_v_u8m2(vuint8m2_t vs2, size_t vl) { + return __riscv_vclz_v_u8m2(vs2, vl); +} + +vuint8m4_t test_vclz_v_u8m4(vuint8m4_t vs2, size_t vl) { + return __riscv_vclz_v_u8m4(vs2, vl); +} + +vuint8m8_t test_vclz_v_u8m8(vuint8m8_t vs2, size_t vl) { + return __riscv_vclz_v_u8m8(vs2, vl); +} + +vuint16mf4_t test_vclz_v_u16mf4(vuint16mf4_t vs2, size_t vl) { + return __riscv_vclz_v_u16mf4(vs2, vl); +} + +vuint16mf2_t test_vclz_v_u16mf2(vuint16mf2_t vs2, size_t vl) { + return __riscv_vclz_v_u16mf2(vs2, vl); +} + +vuint16m1_t test_vclz_v_u16m1(vuint16m1_t vs2, size_t vl) { + return __riscv_vclz_v_u16m1(vs2, vl); +} + +vuint16m2_t test_vclz_v_u16m2(vuint16m2_t vs2, size_t vl) { + return __riscv_vclz_v_u16m2(vs2, vl); +} + +vuint16m4_t test_vclz_v_u16m4(vuint16m4_t vs2, size_t vl) { + return __riscv_vclz_v_u16m4(vs2, vl); +} + +vuint16m8_t test_vclz_v_u16m8(vuint16m8_t vs2, size_t vl) { + return __riscv_vclz_v_u16m8(vs2, vl); +} + +vuint32mf2_t test_vclz_v_u32mf2(vuint32mf2_t vs2, size_t vl) { + return __riscv_vclz_v_u32mf2(vs2, vl); +} + +vuint32m1_t test_vclz_v_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vclz_v_u32m1(vs2, vl); +} + +vuint32m2_t test_vclz_v_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vclz_v_u32m2(vs2, vl); +} + +vuint32m4_t test_vclz_v_u32m4(vuint32m4_t vs2, size_t vl) { + return __riscv_vclz_v_u32m4(vs2, vl); +} + +vuint32m8_t test_vclz_v_u32m8(vuint32m8_t vs2, size_t vl) { + return __riscv_vclz_v_u32m8(vs2, vl); +} + +vuint64m1_t test_vclz_v_u64m1(vuint64m1_t vs2, size_t vl) { + return __riscv_vclz_v_u64m1(vs2, vl); +} + +vuint64m2_t test_vclz_v_u64m2(vuint64m2_t vs2, size_t vl) { + return __riscv_vclz_v_u64m2(vs2, vl); +} + +vuint64m4_t test_vclz_v_u64m4(vuint64m4_t vs2, size_t vl) { + return __riscv_vclz_v_u64m4(vs2, vl); +} + +vuint64m8_t test_vclz_v_u64m8(vuint64m8_t vs2, size_t vl) { + return __riscv_vclz_v_u64m8(vs2, vl); +} + +vuint8mf8_t test_vclz_v_u8mf8_m(vbool64_t mask, vuint8mf8_t vs2, size_t vl) { + return __riscv_vclz_v_u8mf8_m(mask, vs2, vl); +} + +vuint8mf4_t test_vclz_v_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, size_t vl) { + return __riscv_vclz_v_u8mf4_m(mask, vs2, vl); +} + +vuint8mf2_t test_vclz_v_u8mf2_m(vbool16_t mask, vuint8mf2_t vs2, size_t vl) { + return __riscv_vclz_v_u8mf2_m(mask, vs2, vl); +} + +vuint8m1_t test_vclz_v_u8m1_m(vbool8_t mask, vuint8m1_t vs2, size_t vl) { + return __riscv_vclz_v_u8m1_m(mask, vs2, vl); +} + +vuint8m2_t test_vclz_v_u8m2_m(vbool4_t mask, vuint8m2_t vs2, size_t vl) { + return __riscv_vclz_v_u8m2_m(mask, vs2, vl); +} + +vuint8m4_t test_vclz_v_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t vl) { + return __riscv_vclz_v_u8m4_m(mask, vs2, vl); +} + +vuint8m8_t test_vclz_v_u8m8_m(vbool1_t mask, vuint8m8_t vs2, size_t vl) { + return __riscv_vclz_v_u8m8_m(mask, vs2, vl); +} + +vuint16mf4_t test_vclz_v_u16mf4_m(vbool64_t mask, vuint16mf4_t vs2, size_t vl) { + return __riscv_vclz_v_u16mf4_m(mask, vs2, vl); +} + +vuint16mf2_t test_vclz_v_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, size_t vl) { + return __riscv_vclz_v_u16mf2_m(mask, vs2, vl); +} + +vuint16m1_t test_vclz_v_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t vl) { + return __riscv_vclz_v_u16m1_m(mask, vs2, vl); +} + +vuint16m2_t test_vclz_v_u16m2_m(vbool8_t mask, vuint16m2_t vs2, size_t vl) { + return __riscv_vclz_v_u16m2_m(mask, vs2, vl); +} + +vuint16m4_t test_vclz_v_u16m4_m(vbool4_t mask, vuint16m4_t vs2, size_t vl) { + return __riscv_vclz_v_u16m4_m(mask, vs2, vl); +} + +vuint16m8_t test_vclz_v_u16m8_m(vbool2_t mask, vuint16m8_t vs2, size_t vl) { + return __riscv_vclz_v_u16m8_m(mask, vs2, vl); +} + +vuint32mf2_t test_vclz_v_u32mf2_m(vbool64_t mask, vuint32mf2_t vs2, size_t vl) { + return __riscv_vclz_v_u32mf2_m(mask, vs2, vl); +} + +vuint32m1_t test_vclz_v_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t vl) { + return __riscv_vclz_v_u32m1_m(mask, vs2, vl); +} + +vuint32m2_t test_vclz_v_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t vl) { + return __riscv_vclz_v_u32m2_m(mask, vs2, vl); +} + +vuint32m4_t test_vclz_v_u32m4_m(vbool8_t mask, vuint32m4_t vs2, size_t vl) { + return __riscv_vclz_v_u32m4_m(mask, vs2, vl); +} + +vuint32m8_t test_vclz_v_u32m8_m(vbool4_t mask, vuint32m8_t vs2, size_t vl) { + return __riscv_vclz_v_u32m8_m(mask, vs2, vl); +} + +vuint64m1_t test_vclz_v_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t vl) { + return __riscv_vclz_v_u64m1_m(mask, vs2, vl); +} + +vuint64m2_t test_vclz_v_u64m2_m(vbool32_t mask, vuint64m2_t vs2, size_t vl) { + return __riscv_vclz_v_u64m2_m(mask, vs2, vl); +} + +vuint64m4_t test_vclz_v_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t vl) { + return __riscv_vclz_v_u64m4_m(mask, vs2, vl); +} + +vuint64m8_t test_vclz_v_u64m8_m(vbool8_t mask, vuint64m8_t vs2, size_t vl) { + return __riscv_vclz_v_u64m8_m(mask, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 44 } } */ +/* { dg-final { scan-assembler-times {vclz\.v\s+v[0-9]+,\s*v[0-9]} 44 } } */ +/* { dg-final { scan-assembler-times {vclz\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0.t} 22 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vclz_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vclz_overloaded.c new file mode 100644 index 00000000000..b4466bd4c23 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vclz_overloaded.c @@ -0,0 +1,187 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint8mf8_t test_vclz_v_u8mf8(vuint8mf8_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint8mf4_t test_vclz_v_u8mf4(vuint8mf4_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint8mf2_t test_vclz_v_u8mf2(vuint8mf2_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint8m1_t test_vclz_v_u8m1(vuint8m1_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint8m2_t test_vclz_v_u8m2(vuint8m2_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint8m4_t test_vclz_v_u8m4(vuint8m4_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint8m8_t test_vclz_v_u8m8(vuint8m8_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint16mf4_t test_vclz_v_u16mf4(vuint16mf4_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint16mf2_t test_vclz_v_u16mf2(vuint16mf2_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint16m1_t test_vclz_v_u16m1(vuint16m1_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint16m2_t test_vclz_v_u16m2(vuint16m2_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint16m4_t test_vclz_v_u16m4(vuint16m4_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint16m8_t test_vclz_v_u16m8(vuint16m8_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint32mf2_t test_vclz_v_u32mf2(vuint32mf2_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint32m1_t test_vclz_v_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint32m2_t test_vclz_v_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint32m4_t test_vclz_v_u32m4(vuint32m4_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint32m8_t test_vclz_v_u32m8(vuint32m8_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint64m1_t test_vclz_v_u64m1(vuint64m1_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint64m2_t test_vclz_v_u64m2(vuint64m2_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint64m4_t test_vclz_v_u64m4(vuint64m4_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint64m8_t test_vclz_v_u64m8(vuint64m8_t vs2, size_t vl) { + return __riscv_vclz(vs2, vl); +} + +vuint8mf8_t test_vclz_v_u8mf8_m(vbool64_t mask, vuint8mf8_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint8mf4_t test_vclz_v_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint8mf2_t test_vclz_v_u8mf2_m(vbool16_t mask, vuint8mf2_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint8m1_t test_vclz_v_u8m1_m(vbool8_t mask, vuint8m1_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint8m2_t test_vclz_v_u8m2_m(vbool4_t mask, vuint8m2_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint8m4_t test_vclz_v_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint8m8_t test_vclz_v_u8m8_m(vbool1_t mask, vuint8m8_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint16mf4_t test_vclz_v_u16mf4_m(vbool64_t mask, vuint16mf4_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint16mf2_t test_vclz_v_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint16m1_t test_vclz_v_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint16m2_t test_vclz_v_u16m2_m(vbool8_t mask, vuint16m2_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint16m4_t test_vclz_v_u16m4_m(vbool4_t mask, vuint16m4_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint16m8_t test_vclz_v_u16m8_m(vbool2_t mask, vuint16m8_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint32mf2_t test_vclz_v_u32mf2_m(vbool64_t mask, vuint32mf2_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint32m1_t test_vclz_v_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint32m2_t test_vclz_v_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint32m4_t test_vclz_v_u32m4_m(vbool8_t mask, vuint32m4_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint32m8_t test_vclz_v_u32m8_m(vbool4_t mask, vuint32m8_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint64m1_t test_vclz_v_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint64m2_t test_vclz_v_u64m2_m(vbool32_t mask, vuint64m2_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint64m4_t test_vclz_v_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +vuint64m8_t test_vclz_v_u64m8_m(vbool8_t mask, vuint64m8_t vs2, size_t vl) { + return __riscv_vclz(mask, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 44 } } */ +/* { dg-final { scan-assembler-times {vclz\.v\s+v[0-9]+,\s*v[0-9]} 44 } } */ +/* { dg-final { scan-assembler-times {vclz\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0.t} 22 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vctz.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vctz.c new file mode 100644 index 00000000000..ce3cc6dc551 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vctz.c @@ -0,0 +1,187 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O3 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint8mf8_t test_vctz_v_u8mf8(vuint8mf8_t vs2, size_t vl) { + return __riscv_vctz_v_u8mf8(vs2, vl); +} + +vuint8mf4_t test_vctz_v_u8mf4(vuint8mf4_t vs2, size_t vl) { + return __riscv_vctz_v_u8mf4(vs2, vl); +} + +vuint8mf2_t test_vctz_v_u8mf2(vuint8mf2_t vs2, size_t vl) { + return __riscv_vctz_v_u8mf2(vs2, vl); +} + +vuint8m1_t test_vctz_v_u8m1(vuint8m1_t vs2, size_t vl) { + return __riscv_vctz_v_u8m1(vs2, vl); +} + +vuint8m2_t test_vctz_v_u8m2(vuint8m2_t vs2, size_t vl) { + return __riscv_vctz_v_u8m2(vs2, vl); +} + +vuint8m4_t test_vctz_v_u8m4(vuint8m4_t vs2, size_t vl) { + return __riscv_vctz_v_u8m4(vs2, vl); +} + +vuint8m8_t test_vctz_v_u8m8(vuint8m8_t vs2, size_t vl) { + return __riscv_vctz_v_u8m8(vs2, vl); +} + +vuint16mf4_t test_vctz_v_u16mf4(vuint16mf4_t vs2, size_t vl) { + return __riscv_vctz_v_u16mf4(vs2, vl); +} + +vuint16mf2_t test_vctz_v_u16mf2(vuint16mf2_t vs2, size_t vl) { + return __riscv_vctz_v_u16mf2(vs2, vl); +} + +vuint16m1_t test_vctz_v_u16m1(vuint16m1_t vs2, size_t vl) { + return __riscv_vctz_v_u16m1(vs2, vl); +} + +vuint16m2_t test_vctz_v_u16m2(vuint16m2_t vs2, size_t vl) { + return __riscv_vctz_v_u16m2(vs2, vl); +} + +vuint16m4_t test_vctz_v_u16m4(vuint16m4_t vs2, size_t vl) { + return __riscv_vctz_v_u16m4(vs2, vl); +} + +vuint16m8_t test_vctz_v_u16m8(vuint16m8_t vs2, size_t vl) { + return __riscv_vctz_v_u16m8(vs2, vl); +} + +vuint32mf2_t test_vctz_v_u32mf2(vuint32mf2_t vs2, size_t vl) { + return __riscv_vctz_v_u32mf2(vs2, vl); +} + +vuint32m1_t test_vctz_v_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vctz_v_u32m1(vs2, vl); +} + +vuint32m2_t test_vctz_v_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vctz_v_u32m2(vs2, vl); +} + +vuint32m4_t test_vctz_v_u32m4(vuint32m4_t vs2, size_t vl) { + return __riscv_vctz_v_u32m4(vs2, vl); +} + +vuint32m8_t test_vctz_v_u32m8(vuint32m8_t vs2, size_t vl) { + return __riscv_vctz_v_u32m8(vs2, vl); +} + +vuint64m1_t test_vctz_v_u64m1(vuint64m1_t vs2, size_t vl) { + return __riscv_vctz_v_u64m1(vs2, vl); +} + +vuint64m2_t test_vctz_v_u64m2(vuint64m2_t vs2, size_t vl) { + return __riscv_vctz_v_u64m2(vs2, vl); +} + +vuint64m4_t test_vctz_v_u64m4(vuint64m4_t vs2, size_t vl) { + return __riscv_vctz_v_u64m4(vs2, vl); +} + +vuint64m8_t test_vctz_v_u64m8(vuint64m8_t vs2, size_t vl) { + return __riscv_vctz_v_u64m8(vs2, vl); +} + +vuint8mf8_t test_vctz_v_u8mf8_m(vbool64_t mask, vuint8mf8_t vs2, size_t vl) { + return __riscv_vctz_v_u8mf8_m(mask, vs2, vl); +} + +vuint8mf4_t test_vctz_v_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, size_t vl) { + return __riscv_vctz_v_u8mf4_m(mask, vs2, vl); +} + +vuint8mf2_t test_vctz_v_u8mf2_m(vbool16_t mask, vuint8mf2_t vs2, size_t vl) { + return __riscv_vctz_v_u8mf2_m(mask, vs2, vl); +} + +vuint8m1_t test_vctz_v_u8m1_m(vbool8_t mask, vuint8m1_t vs2, size_t vl) { + return __riscv_vctz_v_u8m1_m(mask, vs2, vl); +} + +vuint8m2_t test_vctz_v_u8m2_m(vbool4_t mask, vuint8m2_t vs2, size_t vl) { + return __riscv_vctz_v_u8m2_m(mask, vs2, vl); +} + +vuint8m4_t test_vctz_v_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t vl) { + return __riscv_vctz_v_u8m4_m(mask, vs2, vl); +} + +vuint8m8_t test_vctz_v_u8m8_m(vbool1_t mask, vuint8m8_t vs2, size_t vl) { + return __riscv_vctz_v_u8m8_m(mask, vs2, vl); +} + +vuint16mf4_t test_vctz_v_u16mf4_m(vbool64_t mask, vuint16mf4_t vs2, size_t vl) { + return __riscv_vctz_v_u16mf4_m(mask, vs2, vl); +} + +vuint16mf2_t test_vctz_v_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, size_t vl) { + return __riscv_vctz_v_u16mf2_m(mask, vs2, vl); +} + +vuint16m1_t test_vctz_v_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t vl) { + return __riscv_vctz_v_u16m1_m(mask, vs2, vl); +} + +vuint16m2_t test_vctz_v_u16m2_m(vbool8_t mask, vuint16m2_t vs2, size_t vl) { + return __riscv_vctz_v_u16m2_m(mask, vs2, vl); +} + +vuint16m4_t test_vctz_v_u16m4_m(vbool4_t mask, vuint16m4_t vs2, size_t vl) { + return __riscv_vctz_v_u16m4_m(mask, vs2, vl); +} + +vuint16m8_t test_vctz_v_u16m8_m(vbool2_t mask, vuint16m8_t vs2, size_t vl) { + return __riscv_vctz_v_u16m8_m(mask, vs2, vl); +} + +vuint32mf2_t test_vctz_v_u32mf2_m(vbool64_t mask, vuint32mf2_t vs2, size_t vl) { + return __riscv_vctz_v_u32mf2_m(mask, vs2, vl); +} + +vuint32m1_t test_vctz_v_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t vl) { + return __riscv_vctz_v_u32m1_m(mask, vs2, vl); +} + +vuint32m2_t test_vctz_v_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t vl) { + return __riscv_vctz_v_u32m2_m(mask, vs2, vl); +} + +vuint32m4_t test_vctz_v_u32m4_m(vbool8_t mask, vuint32m4_t vs2, size_t vl) { + return __riscv_vctz_v_u32m4_m(mask, vs2, vl); +} + +vuint32m8_t test_vctz_v_u32m8_m(vbool4_t mask, vuint32m8_t vs2, size_t vl) { + return __riscv_vctz_v_u32m8_m(mask, vs2, vl); +} + +vuint64m1_t test_vctz_v_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t vl) { + return __riscv_vctz_v_u64m1_m(mask, vs2, vl); +} + +vuint64m2_t test_vctz_v_u64m2_m(vbool32_t mask, vuint64m2_t vs2, size_t vl) { + return __riscv_vctz_v_u64m2_m(mask, vs2, vl); +} + +vuint64m4_t test_vctz_v_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t vl) { + return __riscv_vctz_v_u64m4_m(mask, vs2, vl); +} + +vuint64m8_t test_vctz_v_u64m8_m(vbool8_t mask, vuint64m8_t vs2, size_t vl) { + return __riscv_vctz_v_u64m8_m(mask, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 44 } } */ +/* { dg-final { scan-assembler-times {vctz\.v\s+v[0-9]+,\s*v[0-9]} 44 } } */ +/* { dg-final { scan-assembler-times {vctz\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0.t} 22 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vctz_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vctz_overloaded.c new file mode 100644 index 00000000000..df083ea4504 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vctz_overloaded.c @@ -0,0 +1,188 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint8mf8_t test_vctz_v_u8mf8(vuint8mf8_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint8mf4_t test_vctz_v_u8mf4(vuint8mf4_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint8mf2_t test_vctz_v_u8mf2(vuint8mf2_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint8m1_t test_vctz_v_u8m1(vuint8m1_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint8m2_t test_vctz_v_u8m2(vuint8m2_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint8m4_t test_vctz_v_u8m4(vuint8m4_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint8m8_t test_vctz_v_u8m8(vuint8m8_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint16mf4_t test_vctz_v_u16mf4(vuint16mf4_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint16mf2_t test_vctz_v_u16mf2(vuint16mf2_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint16m1_t test_vctz_v_u16m1(vuint16m1_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint16m2_t test_vctz_v_u16m2(vuint16m2_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint16m4_t test_vctz_v_u16m4(vuint16m4_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint16m8_t test_vctz_v_u16m8(vuint16m8_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint32mf2_t test_vctz_v_u32mf2(vuint32mf2_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint32m1_t test_vctz_v_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint32m2_t test_vctz_v_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint32m4_t test_vctz_v_u32m4(vuint32m4_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint32m8_t test_vctz_v_u32m8(vuint32m8_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint64m1_t test_vctz_v_u64m1(vuint64m1_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint64m2_t test_vctz_v_u64m2(vuint64m2_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint64m4_t test_vctz_v_u64m4(vuint64m4_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint64m8_t test_vctz_v_u64m8(vuint64m8_t vs2, size_t vl) { + return __riscv_vctz(vs2, vl); +} + +vuint8mf8_t test_vctz_v_u8mf8_m(vbool64_t mask, vuint8mf8_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint8mf4_t test_vctz_v_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint8mf2_t test_vctz_v_u8mf2_m(vbool16_t mask, vuint8mf2_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint8m1_t test_vctz_v_u8m1_m(vbool8_t mask, vuint8m1_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint8m2_t test_vctz_v_u8m2_m(vbool4_t mask, vuint8m2_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint8m4_t test_vctz_v_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint8m8_t test_vctz_v_u8m8_m(vbool1_t mask, vuint8m8_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint16mf4_t test_vctz_v_u16mf4_m(vbool64_t mask, vuint16mf4_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint16mf2_t test_vctz_v_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint16m1_t test_vctz_v_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint16m2_t test_vctz_v_u16m2_m(vbool8_t mask, vuint16m2_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint16m4_t test_vctz_v_u16m4_m(vbool4_t mask, vuint16m4_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint16m8_t test_vctz_v_u16m8_m(vbool2_t mask, vuint16m8_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint32mf2_t test_vctz_v_u32mf2_m(vbool64_t mask, vuint32mf2_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint32m1_t test_vctz_v_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint32m2_t test_vctz_v_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint32m4_t test_vctz_v_u32m4_m(vbool8_t mask, vuint32m4_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint32m8_t test_vctz_v_u32m8_m(vbool4_t mask, vuint32m8_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint64m1_t test_vctz_v_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint64m2_t test_vctz_v_u64m2_m(vbool32_t mask, vuint64m2_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint64m4_t test_vctz_v_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + +vuint64m8_t test_vctz_v_u64m8_m(vbool8_t mask, vuint64m8_t vs2, size_t vl) { + return __riscv_vctz(mask, vs2, vl); +} + + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 44 } } */ +/* { dg-final { scan-assembler-times {vctz\.v\s+v[0-9]+,\s*v[0-9]} 44 } } */ +/* { dg-final { scan-assembler-times {vctz\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0.t} 22 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrev8.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrev8.c new file mode 100644 index 00000000000..92cb10bd086 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrev8.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O3 -Wno-psabi" } */ +#include + +vuint8mf8_t test_vrev8_v_u8mf8(vuint8mf8_t vs2, size_t vl) { + return __riscv_vrev8_v_u8mf8(vs2, vl); +} + +vuint8m8_t test_vrev8_v_u8m8(vuint8m8_t vs2, size_t vl) { + return __riscv_vrev8_v_u8m8(vs2, vl); +} + +vuint16mf4_t test_vrev8_v_u16mf4(vuint16mf4_t vs2, size_t vl) { + return __riscv_vrev8_v_u16mf4(vs2, vl); +} + +vuint16m4_t test_vrev8_v_u16m4(vuint16m4_t vs2, size_t vl) { + return __riscv_vrev8_v_u16m4(vs2, vl); +} + +vuint32m1_t test_vrev8_v_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u32m1(vs2, vl); +} + +vuint32m2_t test_vrev8_v_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vrev8_v_u32m2(vs2, vl); +} + +vuint64m1_t test_vrev8_v_u64m1(vuint64m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u64m1(vs2, vl); +} + +vuint64m2_t test_vrev8_v_u64m2(vuint64m2_t vs2, size_t vl) { + return __riscv_vrev8_v_u64m2(vs2, vl); +} + +vuint8mf4_t test_vrev8_v_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, size_t vl) { + return __riscv_vrev8_v_u8mf4_m(mask, vs2, vl); +} + +vuint8m4_t test_vrev8_v_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t vl) { + return __riscv_vrev8_v_u8m4_m(mask, vs2, vl); +} + +vuint16mf2_t test_vrev8_v_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, size_t vl) { + return __riscv_vrev8_v_u16mf2_m(mask, vs2, vl); +} + +vuint16m1_t test_vrev8_v_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u16m1_m(mask, vs2, vl); +} + +vuint32m1_t test_vrev8_v_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u32m1_m(mask, vs2, vl); +} + +vuint32m2_t test_vrev8_v_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t vl) { + return __riscv_vrev8_v_u32m2_m(mask, vs2, vl); +} + +vuint64m1_t test_vrev8_v_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u64m1_m(mask, vs2, vl); +} + +vuint64m4_t test_vrev8_v_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t vl) { + return __riscv_vrev8_v_u64m4_m(mask, vs2, vl); +} + +vuint8mf2_t test_vrev8_v_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, size_t vl) { + return __riscv_vrev8_v_u8mf2_tu(maskedoff, vs2, vl); +} + +vuint8m2_t test_vrev8_v_u8m2_tu(vuint8m2_t maskedoff, vuint8m2_t vs2, size_t vl) { + return __riscv_vrev8_v_u8m2_tu(maskedoff, vs2, vl); +} + +vuint16mf2_t test_vrev8_v_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t vl) { + return __riscv_vrev8_v_u16mf2_tu(maskedoff, vs2, vl); +} + +vuint16m2_t test_vrev8_v_u16m2_tu(vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vrev8_v_u16m2_tu(maskedoff, vs2, vl); +} + +vuint32m1_t test_vrev8_v_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u32m1_tu(maskedoff, vs2, vl); +} + +vuint32m1_t test_vrev8_v_u32m1_tum(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u32m1_tum(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vrev8_v_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u64m1_tum(mask, maskedoff, vs2, vl); +} + +vuint64m4_t test_vrev8_v_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t vl) { + return __riscv_vrev8_v_u64m4_tum(mask, maskedoff, vs2, vl); +} + +vuint8m1_t test_vrev8_v_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u8m1_tumu(mask, maskedoff, vs2, vl); +} + +vuint8m8_t test_vrev8_v_u8m8_tumu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, size_t vl) { + return __riscv_vrev8_v_u8m8_tumu(mask, maskedoff, vs2, vl); +} + +vuint16mf2_t test_vrev8_v_u16mf2_tumu(vbool32_t mask, vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t vl) { + return __riscv_vrev8_v_u16mf2_tumu(mask, maskedoff, vs2, vl); +} + +vuint16m2_t test_vrev8_v_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vrev8_v_u16m2_tumu(mask, maskedoff, vs2, vl); +} + +vuint32m1_t test_vrev8_v_u32m1_tumu(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u32m1_tumu(mask, maskedoff, vs2, vl); +} + +vuint32m4_t test_vrev8_v_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vrev8_v_u32m4_tumu(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vrev8_v_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u64m1_tumu(mask, maskedoff, vs2, vl); +} + +vuint64m4_t test_vrev8_v_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t vl) { + return __riscv_vrev8_v_u64m4_tumu(mask, maskedoff, vs2, vl); +} + +vuint8m1_t test_vrev8_v_u8m1_mu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u8m1_mu(mask, maskedoff, vs2, vl); +} + +vuint8m8_t test_vrev8_v_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, size_t vl) { + return __riscv_vrev8_v_u8m8_mu(mask, maskedoff, vs2, vl); +} + +vuint16m1_t test_vrev8_v_u16m1_mu(vbool16_t mask, vuint16m1_t maskedoff, vuint16m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u16m1_mu(mask, maskedoff, vs2, vl); +} + +vuint16m2_t test_vrev8_v_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vrev8_v_u16m2_mu(mask, maskedoff, vs2, vl); +} + +vuint32m2_t test_vrev8_v_u32m2_mu(vbool16_t mask, vuint32m2_t maskedoff, vuint32m2_t vs2, size_t vl) { + return __riscv_vrev8_v_u32m2_mu(mask, maskedoff, vs2, vl); +} + +vuint32m4_t test_vrev8_v_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vrev8_v_u32m4_mu(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vrev8_v_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vrev8_v_u64m1_mu(mask, maskedoff, vs2, vl); +} + +vuint64m8_t test_vrev8_v_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, size_t vl) { + return __riscv_vrev8_v_u64m8_mu(mask, maskedoff, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vrev8\.v\s+v[0-9]+,\s*v[0-9]} 40 } } */ +/* { dg-final { scan-assembler-times {vrev8\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0.t} 27 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrev8_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrev8_overloaded.c new file mode 100644 index 00000000000..86822d0c31a --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrev8_overloaded.