From patchwork Wed Dec 14 08:19:35 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "juzhe.zhong@rivai.ai" X-Patchwork-Id: 33103 Return-Path: Delivered-To: ouuuleilei@gmail.com Received: by 2002:adf:e747:0:0:0:0:0 with SMTP id c7csp79797wrn; Wed, 14 Dec 2022 00:20:50 -0800 (PST) X-Google-Smtp-Source: AA0mqf4PLRo8i+cvPuCx/LtyFwvkrlcysihcWk9iSnZBlSjWfpWct2frvAWDc4jYbpQNMeSxixBW X-Received: by 2002:a17:906:17d7:b0:78d:f454:ba14 with SMTP id u23-20020a17090617d700b0078df454ba14mr20686695eje.19.1671006050437; Wed, 14 Dec 2022 00:20:50 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1671006050; cv=none; d=google.com; s=arc-20160816; b=DiILeJQKWihyJnHjQ+bmHr0wOoiJd2o6NW0UCqkej7J96KjbOAhzvhR0gVgzPjYx+x dZqLgBnT4qySY7Lc4MOHP0FF10fl0FA/klxp7rHL+ovaE3eJaF4Tu207CyR1TdId+66s WQ6Upvf/0GL7pDULr4MMA934nP4iAkgKKpfJFZOQC4hKy+pxBBxz4V86MXsyDB2IaN+5 hvMkXNxybW2FAV/QtpCuntc+DaksNY8+idBu05tnPmMfxXyo4vUR3P3G97ktSalcEq0J POqfmOuDqNUct+h54tjjaCH0YK3U2kL+WuxE5e/SqxnJzFZsCU84KAjx1szhXJoW2anZ 4Itw== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:feedback-id :content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:dmarc-filter:delivered-to; bh=J8898vrtm3PvlyQ60GSZNSIPTsDr2RozCtVbeBsFykQ=; b=hwbcHqP7lg1LqXPplAOfSbAW1okuS1GHsiBnXjt/En3IVf/pmZxPwse8qoatImS9jr ouB5SoTUO6k1cuNPlwX1jiGgxo+mt6K7jbLOSlUjQT5f1ja+WJINdmq7x7/F9Ek82Ucs Ggab+XjBcEThwaU7GShqoRKUeZiceZAX8Vb8Ww70dxxImlB1QGTmAtLaCsKYaJogls+a m/mplSKodOvzS98HTbif++UGUXaAsUcRS84tKXJ3WxMbL++G3c3k9gAMO9cdl34K6oBi QqSYNdKNSbnTm9ZExojyT/Ia0Spj446j1v2QbtzNyng13mbKDf14y1MCd3CoBdHM9Cjh LHJQ== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org designates 2620:52:3:1:0:246e:9693:128c as permitted sender) smtp.mailfrom="gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org" Received: from sourceware.org (server2.sourceware.org. [2620:52:3:1:0:246e:9693:128c]) by mx.google.com with ESMTPS id ds4-20020a170907724400b007c0d89354b6si10912037ejc.245.2022.12.14.00.20.49 for (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 14 Dec 2022 00:20:50 -0800 (PST) Received-SPF: pass (google.com: domain of gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org designates 2620:52:3:1:0:246e:9693:128c as permitted sender) client-ip=2620:52:3:1:0:246e:9693:128c; Authentication-Results: mx.google.com; spf=pass (google.com: domain of gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org designates 2620:52:3:1:0:246e:9693:128c as permitted sender) smtp.mailfrom="gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org" Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id B8D433834C14 for ; Wed, 14 Dec 2022 08:20:48 +0000 (GMT) X-Original-To: gcc-patches@gcc.gnu.org Delivered-To: gcc-patches@gcc.gnu.org Received: from smtpbgsg1.qq.com (smtpbgsg1.qq.com [54.254.200.92]) by sourceware.org (Postfix) with ESMTPS id CFCB63834C13 for ; Wed, 14 Dec 2022 08:19:44 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org CFCB63834C13 Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=rivai.ai Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=rivai.ai X-QQ-mid: bizesmtp63t1671005978tyfo2m01 Received: from rios-cad5.localdomain ( [58.60.1.11]) by bizesmtp.qq.com (ESMTP) with id ; Wed, 14 Dec 2022 16:19:37 +0800 (CST) X-QQ-SSF: 01400000000000D0L000000A0000000 X-QQ-FEAT: LpuzoIPF5uv2acQsf7kML1t05mIiOQSkyPbK5buALxSm3yzsNizj12Ol0xyIR j7l0vhpDYJqkaFT2m3uEDZ+bgJhamMiq8Y/3bdODVR2lgTdzqrV8OP5QhbCbk/WR5nHNJHx 6VHyaitOTdylCVXg51Ilr3v/yenhjLWWiuPPj1W1XBjkE407LGT0jJU+gbB3U/+uW4RE5YG A+sh2iLSjHSwJIZ715lhdgjwZ0/MSP7BFztIDB4ftcm2H4kh+mihTWHDRkXsldzR2uqtbgy O9hTZoXgQN1IfHDEyM7xpP1Sr4qGvR9Dwp0ti+cg69RSXj+p23S1YDG7gtt++vqIpn2rOZZ gVc1lIMhkFu+OfRXwcIm/lTD/WfsPbKNHQeZaggt+Lg3jeyq5GiCd8OK/DmF/fXd3GYzryz X-QQ-GoodBg: 2 From: juzhe.zhong@rivai.ai To: gcc-patches@gcc.gnu.org Cc: kito.cheng@gmail.com, palmer@dabbelt.com, Ju-Zhe Zhong Subject: [PATCH] RISC-V: Add testcases for VSETVL PASS 4 Date: Wed, 14 Dec 2022 16:19:35 +0800 Message-Id: <20221214081935.256992-1-juzhe.zhong@rivai.ai> X-Mailer: git-send-email 2.36.3 MIME-Version: 1.0 X-QQ-SENDSIZE: 520 Feedback-ID: bizesmtp:rivai.ai:qybglogicsvr:qybglogicsvr7 X-Spam-Status: No, score=-12.6 required=5.0 tests=BAYES_00, GIT_PATCH_0, KAM_DMARC_STATUS, KAM_NUMSUBJECT, KAM_SHORT, RCVD_IN_DNSWL_NONE, RCVD_IN_MSPIKE_H2, SPF_HELO_PASS, SPF_PASS, TXREP autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org X-BeenThere: gcc-patches@gcc.gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Gcc-patches mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: gcc-patches-bounces+ouuuleilei=gmail.com@gcc.gnu.org Sender: "Gcc-patches" X-getmail-retrieved-from-mailbox: =?utf-8?q?INBOX?= X-GMAIL-THRID: =?utf-8?q?1752176840385709355?= X-GMAIL-MSGID: =?utf-8?q?1752176840385709355?= From: Ju-Zhe Zhong gcc/testsuite/ChangeLog: * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-1.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-10.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-11.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-12.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-13.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-14.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-15.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-16.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-17.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-18.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-19.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-2.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-20.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-21.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-22.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-23.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-24.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-25.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-26.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-27.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-28.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-3.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-4.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-5.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-6.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-7.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-8.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-9.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_call-1.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_call-2.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_call-3.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_call-4.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_complex_loop-1.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_complex_loop-2.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_conflict-1.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_conflict-10.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_conflict-11.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_conflict-12.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_conflict-2.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_conflict-3.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_conflict-4.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_conflict-5.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_conflict-6.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_conflict-7.