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O2 -Wno-psabi" } */ +#include + +vuint8mf8_t test_vrev8_v_u8mf8(vuint8mf8_t vs2, size_t vl) { + return __riscv_vrev8(vs2, vl); +} + +vuint8m8_t test_vrev8_v_u8m8(vuint8m8_t vs2, size_t vl) { + return __riscv_vrev8(vs2, vl); +} + +vuint16mf4_t test_vrev8_v_u16mf4(vuint16mf4_t vs2, size_t vl) { + return __riscv_vrev8(vs2, vl); +} + +vuint16m4_t test_vrev8_v_u16m4(vuint16m4_t vs2, size_t vl) { + return __riscv_vrev8(vs2, vl); +} + +vuint32m1_t test_vrev8_v_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vrev8(vs2, vl); +} + +vuint32m2_t test_vrev8_v_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vrev8(vs2, vl); +} + +vuint64m1_t test_vrev8_v_u64m1(vuint64m1_t vs2, size_t vl) { + return __riscv_vrev8(vs2, vl); +} + +vuint64m2_t test_vrev8_v_u64m2(vuint64m2_t vs2, size_t vl) { + return __riscv_vrev8(vs2, vl); +} + +vuint8mf4_t test_vrev8_v_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, size_t vl) { + return __riscv_vrev8(mask, vs2, vl); +} + +vuint8m4_t test_vrev8_v_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t vl) { + return __riscv_vrev8(mask, vs2, vl); +} + +vuint16mf2_t test_vrev8_v_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, size_t vl) { + return __riscv_vrev8(mask, vs2, vl); +} + +vuint16m1_t test_vrev8_v_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t vl) { + return __riscv_vrev8(mask, vs2, vl); +} + +vuint32m1_t test_vrev8_v_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t vl) { + return __riscv_vrev8(mask, vs2, vl); +} + +vuint32m2_t test_vrev8_v_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t vl) { + return __riscv_vrev8(mask, vs2, vl); +} + +vuint64m1_t test_vrev8_v_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t vl) { + return __riscv_vrev8(mask, vs2, vl); +} + +vuint64m4_t test_vrev8_v_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t vl) { + return __riscv_vrev8(mask, vs2, vl); +} + +vuint8mf2_t test_vrev8_v_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, size_t vl) { + return __riscv_vrev8_tu(maskedoff, vs2, vl); +} + +vuint8m2_t test_vrev8_v_u8m2_tu(vuint8m2_t maskedoff, vuint8m2_t vs2, size_t vl) { + return __riscv_vrev8_tu(maskedoff, vs2, vl); +} + +vuint16mf2_t test_vrev8_v_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t vl) { + return __riscv_vrev8_tu(maskedoff, vs2, vl); +} + +vuint16m2_t test_vrev8_v_u16m2_tu(vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vrev8_tu(maskedoff, vs2, vl); +} + +vuint32m1_t test_vrev8_v_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vrev8_tu(maskedoff, vs2, vl); +} + +vuint32m1_t test_vrev8_v_u32m1_tum(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vrev8_tum(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vrev8_v_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vrev8_tum(mask, maskedoff, vs2, vl); +} + +vuint64m4_t test_vrev8_v_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t vl) { + return __riscv_vrev8_tum(mask, maskedoff, vs2, vl); +} + +vuint8m1_t test_vrev8_v_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, size_t vl) { + return __riscv_vrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint8m8_t test_vrev8_v_u8m8_tumu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, size_t vl) { + return __riscv_vrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint16mf2_t test_vrev8_v_u16mf2_tumu(vbool32_t mask, vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t vl) { + return __riscv_vrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint16m2_t test_vrev8_v_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint32m1_t test_vrev8_v_u32m1_tumu(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint32m4_t test_vrev8_v_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vrev8_v_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint64m4_t test_vrev8_v_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t vl) { + return __riscv_vrev8_tumu(mask, maskedoff, vs2, vl); +} + +vuint8m1_t test_vrev8_v_u8m1_mu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, size_t vl) { + return __riscv_vrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint8m8_t test_vrev8_v_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, size_t vl) { + return __riscv_vrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint16m1_t test_vrev8_v_u16m1_mu(vbool16_t mask, vuint16m1_t maskedoff, vuint16m1_t vs2, size_t vl) { + return __riscv_vrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint16m2_t test_vrev8_v_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t vl) { + return __riscv_vrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint32m2_t test_vrev8_v_u32m2_mu(vbool16_t mask, vuint32m2_t maskedoff, vuint32m2_t vs2, size_t vl) { + return __riscv_vrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint32m4_t test_vrev8_v_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint64m1_t test_vrev8_v_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t vl) { + return __riscv_vrev8_mu(mask, maskedoff, vs2, vl); +} + +vuint64m8_t test_vrev8_v_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, size_t vl) { + return __riscv_vrev8_mu(mask, maskedoff, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vrev8\.v\s+v[0-9]+,\s*v[0-9]} 40 } } */ +/* { dg-final { scan-assembler-times {vrev8\.v\s+v[0-9]+,\s*v[0-9]+,\s*v0.t} 27 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrol.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrol.c new file mode 100644 index 00000000000..5b9846a624f --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrol.c @@ -0,0 +1,172 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O3 -Wno-psabi" } */ +#include + +vuint8mf8_t test_vrol_vv_u8mf8(vuint8mf8_t vs2, vuint8mf8_t vs1, size_t vl) { + return __riscv_vrol_vv_u8mf8(vs2, vs1, vl); +} + +vuint8m8_t test_vrol_vv_u8m8(vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vrol_vv_u8m8(vs2, vs1, vl); +} + +vuint16mf4_t test_vrol_vx_u16mf4(vuint16mf4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u16mf4(vs2, rs1, vl); +} + +vuint16m4_t test_vrol_vx_u16m4(vuint16m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u16m4(vs2, rs1, vl); +} + +vuint32m1_t test_vrol_vx_u32m1(vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u32m1(vs2, rs1, vl); +} + +vuint32m2_t test_vrol_vx_u32m2(vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u32m2(vs2, rs1, vl); +} + +vuint64m1_t test_vrol_vx_u64m1(vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u64m1(vs2, rs1, vl); +} + +vuint64m2_t test_vrol_vx_u64m2(vuint64m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u64m2(vs2, rs1, vl); +} + +vuint8mf4_t test_vrol_vv_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, vuint8mf4_t vs1, size_t vl) { + return __riscv_vrol_vv_u8mf4_m(mask, vs2, vs1, vl); +} + +vuint8m4_t test_vrol_vx_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u8m4_m(mask, vs2, rs1, vl); +} + +vuint16mf2_t test_vrol_vv_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vrol_vv_u16mf2_m(mask, vs2, vs1, vl); +} + +vuint16m1_t test_vrol_vx_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u16m1_m(mask, vs2, rs1, vl); +} + +vuint32m1_t test_vrol_vx_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u32m1_m(mask, vs2, rs1, vl); +} + +vuint32m2_t test_vrol_vx_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u32m2_m(mask, vs2, rs1, vl); +} + +vuint64m1_t test_vrol_vx_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u64m1_m(mask, vs2, rs1, vl); +} + +vuint64m4_t test_vrol_vx_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u64m4_m(mask, vs2, rs1, vl); +} + +vuint8mf2_t test_vrol_vv_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, vuint8mf2_t vs1, size_t vl) { + return __riscv_vrol_vv_u8mf2_tu(maskedoff, vs2, vs1, vl); +} + +vuint8m2_t test_vrol_vv_u8m2_tu(vuint8m2_t maskedoff, vuint8m2_t vs2, vuint8m2_t vs1, size_t vl) { + return __riscv_vrol_vv_u8m2_tu(maskedoff, vs2, vs1, vl); +} + +vuint16mf2_t test_vrol_vx_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u16mf2_tu(maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vrol_vx_u16m2_tu(vuint16m2_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u16m2_tu(maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vrol_vx_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u32m1_tu(maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vrol_vx_u32m1_tum(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u32m1_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vrol_vx_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u64m1_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vrol_vx_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u64m4_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint8m1_t test_vrol_vv_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, vuint8m1_t vs1, size_t vl) { + return __riscv_vrol_vv_u8m1_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint8m8_t test_vrol_vv_u8m8_tumu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vrol_vv_u8m8_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16mf2_t test_vrol_vv_u16mf2_tumu(vbool32_t mask, vuint16mf2_t maskedoff, vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vrol_vv_u16mf2_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m2_t test_vrol_vx_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u16m2_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vrol_vx_u32m1_tumu(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u32m1_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m4_t test_vrol_vx_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u32m4_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vrol_vx_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u64m1_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vrol_vx_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u64m4_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint8m1_t test_vrol_vv_u8m1_mu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, vuint8m1_t vs1, size_t vl) { + return __riscv_vrol_vv_u8m1_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint8m8_t test_vrol_vv_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vrol_vv_u8m8_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m1_t test_vrol_vx_u16m1_mu(vbool16_t mask, vuint16m1_t maskedoff, vuint16m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u16m1_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vrol_vx_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u16m2_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32mf2_t test_vrol_vx_u32mf2_mu(vbool64_t mask, vuint32mf2_t maskedoff, vuint32mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u32mf2_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m4_t test_vrol_vx_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u32m4_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vrol_vx_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u64m1_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vrol_vv_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vrol_vv_u64m8_mu(mask, maskedoff, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vrol\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]} 12 } } */ +/* { dg-final { scan-assembler-times {vrol\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t} 8 } } */ +/* { dg-final { scan-assembler-times {vrol\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]} 28 } } */ +/* { dg-final { scan-assembler-times {vrol\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]+,\s*v0.t} 19 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrol_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrol_overloaded.c new file mode 100644 index 00000000000..ff82225b969 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vrol_overloaded.c @@ -0,0 +1,172 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O2 -Wno-psabi" } */ +#include + +vuint8mf8_t test_vrol_vv_u8mf8(vuint8mf8_t vs2, vuint8mf8_t vs1, size_t vl) { + return __riscv_vrol(vs2, vs1, vl); +} + +vuint8m8_t test_vrol_vv_u8m8(vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vrol(vs2, vs1, vl); +} + +vuint16mf4_t test_vrol_vx_u16mf4(vuint16mf4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol(vs2, rs1, vl); +} + +vuint16m4_t test_vrol_vx_u16m4(vuint16m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol(vs2, rs1, vl); +} + +vuint32m1_t test_vrol_vx_u32m1(vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol(vs2, rs1, vl); +} + +vuint32m2_t test_vrol_vx_u32m2(vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol(vs2, rs1, vl); +} + +vuint64m1_t test_vrol_vx_u64m1(vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol(vs2, rs1, vl); +} + +vuint64m2_t test_vrol_vx_u64m2(vuint64m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol(vs2, rs1, vl); +} + +vuint8mf4_t test_vrol_vv_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, vuint8mf4_t vs1, size_t vl) { + return __riscv_vrol(mask, vs2, vs1, vl); +} + +vuint8m4_t test_vrol_vx_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol(mask, vs2, rs1, vl); +} + +vuint16mf2_t test_vrol_vv_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vrol(mask, vs2, vs1, vl); +} + +vuint16m1_t test_vrol_vx_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol(mask, vs2, rs1, vl); +} + +vuint32m1_t test_vrol_vx_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol(mask, vs2, rs1, vl); +} + +vuint32m2_t test_vrol_vx_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol(mask, vs2, rs1, vl); +} + +vuint64m1_t test_vrol_vx_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol(mask, vs2, rs1, vl); +} + +vuint64m4_t test_vrol_vx_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol(mask, vs2, rs1, vl); +} + +vuint8mf2_t test_vrol_vv_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, vuint8mf2_t vs1, size_t vl) { + return __riscv_vrol_tu(maskedoff, vs2, vs1, vl); +} + +vuint8m2_t test_vrol_vv_u8m2_tu(vuint8m2_t maskedoff, vuint8m2_t vs2, vuint8m2_t vs1, size_t vl) { + return __riscv_vrol_tu(maskedoff, vs2, vs1, vl); +} + +vuint16mf2_t test_vrol_vx_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_tu(maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vrol_vx_u16m2_tu(vuint16m2_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_tu(maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vrol_vx_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_tu(maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vrol_vx_u32m1_tum(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vrol_vx_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vrol_vx_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint8m1_t test_vrol_vv_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, vuint8m1_t vs1, size_t vl) { + return __riscv_vrol_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint8m8_t test_vrol_vv_u8m8_tumu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vrol_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16mf2_t test_vrol_vv_u16mf2_tumu(vbool32_t mask, vuint16mf2_t maskedoff, vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vrol_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m2_t test_vrol_vx_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vrol_vx_u32m1_tumu(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m4_t test_vrol_vx_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vrol_vx_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vrol_vx_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint8m1_t test_vrol_vv_u8m1_mu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, vuint8m1_t vs1, size_t vl) { + return __riscv_vrol_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint8m8_t test_vrol_vv_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vrol_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m1_t test_vrol_vx_u16m1_mu(vbool16_t mask, vuint16m1_t maskedoff, vuint16m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vrol_vx_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32mf2_t test_vrol_vx_u32mf2_mu(vbool64_t mask, vuint32mf2_t maskedoff, vuint32mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m4_t test_vrol_vx_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vrol_vx_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vrol_vv_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vrol_mu(mask, maskedoff, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vrol\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]} 12 } } */ +/* { dg-final { scan-assembler-times {vrol\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t} 8 } } */ +/* { dg-final { scan-assembler-times {vrol\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]} 28 } } */ +/* { dg-final { scan-assembler-times {vrol\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]+,\s*v0.t} 19 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vror.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vror.c new file mode 100644 index 00000000000..0c36e5ff13f --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vror.c @@ -0,0 +1,172 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O3 -Wno-psabi" } */ +#include + +vuint8mf8_t test_vror_vv_u8mf8(vuint8mf8_t vs2, vuint8mf8_t vs1, size_t vl) { + return __riscv_vror_vv_u8mf8(vs2, vs1, vl); +} + +vuint8m8_t test_vror_vv_u8m8(vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vror_vv_u8m8(vs2, vs1, vl); +} + +vuint16mf4_t test_vror_vx_u16mf4(vuint16mf4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u16mf4(vs2, rs1, vl); +} + +vuint16m4_t test_vror_vx_u16m4(vuint16m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u16m4(vs2, rs1, vl); +} + +vuint32m1_t test_vror_vx_u32m1(vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u32m1(vs2, rs1, vl); +} + +vuint32m2_t test_vror_vx_u32m2(vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u32m2(vs2, rs1, vl); +} + +vuint64m1_t test_vror_vx_u64m1(vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u64m1(vs2, rs1, vl); +} + +vuint64m2_t test_vror_vx_u64m2(vuint64m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u64m2(vs2, rs1, vl); +} + +vuint8mf4_t test_vror_vv_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, vuint8mf4_t vs1, size_t vl) { + return __riscv_vror_vv_u8mf4_m(mask, vs2, vs1, vl); +} + +vuint8m4_t test_vror_vx_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u8m4_m(mask, vs2, rs1, vl); +} + +vuint16mf2_t test_vror_vv_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vror_vv_u16mf2_m(mask, vs2, vs1, vl); +} + +vuint16m1_t test_vror_vx_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u16m1_m(mask, vs2, rs1, vl); +} + +vuint32m1_t test_vror_vx_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u32m1_m(mask, vs2, rs1, vl); +} + +vuint32m2_t test_vror_vx_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u32m2_m(mask, vs2, rs1, vl); +} + +vuint64m1_t test_vror_vx_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u64m1_m(mask, vs2, rs1, vl); +} + +vuint64m4_t test_vror_vx_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u64m4_m(mask, vs2, rs1, vl); +} + +vuint8mf2_t test_vror_vv_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, vuint8mf2_t vs1, size_t vl) { + return __riscv_vror_vv_u8mf2_tu(maskedoff, vs2, vs1, vl); +} + +vuint8m2_t test_vror_vv_u8m2_tu(vuint8m2_t maskedoff, vuint8m2_t vs2, vuint8m2_t vs1, size_t vl) { + return __riscv_vror_vv_u8m2_tu(maskedoff, vs2, vs1, vl); +} + +vuint16mf2_t test_vror_vx_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u16mf2_tu(maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vror_vx_u16m2_tu(vuint16m2_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u16m2_tu(maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vror_vx_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u32m1_tu(maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vror_vx_u32m1_tum(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u32m1_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vror_vx_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u64m1_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vror_vx_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u64m4_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint8m1_t test_vror_vv_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, vuint8m1_t vs1, size_t vl) { + return __riscv_vror_vv_u8m1_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint8m8_t test_vror_vv_u8m8_tumu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vror_vv_u8m8_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16mf2_t test_vror_vv_u16mf2_tumu(vbool32_t mask, vuint16mf2_t maskedoff, vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vror_vv_u16mf2_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m2_t test_vror_vx_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u16m2_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vror_vx_u32m1_tumu(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u32m1_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m4_t test_vror_vx_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u32m4_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vror_vx_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u64m1_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vror_vx_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u64m4_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint8m1_t test_vror_vv_u8m1_mu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, vuint8m1_t vs1, size_t vl) { + return __riscv_vror_vv_u8m1_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint8m8_t test_vror_vv_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vror_vv_u8m8_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m1_t