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_conflict-8.c: New test. * gcc.target/riscv/rvv/vsetvl/vlmax_conflict-9.c: New test. --- .../riscv/rvv/vsetvl/vlmax_bb_prop-1.c | 182 ++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-10.c | 230 +++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-11.c | 43 ++ .../riscv/rvv/vsetvl/vlmax_bb_prop-12.c | 266 ++++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-13.c | 221 +++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-14.c | 221 +++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-15.c | 41 ++ .../riscv/rvv/vsetvl/vlmax_bb_prop-16.c | 257 ++++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-17.c | 177 ++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-18.c | 177 ++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-19.c | 34 ++ .../riscv/rvv/vsetvl/vlmax_bb_prop-2.c | 182 ++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-20.c | 203 +++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-21.c | 155 +++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-22.c | 155 +++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-23.c | 30 + .../riscv/rvv/vsetvl/vlmax_bb_prop-24.c | 180 ++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-25.c | 572 ++++++++++++++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-26.c | 492 +++++++++++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-27.c | 491 +++++++++++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-28.c | 86 +++ .../riscv/rvv/vsetvl/vlmax_bb_prop-3.c | 35 ++ .../riscv/rvv/vsetvl/vlmax_bb_prop-4.c | 210 +++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-5.c | 167 +++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-6.c | 167 +++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-7.c | 32 + .../riscv/rvv/vsetvl/vlmax_bb_prop-8.c | 194 ++++++ .../riscv/rvv/vsetvl/vlmax_bb_prop-9.c | 230 +++++++ .../riscv/rvv/vsetvl/vlmax_call-1.c | 239 ++++++++ .../riscv/rvv/vsetvl/vlmax_call-2.c | 207 +++++++ .../riscv/rvv/vsetvl/vlmax_call-3.c | 207 +++++++ .../riscv/rvv/vsetvl/vlmax_call-4.c | 39 ++ .../riscv/rvv/vsetvl/vlmax_complex_loop-1.c | 52 ++ .../riscv/rvv/vsetvl/vlmax_complex_loop-2.c | 56 ++ .../riscv/rvv/vsetvl/vlmax_conflict-1.c | 23 + .../riscv/rvv/vsetvl/vlmax_conflict-10.c | 27 + .../riscv/rvv/vsetvl/vlmax_conflict-11.c | 24 + .../riscv/rvv/vsetvl/vlmax_conflict-12.c | 39 ++ .../riscv/rvv/vsetvl/vlmax_conflict-2.c | 23 + .../riscv/rvv/vsetvl/vlmax_conflict-3.c | 30 + .../riscv/rvv/vsetvl/vlmax_conflict-4.c | 29 + .../riscv/rvv/vsetvl/vlmax_conflict-5.c | 32 + .../riscv/rvv/vsetvl/vlmax_conflict-6.c | 26 + .../riscv/rvv/vsetvl/vlmax_conflict-7.c | 26 + .../riscv/rvv/vsetvl/vlmax_conflict-8.c | 27 + .../riscv/rvv/vsetvl/vlmax_conflict-9.c | 27 + 46 files changed, 6563 insertions(+) create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-1.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-10.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-11.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-12.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-13.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-14.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-15.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-16.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-17.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-18.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-19.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-2.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-20.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-21.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-22.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-23.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-24.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-25.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-26.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-27.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-28.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-3.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-4.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-5.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-6.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-7.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-8.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-9.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-1.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-2.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-3.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-4.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_complex_loop-1.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_complex_loop-2.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-1.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-10.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-11.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-12.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-2.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-3.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-4.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-5.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-6.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-7.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-8.c create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-9.c diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-1.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-1.c new file mode 100644 index 00000000000..3e27a8abf10 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-1.c @@ -0,0 +1,182 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint8mf8_t v = *(vint8mf8_t*)(in + 500); + *(vint8mf8_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf8_t v = *(vint8mf8_t*)(in + 600); + *(vint8mf8_t*)(out + 600) = v; + } else { + vint8mf8_t v = *(vint8mf8_t*)(in + 700); + *(vint8mf8_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf8_t v = *(vint8mf8_t*)(in + 900 + i); + *(vint8mf8_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint8mf4_t v = *(vint8mf4_t*)(in + 500); + *(vint8mf4_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf4_t v = *(vint8mf4_t*)(in + 600); + *(vint8mf4_t*)(out + 600) = v; + } else { + vint8mf4_t v = *(vint8mf4_t*)(in + 700); + *(vint8mf4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf4_t v = *(vint8mf4_t*)(in + 900 + i); + *(vint8mf4_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint8mf2_t v = *(vint8mf2_t*)(in + 500); + *(vint8mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf2_t v = *(vint8mf2_t*)(in + 600); + *(vint8mf2_t*)(out + 600) = v; + } else { + vint8mf2_t v = *(vint8mf2_t*)(in + 700); + *(vint8mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf2_t v = *(vint8mf2_t*)(in + 900 + i); + *(vint8mf2_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint16mf4_t v = *(vint16mf4_t*)(in + 500); + *(vint16mf4_t*)(out + 500) = v; + } else if (n == 1) { + vint16mf4_t v = *(vint16mf4_t*)(in + 600); + *(vint16mf4_t*)(out + 600) = v; + } else { + vint16mf4_t v = *(vint16mf4_t*)(in + 700); + *(vint16mf4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf4_t v = *(vint16mf4_t*)(in + 900 + i); + *(vint16mf4_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint16mf2_t v = *(vint16mf2_t*)(in + 500); + *(vint16mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint16mf2_t v = *(vint16mf2_t*)(in + 600); + *(vint16mf2_t*)(out + 600) = v; + } else { + vint16mf2_t v = *(vint16mf2_t*)(in + 700); + *(vint16mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf2_t v = *(vint16mf2_t*)(in + 900 + i); + *(vint16mf2_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint32mf2_t v = *(vint32mf2_t*)(in + 500); + *(vint32mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint32mf2_t v = *(vint32mf2_t*)(in + 600); + *(vint32mf2_t*)(out + 600) = v; + } else { + vint32mf2_t v = *(vint32mf2_t*)(in + 700); + *(vint32mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint32mf2_t v = *(vint32mf2_t*)(in + 900 + i); + *(vint32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-10.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-10.c new file mode 100644 index 00000000000..51d3fcf7613 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-10.c @@ -0,0 +1,230 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint8mf8_t v = *(vint8mf8_t*)(in + 500); + *(vint8mf8_t*)(out + 500) = v; + break; + } + case 1:{ + vint8mf8_t v = *(vint8mf8_t*)(in + 500); + *(vint8mf8_t*)(out + 500) = v; + break; + } + default:{ + vint8mf8_t v = *(vint8mf8_t*)(in + 700); + *(vint8mf8_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf8_t v = *(vint8mf8_t*)(in + 900 + i); + *(vint8mf8_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint8mf4_t v = *(vint8mf4_t*)(in + 500); + *(vint8mf4_t*)(out + 500) = v; + break; + } + case 1:{ + vint8mf4_t v = *(vint8mf4_t*)(in + 500); + *(vint8mf4_t*)(out + 500) = v; + break; + } + default:{ + vint8mf4_t v = *(vint8mf4_t*)(in + 700); + *(vint8mf4_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf4_t v = *(vint8mf4_t*)(in + 900 + i); + *(vint8mf4_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint8mf2_t v = *(vint8mf2_t*)(in + 500); + *(vint8mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vint8mf2_t v = *(vint8mf2_t*)(in + 500); + *(vint8mf2_t*)(out + 500) = v; + break; + } + default:{ + vint8mf2_t v = *(vint8mf2_t*)(in + 700); + *(vint8mf2_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf2_t v = *(vint8mf2_t*)(in + 900 + i); + *(vint8mf2_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint16mf4_t v = *(vint16mf4_t*)(in + 500); + *(vint16mf4_t*)(out + 500) = v; + break; + } + case 1:{ + vint16mf4_t v = *(vint16mf4_t*)(in + 500); + *(vint16mf4_t*)(out + 500) = v; + break; + } + default:{ + vint16mf4_t v = *(vint16mf4_t*)(in + 700); + *(vint16mf4_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf4_t v = *(vint16mf4_t*)(in + 900 + i); + *(vint16mf4_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint16mf2_t v = *(vint16mf2_t*)(in + 500); + *(vint16mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vint16mf2_t v = *(vint16mf2_t*)(in + 500); + *(vint16mf2_t*)(out + 500) = v; + break; + } + default:{ + vint16mf2_t v = *(vint16mf2_t*)(in + 700); + *(vint16mf2_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf2_t v = *(vint16mf2_t*)(in + 900 + i); + *(vint16mf2_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vuint32mf2_t v = *(vuint32mf2_t*)(in + 500); + *(vuint32mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vuint32mf2_t v = *(vuint32mf2_t*)(in + 500); + *(vuint32mf2_t*)(out + 500) = v; + break; + } + default:{ + vuint32mf2_t v = *(vuint32mf2_t*)(in + 700); + *(vuint32mf2_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 900 + i); + *(vuint32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-11.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-11.c new file mode 100644 index 00000000000..3c2badd7793 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-11.c @@ -0,0 +1,43 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 500); + *(vfloat32mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 500); + *(vfloat32mf2_t*)(out + 500) = v; + break; + } + default:{ + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 700); + *(vfloat32mf2_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 900 + i); + *(vfloat32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-12.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-12.c new file mode 100644 index 00000000000..6ace4c4ef18 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-12.c @@ -0,0 +1,266 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool64_t v = *(vbool64_t*)(in + 500); + *(vbool64_t*)(out + 500) = v; + break; + } + case 1:{ + vbool64_t v = *(vbool64_t*)(in + 500); + *(vbool64_t*)(out + 500) = v; + break; + } + default:{ + vbool64_t v = *(vbool64_t*)(in + 700); + *(vbool64_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool64_t v = *(vbool64_t*)(in + 900 + i); + *(vbool64_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool32_t v = *(vbool32_t*)(in + 500); + *(vbool32_t*)(out + 500) = v; + break; + } + case 1:{ + vbool32_t v = *(vbool32_t*)(in + 500); + *(vbool32_t*)(out + 500) = v; + break; + } + default:{ + vbool32_t v = *(vbool32_t*)(in + 700); + *(vbool32_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool32_t v = *(vbool32_t*)(in + 900 + i); + *(vbool32_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool16_t v = *(vbool16_t*)(in + 500); + *(vbool16_t*)(out + 500) = v; + break; + } + case 1:{ + vbool16_t v = *(vbool16_t*)(in + 500); + *(vbool16_t*)(out + 500) = v; + break; + } + default:{ + vbool16_t v = *(vbool16_t*)(in + 700); + *(vbool16_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool16_t v = *(vbool16_t*)(in + 900 + i); + *(vbool16_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool8_t v = *(vbool8_t*)(in + 500); + *(vbool8_t*)(out + 500) = v; + break; + } + case 1:{ + vbool8_t v = *(vbool8_t*)(in + 500); + *(vbool8_t*)(out + 500) = v; + break; + } + default:{ + vbool8_t v = *(vbool8_t*)(in + 700); + *(vbool8_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool8_t v = *(vbool8_t*)(in + 900 + i); + *(vbool8_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool4_t v = *(vbool4_t*)(in + 500); + *(vbool4_t*)(out + 500) = v; + break; + } + case 1:{ + vbool4_t v = *(vbool4_t*)(in + 500); + *(vbool4_t*)(out + 500) = v; + break; + } + default:{ + vbool4_t v = *(vbool4_t*)(in + 700); + *(vbool4_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool4_t v = *(vbool4_t*)(in + 900 + i); + *(vbool4_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool2_t v = *(vbool2_t*)(in + 500); + *(vbool2_t*)(out + 500) = v; + break; + } + case 1:{ + vbool2_t v = *(vbool2_t*)(in + 500); + *(vbool2_t*)(out + 500) = v; + break; + } + default:{ + vbool2_t v = *(vbool2_t*)(in + 700); + *(vbool2_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool2_t v = *(vbool2_t*)(in + 900 + i); + *(vbool2_t*)(out + 900 + i) = v; + } +} + +void f7 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool1_t v = *(vbool1_t*)(in + 500); + *(vbool1_t*)(out + 500) = v; + break; + } + case 1:{ + vbool1_t v = *(vbool1_t*)(in + 500); + *(vbool1_t*)(out + 500) = v; + break; + } + default:{ + vbool1_t v = *(vbool1_t*)(in + 700); + *(vbool1_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool1_t v = *(vbool1_t*)(in + 900 + i); + *(vbool1_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m1,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" no-opts "-O1" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-13.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-13.c new file mode 100644 index 00000000000..8ce380bea07 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-13.c @@ -0,0 +1,221 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint8mf8_t v = *(vint8mf8_t*)(in + 500); + *(vint8mf8_t*)(out + 500) = v; + break; + } + case 1:{ + vint8mf8_t v = *(vint8mf8_t*)(in + 500); + *(vint8mf8_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf8_t v = *(vint8mf8_t*)(in + 900 + i); + *(vint8mf8_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint8mf4_t v = *(vint8mf4_t*)(in + 500); + *(vint8mf4_t*)(out + 500) = v; + break; + } + case 1:{ + vint8mf4_t v = *(vint8mf4_t*)(in + 500); + *(vint8mf4_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf4_t v = *(vint8mf4_t*)(in + 900 + i); + *(vint8mf4_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint8mf2_t v = *(vint8mf2_t*)(in + 500); + *(vint8mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vint8mf2_t v = *(vint8mf2_t*)(in + 500); + *(vint8mf2_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf2_t v = *(vint8mf2_t*)(in + 900 + i); + *(vint8mf2_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint16mf4_t v = *(vint16mf4_t*)(in + 500); + *(vint16mf4_t*)(out + 500) = v; + break; + } + case 1:{ + vint16mf4_t v = *(vint16mf4_t*)(in + 500); + *(vint16mf4_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf4_t v = *(vint16mf4_t*)(in + 900 + i); + *(vint16mf4_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint16mf2_t v = *(vint16mf2_t*)(in + 500); + *(vint16mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vint16mf2_t v = *(vint16mf2_t*)(in + 500); + *(vint16mf2_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf2_t v = *(vint16mf2_t*)(in + 900 + i); + *(vint16mf2_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint32mf2_t v = *(vint32mf2_t*)(in + 500); + *(vint32mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vint32mf2_t v = *(vint32mf2_t*)(in + 500); + *(vint32mf2_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint32mf2_t v = *(vint32mf2_t*)(in + 900 + i); + *(vint32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-14.