test_vror_vx_u16m1_mu(vbool16_t mask, vuint16m1_t maskedoff, vuint16m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u16m1_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vror_vx_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u16m2_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32mf2_t test_vror_vx_u32mf2_mu(vbool64_t mask, vuint32mf2_t maskedoff, vuint32mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u32mf2_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m4_t test_vror_vx_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u32m4_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vror_vx_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u64m1_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vror_vv_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vror_vv_u64m8_mu(mask, maskedoff, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vror\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]} 12 } } */ +/* { dg-final { scan-assembler-times {vror\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t} 8 } } */ +/* { dg-final { scan-assembler-times {vror\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]} 28 } } */ +/* { dg-final { scan-assembler-times {vror\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]+,\s*v0.t} 19 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vror_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vror_overloaded.c new file mode 100644 index 00000000000..7274e013121 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vror_overloaded.c @@ -0,0 +1,172 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O2 -Wno-psabi" } */ +#include + +vuint8mf8_t test_vror_vv_u8mf8(vuint8mf8_t vs2, vuint8mf8_t vs1, size_t vl) { + return __riscv_vror(vs2, vs1, vl); +} + +vuint8m8_t test_vror_vv_u8m8(vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vror(vs2, vs1, vl); +} + +vuint16mf4_t test_vror_vx_u16mf4(vuint16mf4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror(vs2, rs1, vl); +} + +vuint16m4_t test_vror_vx_u16m4(vuint16m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror(vs2, rs1, vl); +} + +vuint32m1_t test_vror_vx_u32m1(vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror(vs2, rs1, vl); +} + +vuint32m2_t test_vror_vx_u32m2(vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror(vs2, rs1, vl); +} + +vuint64m1_t test_vror_vx_u64m1(vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror(vs2, rs1, vl); +} + +vuint64m2_t test_vror_vx_u64m2(vuint64m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror(vs2, rs1, vl); +} + +vuint8mf4_t test_vror_vv_u8mf4_m(vbool32_t mask, vuint8mf4_t vs2, vuint8mf4_t vs1, size_t vl) { + return __riscv_vror(mask, vs2, vs1, vl); +} + +vuint8m4_t test_vror_vx_u8m4_m(vbool2_t mask, vuint8m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror(mask, vs2, rs1, vl); +} + +vuint16mf2_t test_vror_vv_u16mf2_m(vbool32_t mask, vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vror(mask, vs2, vs1, vl); +} + +vuint16m1_t test_vror_vx_u16m1_m(vbool16_t mask, vuint16m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror(mask, vs2, rs1, vl); +} + +vuint32m1_t test_vror_vx_u32m1_m(vbool32_t mask, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror(mask, vs2, rs1, vl); +} + +vuint32m2_t test_vror_vx_u32m2_m(vbool16_t mask, vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror(mask, vs2, rs1, vl); +} + +vuint64m1_t test_vror_vx_u64m1_m(vbool64_t mask, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror(mask, vs2, rs1, vl); +} + +vuint64m4_t test_vror_vx_u64m4_m(vbool16_t mask, vuint64m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror(mask, vs2, rs1, vl); +} + +vuint8mf2_t test_vror_vv_u8mf2_tu(vuint8mf2_t maskedoff, vuint8mf2_t vs2, vuint8mf2_t vs1, size_t vl) { + return __riscv_vror_tu(maskedoff, vs2, vs1, vl); +} + +vuint8m2_t test_vror_vv_u8m2_tu(vuint8m2_t maskedoff, vuint8m2_t vs2, vuint8m2_t vs1, size_t vl) { + return __riscv_vror_tu(maskedoff, vs2, vs1, vl); +} + +vuint16mf2_t test_vror_vx_u16mf2_tu(vuint16mf2_t maskedoff, vuint16mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_tu(maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vror_vx_u16m2_tu(vuint16m2_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_tu(maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vror_vx_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_tu(maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vror_vx_u32m1_tum(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vror_vx_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vror_vx_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint8m1_t test_vror_vv_u8m1_tumu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, vuint8m1_t vs1, size_t vl) { + return __riscv_vror_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint8m8_t test_vror_vv_u8m8_tumu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vror_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16mf2_t test_vror_vv_u16mf2_tumu(vbool32_t mask, vuint16mf2_t maskedoff, vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vror_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m2_t test_vror_vx_u16m2_tumu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m1_t test_vror_vx_u32m1_tumu(vbool32_t mask, vuint32m1_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m4_t test_vror_vx_u32m4_tumu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vror_vx_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vror_vx_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint8m1_t test_vror_vv_u8m1_mu(vbool8_t mask, vuint8m1_t maskedoff, vuint8m1_t vs2, vuint8m1_t vs1, size_t vl) { + return __riscv_vror_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint8m8_t test_vror_vv_u8m8_mu(vbool1_t mask, vuint8m8_t maskedoff, vuint8m8_t vs2, vuint8m8_t vs1, size_t vl) { + return __riscv_vror_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m1_t test_vror_vx_u16m1_mu(vbool16_t mask, vuint16m1_t maskedoff, vuint16m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vror_vx_u16m2_mu(vbool8_t mask, vuint16m2_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32mf2_t test_vror_vx_u32mf2_mu(vbool64_t mask, vuint32mf2_t maskedoff, vuint32mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m4_t test_vror_vx_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint32m4_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vror_vx_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vror_vv_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vror_mu(mask, maskedoff, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vror\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]} 12 } } */ +/* { dg-final { scan-assembler-times {vror\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t} 8 } } */ +/* { dg-final { scan-assembler-times {vror\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]} 28 } } */ +/* { dg-final { scan-assembler-times {vror\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]+,\s*v0.t} 19 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vwsll.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vwsll.c new file mode 100644 index 00000000000..f3170880679 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vwsll.c @@ -0,0 +1,164 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O3 -Wno-psabi" } */ +#include + +vuint16mf4_t test_vwsll_vv_u16mf4(vuint8mf8_t vs2, vuint8mf8_t vs1, size_t vl) { + return __riscv_vwsll_vv_u16mf4(vs2, vs1, vl); +} + +vuint16mf4_t test_vwsll_vx_u16mf4(vuint8mf8_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u16mf4(vs2, rs1, vl); +} + +vuint16m1_t test_vwsll_vv_u16m1(vuint8mf2_t vs2, vuint8mf2_t vs1, size_t vl) { + return __riscv_vwsll_vv_u16m1(vs2, vs1, vl); +} + +vuint16m1_t test_vwsll_vx_u16m1(vuint8mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u16m1(vs2, rs1, vl); +} + +vuint32m1_t test_vwsll_vv_u32m1(vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vwsll_vv_u32m1(vs2, vs1, vl); +} + +vuint32m1_t test_vwsll_vx_u32m1(vuint16mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u32m1(vs2, rs1, vl); +} + +vuint64m2_t test_vwsll_vv_u64m2(vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vwsll_vv_u64m2(vs2, vs1, vl); +} + +vuint64m2_t test_vwsll_vx_u64m2(vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u64m2(vs2, rs1, vl); +} + +vuint16m1_t test_vwsll_vv_u16m1_m(vbool16_t mask, vuint8mf2_t vs2, vuint8mf2_t vs1, size_t vl) { + return __riscv_vwsll_vv_u16m1_m(mask, vs2, vs1, vl); +} + +vuint16m1_t test_vwsll_vx_u16m1_m(vbool16_t mask, vuint8mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u16m1_m(mask, vs2, rs1, vl); +} + +vuint32m2_t test_vwsll_vv_u32m2_m(vbool16_t mask, vuint16m1_t vs2, vuint16m1_t vs1, size_t vl) { + return __riscv_vwsll_vv_u32m2_m(mask, vs2, vs1, vl); +} + +vuint32m2_t test_vwsll_vx_u32m2_m(vbool16_t mask, vuint16m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u32m2_m(mask, vs2, rs1, vl); +} + +vuint64m4_t test_vwsll_vv_u64m4_m(vbool16_t mask, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vwsll_vv_u64m4_m(mask, vs2, vs1, vl); +} + +vuint64m4_t test_vwsll_vx_u64m4_m(vbool16_t mask, vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u64m4_m(mask, vs2, rs1, vl); +} + +vuint16m1_t test_vwsll_vv_u16m1_tu(vuint16m1_t maskedoff, vuint8mf2_t vs2, vuint8mf2_t vs1, size_t vl) { + return __riscv_vwsll_vv_u16m1_tu(maskedoff, vs2, vs1, vl); +} + +vuint16m1_t test_vwsll_vx_u16m1_tu(vuint16m1_t maskedoff, vuint8mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u16m1_tu(maskedoff, vs2, rs1, vl); +} + +vuint32mf2_t test_vwsll_vv_u32mf2_tu(vuint32mf2_t maskedoff, vuint16mf4_t vs2, vuint16mf4_t vs1, size_t vl) { + return __riscv_vwsll_vv_u32mf2_tu(maskedoff, vs2, vs1, vl); +} + +vuint32mf2_t test_vwsll_vx_u32mf2_tu(vuint32mf2_t maskedoff, vuint16mf4_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u32mf2_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vwsll_vv_u64m1_tu(vuint64m1_t maskedoff, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vwsll_vv_u64m1_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vwsll_vx_u64m1_tu(vuint64m1_t maskedoff, vuint32mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u64m1_tu(maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vwsll_vv_u16m2_tum(vbool8_t mask, vuint16m2_t maskedoff, vuint8m1_t vs2, vuint8m1_t vs1, size_t vl) { + return __riscv_vwsll_vv_u16m2_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m2_t test_vwsll_vx_u16m2_tum(vbool8_t mask, vuint16m2_t maskedoff, vuint8m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u16m2_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m2_t test_vwsll_vv_u32m2_tum(vbool16_t mask, vuint32m2_t maskedoff, vuint16m1_t vs2, vuint16m1_t vs1, size_t vl) { + return __riscv_vwsll_vv_u32m2_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint32m2_t test_vwsll_vx_u32m2_tum(vbool16_t mask, vuint32m2_t maskedoff, vuint16m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u32m2_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vwsll_vv_u64m2_tum(vbool32_t mask, vuint64m2_t maskedoff, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vwsll_vv_u64m2_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vwsll_vx_u64m2_tum(vbool32_t mask, vuint64m2_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u64m2_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint16mf4_t test_vwsll_vv_u16mf4_tumu(vbool64_t mask, vuint16mf4_t maskedoff, vuint8mf8_t vs2, vuint8mf8_t vs1, size_t vl) { + return __riscv_vwsll_vv_u16mf4_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16mf4_t test_vwsll_vx_u16mf4_tumu(vbool64_t mask, vuint16mf4_t maskedoff, vuint8mf8_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u16mf4_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32mf2_t test_vwsll_vv_u32mf2_tumu(vbool64_t mask, vuint32mf2_t maskedoff, vuint16mf4_t vs2, vuint16mf4_t vs1, size_t vl) { + return __riscv_vwsll_vv_u32mf2_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint32mf2_t test_vwsll_vx_u32mf2_tumu(vbool64_t mask, vuint32mf2_t maskedoff, vuint16mf4_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u32mf2_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vwsll_vv_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vwsll_vv_u64m4_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vwsll_vx_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u64m4_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint16m4_t test_vwsll_vv_u16m4_mu(vbool4_t mask, vuint16m4_t maskedoff, vuint8m2_t vs2, vuint8m2_t vs1, size_t vl) { + return __riscv_vwsll_vv_u16m4_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m4_t test_vwsll_vx_u16m4_mu(vbool4_t mask, vuint16m4_t maskedoff, vuint8m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u16m4_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m4_t test_vwsll_vv_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint16m2_t vs2, vuint16m2_t vs1, size_t vl) { + return __riscv_vwsll_vv_u32m4_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint32m4_t test_vwsll_vx_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u32m4_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vwsll_vv_u64m4_mu(vbool16_t mask, vuint64m4_t maskedoff, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vwsll_vv_u64m4_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vwsll_vx_u64m4_mu(vbool16_t mask, vuint64m4_t maskedoff, vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_vx_u64m4_mu(mask, maskedoff, vs2, rs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 14 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 12 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 6 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 6 } } */ +/* { dg-final { scan-assembler-times {vwsll\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]} 19 } } */ +/* { dg-final { scan-assembler-times {vwsll\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t} 12 } } */ +/* { dg-final { scan-assembler-times {vwsll\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]} 19 } } */ +/* { dg-final { scan-assembler-times {vwsll\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]+,\s*v0.t} 12 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vwsll_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vwsll_overloaded.c new file mode 100644 index 00000000000..c38b37f3ca0 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/vwsll_overloaded.c @@ -0,0 +1,165 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbb -mabi=lp64d -O2 -Wno-psabi" } */ +#include + +vuint16mf4_t test_vwsll_vv_u16mf4(vuint8mf8_t vs2, vuint8mf8_t vs1, size_t vl) { + return __riscv_vwsll(vs2, vs1, vl); +} + +vuint16mf4_t test_vwsll_vx_u16mf4(vuint8mf8_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll(vs2, rs1, vl); +} + +vuint16m1_t test_vwsll_vv_u16m1(vuint8mf2_t vs2, vuint8mf2_t vs1, size_t vl) { + return __riscv_vwsll(vs2, vs1, vl); +} + +vuint16m1_t test_vwsll_vx_u16m1(vuint8mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll(vs2, rs1, vl); +} + +vuint32m1_t test_vwsll_vv_u32m1(vuint16mf2_t vs2, vuint16mf2_t vs1, size_t vl) { + return __riscv_vwsll(vs2, vs1, vl); +} + +vuint32m1_t test_vwsll_vx_u32m1(vuint16mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll(vs2, rs1, vl); +} + +vuint64m2_t test_vwsll_vv_u64m2(vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vwsll(vs2, vs1, vl); +} + +vuint64m2_t test_vwsll_vx_u64m2(vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll(vs2, rs1, vl); +} + +vuint16m1_t test_vwsll_vv_u16m1_m(vbool16_t mask, vuint8mf2_t vs2, vuint8mf2_t vs1, size_t vl) { + return __riscv_vwsll(mask, vs2, vs1, vl); +} + +vuint16m1_t test_vwsll_vx_u16m1_m(vbool16_t mask, vuint8mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll(mask, vs2, rs1, vl); +} + +vuint32m2_t test_vwsll_vv_u32m2_m(vbool16_t mask, vuint16m1_t vs2, vuint16m1_t vs1, size_t vl) { + return __riscv_vwsll(mask, vs2, vs1, vl); +} + +vuint32m2_t test_vwsll_vx_u32m2_m(vbool16_t mask, vuint16m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll(mask, vs2, rs1, vl); +} + +vuint64m4_t test_vwsll_vv_u64m4_m(vbool16_t mask, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vwsll(mask, vs2, vs1, vl); +} + +vuint64m4_t test_vwsll_vx_u64m4_m(vbool16_t mask, vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll(mask, vs2, rs1, vl); +} + +vuint16m1_t test_vwsll_vv_u16m1_tu(vuint16m1_t maskedoff, vuint8mf2_t vs2, vuint8mf2_t vs1, size_t vl) { + return __riscv_vwsll_tu(maskedoff, vs2, vs1, vl); +} + +vuint16m1_t test_vwsll_vx_u16m1_tu(vuint16m1_t maskedoff, vuint8mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_tu(maskedoff, vs2, rs1, vl); +} + +vuint32mf2_t test_vwsll_vv_u32mf2_tu(vuint32mf2_t maskedoff, vuint16mf4_t vs2, vuint16mf4_t vs1, size_t vl) { + return __riscv_vwsll_tu(maskedoff, vs2, vs1, vl); +} + +vuint32mf2_t test_vwsll_vx_u32mf2_tu(vuint32mf2_t maskedoff, vuint16mf4_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vwsll_vv_u64m1_tu(vuint64m1_t maskedoff, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vwsll_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vwsll_vx_u64m1_tu(vuint64m1_t maskedoff, vuint32mf2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_tu(maskedoff, vs2, rs1, vl); +} + +vuint16m2_t test_vwsll_vv_u16m2_tum(vbool8_t mask, vuint16m2_t maskedoff, vuint8m1_t vs2, vuint8m1_t vs1, size_t vl) { + return __riscv_vwsll_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m2_t test_vwsll_vx_u16m2_tum(vbool8_t mask, vuint16m2_t maskedoff, vuint8m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint32m2_t test_vwsll_vv_u32m2_tum(vbool16_t mask, vuint32m2_t maskedoff, vuint16m1_t vs2, vuint16m1_t vs1, size_t vl) { + return __riscv_vwsll_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint32m2_t test_vwsll_vx_u32m2_tum(vbool16_t mask, vuint32m2_t maskedoff, vuint16m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vwsll_vv_u64m2_tum(vbool32_t mask, vuint64m2_t maskedoff, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vwsll_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vwsll_vx_u64m2_tum(vbool32_t mask, vuint64m2_t maskedoff, vuint32m1_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint16mf4_t test_vwsll_vv_u16mf4_tumu(vbool64_t mask, vuint16mf4_t maskedoff, vuint8mf8_t vs2, vuint8mf8_t vs1, size_t vl) { + return __riscv_vwsll_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16mf4_t test_vwsll_vx_u16mf4_tumu(vbool64_t mask, vuint16mf4_t maskedoff, vuint8mf8_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint32mf2_t test_vwsll_vv_u32mf2_tumu(vbool64_t mask, vuint32mf2_t maskedoff, vuint16mf4_t vs2, vuint16mf4_t vs1, size_t vl) { + return __riscv_vwsll_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint32mf2_t test_vwsll_vx_u32mf2_tumu(vbool64_t mask, vuint32mf2_t maskedoff, vuint16mf4_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vwsll_vv_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vwsll_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vwsll_vx_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint16m4_t test_vwsll_vv_u16m4_mu(vbool4_t mask, vuint16m4_t maskedoff, vuint8m2_t vs2, vuint8m2_t vs1, size_t vl) { + return __riscv_vwsll_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint16m4_t test_vwsll_vx_u16m4_mu(vbool4_t mask, vuint16m4_t maskedoff, vuint8m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_mu(mask, maskedoff, vs2, rs1, vl); +} + + +vuint32m4_t test_vwsll_vv_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint16m2_t vs2, vuint16m2_t vs1, size_t vl) { + return __riscv_vwsll_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint32m4_t test_vwsll_vx_u32m4_mu(vbool8_t mask, vuint32m4_t maskedoff, vuint16m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vwsll_vv_u64m4_mu(vbool16_t mask, vuint64m4_t maskedoff, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vwsll_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vwsll_vx_u64m4_mu(vbool16_t mask, vuint64m4_t maskedoff, vuint32m2_t vs2, size_t rs1, size_t vl) { + return __riscv_vwsll_mu(mask, maskedoff, vs2, rs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 14 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 12 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 6 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 6 } } */ +/* { dg-final { scan-assembler-times {vwsll\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]} 19 } } */ +/* { dg-final { scan-assembler-times {vwsll\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t} 12 } } */ +/* { dg-final { scan-assembler-times {vwsll\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]} 19 } } */ +/* { dg-final { scan-assembler-times {vwsll\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]+,\s*v0.t} 12 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbb/zvkb.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/zvkb.c new file mode 100644 index 00000000000..cf956ced59e --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbb/zvkb.c @@ -0,0 +1,48 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkb -mabi=lp64d -O3 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; + +vuint8mf8_t test_vandn_vv_u8mf8(vuint8mf8_t vs2, vuint8mf8_t vs1, size_t vl) { + return __riscv_vandn_vv_u8mf8(vs2, vs1, vl); +} + +vuint8mf8_t test_vandn_vx_u8mf8(vuint8mf8_t vs2, uint8_t rs1, size_t vl) { + return __riscv_vandn_vx_u8mf8(vs2, rs1, vl); +} + +vuint8mf8_t test_vbrev8_v_u8mf8(vuint8mf8_t vs2, size_t vl) { + return __riscv_vbrev8_v_u8mf8(vs2, vl); +} + +vuint8mf4_t test_vbrev8_v_u8mf4(vuint8mf4_t vs2, size_t vl) { + return __riscv_vbrev8_v_u8mf4(vs2, vl); +} + +vuint8mf8_t test_vrev8_v_u8mf8(vuint8mf8_t vs2, size_t vl) { + return __riscv_vrev8_v_u8mf8(vs2, vl); +} + +vuint8mf4_t test_vrev8_v_u8mf4(vuint8mf4_t vs2, size_t vl) { + return __riscv_vrev8_v_u8mf4(vs2, vl); +} + +vuint8mf8_t test_vror_vv_u8mf8(vuint8mf8_t vs2, vuint8mf8_t vs1, size_t vl) { + return __riscv_vror_vv_u8mf8(vs2, vs1, vl); +} + +vuint8mf8_t test_vror_vx_u8mf8(vuint8mf8_t vs2, size_t rs1, size_t vl) { + return __riscv_vror_vx_u8mf8(vs2, rs1, vl); +} + +vuint8mf8_t test_vrol_vv_u8mf8(vuint8mf8_t vs2, vuint8mf8_t vs1, size_t vl) { + return __riscv_vrol_vv_u8mf8(vs2, vs1, vl); +} + +vuint8mf8_t test_vrol_vx_u8mf8(vuint8mf8_t vs2, size_t rs1, size_t vl) { + return __riscv_vrol_vx_u8mf8(vs2, rs1, vl); +} \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmul.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmul.c new file mode 100644 index 00000000000..ba3e5cf858e --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmul.c @@ -0,0 +1,208 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbc -mabi=lp64d -O3 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint64m1_t test_vclmul_vv_u64m1(vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m1(vs2, vs1, vl); +} + +vuint64m1_t test_vclmul_vx_u64m1(vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m1(vs2, rs1, vl); +} + +vuint64m2_t test_vclmul_vv_u64m2(vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m2(vs2, vs1, vl); +} + +vuint64m2_t test_vclmul_vx_u64m2(vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m2(vs2, rs1, vl); +} + +vuint64m4_t test_vclmul_vv_u64m4(vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m4(vs2, vs1, vl); +} + +vuint64m4_t test_vclmul_vx_u64m4(vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m4(vs2, rs1, vl); +} + +vuint64m8_t test_vclmul_vv_u64m8(vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m8(vs2, vs1, vl); +} + +vuint64m8_t test_vclmul_vx_u64m8(vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m8(vs2, rs1, vl); +} + +vuint64m1_t test_vclmul_vv_u64m1_m(vbool64_t mask, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m1_m(mask, vs2, vs1, vl); +} + +vuint64m1_t test_vclmul_vx_u64m1_m(vbool64_t mask, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m1_m(mask, vs2, rs1, vl); +} + +vuint64m2_t test_vclmul_vv_u64m2_m(vbool32_t mask, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m2_m(mask, vs2, vs1, vl); +} + +vuint64m2_t test_vclmul_vx_u64m2_m(vbool32_t mask, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m2_m(mask, vs2, rs1, vl); +} + +vuint64m4_t test_vclmul_vv_u64m4_m(vbool16_t mask, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m4_m(mask, vs2, vs1, vl); +} + +vuint64m4_t test_vclmul_vx_u64m4_m(vbool16_t mask, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m4_m(mask, vs2, rs1, vl); +} + +vuint64m8_t test_vclmul_vv_u64m8_m(vbool8_t mask, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m8_m(mask, vs2, vs1, vl); +} + +vuint64m8_t test_vclmul_vx_u64m8_m(vbool8_t mask, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m8_m(mask, vs2, rs1, vl); +} + +vuint64m1_t test_vclmul_vv_u64m1_tu(vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m1_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmul_vx_u64m1_tu(vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m1_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmul_vv_u64m2_tu(vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m2_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmul_vx_u64m2_tu(vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m2_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmul_vv_u64m4_tu(vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m4_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmul_vx_u64m4_tu(vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m4_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmul_vv_u64m8_tu(vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m8_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmul_vx_u64m8_tu(vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m8_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vclmul_vv_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m1_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmul_vx_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m1_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmul_vv_u64m2_tum(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m2_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmul_vx_u64m2_tum(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m2_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmul_vv_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m4_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmul_vx_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m4_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmul_vv_u64m8_tum(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m8_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmul_vx_u64m8_tum(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m8_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vclmul_vv_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m1_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmul_vx_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m1_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmul_vv_u64m2_tumu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m2_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmul_vx_u64m2_tumu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m2_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmul_vv_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m4_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmul_vx_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m4_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmul_vv_u64m8_tumu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m8_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmul_vx_u64m8_tumu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m8_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vclmul_vv_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m1_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmul_vx_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m1_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmul_vv_u64m2_mu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m2_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmul_vx_u64m2_mu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m2_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmul_vv_u64m4_mu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m4_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmul_vx_u64m4_mu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m4_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmul_vv_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmul_vv_u64m8_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmul_vx_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_vx_u64m8_mu(mask, maskedoff, vs2, rs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vclmul\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]} 24 } } */ +/* { dg-final { scan-assembler-times {vclmul\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t} 16 } } */ +/* { dg-final { scan-assembler-times {vclmul\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]} 24 } } */ +/* { dg-final { scan-assembler-times {vclmul\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]+,\s*v0.t} 16 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmul_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmul_overloaded.c new file mode 100644 index 00000000000..1e25831f3f5 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmul_overloaded.c @@ -0,0 +1,208 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbc -mabi=lp64d -O3 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint64m1_t test_vclmul_vv_u64m1(vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmul(vs2, vs1, vl); +} + +vuint64m1_t test_vclmul_vx_u64m1(vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul(vs2, rs1, vl); +} + +vuint64m2_t test_vclmul_vv_u64m2(vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmul(vs2, vs1, vl); +} + +vuint64m2_t test_vclmul_vx_u64m2(vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul(vs2, rs1, vl); +} + +vuint64m4_t test_vclmul_vv_u64m4(vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmul(vs2, vs1, vl); +} + +vuint64m4_t test_vclmul_vx_u64m4(vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul(vs2, rs1, vl); +} + +vuint64m8_t test_vclmul_vv_u64m8(vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmul(vs2, vs1, vl); +} + +vuint64m8_t test_vclmul_vx_u64m8(vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul(vs2, rs1, vl); +} + +vuint64m1_t test_vclmul_vv_u64m1_m(vbool64_t mask, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmul(mask, vs2, vs1, vl); +} + +vuint64m1_t test_vclmul_vx_u64m1_m(vbool64_t mask, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul(mask, vs2, rs1, vl); +} + +vuint64m2_t test_vclmul_vv_u64m2_m(vbool32_t mask, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmul(mask, vs2, vs1, vl); +} + +vuint64m2_t test_vclmul_vx_u64m2_m(vbool32_t mask, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul(mask, vs2, rs1, vl); +} + +vuint64m4_t test_vclmul_vv_u64m4_m(vbool16_t mask, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmul(mask, vs2, vs1, vl); +} + +vuint64m4_t test_vclmul_vx_u64m4_m(vbool16_t mask, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul(mask, vs2, rs1, vl); +} + +vuint64m8_t test_vclmul_vv_u64m8_m(vbool8_t mask, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmul(mask, vs2, vs1, vl); +} + +vuint64m8_t test_vclmul_vx_u64m8_m(vbool8_t mask, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul(mask, vs2, rs1, vl); +} + +vuint64m1_t test_vclmul_vv_u64m1_tu(vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmul_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmul_vx_u64m1_tu(vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmul_vv_u64m2_tu(vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmul_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmul_vx_u64m2_tu(vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmul_vv_u64m4_tu(vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmul_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmul_vx_u64m4_tu(vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmul_vv_u64m8_tu(vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmul_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmul_vx_u64m8_tu(vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vclmul_vv_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmul_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmul_vx_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmul_vv_u64m2_tum(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmul_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmul_vx_u64m2_tum(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmul_vv_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmul_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmul_vx_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmul_vv_u64m8_tum(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmul_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmul_vx_u64m8_tum(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vclmul_vv_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmul_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmul_vx_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmul_vv_u64m2_tumu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmul_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmul_vx_u64m2_tumu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmul_vv_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmul_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmul_vx_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmul_vv_u64m8_tumu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmul_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmul_vx_u64m8_tumu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vclmul_vv_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmul_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmul_vx_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmul_vv_u64m2_mu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmul_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmul_vx_u64m2_mu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmul_vv_u64m4_mu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmul_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmul_vx_u64m4_mu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmul_vv_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmul_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmul_vx_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmul_mu(mask, maskedoff, vs2, rs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vclmul\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]} 24 } } */ +/* { dg-final { scan-assembler-times {vclmul\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t} 16 } } */ +/* { dg-final { scan-assembler-times {vclmul\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]} 24 } } */ +/* { dg-final { scan-assembler-times {vclmul\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]+,\s*v0.t} 16 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmulh.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmulh.c new file mode 100644 index 00000000000..c14b8a56490 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmulh.c @@ -0,0 +1,208 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbc -mabi=lp64d -O3 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint64m1_t test_vclmulh_vv_u64m1(vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m1(vs2, vs1, vl); +} + +vuint64m1_t test_vclmulh_vx_u64m1(vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m1(vs2, rs1, vl); +} + +vuint64m2_t test_vclmulh_vv_u64m2(vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m2(vs2, vs1, vl); +} + +vuint64m2_t test_vclmulh_vx_u64m2(vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m2(vs2, rs1, vl); +} + +vuint64m4_t test_vclmulh_vv_u64m4(vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m4(vs2, vs1, vl); +} + +vuint64m4_t test_vclmulh_vx_u64m4(vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m4(vs2, rs1, vl); +} + +vuint64m8_t test_vclmulh_vv_u64m8(vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m8(vs2, vs1, vl); +} + +vuint64m8_t test_vclmulh_vx_u64m8(vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m8(vs2, rs1, vl); +} + +vuint64m1_t test_vclmulh_vv_u64m1_m(vbool64_t mask, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m1_m(mask, vs2, vs1, vl); +} + +vuint64m1_t test_vclmulh_vx_u64m1_m(vbool64_t mask, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m1_m(mask, vs2, rs1, vl); +} + +vuint64m2_t test_vclmulh_vv_u64m2_m(vbool32_t mask, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m2_m(mask, vs2, vs1, vl); +} + +vuint64m2_t test_vclmulh_vx_u64m2_m(vbool32_t mask, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m2_m(mask, vs2, rs1, vl); +} + +vuint64m4_t test_vclmulh_vv_u64m4_m(vbool16_t mask, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m4_m(mask, vs2, vs1, vl); +} + +vuint64m4_t test_vclmulh_vx_u64m4_m(vbool16_t mask, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m4_m(mask, vs2, rs1, vl); +} + +vuint64m8_t test_vclmulh_vv_u64m8_m(vbool8_t mask, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m8_m(mask, vs2, vs1, vl); +} + +vuint64m8_t test_vclmulh_vx_u64m8_m(vbool8_t mask, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m8_m(mask, vs2, rs1, vl); +} + +vuint64m1_t test_vclmulh_vv_u64m1_tu(vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m1_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmulh_vx_u64m1_tu(vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m1_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmulh_vv_u64m2_tu(vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m2_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmulh_vx_u64m2_tu(vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m2_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmulh_vv_u64m4_tu(vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m4_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmulh_vx_u64m4_tu(vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m4_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmulh_vv_u64m8_tu(vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m8_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmulh_vx_u64m8_tu(vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m8_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vclmulh_vv_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m1_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmulh_vx_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m1_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmulh_vv_u64m2_tum(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m2_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmulh_vx_u64m2_tum(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m2_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmulh_vv_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m4_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmulh_vx_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m4_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmulh_vv_u64m8_tum(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m8_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmulh_vx_u64m8_tum(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m8_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vclmulh_vv_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m1_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmulh_vx_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m1_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmulh_vv_u64m2_tumu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m2_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmulh_vx_u64m2_tumu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m2_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmulh_vv_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m4_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmulh_vx_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m4_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmulh_vv_u64m8_tumu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m8_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmulh_vx_u64m8_tumu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m8_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vclmulh_vv_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m1_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmulh_vx_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m1_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmulh_vv_u64m2_mu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m2_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmulh_vx_u64m2_mu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m2_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmulh_vv_u64m4_mu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m4_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmulh_vx_u64m4_mu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m4_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmulh_vv_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmulh_vv_u64m8_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmulh_vx_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_vx_u64m8_mu(mask, maskedoff, vs2, rs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vclmulh\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]} 24 } } */ +/* { dg-final { scan-assembler-times {vclmulh\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t} 16 } } */ +/* { dg-final { scan-assembler-times {vclmulh\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]} 24 } } */ +/* { dg-final { scan-assembler-times {vclmulh\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]+,\s*v0.t} 16 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmulh_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmulh_overloaded.c new file mode 100644 index 00000000000..ed3c4388af6 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvbc/vclmulh_overloaded.c @@ -0,0 +1,208 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvbc -mabi=lp64d -O3 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint64m1_t test_vclmulh_vv_u64m1(vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmulh(vs2, vs1, vl); +} + +vuint64m1_t test_vclmulh_vx_u64m1(vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh(vs2, rs1, vl); +} + +vuint64m2_t test_vclmulh_vv_u64m2(vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmulh(vs2, vs1, vl); +} + +vuint64m2_t test_vclmulh_vx_u64m2(vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh(vs2, rs1, vl); +} + +vuint64m4_t test_vclmulh_vv_u64m4(vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmulh(vs2, vs1, vl); +} + +vuint64m4_t test_vclmulh_vx_u64m4(vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh(vs2, rs1, vl); +} + +vuint64m8_t test_vclmulh_vv_u64m8(vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmulh(vs2, vs1, vl); +} + +vuint64m8_t test_vclmulh_vx_u64m8(vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh(vs2, rs1, vl); +} + +vuint64m1_t test_vclmulh_vv_u64m1_m(vbool64_t mask, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmulh(mask, vs2, vs1, vl); +} + +vuint64m1_t test_vclmulh_vx_u64m1_m(vbool64_t mask, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh(mask, vs2, rs1, vl); +} + +vuint64m2_t test_vclmulh_vv_u64m2_m(vbool32_t mask, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmulh(mask, vs2, vs1, vl); +} + +vuint64m2_t test_vclmulh_vx_u64m2_m(vbool32_t mask, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh(mask, vs2, rs1, vl); +} + +vuint64m4_t test_vclmulh_vv_u64m4_m(vbool16_t mask, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmulh(mask, vs2, vs1, vl); +} + +vuint64m4_t test_vclmulh_vx_u64m4_m(vbool16_t mask, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh(mask, vs2, rs1, vl); +} + +vuint64m8_t test_vclmulh_vv_u64m8_m(vbool8_t mask, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmulh(mask, vs2, vs1, vl); +} + +vuint64m8_t test_vclmulh_vx_u64m8_m(vbool8_t mask, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh(mask, vs2, rs1, vl); +} + +vuint64m1_t test_vclmulh_vv_u64m1_tu(vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmulh_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmulh_vx_u64m1_tu(vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmulh_vv_u64m2_tu(vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmulh_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmulh_vx_u64m2_tu(vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmulh_vv_u64m4_tu(vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmulh_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmulh_vx_u64m4_tu(vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmulh_vv_u64m8_tu(vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmulh_tu(maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmulh_vx_u64m8_tu(vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_tu(maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vclmulh_vv_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmulh_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmulh_vx_u64m1_tum(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmulh_vv_u64m2_tum(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmulh_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmulh_vx_u64m2_tum(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmulh_vv_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmulh_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmulh_vx_u64m4_tum(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmulh_vv_u64m8_tum(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmulh_tum(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmulh_vx_u64m8_tum(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_tum(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vclmulh_vv_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmulh_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmulh_vx_u64m1_tumu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmulh_vv_u64m2_tumu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmulh_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmulh_vx_u64m2_tumu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmulh_vv_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmulh_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmulh_vx_u64m4_tumu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmulh_vv_u64m8_tumu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmulh_tumu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmulh_vx_u64m8_tumu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_tumu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m1_t test_vclmulh_vv_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vclmulh_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m1_t test_vclmulh_vx_u64m1_mu(vbool64_t mask, vuint64m1_t maskedoff, vuint64m1_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m2_t test_vclmulh_vv_u64m2_mu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vclmulh_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m2_t test_vclmulh_vx_u64m2_mu(vbool32_t mask, vuint64m2_t maskedoff, vuint64m2_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m4_t test_vclmulh_vv_u64m4_mu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vclmulh_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m4_t test_vclmulh_vx_u64m4_mu(vbool16_t mask, vuint64m4_t maskedoff, vuint64m4_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_mu(mask, maskedoff, vs2, rs1, vl); +} + +vuint64m8_t test_vclmulh_vv_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vclmulh_mu(mask, maskedoff, vs2, vs1, vl); +} + +vuint64m8_t test_vclmulh_vx_u64m8_mu(vbool8_t mask, vuint64m8_t maskedoff, vuint64m8_t vs2, uint64_t rs1, size_t vl) { + return __riscv_vclmulh_mu(mask, maskedoff, vs2, rs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 16 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*mu} 8 } } */ +/* { dg-final { scan-assembler-times {vclmulh\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]} 24 } } */ +/* { dg-final { scan-assembler-times {vclmulh\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+,\s*v0.t} 16 } } */ +/* { dg-final { scan-assembler-times {vclmulh\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]} 24 } } */ +/* { dg-final { scan-assembler-times {vclmulh\.vx\s+v[0-9]+,\s*v[0-9]+,\s*a[0-9]+,\s*v0.t} 16 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvk.exp b/gcc/testsuite/gcc.target/riscv/zvk/zvk.exp new file mode 100644 index 00000000000..5e2778a51a8 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvk.exp @@ -0,0 +1,54 @@ +# Copyright (C) 2022-2023 Free Software Foundation, Inc. + +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 3 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with GCC; see the file COPYING3. If not see +# . + +# GCC testsuite that uses the `dg.exp' driver. + +# Exit immediately if this isn't a RISC-V target. +if ![istarget riscv*-*-*] then { + return +} + +# Load support procs. +load_lib gcc-dg.exp + +# If a testcase doesn't have special options, use these. +global DEFAULT_CFLAGS +if ![info exists DEFAULT_CFLAGS] then { + set DEFAULT_CFLAGS " -ansi -pedantic-errors" +} + +# Initialize `dg'. +dg-init + +# Main loop. +dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/zvbb/*.