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-14.c new file mode 100644 index 00000000000..a43aad71808 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-14.c @@ -0,0 +1,221 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vuint8mf8_t v = *(vuint8mf8_t*)(in + 500); + *(vuint8mf8_t*)(out + 500) = v; + break; + } + case 1:{ + vuint8mf8_t v = *(vuint8mf8_t*)(in + 500); + *(vuint8mf8_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 900 + i); + *(vuint8mf8_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vuint8mf4_t v = *(vuint8mf4_t*)(in + 500); + *(vuint8mf4_t*)(out + 500) = v; + break; + } + case 1:{ + vuint8mf4_t v = *(vuint8mf4_t*)(in + 500); + *(vuint8mf4_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 900 + i); + *(vuint8mf4_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vuint8mf2_t v = *(vuint8mf2_t*)(in + 500); + *(vuint8mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vuint8mf2_t v = *(vuint8mf2_t*)(in + 500); + *(vuint8mf2_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 900 + i); + *(vuint8mf2_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vuint16mf4_t v = *(vuint16mf4_t*)(in + 500); + *(vuint16mf4_t*)(out + 500) = v; + break; + } + case 1:{ + vuint16mf4_t v = *(vuint16mf4_t*)(in + 500); + *(vuint16mf4_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 900 + i); + *(vuint16mf4_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vuint16mf2_t v = *(vuint16mf2_t*)(in + 500); + *(vuint16mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vuint16mf2_t v = *(vuint16mf2_t*)(in + 500); + *(vuint16mf2_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 900 + i); + *(vuint16mf2_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vuint32mf2_t v = *(vuint32mf2_t*)(in + 500); + *(vuint32mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vuint32mf2_t v = *(vuint32mf2_t*)(in + 500); + *(vuint32mf2_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 900 + i); + *(vuint32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-15.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-15.c new file mode 100644 index 00000000000..6938cf80723 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-15.c @@ -0,0 +1,41 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 500); + *(vfloat32mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 500); + *(vfloat32mf2_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 900 + i); + *(vfloat32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-16.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-16.c new file mode 100644 index 00000000000..10901a0b205 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-16.c @@ -0,0 +1,257 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool64_t v = *(vbool64_t*)(in + 500); + *(vbool64_t*)(out + 500) = v; + break; + } + case 1:{ + vbool64_t v = *(vbool64_t*)(in + 500); + *(vbool64_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool64_t v = *(vbool64_t*)(in + 900 + i); + *(vbool64_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool32_t v = *(vbool32_t*)(in + 500); + *(vbool32_t*)(out + 500) = v; + break; + } + case 1:{ + vbool32_t v = *(vbool32_t*)(in + 500); + *(vbool32_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool32_t v = *(vbool32_t*)(in + 900 + i); + *(vbool32_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool16_t v = *(vbool16_t*)(in + 500); + *(vbool16_t*)(out + 500) = v; + break; + } + case 1:{ + vbool16_t v = *(vbool16_t*)(in + 500); + *(vbool16_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool16_t v = *(vbool16_t*)(in + 900 + i); + *(vbool16_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool8_t v = *(vbool8_t*)(in + 500); + *(vbool8_t*)(out + 500) = v; + break; + } + case 1:{ + vbool8_t v = *(vbool8_t*)(in + 500); + *(vbool8_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool8_t v = *(vbool8_t*)(in + 900 + i); + *(vbool8_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool4_t v = *(vbool4_t*)(in + 500); + *(vbool4_t*)(out + 500) = v; + break; + } + case 1:{ + vbool4_t v = *(vbool4_t*)(in + 500); + *(vbool4_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool4_t v = *(vbool4_t*)(in + 900 + i); + *(vbool4_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool2_t v = *(vbool2_t*)(in + 500); + *(vbool2_t*)(out + 500) = v; + break; + } + case 1:{ + vbool2_t v = *(vbool2_t*)(in + 500); + *(vbool2_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool2_t v = *(vbool2_t*)(in + 900 + i); + *(vbool2_t*)(out + 900 + i) = v; + } +} + +void f7 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vbool1_t v = *(vbool1_t*)(in + 500); + *(vbool1_t*)(out + 500) = v; + break; + } + case 1:{ + vbool1_t v = *(vbool1_t*)(in + 500); + *(vbool1_t*)(out + 500) = v; + break; + } + default:{ + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool1_t v = *(vbool1_t*)(in + 900 + i); + *(vbool1_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m1,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m1,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]\s+\.L[0-9][0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-17.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-17.c new file mode 100644 index 00000000000..01345617fab --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-17.c @@ -0,0 +1,177 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vint8mf8_t v = *(vint8mf8_t*)(in + 100); + *(vint8mf8_t*)(out + 100) = v; + } + else + { + vint8mf8_t v = *(vint8mf8_t*)(in + 200); + *(vint8mf8_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vint8mf8_t v = *(vint8mf8_t*)(in + i); + *(vint8mf8_t*)(out + i) = v; + } +} + +void f2 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vint8mf4_t v = *(vint8mf4_t*)(in + 100); + *(vint8mf4_t*)(out + 100) = v; + } + else + { + vint8mf4_t v = *(vint8mf4_t*)(in + 200); + *(vint8mf4_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vint8mf4_t v = *(vint8mf4_t*)(in + i); + *(vint8mf4_t*)(out + i) = v; + } +} + +void f3 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vint8mf2_t v = *(vint8mf2_t*)(in + 100); + *(vint8mf2_t*)(out + 100) = v; + } + else + { + vint8mf2_t v = *(vint8mf2_t*)(in + 200); + *(vint8mf2_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vint8mf2_t v = *(vint8mf2_t*)(in + i); + *(vint8mf2_t*)(out + i) = v; + } +} + +void f4 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vint16mf4_t v = *(vint16mf4_t*)(in + 100); + *(vint16mf4_t*)(out + 100) = v; + } + else + { + vint16mf4_t v = *(vint16mf4_t*)(in + 200); + *(vint16mf4_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vint16mf4_t v = *(vint16mf4_t*)(in + i); + *(vint16mf4_t*)(out + i) = v; + } +} + +void f5 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vint16mf2_t v = *(vint16mf2_t*)(in + 100); + *(vint16mf2_t*)(out + 100) = v; + } + else + { + vint16mf2_t v = *(vint16mf2_t*)(in + 200); + *(vint16mf2_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vint16mf2_t v = *(vint16mf2_t*)(in + i); + *(vint16mf2_t*)(out + i) = v; + } +} + +void f6 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vint32mf2_t v = *(vint32mf2_t*)(in + 100); + *(vint32mf2_t*)(out + 100) = v; + } + else + { + vint32mf2_t v = *(vint32mf2_t*)(in + 200); + *(vint32mf2_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vint32mf2_t v = *(vint32mf2_t*)(in + i); + *(vint32mf2_t*)(out + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-18.