\[cS\]]] \ + "" $DEFAULT_CFLAGS +dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/zvbc/*.\[cS\]]] \ + "" $DEFAULT_CFLAGS +dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/zvkg/*.\[cS\]]] \ + "" $DEFAULT_CFLAGS +dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/zvkned/*.\[cS\]]] \ + "" $DEFAULT_CFLAGS +dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/zvknha/*.\[cS\]]] \ + "" $DEFAULT_CFLAGS +dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/zvknhb/*.\[cS\]]] \ + "" $DEFAULT_CFLAGS +dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/zvksed/*.\[cS\]]] \ + "" $DEFAULT_CFLAGS +dg-runtest [lsort [glob -nocomplain $srcdir/$subdir/zvksh/*.\[cS\]]] \ + "" $DEFAULT_CFLAGS +# All done. +dg-finish diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkg/vghsh.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkg/vghsh.c new file mode 100644 index 00000000000..3837f99fea3 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkg/vghsh.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkg -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vghsh_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vghsh_vv_u32mf2(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vghsh_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vghsh_vv_u32m1(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vghsh_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vghsh_vv_u32m2(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vghsh_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vghsh_vv_u32m4(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vghsh_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vghsh_vv_u32m8(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vghsh_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vghsh_vv_u32mf2_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vghsh_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vghsh_vv_u32m1_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vghsh_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vghsh_vv_u32m2_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vghsh_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vghsh_vv_u32m4_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vghsh_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vghsh_vv_u32m8_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vghsh\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkg/vghsh_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkg/vghsh_overloaded.c new file mode 100644 index 00000000000..2d2004bc653 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkg/vghsh_overloaded.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkg -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vghsh_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vghsh(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vghsh_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vghsh(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vghsh_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vghsh(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vghsh_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vghsh(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vghsh_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vghsh(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vghsh_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vghsh_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vghsh_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vghsh_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vghsh_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vghsh_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vghsh_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vghsh_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vghsh_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vghsh_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vghsh\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkg/vgmul.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkg/vgmul.c new file mode 100644 index 00000000000..902de106c12 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkg/vgmul.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkg -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vgmul_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vgmul_vv_u32mf2(vd, vs2, vl); +} + +vuint32m1_t test_vgmul_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vgmul_vv_u32m1(vd, vs2, vl); +} + +vuint32m2_t test_vgmul_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vgmul_vv_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vgmul_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vgmul_vv_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vgmul_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vgmul_vv_u32m8(vd, vs2, vl); +} + +vuint32mf2_t test_vgmul_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vgmul_vv_u32mf2_tu(vd, vs2, vl); +} + +vuint32m1_t test_vgmul_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vgmul_vv_u32m1_tu(vd, vs2, vl); +} + +vuint32m2_t test_vgmul_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vgmul_vv_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vgmul_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vgmul_vv_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vgmul_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vgmul_vv_u32m8_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vgmul\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkg/vgmul_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkg/vgmul_overloaded.c new file mode 100644 index 00000000000..53397ebc69b --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkg/vgmul_overloaded.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkg -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vgmul_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vgmul(vd, vs2, vl); +} + +vuint32m1_t test_vgmul_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vgmul(vd, vs2, vl); +} + +vuint32m2_t test_vgmul_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vgmul(vd, vs2, vl); +} + +vuint32m4_t test_vgmul_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vgmul(vd, vs2, vl); +} + +vuint32m8_t test_vgmul_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vgmul(vd, vs2, vl); +} + +vuint32mf2_t test_vgmul_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vgmul_tu(vd, vs2, vl); +} + +vuint32m1_t test_vgmul_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vgmul_tu(vd, vs2, vl); +} + +vuint32m2_t test_vgmul_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vgmul_tu(vd, vs2, vl); +} + +vuint32m4_t test_vgmul_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vgmul_tu(vd, vs2, vl); +} + +vuint32m8_t test_vgmul_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vgmul_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vgmul\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdf.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdf.c new file mode 100644 index 00000000000..8fcfd493f2f --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdf.c @@ -0,0 +1,169 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ +#include "riscv_vector.h" +/* non-policy */ +vuint32mf2_t test_vaesdf_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vv_u32mf2(vd, vs2, vl); +} + +vuint32mf2_t test_vaesdf_vs_u32mf2_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32mf2_u32mf2(vd, vs2, vl); +} + +vuint32m1_t test_vaesdf_vs_u32mf2_u32m1(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32mf2_u32m1(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vs_u32mf2_u32m2(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32mf2_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32mf2_u32m4(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32mf2_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32mf2_u32m8(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32mf2_u32m8(vd, vs2, vl); +} + +vuint32m1_t test_vaesdf_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vv_u32m1(vd, vs2, vl); +} + +vuint32m1_t test_vaesdf_vs_u32m1_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m1_u32m1(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vs_u32m1_u32m2(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m1_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32m1_u32m4(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m1_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m1_u32m8(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m1_u32m8(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vv_u32m2(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vs_u32m2_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m2_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32m2_u32m4(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m2_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m2_u32m8(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m2_u32m8(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdf_vv_u32m4(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32m4_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m4_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m4_u32m8(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m4_u32m8(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdf_vv_u32m8(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m8_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m8_u32m8(vd, vs2, vl); +} + +/* policy */ +vuint32mf2_t test_vaesdf_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vv_u32mf2_tu(vd, vs2, vl); +} + +vuint32mf2_t test_vaesdf_vs_u32mf2_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32mf2_u32mf2_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesdf_vs_u32mf2_u32m1_tu(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32mf2_u32m1_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vs_u32mf2_u32m2_tu(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32mf2_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32mf2_u32m4_tu(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32mf2_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32mf2_u32m8_tu(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32mf2_u32m8_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesdf_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vv_u32m1_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesdf_vs_u32m1_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m1_u32m1_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vs_u32m1_u32m2_tu(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m1_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32m1_u32m4_tu(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m1_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m1_u32m8_tu(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m1_u32m8_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vv_u32m2_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vs_u32m2_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m2_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32m2_u32m4_tu(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m2_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m2_u32m8_tu(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m2_u32m8_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdf_vv_u32m4_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32m4_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m4_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m4_u32m8_tu(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m4_u32m8_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdf_vv_u32m8_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m8_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdf_vs_u32m8_u32m8_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vaesdf\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ +/* { dg-final { scan-assembler-times {vaesdf\.vs\s+v[0-9]+,\s*v[0-9]} 30 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdf_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdf_overloaded.c new file mode 100644 index 00000000000..b8570818358 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdf_overloaded.c @@ -0,0 +1,169 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ +#include "riscv_vector.h" +/* non-policy */ +vuint32mf2_t test_vaesdf_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vv(vd, vs2, vl); +} + +vuint32mf2_t test_vaesdf_vs_u32mf2_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m1_t test_vaesdf_vs_u32mf2_u32m1(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vs_u32mf2_u32m2(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32mf2_u32m4(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32mf2_u32m8(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m1_t test_vaesdf_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vv(vd, vs2, vl); +} + +vuint32m1_t test_vaesdf_vs_u32m1_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vs_u32m1_u32m2(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32m1_u32m4(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m1_u32m8(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vv(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vs_u32m2_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32m2_u32m4(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m2_u32m8(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdf_vv(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32m4_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m4_u32m8(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdf_vv(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m8_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdf_vs(vd, vs2, vl); +} + +/* policy */ +vuint32mf2_t test_vaesdf_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vv_tu(vd, vs2, vl); +} + +vuint32mf2_t test_vaesdf_vs_u32mf2_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesdf_vs_u32mf2_u32m1_tu(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vs_u32mf2_u32m2_tu(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32mf2_u32m4_tu(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32mf2_u32m8_tu(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesdf_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vv_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesdf_vs_u32m1_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vs_u32m1_u32m2_tu(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32m1_u32m4_tu(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m1_u32m8_tu(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vv_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdf_vs_u32m2_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32m2_u32m4_tu(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m2_u32m8_tu(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdf_vv_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdf_vs_u32m4_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m4_u32m8_tu(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdf_vv_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdf_vs_u32m8_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdf_vs_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vaesdf\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ +/* { dg-final { scan-assembler-times {vaesdf\.vs\s+v[0-9]+,\s*v[0-9]} 30 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdm.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdm.c new file mode 100644 index 00000000000..1d4a1711cc9 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdm.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vaesdm_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vv_u32mf2(vd, vs2, vl); +} + +vuint32mf2_t test_vaesdm_vs_u32mf2_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32mf2_u32mf2(vd, vs2, vl); +} + +vuint32m1_t test_vaesdm_vs_u32mf2_u32m1(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32mf2_u32m1(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vs_u32mf2_u32m2(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32mf2_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32mf2_u32m4(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32mf2_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32mf2_u32m8(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32mf2_u32m8(vd, vs2, vl); +} + +vuint32m1_t test_vaesdm_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vv_u32m1(vd, vs2, vl); +} + +vuint32m1_t test_vaesdm_vs_u32m1_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m1_u32m1(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vs_u32m1_u32m2(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m1_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32m1_u32m4(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m1_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m1_u32m8(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m1_u32m8(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vv_u32m2(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vs_u32m2_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m2_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32m2_u32m4(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m2_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m2_u32m8(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m2_u32m8(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdm_vv_u32m4(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32m4_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m4_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m4_u32m8(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m4_u32m8(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdm_vv_u32m8(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m8_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m8_u32m8(vd, vs2, vl); +} + +/* policy */ +vuint32mf2_t test_vaesdm_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vv_u32mf2_tu(vd, vs2, vl); +} + +vuint32mf2_t test_vaesdm_vs_u32mf2_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32mf2_u32mf2_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesdm_vs_u32mf2_u32m1_tu(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32mf2_u32m1_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vs_u32mf2_u32m2_tu(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32mf2_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32mf2_u32m4_tu(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32mf2_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32mf2_u32m8_tu(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32mf2_u32m8_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesdm_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vv_u32m1_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesdm_vs_u32m1_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m1_u32m1_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vs_u32m1_u32m2_tu(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m1_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32m1_u32m4_tu(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m1_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m1_u32m8_tu(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m1_u32m8_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vv_u32m2_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vs_u32m2_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m2_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32m2_u32m4_tu(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m2_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m2_u32m8_tu(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m2_u32m8_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdm_vv_u32m4_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32m4_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m4_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m4_u32m8_tu(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m4_u32m8_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdm_vv_u32m8_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m8_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdm_vs_u32m8_u32m8_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vaesdm\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ +/* { dg-final { scan-assembler-times {vaesdm\.vs\s+v[0-9]+,\s*v[0-9]} 30 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdm_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdm_overloaded.c new file mode 100644 index 00000000000..4247ba3901b --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesdm_overloaded.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vaesdm_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vv(vd, vs2, vl); +} + +vuint32mf2_t test_vaesdm_vs_u32mf2_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m1_t test_vaesdm_vs_u32mf2_u32m1(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vs_u32mf2_u32m2(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32mf2_u32m4(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32mf2_u32m8(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m1_t test_vaesdm_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vv(vd, vs2, vl); +} + +vuint32m1_t test_vaesdm_vs_u32m1_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vs_u32m1_u32m2(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32m1_u32m4(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m1_u32m8(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vv(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vs_u32m2_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32m2_u32m4(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m2_u32m8(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdm_vv(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32m4_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m4_u32m8(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdm_vv(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m8_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdm_vs(vd, vs2, vl); +} + +/* policy */ +vuint32mf2_t test_vaesdm_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vv_tu(vd, vs2, vl); +} + +vuint32mf2_t test_vaesdm_vs_u32mf2_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesdm_vs_u32mf2_u32m1_tu(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vs_u32mf2_u32m2_tu(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32mf2_u32m4_tu(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32mf2_u32m8_tu(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesdm_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vv_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesdm_vs_u32m1_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vs_u32m1_u32m2_tu(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32m1_u32m4_tu(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m1_u32m8_tu(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vv_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesdm_vs_u32m2_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32m2_u32m4_tu(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m2_u32m8_tu(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdm_vv_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesdm_vs_u32m4_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m4_u32m8_tu(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdm_vv_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesdm_vs_u32m8_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesdm_vs_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vaesdm\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ +/* { dg-final { scan-assembler-times {vaesdm\.vs\s+v[0-9]+,\s*v[0-9]} 30 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesef.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesef.c new file mode 100644 index 00000000000..93a79ffa51c --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesef.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vaesef_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vv_u32mf2(vd, vs2, vl); +} + +vuint32mf2_t test_vaesef_vs_u32mf2_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32mf2_u32mf2(vd, vs2, vl); +} + +vuint32m1_t test_vaesef_vs_u32mf2_u32m1(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32mf2_u32m1(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vs_u32mf2_u32m2(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32mf2_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32mf2_u32m4(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32mf2_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32mf2_u32m8(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32mf2_u32m8(vd, vs2, vl); +} + +vuint32m1_t test_vaesef_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vv_u32m1(vd, vs2, vl); +} + +vuint32m1_t test_vaesef_vs_u32m1_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m1_u32m1(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vs_u32m1_u32m2(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m1_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32m1_u32m4(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m1_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m1_u32m8(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m1_u32m8(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vv_u32m2(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vs_u32m2_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m2_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32m2_u32m4(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m2_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m2_u32m8(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m2_u32m8(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesef_vv_u32m4(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32m4_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m4_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m4_u32m8(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m4_u32m8(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesef_vv_u32m8(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m8_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m8_u32m8(vd, vs2, vl); +} + +/* policy */ +vuint32mf2_t test_vaesef_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vv_u32mf2_tu(vd, vs2, vl); +} + +vuint32mf2_t test_vaesef_vs_u32mf2_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32mf2_u32mf2_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesef_vs_u32mf2_u32m1_tu(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32mf2_u32m1_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vs_u32mf2_u32m2_tu(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32mf2_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32mf2_u32m4_tu(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32mf2_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32mf2_u32m8_tu(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32mf2_u32m8_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesef_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vv_u32m1_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesef_vs_u32m1_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m1_u32m1_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vs_u32m1_u32m2_tu(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m1_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32m1_u32m4_tu(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m1_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m1_u32m8_tu(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m1_u32m8_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vv_u32m2_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vs_u32m2_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m2_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32m2_u32m4_tu(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m2_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m2_u32m8_tu(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m2_u32m8_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesef_vv_u32m4_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32m4_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m4_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m4_u32m8_tu(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m4_u32m8_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesef_vv_u32m8_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m8_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesef_vs_u32m8_u32m8_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vaesef\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ +/* { dg-final { scan-assembler-times {vaesef\.vs\s+v[0-9]+,\s*v[0-9]} 30 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesef_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesef_overloaded.c new file mode 100644 index 00000000000..9e3998ef055 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesef_overloaded.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vaesef_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vv(vd, vs2, vl); +} + +vuint32mf2_t test_vaesef_vs_u32mf2_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m1_t test_vaesef_vs_u32mf2_u32m1(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vs_u32mf2_u32m2(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32mf2_u32m4(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32mf2_u32m8(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m1_t test_vaesef_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vv(vd, vs2, vl); +} + +vuint32m1_t test_vaesef_vs_u32m1_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vs_u32m1_u32m2(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32m1_u32m4(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m1_u32m8(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vv(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vs_u32m2_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32m2_u32m4(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m2_u32m8(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesef_vv(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32m4_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m4_u32m8(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesef_vv(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m8_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesef_vs(vd, vs2, vl); +} + +/* policy */ +vuint32mf2_t test_vaesef_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vv_tu(vd, vs2, vl); +} + +vuint32mf2_t test_vaesef_vs_u32mf2_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesef_vs_u32mf2_u32m1_tu(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vs_u32mf2_u32m2_tu(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32mf2_u32m4_tu(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32mf2_u32m8_tu(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesef_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vv_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesef_vs_u32m1_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vs_u32m1_u32m2_tu(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32m1_u32m4_tu(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m1_u32m8_tu(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vv_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesef_vs_u32m2_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32m2_u32m4_tu(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m2_u32m8_tu(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesef_vv_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesef_vs_u32m4_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m4_u32m8_tu(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesef_vv_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesef_vs_u32m8_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesef_vs_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vaesef\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ +/* { dg-final { scan-assembler-times {vaesef\.vs\s+v[0-9]+,\s*v[0-9]} 30 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesem.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesem.c new file mode 100644 index 00000000000..43e468c6f0e --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesem.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vaesem_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vv_u32mf2(vd, vs2, vl); +} + +vuint32mf2_t test_vaesem_vs_u32mf2_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32mf2_u32mf2(vd, vs2, vl); +} + +vuint32m1_t test_vaesem_vs_u32mf2_u32m1(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32mf2_u32m1(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vs_u32mf2_u32m2(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32mf2_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32mf2_u32m4(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32mf2_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32mf2_u32m8(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32mf2_u32m8(vd, vs2, vl); +} + +vuint32m1_t test_vaesem_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vv_u32m1(vd, vs2, vl); +} + +vuint32m1_t test_vaesem_vs_u32m1_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m1_u32m1(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vs_u32m1_u32m2(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m1_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32m1_u32m4(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m1_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m1_u32m8(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m1_u32m8(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vv_u32m2(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vs_u32m2_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m2_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32m2_u32m4(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m2_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m2_u32m8(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m2_u32m8(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesem_vv_u32m4(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32m4_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m4_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m4_u32m8(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m4_u32m8(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesem_vv_u32m8(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m8_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m8_u32m8(vd, vs2, vl); +} + +/* policy */ +vuint32mf2_t test_vaesem_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vv_u32mf2_tu(vd, vs2, vl); +} + +vuint32mf2_t test_vaesem_vs_u32mf2_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32mf2_u32mf2_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesem_vs_u32mf2_u32m1_tu(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32mf2_u32m1_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vs_u32mf2_u32m2_tu(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32mf2_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32mf2_u32m4_tu(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32mf2_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32mf2_u32m8_tu(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32mf2_u32m8_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesem_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vv_u32m1_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesem_vs_u32m1_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m1_u32m1_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vs_u32m1_u32m2_tu(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m1_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32m1_u32m4_tu(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m1_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m1_u32m8_tu(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m1_u32m8_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vv_u32m2_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vs_u32m2_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m2_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32m2_u32m4_tu(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m2_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m2_u32m8_tu(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m2_u32m8_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesem_vv_u32m4_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32m4_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m4_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m4_u32m8_tu(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m4_u32m8_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesem_vv_u32m8_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m8_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesem_vs_u32m8_u32m8_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vaesem\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ +/* { dg-final { scan-assembler-times {vaesem\.vs\s+v[0-9]+,\s*v[0-9]} 30 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesem_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesem_overloaded.c new file mode 100644 index 00000000000..bb2e7dea733 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesem_overloaded.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vaesem_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vv(vd, vs2, vl); +} + +vuint32mf2_t test_vaesem_vs_u32mf2_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m1_t test_vaesem_vs_u32mf2_u32m1(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vs_u32mf2_u32m2(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32mf2_u32m4(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32mf2_u32m8(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m1_t test_vaesem_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vv(vd, vs2, vl); +} + +vuint32m1_t test_vaesem_vs_u32m1_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vs_u32m1_u32m2(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32m1_u32m4(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m1_u32m8(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vv(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vs_u32m2_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32m2_u32m4(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m2_u32m8(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesem_vv(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32m4_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m4_u32m8(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesem_vv(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m8_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesem_vs(vd, vs2, vl); +} + +/* policy */ +vuint32mf2_t test_vaesem_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vv_tu(vd, vs2, vl); +} + +vuint32mf2_t test_vaesem_vs_u32mf2_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesem_vs_u32mf2_u32m1_tu(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vs_u32mf2_u32m2_tu(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32mf2_u32m4_tu(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32mf2_u32m8_tu(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesem_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vv_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesem_vs_u32m1_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vs_u32m1_u32m2_tu(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32m1_u32m4_tu(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m1_u32m8_tu(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vv_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesem_vs_u32m2_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32m2_u32m4_tu(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m2_u32m8_tu(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesem_vv_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesem_vs_u32m4_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m4_u32m8_tu(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesem_vv_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesem_vs_u32m8_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesem_vs_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vaesem\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ +/* { dg-final { scan-assembler-times {vaesem\.vs\s+v[0-9]+,\s*v[0-9]} 30 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf1.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf1.c new file mode 100644 index 00000000000..0edbb6d9108 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf1.c @@ -0,0 +1,50 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ + +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vaeskf1_vi_u32mf2(vuint32mf2_t vs2, size_t vl) { + return __riscv_vaeskf1_vi_u32mf2(vs2, 0, vl); +} + +vuint32m1_t test_vaeskf1_vi_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vaeskf1_vi_u32m1(vs2, 0, vl); +} + +vuint32m2_t test_vaeskf1_vi_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vaeskf1_vi_u32m2(vs2, 0, vl); +} + +vuint32m4_t test_vaeskf1_vi_u32m4(vuint32m4_t vs2, size_t vl) { + return __riscv_vaeskf1_vi_u32m4(vs2, 0, vl); +} + +vuint32m8_t test_vaeskf1_vi_u32m8(vuint32m8_t vs2, size_t vl) { + return __riscv_vaeskf1_vi_u32m8(vs2, 0, vl); +} + +/* policy */ +vuint32mf2_t test_vaeskf1_vi_u32mf2_tu(vuint32mf2_t maskedoff, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaeskf1_vi_u32mf2_tu(maskedoff, vs2, 0, vl); +} + +vuint32m1_t test_vaeskf1_vi_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vaeskf1_vi_u32m1_tu(maskedoff, vs2, 0, vl); +} + +vuint32m2_t test_vaeskf1_vi_u32m2_tu(vuint32m2_t maskedoff, vuint32m2_t vs2, size_t vl) { + return __riscv_vaeskf1_vi_u32m2_tu(maskedoff, vs2, 0, vl); +} + +vuint32m4_t test_vaeskf1_vi_u32m4_tu(vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vaeskf1_vi_u32m4_tu(maskedoff, vs2, 0, vl); +} + +vuint32m8_t test_vaeskf1_vi_u32m8_tu(vuint32m8_t maskedoff, vuint32m8_t vs2, size_t vl) { + return __riscv_vaeskf1_vi_u32m8_tu(maskedoff, vs2, 0, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vaeskf1\.vi\s+v[0-9]+,\s*v[0-9]+,0} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf1_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf1_overloaded.c new file mode 100644 index 00000000000..63e3537a06b --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf1_overloaded.c @@ -0,0 +1,50 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ + +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vaeskf1_vi_u32mf2(vuint32mf2_t vs2, size_t vl) { + return __riscv_vaeskf1(vs2, 0, vl); +} + +vuint32m1_t test_vaeskf1_vi_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vaeskf1(vs2, 0, vl); +} + +vuint32m2_t test_vaeskf1_vi_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vaeskf1(vs2, 0, vl); +} + +vuint32m4_t test_vaeskf1_vi_u32m4(vuint32m4_t vs2, size_t vl) { + return __riscv_vaeskf1(vs2, 0, vl); +} + +vuint32m8_t test_vaeskf1_vi_u32m8(vuint32m8_t vs2, size_t vl) { + return __riscv_vaeskf1(vs2, 0, vl); +} + +/* policy */ +vuint32mf2_t test_vaeskf1_vi_u32mf2_tu(vuint32mf2_t maskedoff, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaeskf1_tu(maskedoff, vs2, 0, vl); +} + +vuint32m1_t test_vaeskf1_vi_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vaeskf1_tu(maskedoff, vs2, 0, vl); +} + +vuint32m2_t test_vaeskf1_vi_u32m2_tu(vuint32m2_t maskedoff, vuint32m2_t vs2, size_t vl) { + return __riscv_vaeskf1_tu(maskedoff, vs2, 0, vl); +} + +vuint32m4_t test_vaeskf1_vi_u32m4_tu(vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vaeskf1_tu(maskedoff, vs2, 0, vl); +} + +vuint32m8_t test_vaeskf1_vi_u32m8_tu(vuint32m8_t maskedoff, vuint32m8_t vs2, size_t vl) { + return __riscv_vaeskf1_tu(maskedoff, vs2, 0, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vaeskf1\.vi\s+v[0-9]+,\s*v[0-9]+,0} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf2.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf2.c new file mode 100644 index 00000000000..06fed681d6a --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf2.c @@ -0,0 +1,50 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ + +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vaeskf2_vi_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaeskf2_vi_u32mf2(vd, vs2, 0, vl); +} + +vuint32m1_t test_vaeskf2_vi_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaeskf2_vi_u32m1(vd, vs2, 0, vl); +} + +vuint32m2_t test_vaeskf2_vi_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaeskf2_vi_u32m2(vd, vs2, 0, vl); +} + +vuint32m4_t test_vaeskf2_vi_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaeskf2_vi_u32m4(vd, vs2, 0, vl); +} + +vuint32m8_t test_vaeskf2_vi_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaeskf2_vi_u32m8(vd, vs2, 0, vl); +} + +/* policy */ +vuint32mf2_t test_vaeskf2_vi_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaeskf2_vi_u32mf2_tu(vd, vs2, 0, vl); +} + +vuint32m1_t test_vaeskf2_vi_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaeskf2_vi_u32m1_tu(vd, vs2, 0, vl); +} + +vuint32m2_t test_vaeskf2_vi_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaeskf2_vi_u32m2_tu(vd, vs2, 0, vl); +} + +vuint32m4_t test_vaeskf2_vi_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaeskf2_vi_u32m4_tu(vd, vs2, 0, vl); +} + +vuint32m8_t test_vaeskf2_vi_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaeskf2_vi_u32m8_tu(vd, vs2, 0, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vaeskf2\.vi\s+v[0-9]+,\s*v[0-9]+,0} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf2_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf2_overloaded.c new file mode 100644 index 00000000000..da7f42aef88 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaeskf2_overloaded.c @@ -0,0 +1,50 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ + +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vaeskf2_vi_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaeskf2(vd, vs2, 0, vl); +} + +vuint32m1_t test_vaeskf2_vi_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaeskf2(vd, vs2, 0, vl); +} + +vuint32m2_t test_vaeskf2_vi_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaeskf2(vd, vs2, 0, vl); +} + +vuint32m4_t test_vaeskf2_vi_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaeskf2(vd, vs2, 0, vl); +} + +vuint32m8_t test_vaeskf2_vi_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaeskf2(vd, vs2, 0, vl); +} + +/* policy */ +vuint32mf2_t test_vaeskf2_vi_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaeskf2_tu(vd, vs2, 0, vl); +} + +vuint32m1_t test_vaeskf2_vi_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaeskf2_tu(vd, vs2, 0, vl); +} + +vuint32m2_t test_vaeskf2_vi_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaeskf2_tu(vd, vs2, 0, vl); +} + +vuint32m4_t test_vaeskf2_vi_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaeskf2_tu(vd, vs2, 0, vl); +} + +vuint32m8_t test_vaeskf2_vi_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaeskf2_tu(vd, vs2, 0, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vaeskf2\.vi\s+v[0-9]+,\s*v[0-9]+,0} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesz.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesz.c new file mode 100644 index 00000000000..fbbbeaa78ed --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesz.c @@ -0,0 +1,130 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ + +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vaesz_vs_u32mf2_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32mf2_u32mf2(vd, vs2, vl); +} + +vuint32m1_t test_vaesz_vs_u32mf2_u32m1(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32mf2_u32m1(vd, vs2, vl); +} + +vuint32m2_t test_vaesz_vs_u32mf2_u32m2(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32mf2_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32mf2_u32m4(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32mf2_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32mf2_u32m8(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32mf2_u32m8(vd, vs2, vl); +} + +vuint32m1_t test_vaesz_vs_u32m1_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m1_u32m1(vd, vs2, vl); +} + +vuint32m2_t test_vaesz_vs_u32m1_u32m2(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m1_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32m1_u32m4(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m1_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m1_u32m8(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m1_u32m8(vd, vs2, vl); +} + +vuint32m2_t test_vaesz_vs_u32m2_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m2_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32m2_u32m4(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m2_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m2_u32m8(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m2_u32m8(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32m4_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m4_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m4_u32m8(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m4_u32m8(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m8_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m8_u32m8(vd, vs2, vl); +} + +/* policy */ +vuint32mf2_t test_vaesz_vs_u32mf2_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32mf2_u32mf2_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesz_vs_u32mf2_u32m1_tu(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32mf2_u32m1_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesz_vs_u32mf2_u32m2_tu(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32mf2_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32mf2_u32m4_tu(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32mf2_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32mf2_u32m8_tu(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32mf2_u32m8_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesz_vs_u32m1_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m1_u32m1_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesz_vs_u32m1_u32m2_tu(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m1_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32m1_u32m4_tu(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m1_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m1_u32m8_tu(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m1_u32m8_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesz_vs_u32m2_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m2_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32m2_u32m4_tu(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m2_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m2_u32m8_tu(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m2_u32m8_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32m4_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m4_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m4_u32m8_tu(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m4_u32m8_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m8_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesz_vs_u32m8_u32m8_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 15 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 15 } } */ +/* { dg-final { scan-assembler-times {vaesz\.vs\s+v[0-9]+,\s*v[0-9]} 30 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesz_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesz_overloaded.c new file mode 100644 index 00000000000..9130fbdc4ef --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvkned/vaesz_overloaded.c @@ -0,0 +1,130 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkned -mabi=lp64d -O2 -Wno-psabi" } */ + +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vaesz_vs_u32mf2_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m1_t test_vaesz_vs_u32mf2_u32m1(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m2_t test_vaesz_vs_u32mf2_u32m2(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32mf2_u32m4(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32mf2_u32m8(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m1_t test_vaesz_vs_u32m1_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m2_t test_vaesz_vs_u32m1_u32m2(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32m1_u32m4(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m1_u32m8(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m2_t test_vaesz_vs_u32m2_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32m2_u32m4(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m2_u32m8(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32m4_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m4_u32m8(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m8_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesz(vd, vs2, vl); +} + +/* policy */ +vuint32mf2_t test_vaesz_vs_u32mf2_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesz_vs_u32mf2_u32m1_tu(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesz_vs_u32mf2_u32m2_tu(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32mf2_u32m4_tu(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32mf2_u32m8_tu(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m1_t test_vaesz_vs_u32m1_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesz_vs_u32m1_u32m2_tu(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32m1_u32m4_tu(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m1_u32m8_tu(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m2_t test_vaesz_vs_u32m2_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32m2_u32m4_tu(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m2_u32m8_tu(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m4_t test_vaesz_vs_u32m4_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m4_u32m8_tu(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +vuint32m8_t test_vaesz_vs_u32m8_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vaesz_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 15 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 15 } } */ +/* { dg-final { scan-assembler-times {vaesz\.vs\s+v[0-9]+,\s*v[0-9]} 30 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch.c new file mode 100644 index 00000000000..2dea4bbb89f --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvknha -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsha2ch_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32mf2(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ch_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m1(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ch_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m2(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ch_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m4(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ch_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m8(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vsha2ch_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32mf2_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ch_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m1_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ch_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m2_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ch_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m4_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ch_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m8_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsha2ch\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch_overloaded.c new file mode 100644 index 00000000000..5a16400f800 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ch_overloaded.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvknha -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsha2ch_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ch_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ch_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ch_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ch_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vsha2ch_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ch_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ch_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ch_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ch_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsha2ch\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl.c new file mode 100644 index 00000000000..b2bbc1559f6 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvknha -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsha2cl_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32mf2(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2cl_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m1(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2cl_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m2(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2cl_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m4(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2cl_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m8(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vsha2cl_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32mf2_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2cl_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m1_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2cl_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m2_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2cl_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m4_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2cl_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m8_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsha2cl\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl_overloaded.c new file mode 100644 index 00000000000..7a54466b204 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2cl_overloaded.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvknha -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsha2cl_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2cl_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2cl_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2cl_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2cl_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vsha2cl_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2cl_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2cl_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2cl_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2cl_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsha2cl\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms.c new file mode 100644 index 00000000000..57523576c3a --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvknha -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsha2ms_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32mf2(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ms_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m1(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ms_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m2(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ms_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m4(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ms_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m8(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vsha2ms_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32mf2_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ms_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m1_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ms_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m2_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ms_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m4_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ms_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m8_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsha2ms\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms_overloaded.c new file mode 100644 index 00000000000..4d31ee0ee34 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknha/vsha2ms_overloaded.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvknha -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsha2ms_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ms_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ms_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ms_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ms_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vsha2ms_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ms_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ms_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ms_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ms_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsha2ms\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch.c new file mode 100644 index 00000000000..811c313887b --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch.c @@ -0,0 +1,83 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvknhb -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsha2ch_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32mf2(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ch_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m1(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ch_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m2(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ch_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m4(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ch_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m8(vd, vs2, vs1, vl); +} + +vuint64m1_t test_vsha2ch_vv_u64m1(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u64m1(vd, vs2, vs1, vl); +} + +vuint64m2_t test_vsha2ch_vv_u64m2(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u64m2(vd, vs2, vs1, vl); +} + +vuint64m4_t test_vsha2ch_vv_u64m4(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u64m4(vd, vs2, vs1, vl); +} + +vuint64m8_t test_vsha2ch_vv_u64m8(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u64m8(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vsha2ch_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32mf2_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ch_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m1_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ch_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m2_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ch_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m4_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ch_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u32m8_tu(vd, vs2, vs1, vl); +} + +vuint64m1_t test_vsha2ch_vv_u64m1_tu(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u64m1_tu(vd, vs2, vs1, vl); +} + +vuint64m2_t test_vsha2ch_vv_u64m2_tu(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u64m2_tu(vd, vs2, vs1, vl); +} + +vuint64m4_t test_vsha2ch_vv_u64m4_tu(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u64m4_tu(vd, vs2, vs1, vl); +} + +vuint64m8_t test_vsha2ch_vv_u64m8_tu(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vsha2ch_vv_u64m8_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 9 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 9 } } */ +/* { dg-final { scan-assembler-times {vsha2ch\.vv\s+v[0-9]+,\s*v[0-9]} 18 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch_overloaded.c new file mode 100644 index 00000000000..a09f9876c75 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ch_overloaded.c @@ -0,0 +1,83 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvknhb -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsha2ch_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ch_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ch_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ch_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ch_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint64m1_t test_vsha2ch_vv_u64m1(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint64m2_t test_vsha2ch_vv_u64m2(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint64m4_t test_vsha2ch_vv_u64m4(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint64m8_t test_vsha2ch_vv_u64m8(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vsha2ch(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vsha2ch_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ch_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ch_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ch_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ch_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +vuint64m1_t test_vsha2ch_vv_u64m1_tu(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +vuint64m2_t test_vsha2ch_vv_u64m2_tu(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +vuint64m4_t test_vsha2ch_vv_u64m4_tu(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +vuint64m8_t test_vsha2ch_vv_u64m8_tu(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vsha2ch_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 9 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 9 } } */ +/* { dg-final { scan-assembler-times {vsha2ch\.vv\s+v[0-9]+,\s*v[0-9]} 18 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl.c new file mode 100644 index 00000000000..f44c5a2cfbf --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl.c @@ -0,0 +1,83 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvknhb -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsha2cl_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32mf2(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2cl_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m1(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2cl_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m2(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2cl_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m4(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2cl_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m8(vd, vs2, vs1, vl); +} + +vuint64m1_t test_vsha2cl_vv_u64m1(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u64m1(vd, vs2, vs1, vl); +} + +vuint64m2_t test_vsha2cl_vv_u64m2(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u64m2(vd, vs2, vs1, vl); +} + +vuint64m4_t test_vsha2cl_vv_u64m4(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u64m4(vd, vs2, vs1, vl); +} + +vuint64m8_t test_vsha2cl_vv_u64m8(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u64m8(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vsha2cl_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32mf2_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2cl_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m1_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2cl_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m2_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2cl_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m4_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2cl_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u32m8_tu(vd, vs2, vs1, vl); +} + +vuint64m1_t test_vsha2cl_vv_u64m1_tu(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u64m1_tu(vd, vs2, vs1, vl); +} + +vuint64m2_t test_vsha2cl_vv_u64m2_tu(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u64m2_tu(vd, vs2, vs1, vl); +} + +vuint64m4_t test_vsha2cl_vv_u64m4_tu(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u64m4_tu(vd, vs2, vs1, vl); +} + +vuint64m8_t test_vsha2cl_vv_u64m8_tu(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vsha2cl_vv_u64m8_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 9 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 9 } } */ +/* { dg-final { scan-assembler-times {vsha2cl\.vv\s+v[0-9]+,\s*v[0-9]} 18 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl_overloaded.c new file mode 100644 index 00000000000..2354ab54a63 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2cl_overloaded.c @@ -0,0 +1,83 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvknhb -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsha2cl_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2cl_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2cl_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2cl_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2cl_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint64m1_t test_vsha2cl_vv_u64m1(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint64m2_t test_vsha2cl_vv_u64m2(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint64m4_t test_vsha2cl_vv_u64m4(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint64m8_t test_vsha2cl_vv_u64m8(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vsha2cl(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vsha2cl_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2cl_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2cl_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2cl_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2cl_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +vuint64m1_t test_vsha2cl_vv_u64m1_tu(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +vuint64m2_t test_vsha2cl_vv_u64m2_tu(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +vuint64m4_t test_vsha2cl_vv_u64m4_tu(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +vuint64m8_t test_vsha2cl_vv_u64m8_tu(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vsha2cl_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 9 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 9 } } */ +/* { dg-final { scan-assembler-times {vsha2cl\.vv\s+v[0-9]+,\s*v[0-9]} 18 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms.c new file mode 100644 index 00000000000..45aba16119d --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms.c @@ -0,0 +1,83 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvknhb -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsha2ms_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32mf2(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ms_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m1(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ms_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m2(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ms_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m4(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ms_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m8(vd, vs2, vs1, vl); +} + +vuint64m1_t