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-18.c new file mode 100644 index 00000000000..c296670e2d5 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-18.c @@ -0,0 +1,177 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 100); + *(vuint8mf8_t*)(out + 100) = v; + } + else + { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 200); + *(vuint8mf8_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vuint8mf8_t v = *(vuint8mf8_t*)(in + i); + *(vuint8mf8_t*)(out + i) = v; + } +} + +void f2 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 100); + *(vuint8mf4_t*)(out + 100) = v; + } + else + { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 200); + *(vuint8mf4_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vuint8mf4_t v = *(vuint8mf4_t*)(in + i); + *(vuint8mf4_t*)(out + i) = v; + } +} + +void f3 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 100); + *(vuint8mf2_t*)(out + 100) = v; + } + else + { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 200); + *(vuint8mf2_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vuint8mf2_t v = *(vuint8mf2_t*)(in + i); + *(vuint8mf2_t*)(out + i) = v; + } +} + +void f4 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 100); + *(vuint16mf4_t*)(out + 100) = v; + } + else + { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 200); + *(vuint16mf4_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vuint16mf4_t v = *(vuint16mf4_t*)(in + i); + *(vuint16mf4_t*)(out + i) = v; + } +} + +void f5 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 100); + *(vuint16mf2_t*)(out + 100) = v; + } + else + { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 200); + *(vuint16mf2_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vuint16mf2_t v = *(vuint16mf2_t*)(in + i); + *(vuint16mf2_t*)(out + i) = v; + } +} + +void f6 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 100); + *(vuint32mf2_t*)(out + 100) = v; + } + else + { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 200); + *(vuint32mf2_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vuint32mf2_t v = *(vuint32mf2_t*)(in + i); + *(vuint32mf2_t*)(out + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-19.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-19.c new file mode 100644 index 00000000000..d87b2381daf --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-19.c @@ -0,0 +1,34 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f6 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 100); + *(vfloat32mf2_t*)(out + 100) = v; + } + else + { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 200); + *(vfloat32mf2_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + i); + *(vfloat32mf2_t*)(out + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-2.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-2.c new file mode 100644 index 00000000000..ce94f4a12b2 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-2.c @@ -0,0 +1,182 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 500); + *(vuint8mf8_t*)(out + 500) = v; + } else if (n == 1) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 600); + *(vuint8mf8_t*)(out + 600) = v; + } else { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 700); + *(vuint8mf8_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 900 + i); + *(vuint8mf8_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 500); + *(vuint8mf4_t*)(out + 500) = v; + } else if (n == 1) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 600); + *(vuint8mf4_t*)(out + 600) = v; + } else { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 700); + *(vuint8mf4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 900 + i); + *(vuint8mf4_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 500); + *(vuint8mf2_t*)(out + 500) = v; + } else if (n == 1) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 600); + *(vuint8mf2_t*)(out + 600) = v; + } else { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 700); + *(vuint8mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 900 + i); + *(vuint8mf2_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 500); + *(vuint16mf4_t*)(out + 500) = v; + } else if (n == 1) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 600); + *(vuint16mf4_t*)(out + 600) = v; + } else { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 700); + *(vuint16mf4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 900 + i); + *(vuint16mf4_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 500); + *(vuint16mf2_t*)(out + 500) = v; + } else if (n == 1) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 600); + *(vuint16mf2_t*)(out + 600) = v; + } else { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 700); + *(vuint16mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 900 + i); + *(vuint16mf2_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 500); + *(vuint32mf2_t*)(out + 500) = v; + } else if (n == 1) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 600); + *(vuint32mf2_t*)(out + 600) = v; + } else { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 700); + *(vuint32mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 900 + i); + *(vuint32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" no-opts "-O1" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-20.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-20.c new file mode 100644 index 00000000000..273a2853282 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-20.c @@ -0,0 +1,203 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool64_t v = *(vbool64_t*)(in + 100); + *(vbool64_t*)(out + 100) = v; + } + else + { + vbool64_t v = *(vbool64_t*)(in + 200); + *(vbool64_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vbool64_t v = *(vbool64_t*)(in + i); + *(vbool64_t*)(out + i) = v; + } +} + +void f2 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool32_t v = *(vbool32_t*)(in + 100); + *(vbool32_t*)(out + 100) = v; + } + else + { + vbool32_t v = *(vbool32_t*)(in + 200); + *(vbool32_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vbool32_t v = *(vbool32_t*)(in + i); + *(vbool32_t*)(out + i) = v; + } +} + +void f3 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool16_t v = *(vbool16_t*)(in + 100); + *(vbool16_t*)(out + 100) = v; + } + else + { + vbool16_t v = *(vbool16_t*)(in + 200); + *(vbool16_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vbool16_t v = *(vbool16_t*)(in + i); + *(vbool16_t*)(out + i) = v; + } +} + +void f4 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool8_t v = *(vbool8_t*)(in + 100); + *(vbool8_t*)(out + 100) = v; + } + else + { + vbool8_t v = *(vbool8_t*)(in + 200); + *(vbool8_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vbool8_t v = *(vbool8_t*)(in + i); + *(vbool8_t*)(out + i) = v; + } +} + +void f5 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool4_t v = *(vbool4_t*)(in + 100); + *(vbool4_t*)(out + 100) = v; + } + else + { + vbool4_t v = *(vbool4_t*)(in + 200); + *(vbool4_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vbool4_t v = *(vbool4_t*)(in + i); + *(vbool4_t*)(out + i) = v; + } +} + +void f6 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool2_t v = *(vbool2_t*)(in + 100); + *(vbool2_t*)(out + 100) = v; + } + else + { + vbool2_t v = *(vbool2_t*)(in + 200); + *(vbool2_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vbool2_t v = *(vbool2_t*)(in + i); + *(vbool2_t*)(out + i) = v; + } +} + +void f7 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool1_t v = *(vbool1_t*)(in + 100); + *(vbool1_t*)(out + 100) = v; + } + else + { + vbool1_t v = *(vbool1_t*)(in + 200); + *(vbool1_t*)(out + 200) = v; + if (cond == 2) + { + out[1000] = 8000; + } + else + { + out[2000] = 9000; + } + } + for (int i = 0; i < n; i++) + { + vbool1_t v = *(vbool1_t*)(in + i); + *(vbool1_t*)(out + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m1,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m4,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 6 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-21.