test_vsha2ms_vv_u64m1(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u64m1(vd, vs2, vs1, vl); +} + +vuint64m2_t test_vsha2ms_vv_u64m2(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u64m2(vd, vs2, vs1, vl); +} + +vuint64m4_t test_vsha2ms_vv_u64m4(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u64m4(vd, vs2, vs1, vl); +} + +vuint64m8_t test_vsha2ms_vv_u64m8(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u64m8(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vsha2ms_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32mf2_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ms_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m1_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ms_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m2_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ms_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m4_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ms_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u32m8_tu(vd, vs2, vs1, vl); +} + +vuint64m1_t test_vsha2ms_vv_u64m1_tu(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u64m1_tu(vd, vs2, vs1, vl); +} + +vuint64m2_t test_vsha2ms_vv_u64m2_tu(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u64m2_tu(vd, vs2, vs1, vl); +} + +vuint64m4_t test_vsha2ms_vv_u64m4_tu(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u64m4_tu(vd, vs2, vs1, vl); +} + +vuint64m8_t test_vsha2ms_vv_u64m8_tu(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vsha2ms_vv_u64m8_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 9 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 9 } } */ +/* { dg-final { scan-assembler-times {vsha2ms\.vv\s+v[0-9]+,\s*v[0-9]} 18 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms_overloaded.c new file mode 100644 index 00000000000..3cad2e09fc7 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvknhb/vsha2ms_overloaded.c @@ -0,0 +1,83 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvknhb -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsha2ms_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ms_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ms_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ms_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ms_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint64m1_t test_vsha2ms_vv_u64m1(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint64m2_t test_vsha2ms_vv_u64m2(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint64m4_t test_vsha2ms_vv_u64m4(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint64m8_t test_vsha2ms_vv_u64m8(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vsha2ms(vd, vs2, vs1, vl); +} + +vuint32mf2_t test_vsha2ms_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +vuint32m1_t test_vsha2ms_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +vuint32m2_t test_vsha2ms_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +vuint32m4_t test_vsha2ms_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +vuint32m8_t test_vsha2ms_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +vuint64m1_t test_vsha2ms_vv_u64m1_tu(vuint64m1_t vd, vuint64m1_t vs2, vuint64m1_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +vuint64m2_t test_vsha2ms_vv_u64m2_tu(vuint64m2_t vd, vuint64m2_t vs2, vuint64m2_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +vuint64m4_t test_vsha2ms_vv_u64m4_tu(vuint64m4_t vd, vuint64m4_t vs2, vuint64m4_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +vuint64m8_t test_vsha2ms_vv_u64m8_tu(vuint64m8_t vd, vuint64m8_t vs2, vuint64m8_t vs1, size_t vl) { + return __riscv_vsha2ms_tu(vd, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 9 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 9 } } */ +/* { dg-final { scan-assembler-times {vsha2ms\.vv\s+v[0-9]+,\s*v[0-9]} 18 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4k.c b/gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4k.c new file mode 100644 index 00000000000..7a8a0857f31 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4k.c @@ -0,0 +1,50 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvksed -mabi=lp64d -O2 -Wno-psabi" } */ + +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vsm4k_vi_u32mf2(vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4k_vi_u32mf2(vs2, 0, vl); +} + +vuint32m1_t test_vsm4k_vi_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4k_vi_u32m1(vs2, 0, vl); +} + +vuint32m2_t test_vsm4k_vi_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4k_vi_u32m2(vs2, 0, vl); +} + +vuint32m4_t test_vsm4k_vi_u32m4(vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4k_vi_u32m4(vs2, 0, vl); +} + +vuint32m8_t test_vsm4k_vi_u32m8(vuint32m8_t vs2, size_t vl) { + return __riscv_vsm4k_vi_u32m8(vs2, 0, vl); +} + +/* policy */ +vuint32mf2_t test_vsm4k_vi_u32mf2_tu(vuint32mf2_t maskedoff, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4k_vi_u32mf2_tu(maskedoff, vs2, 0, vl); +} + +vuint32m1_t test_vsm4k_vi_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4k_vi_u32m1_tu(maskedoff, vs2, 0, vl); +} + +vuint32m2_t test_vsm4k_vi_u32m2_tu(vuint32m2_t maskedoff, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4k_vi_u32m2_tu(maskedoff, vs2, 0, vl); +} + +vuint32m4_t test_vsm4k_vi_u32m4_tu(vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4k_vi_u32m4_tu(maskedoff, vs2, 0, vl); +} + +vuint32m8_t test_vsm4k_vi_u32m8_tu(vuint32m8_t maskedoff, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm4k_vi_u32m8_tu(maskedoff, vs2, 0, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsm4k\.vi\s+v[0-9]+,\s*v[0-9]+,0} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4k_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4k_overloaded.c new file mode 100644 index 00000000000..dd06a7e58d8 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4k_overloaded.c @@ -0,0 +1,50 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvksed -mabi=lp64d -O2 -Wno-psabi" } */ + +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vsm4k_vi_u32mf2(vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4k(vs2, 0, vl); +} + +vuint32m1_t test_vsm4k_vi_u32m1(vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4k(vs2, 0, vl); +} + +vuint32m2_t test_vsm4k_vi_u32m2(vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4k(vs2, 0, vl); +} + +vuint32m4_t test_vsm4k_vi_u32m4(vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4k(vs2, 0, vl); +} + +vuint32m8_t test_vsm4k_vi_u32m8(vuint32m8_t vs2, size_t vl) { + return __riscv_vsm4k(vs2, 0, vl); +} + +/* policy */ +vuint32mf2_t test_vsm4k_vi_u32mf2_tu(vuint32mf2_t maskedoff, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4k_tu(maskedoff, vs2, 0, vl); +} + +vuint32m1_t test_vsm4k_vi_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4k_tu(maskedoff, vs2, 0, vl); +} + +vuint32m2_t test_vsm4k_vi_u32m2_tu(vuint32m2_t maskedoff, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4k_tu(maskedoff, vs2, 0, vl); +} + +vuint32m4_t test_vsm4k_vi_u32m4_tu(vuint32m4_t maskedoff, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4k_tu(maskedoff, vs2, 0, vl); +} + +vuint32m8_t test_vsm4k_vi_u32m8_tu(vuint32m8_t maskedoff, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm4k_tu(maskedoff, vs2, 0, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsm4k\.vi\s+v[0-9]+,\s*v[0-9]+,0} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4r.c b/gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4r.c new file mode 100644 index 00000000000..dac66db3abb --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4r.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvksed -mabi=lp64d -O2 -Wno-psabi" } */ +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vsm4r_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vv_u32mf2(vd, vs2, vl); +} + +vuint32mf2_t test_vsm4r_vs_u32mf2_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32mf2_u32mf2(vd, vs2, vl); +} + +vuint32m1_t test_vsm4r_vs_u32mf2_u32m1(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32mf2_u32m1(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vs_u32mf2_u32m2(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32mf2_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32mf2_u32m4(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32mf2_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32mf2_u32m8(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32mf2_u32m8(vd, vs2, vl); +} + +vuint32m1_t test_vsm4r_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vv_u32m1(vd, vs2, vl); +} + +vuint32m1_t test_vsm4r_vs_u32m1_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m1_u32m1(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vs_u32m1_u32m2(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m1_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32m1_u32m4(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m1_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m1_u32m8(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m1_u32m8(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vv_u32m2(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vs_u32m2_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m2_u32m2(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32m2_u32m4(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m2_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m2_u32m8(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m2_u32m8(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4r_vv_u32m4(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32m4_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m4_u32m4(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m4_u32m8(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m4_u32m8(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm4r_vv_u32m8(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m8_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m8_u32m8(vd, vs2, vl); +} + +/* policy */ +vuint32mf2_t test_vsm4r_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vv_u32mf2_tu(vd, vs2, vl); +} + +vuint32mf2_t test_vsm4r_vs_u32mf2_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32mf2_u32mf2_tu(vd, vs2, vl); +} + +vuint32m1_t test_vsm4r_vs_u32mf2_u32m1_tu(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32mf2_u32m1_tu(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vs_u32mf2_u32m2_tu(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32mf2_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32mf2_u32m4_tu(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32mf2_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32mf2_u32m8_tu(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32mf2_u32m8_tu(vd, vs2, vl); +} + +vuint32m1_t test_vsm4r_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vv_u32m1_tu(vd, vs2, vl); +} + +vuint32m1_t test_vsm4r_vs_u32m1_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m1_u32m1_tu(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vs_u32m1_u32m2_tu(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m1_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32m1_u32m4_tu(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m1_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m1_u32m8_tu(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m1_u32m8_tu(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vv_u32m2_tu(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vs_u32m2_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m2_u32m2_tu(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32m2_u32m4_tu(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m2_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m2_u32m8_tu(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m2_u32m8_tu(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4r_vv_u32m4_tu(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32m4_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m4_u32m4_tu(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m4_u32m8_tu(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m4_u32m8_tu(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm4r_vv_u32m8_tu(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m8_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm4r_vs_u32m8_u32m8_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vsm4r\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ +/* { dg-final { scan-assembler-times {vsm4r\.vs\s+v[0-9]+,\s*v[0-9]} 30 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4r_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4r_overloaded.c new file mode 100644 index 00000000000..6311adfb2d5 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvksed/vsm4r_overloaded.c @@ -0,0 +1,170 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvksed -mabi=lp64d -O2 -Wno-psabi" } */ +#include "riscv_vector.h" + +/* non-policy */ +vuint32mf2_t test_vsm4r_vv_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vv(vd, vs2, vl); +} + +vuint32mf2_t test_vsm4r_vs_u32mf2_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m1_t test_vsm4r_vs_u32mf2_u32m1(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vs_u32mf2_u32m2(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32mf2_u32m4(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32mf2_u32m8(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m1_t test_vsm4r_vv_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vv(vd, vs2, vl); +} + +vuint32m1_t test_vsm4r_vs_u32m1_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vs_u32m1_u32m2(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32m1_u32m4(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m1_u32m8(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vv_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vv(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vs_u32m2_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32m2_u32m4(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m2_u32m8(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vv_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4r_vv(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32m4_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m4_u32m8(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vv_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm4r_vv(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m8_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm4r_vs(vd, vs2, vl); +} + +/* policy */ +vuint32mf2_t test_vsm4r_vv_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vv_tu(vd, vs2, vl); +} + +vuint32mf2_t test_vsm4r_vs_u32mf2_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m1_t test_vsm4r_vs_u32mf2_u32m1_tu(vuint32m1_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vs_u32mf2_u32m2_tu(vuint32m2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32mf2_u32m4_tu(vuint32m4_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32mf2_u32m8_tu(vuint32m8_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m1_t test_vsm4r_vv_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vv_tu(vd, vs2, vl); +} + +vuint32m1_t test_vsm4r_vs_u32m1_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vs_u32m1_u32m2_tu(vuint32m2_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32m1_u32m4_tu(vuint32m4_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m1_u32m8_tu(vuint32m8_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vv_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vv_tu(vd, vs2, vl); +} + +vuint32m2_t test_vsm4r_vs_u32m2_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32m2_u32m4_tu(vuint32m4_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m2_u32m8_tu(vuint32m8_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vv_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4r_vv_tu(vd, vs2, vl); +} + +vuint32m4_t test_vsm4r_vs_u32m4_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m4_u32m8_tu(vuint32m8_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vv_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm4r_vv_tu(vd, vs2, vl); +} + +vuint32m8_t test_vsm4r_vs_u32m8_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm4r_vs_tu(vd, vs2, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 20 } } */ +/* { dg-final { scan-assembler-times {vsm4r\.vv\s+v[0-9]+,\s*v[0-9]} 10 } } */ +/* { dg-final { scan-assembler-times {vsm4r\.vs\s+v[0-9]+,\s*v[0-9]} 30 } } */ diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3c.c b/gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3c.c new file mode 100644 index 00000000000..1cea2489708 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3c.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvksh -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsm3c_vi_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm3c_vi_u32mf2(vd, vs2, 0, vl); +} + +vuint32m1_t test_vsm3c_vi_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm3c_vi_u32m1(vd, vs2, 0, vl); +} + +vuint32m2_t test_vsm3c_vi_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm3c_vi_u32m2(vd, vs2, 0, vl); +} + +vuint32m4_t test_vsm3c_vi_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm3c_vi_u32m4(vd, vs2, 0, vl); +} + +vuint32m8_t test_vsm3c_vi_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm3c_vi_u32m8(vd, vs2, 0, vl); +} + +vuint32mf2_t test_vsm3c_vi_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm3c_vi_u32mf2_tu(vd, vs2, 0, vl); +} + +vuint32m1_t test_vsm3c_vi_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm3c_vi_u32m1_tu(vd, vs2, 0, vl); +} + +vuint32m2_t test_vsm3c_vi_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm3c_vi_u32m2_tu(vd, vs2, 0, vl); +} + +vuint32m4_t test_vsm3c_vi_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm3c_vi_u32m4_tu(vd, vs2, 0, vl); +} + +vuint32m8_t test_vsm3c_vi_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm3c_vi_u32m8_tu(vd, vs2, 0, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsm3c\.vi\s+v[0-9]+,\s*v[0-9]+,0} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3c_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3c_overloaded.c new file mode 100644 index 00000000000..01b4c0fbb95 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3c_overloaded.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvksh -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsm3c_vi_u32mf2(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm3c(vd, vs2, 0, vl); +} + +vuint32m1_t test_vsm3c_vi_u32m1(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm3c(vd, vs2, 0, vl); +} + +vuint32m2_t test_vsm3c_vi_u32m2(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm3c(vd, vs2, 0, vl); +} + +vuint32m4_t test_vsm3c_vi_u32m4(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm3c(vd, vs2, 0, vl); +} + +vuint32m8_t test_vsm3c_vi_u32m8(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm3c(vd, vs2, 0, vl); +} + +vuint32mf2_t test_vsm3c_vi_u32mf2_tu(vuint32mf2_t vd, vuint32mf2_t vs2, size_t vl) { + return __riscv_vsm3c_tu(vd, vs2, 0, vl); +} + +vuint32m1_t test_vsm3c_vi_u32m1_tu(vuint32m1_t vd, vuint32m1_t vs2, size_t vl) { + return __riscv_vsm3c_tu(vd, vs2, 0, vl); +} + +vuint32m2_t test_vsm3c_vi_u32m2_tu(vuint32m2_t vd, vuint32m2_t vs2, size_t vl) { + return __riscv_vsm3c_tu(vd, vs2, 0, vl); +} + +vuint32m4_t test_vsm3c_vi_u32m4_tu(vuint32m4_t vd, vuint32m4_t vs2, size_t vl) { + return __riscv_vsm3c_tu(vd, vs2, 0, vl); +} + +vuint32m8_t test_vsm3c_vi_u32m8_tu(vuint32m8_t vd, vuint32m8_t vs2, size_t vl) { + return __riscv_vsm3c_tu(vd, vs2, 0, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsm3c\.vi\s+v[0-9]+,\s*v[0-9]+,0} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3me.c b/gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3me.c new file mode 100644 index 00000000000..78fdf741643 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3me.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvksh -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsm3me_vv_u32mf2(vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsm3me_vv_u32mf2(vs2, vs1, vl); +} + +vuint32m1_t test_vsm3me_vv_u32m1(vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsm3me_vv_u32m1(vs2, vs1, vl); +} + +vuint32m2_t test_vsm3me_vv_u32m2(vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsm3me_vv_u32m2(vs2, vs1, vl); +} + +vuint32m4_t test_vsm3me_vv_u32m4(vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsm3me_vv_u32m4(vs2, vs1, vl); +} + +vuint32m8_t test_vsm3me_vv_u32m8(vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsm3me_vv_u32m8(vs2, vs1, vl); +} + +vuint32mf2_t test_vsm3me_vv_u32mf2_tu(vuint32mf2_t maskedoff, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsm3me_vv_u32mf2_tu(maskedoff, vs2, vs1, vl); +} + +vuint32m1_t test_vsm3me_vv_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsm3me_vv_u32m1_tu(maskedoff, vs2, vs1, vl); +} + +vuint32m2_t test_vsm3me_vv_u32m2_tu(vuint32m2_t maskedoff, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsm3me_vv_u32m2_tu(maskedoff, vs2, vs1, vl); +} + +vuint32m4_t test_vsm3me_vv_u32m4_tu(vuint32m4_t maskedoff, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsm3me_vv_u32m4_tu(maskedoff, vs2, vs1, vl); +} + +vuint32m8_t test_vsm3me_vv_u32m8_tu(vuint32m8_t maskedoff, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsm3me_vv_u32m8_tu(maskedoff, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsm3me\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3me_overloaded.c b/gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3me_overloaded.c new file mode 100644 index 00000000000..00c9cfe56ca --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvk/zvksh/vsm3me_overloaded.c @@ -0,0 +1,51 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvksh -mabi=lp64d -O2 -Wno-psabi" } */ +#include +#include + +typedef _Float16 float16_t; +typedef float float32_t; +typedef double float64_t; +vuint32mf2_t test_vsm3me_vv_u32mf2(vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsm3me(vs2, vs1, vl); +} + +vuint32m1_t test_vsm3me_vv_u32m1(vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsm3me(vs2, vs1, vl); +} + +vuint32m2_t test_vsm3me_vv_u32m2(vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsm3me(vs2, vs1, vl); +} + +vuint32m4_t test_vsm3me_vv_u32m4(vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsm3me(vs2, vs1, vl); +} + +vuint32m8_t test_vsm3me_vv_u32m8(vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsm3me(vs2, vs1, vl); +} + +vuint32mf2_t test_vsm3me_vv_u32mf2_tu(vuint32mf2_t maskedoff, vuint32mf2_t vs2, vuint32mf2_t vs1, size_t vl) { + return __riscv_vsm3me_tu(maskedoff, vs2, vs1, vl); +} + +vuint32m1_t test_vsm3me_vv_u32m1_tu(vuint32m1_t maskedoff, vuint32m1_t vs2, vuint32m1_t vs1, size_t vl) { + return __riscv_vsm3me_tu(maskedoff, vs2, vs1, vl); +} + +vuint32m2_t test_vsm3me_vv_u32m2_tu(vuint32m2_t maskedoff, vuint32m2_t vs2, vuint32m2_t vs1, size_t vl) { + return __riscv_vsm3me_tu(maskedoff, vs2, vs1, vl); +} + +vuint32m4_t test_vsm3me_vv_u32m4_tu(vuint32m4_t maskedoff, vuint32m4_t vs2, vuint32m4_t vs1, size_t vl) { + return __riscv_vsm3me_tu(maskedoff, vs2, vs1, vl); +} + +vuint32m8_t test_vsm3me_vv_u32m8_tu(vuint32m8_t maskedoff, vuint32m8_t vs2, vuint32m8_t vs1, size_t vl) { + return __riscv_vsm3me_tu(maskedoff, vs2, vs1, vl); +} + +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*ta,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsetvli\s*zero,\s*[a-x0-9]+,\s*[a-x0-9]+,m[a-x0-9]+,\s*tu,\s*ma} 5 } } */ +/* { dg-final { scan-assembler-times {vsm3me\.vv\s+v[0-9]+,\s*v[0-9]+,\s*v[0-9]+} 10 } } */ \ No newline at end of file diff --git a/gcc/testsuite/gcc.target/riscv/zvkb.c b/gcc/testsuite/gcc.target/riscv/zvkb.c new file mode 100644 index 00000000000..d5c28e79ef6 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/zvkb.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv64gc_zvkb" { target { rv64 } } } */ +/* { dg-options "-march=rv32gc_zvkb" { target { rv32 } } } */ + +#ifndef __riscv_zvkb +#error "Feature macro not defined" +#endif + +int +foo (int a) +{ + return a; +}