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-21.c new file mode 100644 index 00000000000..25ae317364b --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-21.c @@ -0,0 +1,155 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vint8mf8_t v = *(vint8mf8_t*)(in + 100); + *(vint8mf8_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vint8mf8_t v = *(vint8mf8_t*)(in + 200); + *(vint8mf8_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vint8mf8_t v = *(vint8mf8_t*)(in + i); + *(vint8mf8_t*)(out + i) = v; + } +} + +void f2 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vint8mf4_t v = *(vint8mf4_t*)(in + 100); + *(vint8mf4_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vint8mf4_t v = *(vint8mf4_t*)(in + 200); + *(vint8mf4_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vint8mf4_t v = *(vint8mf4_t*)(in + i); + *(vint8mf4_t*)(out + i) = v; + } +} + +void f3 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vint8mf2_t v = *(vint8mf2_t*)(in + 100); + *(vint8mf2_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vint8mf2_t v = *(vint8mf2_t*)(in + 200); + *(vint8mf2_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vint8mf2_t v = *(vint8mf2_t*)(in + i); + *(vint8mf2_t*)(out + i) = v; + } +} + +void f4 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vint16mf4_t v = *(vint16mf4_t*)(in + 100); + *(vint16mf4_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vint16mf4_t v = *(vint16mf4_t*)(in + 200); + *(vint16mf4_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vint16mf4_t v = *(vint16mf4_t*)(in + i); + *(vint16mf4_t*)(out + i) = v; + } +} + +void f5 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vint16mf2_t v = *(vint16mf2_t*)(in + 100); + *(vint16mf2_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vint16mf2_t v = *(vint16mf2_t*)(in + 200); + *(vint16mf2_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vint16mf2_t v = *(vint16mf2_t*)(in + i); + *(vint16mf2_t*)(out + i) = v; + } +} + +void f6 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vint32mf2_t v = *(vint32mf2_t*)(in + 100); + *(vint32mf2_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vint32mf2_t v = *(vint32mf2_t*)(in + 200); + *(vint32mf2_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vint32mf2_t v = *(vint32mf2_t*)(in + i); + *(vint32mf2_t*)(out + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-22.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-22.c new file mode 100644 index 00000000000..ecf68f24b4d --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-22.c @@ -0,0 +1,155 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 100); + *(vuint8mf8_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 200); + *(vuint8mf8_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vuint8mf8_t v = *(vuint8mf8_t*)(in + i); + *(vuint8mf8_t*)(out + i) = v; + } +} + +void f2 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 100); + *(vuint8mf4_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 200); + *(vuint8mf4_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vuint8mf4_t v = *(vuint8mf4_t*)(in + i); + *(vuint8mf4_t*)(out + i) = v; + } +} + +void f3 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 100); + *(vuint8mf2_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 200); + *(vuint8mf2_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vuint8mf2_t v = *(vuint8mf2_t*)(in + i); + *(vuint8mf2_t*)(out + i) = v; + } +} + +void f4 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 100); + *(vuint16mf4_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 200); + *(vuint16mf4_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vuint16mf4_t v = *(vuint16mf4_t*)(in + i); + *(vuint16mf4_t*)(out + i) = v; + } +} + +void f5 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 100); + *(vuint16mf2_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 200); + *(vuint16mf2_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vuint16mf2_t v = *(vuint16mf2_t*)(in + i); + *(vuint16mf2_t*)(out + i) = v; + } +} + +void f6 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 100); + *(vuint32mf2_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 200); + *(vuint32mf2_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vuint32mf2_t v = *(vuint32mf2_t*)(in + i); + *(vuint32mf2_t*)(out + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-23.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-23.c new file mode 100644 index 00000000000..87ae0f59684 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-23.c @@ -0,0 +1,30 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 100); + *(vuint32mf2_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 200); + *(vuint32mf2_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vuint32mf2_t v = *(vuint32mf2_t*)(in + i); + *(vuint32mf2_t*)(out + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-24.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-24.c new file mode 100644 index 00000000000..b87c64bcef1 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-24.c @@ -0,0 +1,180 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool64_t v = *(vbool64_t*)(in + 100); + *(vbool64_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vbool64_t v = *(vbool64_t*)(in + 200); + *(vbool64_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vbool64_t v = *(vbool64_t*)(in + i); + *(vbool64_t*)(out + i) = v; + } +} + +void f2 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool32_t v = *(vbool32_t*)(in + 100); + *(vbool32_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vbool32_t v = *(vbool32_t*)(in + 200); + *(vbool32_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vbool32_t v = *(vbool32_t*)(in + i); + *(vbool32_t*)(out + i) = v; + } +} + +void f3 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool16_t v = *(vbool16_t*)(in + 100); + *(vbool16_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vbool16_t v = *(vbool16_t*)(in + 200); + *(vbool16_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vbool16_t v = *(vbool16_t*)(in + i); + *(vbool16_t*)(out + i) = v; + } +} + +void f4 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool8_t v = *(vbool8_t*)(in + 100); + *(vbool8_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vbool8_t v = *(vbool8_t*)(in + 200); + *(vbool8_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vbool8_t v = *(vbool8_t*)(in + i); + *(vbool8_t*)(out + i) = v; + } +} + +void f5 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool4_t v = *(vbool4_t*)(in + 100); + *(vbool4_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vbool4_t v = *(vbool4_t*)(in + 200); + *(vbool4_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vbool4_t v = *(vbool4_t*)(in + i); + *(vbool4_t*)(out + i) = v; + } +} + +void f6 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool2_t v = *(vbool2_t*)(in + 100); + *(vbool2_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vbool2_t v = *(vbool2_t*)(in + 200); + *(vbool2_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vbool2_t v = *(vbool2_t*)(in + i); + *(vbool2_t*)(out + i) = v; + } +} + +void f7 (int * restrict in, int * restrict out, int n, int cond) +{ + if (cond == 1) + { + vbool1_t v = *(vbool1_t*)(in + 100); + *(vbool1_t*)(out + 100) = v; + } + else + { + if (cond == 2) + { + vbool1_t v = *(vbool1_t*)(in + 200); + *(vbool1_t*)(out + 200) = v; + out[1000] = 8000; + } + } + for (int i = 0; i < n; i++) + { + vbool1_t v = *(vbool1_t*)(in + i); + *(vbool1_t*)(out + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m1,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m1,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-25.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-25.c new file mode 100644 index 00000000000..a3ed7d82a19 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-25.c @@ -0,0 +1,572 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool64_t v = *(vbool64_t*)(in + 500); + *(vbool64_t*)(out + 500) = v; + } else if (n == 1) { + vbool64_t v = *(vbool64_t*)(in + 600); + *(vbool64_t*)(out + 600) = v; + } else { + vbool64_t v = *(vbool64_t*)(in + 700); + *(vbool64_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool64_t v = *(vbool64_t*)(in + 900 + i); + *(vbool64_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vbool64_t v = *(vbool64_t*)(in + 500); + *(vbool64_t*)(out + 500) = v; + } else if (n == 1) { + vbool64_t v = *(vbool64_t*)(in + 600); + *(vbool64_t*)(out + 600) = v; + } else { + vbool64_t v = *(vbool64_t*)(in + 700); + *(vbool64_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool64_t v = *(vbool64_t*)(in + 900 + i); + *(vbool64_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool32_t v = *(vbool32_t*)(in + 500); + *(vbool32_t*)(out + 500) = v; + } else if (n == 1) { + vbool32_t v = *(vbool32_t*)(in + 600); + *(vbool32_t*)(out + 600) = v; + } else { + vbool32_t v = *(vbool32_t*)(in + 700); + *(vbool32_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool32_t v = *(vbool32_t*)(in + 900 + i); + *(vbool32_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vbool32_t v = *(vbool32_t*)(in + 500); + *(vbool32_t*)(out + 500) = v; + } else if (n == 1) { + vbool32_t v = *(vbool32_t*)(in + 600); + *(vbool32_t*)(out + 600) = v; + } else { + vbool32_t v = *(vbool32_t*)(in + 700); + *(vbool32_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool32_t v = *(vbool32_t*)(in + 900 + i); + *(vbool32_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool16_t v = *(vbool16_t*)(in + 500); + *(vbool16_t*)(out + 500) = v; + } else if (n == 1) { + vbool16_t v = *(vbool16_t*)(in + 600); + *(vbool16_t*)(out + 600) = v; + } else { + vbool16_t v = *(vbool16_t*)(in + 700); + *(vbool16_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool16_t v = *(vbool16_t*)(in + 900 + i); + *(vbool16_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vbool16_t v = *(vbool16_t*)(in + 500); + *(vbool16_t*)(out + 500) = v; + } else if (n == 1) { + vbool16_t v = *(vbool16_t*)(in + 600); + *(vbool16_t*)(out + 600) = v; + } else { + vbool16_t v = *(vbool16_t*)(in + 700); + *(vbool16_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool16_t v = *(vbool16_t*)(in + 900 + i); + *(vbool16_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool8_t v = *(vbool8_t*)(in + 500); + *(vbool8_t*)(out + 500) = v; + } else if (n == 1) { + vbool8_t v = *(vbool8_t*)(in + 600); + *(vbool8_t*)(out + 600) = v; + } else { + vbool8_t v = *(vbool8_t*)(in + 700); + *(vbool8_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool8_t v = *(vbool8_t*)(in + 900 + i); + *(vbool8_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vbool8_t v = *(vbool8_t*)(in + 500); + *(vbool8_t*)(out + 500) = v; + } else if (n == 1) { + vbool8_t v = *(vbool8_t*)(in + 600); + *(vbool8_t*)(out + 600) = v; + } else { + vbool8_t v = *(vbool8_t*)(in + 700); + *(vbool8_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool8_t v = *(vbool8_t*)(in + 900 + i); + *(vbool8_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool4_t v = *(vbool4_t*)(in + 500); + *(vbool4_t*)(out + 500) = v; + } else if (n == 1) { + vbool4_t v = *(vbool4_t*)(in + 600); + *(vbool4_t*)(out + 600) = v; + } else { + vbool4_t v = *(vbool4_t*)(in + 700); + *(vbool4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool4_t v = *(vbool4_t*)(in + 900 + i); + *(vbool4_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vbool4_t v = *(vbool4_t*)(in + 500); + *(vbool4_t*)(out + 500) = v; + } else if (n == 1) { + vbool4_t v = *(vbool4_t*)(in + 600); + *(vbool4_t*)(out + 600) = v; + } else { + vbool4_t v = *(vbool4_t*)(in + 700); + *(vbool4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool4_t v = *(vbool4_t*)(in + 900 + i); + *(vbool4_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool2_t v = *(vbool2_t*)(in + 500); + *(vbool2_t*)(out + 500) = v; + } else if (n == 1) { + vbool2_t v = *(vbool2_t*)(in + 600); + *(vbool2_t*)(out + 600) = v; + } else { + vbool2_t v = *(vbool2_t*)(in + 700); + *(vbool2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool2_t v = *(vbool2_t*)(in + 900 + i); + *(vbool2_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vbool2_t v = *(vbool2_t*)(in + 500); + *(vbool2_t*)(out + 500) = v; + } else if (n == 1) { + vbool2_t v = *(vbool2_t*)(in + 600); + *(vbool2_t*)(out + 600) = v; + } else { + vbool2_t v = *(vbool2_t*)(in + 700); + *(vbool2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool2_t v = *(vbool2_t*)(in + 900 + i); + *(vbool2_t*)(out + 900 + i) = v; + } +} + +void f7 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool1_t v = *(vbool1_t*)(in + 500); + *(vbool1_t*)(out + 500) = v; + } else if (n == 1) { + vbool1_t v = *(vbool1_t*)(in + 600); + *(vbool1_t*)(out + 600) = v; + } else { + vbool1_t v = *(vbool1_t*)(in + 700); + *(vbool1_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool1_t v = *(vbool1_t*)(in + 900 + i); + *(vbool1_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vbool1_t v = *(vbool1_t*)(in + 500); + *(vbool1_t*)(out + 500) = v; + } else if (n == 1) { + vbool1_t v = *(vbool1_t*)(in + 600); + *(vbool1_t*)(out + 600) = v; + } else { + vbool1_t v = *(vbool1_t*)(in + 700); + *(vbool1_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool1_t v = *(vbool1_t*)(in + 900 + i); + *(vbool1_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m1,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m4,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-26.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-26.c new file mode 100644 index 00000000000..ae6fa93bdfb --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-26.c @@ -0,0 +1,492 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint8mf8_t v = *(vint8mf8_t*)(in + 500); + *(vint8mf8_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf8_t v = *(vint8mf8_t*)(in + 600); + *(vint8mf8_t*)(out + 600) = v; + } else { + vint8mf8_t v = *(vint8mf8_t*)(in + 700); + *(vint8mf8_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf8_t v = *(vint8mf8_t*)(in + 900 + i); + *(vint8mf8_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vint8mf8_t v = *(vint8mf8_t*)(in + 500); + *(vint8mf8_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf8_t v = *(vint8mf8_t*)(in + 600); + *(vint8mf8_t*)(out + 600) = v; + } else { + vint8mf8_t v = *(vint8mf8_t*)(in + 700); + *(vint8mf8_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf8_t v = *(vint8mf8_t*)(in + 900 + i); + *(vint8mf8_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint8mf4_t v = *(vint8mf4_t*)(in + 500); + *(vint8mf4_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf4_t v = *(vint8mf4_t*)(in + 600); + *(vint8mf4_t*)(out + 600) = v; + } else { + vint8mf4_t v = *(vint8mf4_t*)(in + 700); + *(vint8mf4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf4_t v = *(vint8mf4_t*)(in + 900 + i); + *(vint8mf4_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vint8mf4_t v = *(vint8mf4_t*)(in + 500); + *(vint8mf4_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf4_t v = *(vint8mf4_t*)(in + 600); + *(vint8mf4_t*)(out + 600) = v; + } else { + vint8mf4_t v = *(vint8mf4_t*)(in + 700); + *(vint8mf4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf4_t v = *(vint8mf4_t*)(in + 900 + i); + *(vint8mf4_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint8mf2_t v = *(vint8mf2_t*)(in + 500); + *(vint8mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf2_t v = *(vint8mf2_t*)(in + 600); + *(vint8mf2_t*)(out + 600) = v; + } else { + vint8mf2_t v = *(vint8mf2_t*)(in + 700); + *(vint8mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf2_t v = *(vint8mf2_t*)(in + 900 + i); + *(vint8mf2_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vint8mf2_t v = *(vint8mf2_t*)(in + 500); + *(vint8mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf2_t v = *(vint8mf2_t*)(in + 600); + *(vint8mf2_t*)(out + 600) = v; + } else { + vint8mf2_t v = *(vint8mf2_t*)(in + 700); + *(vint8mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf2_t v = *(vint8mf2_t*)(in + 900 + i); + *(vint8mf2_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint16mf4_t v = *(vint16mf4_t*)(in + 500); + *(vint16mf4_t*)(out + 500) = v; + } else if (n == 1) { + vint16mf4_t v = *(vint16mf4_t*)(in + 600); + *(vint16mf4_t*)(out + 600) = v; + } else { + vint16mf4_t v = *(vint16mf4_t*)(in + 700); + *(vint16mf4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf4_t v = *(vint16mf4_t*)(in + 900 + i); + *(vint16mf4_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vint16mf4_t v = *(vint16mf4_t*)(in + 500); + *(vint16mf4_t*)(out + 500) = v; + } else if (n == 1) { + vint16mf4_t v = *(vint16mf4_t*)(in + 600); + *(vint16mf4_t*)(out + 600) = v; + } else { + vint16mf4_t v = *(vint16mf4_t*)(in + 700); + *(vint16mf4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf4_t v = *(vint16mf4_t*)(in + 900 + i); + *(vint16mf4_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint16mf2_t v = *(vint16mf2_t*)(in + 500); + *(vint16mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint16mf2_t v = *(vint16mf2_t*)(in + 600); + *(vint16mf2_t*)(out + 600) = v; + } else { + vint16mf2_t v = *(vint16mf2_t*)(in + 700); + *(vint16mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf2_t v = *(vint16mf2_t*)(in + 900 + i); + *(vint16mf2_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vint16mf2_t v = *(vint16mf2_t*)(in + 500); + *(vint16mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint16mf2_t v = *(vint16mf2_t*)(in + 600); + *(vint16mf2_t*)(out + 600) = v; + } else { + vint16mf2_t v = *(vint16mf2_t*)(in + 700); + *(vint16mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf2_t v = *(vint16mf2_t*)(in + 900 + i); + *(vint16mf2_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint32mf2_t v = *(vint32mf2_t*)(in + 500); + *(vint32mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint32mf2_t v = *(vint32mf2_t*)(in + 600); + *(vint32mf2_t*)(out + 600) = v; + } else { + vint32mf2_t v = *(vint32mf2_t*)(in + 700); + *(vint32mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint32mf2_t v = *(vint32mf2_t*)(in + 900 + i); + *(vint32mf2_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vint32mf2_t v = *(vint32mf2_t*)(in + 500); + *(vint32mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint32mf2_t v = *(vint32mf2_t*)(in + 600); + *(vint32mf2_t*)(out + 600) = v; + } else { + vint32mf2_t v = *(vint32mf2_t*)(in + 700); + *(vint32mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint32mf2_t v = *(vint32mf2_t*)(in + 900 + i); + *(vint32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ + diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-27.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-27.c new file mode 100644 index 00000000000..e0495653047 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-27.c @@ -0,0 +1,491 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 500); + *(vuint8mf8_t*)(out + 500) = v; + } else if (n == 1) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 600); + *(vuint8mf8_t*)(out + 600) = v; + } else { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 700); + *(vuint8mf8_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 900 + i); + *(vuint8mf8_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 500); + *(vuint8mf8_t*)(out + 500) = v; + } else if (n == 1) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 600); + *(vuint8mf8_t*)(out + 600) = v; + } else { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 700); + *(vuint8mf8_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 900 + i); + *(vuint8mf8_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 500); + *(vuint8mf4_t*)(out + 500) = v; + } else if (n == 1) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 600); + *(vuint8mf4_t*)(out + 600) = v; + } else { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 700); + *(vuint8mf4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 900 + i); + *(vuint8mf4_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 500); + *(vuint8mf4_t*)(out + 500) = v; + } else if (n == 1) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 600); + *(vuint8mf4_t*)(out + 600) = v; + } else { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 700); + *(vuint8mf4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 900 + i); + *(vuint8mf4_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 500); + *(vuint8mf2_t*)(out + 500) = v; + } else if (n == 1) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 600); + *(vuint8mf2_t*)(out + 600) = v; + } else { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 700); + *(vuint8mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 900 + i); + *(vuint8mf2_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 500); + *(vuint8mf2_t*)(out + 500) = v; + } else if (n == 1) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 600); + *(vuint8mf2_t*)(out + 600) = v; + } else { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 700); + *(vuint8mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 900 + i); + *(vuint8mf2_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 500); + *(vuint16mf4_t*)(out + 500) = v; + } else if (n == 1) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 600); + *(vuint16mf4_t*)(out + 600) = v; + } else { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 700); + *(vuint16mf4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 900 + i); + *(vuint16mf4_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 500); + *(vuint16mf4_t*)(out + 500) = v; + } else if (n == 1) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 600); + *(vuint16mf4_t*)(out + 600) = v; + } else { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 700); + *(vuint16mf4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 900 + i); + *(vuint16mf4_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 500); + *(vuint16mf2_t*)(out + 500) = v; + } else if (n == 1) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 600); + *(vuint16mf2_t*)(out + 600) = v; + } else { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 700); + *(vuint16mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 900 + i); + *(vuint16mf2_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 500); + *(vuint16mf2_t*)(out + 500) = v; + } else if (n == 1) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 600); + *(vuint16mf2_t*)(out + 600) = v; + } else { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 700); + *(vuint16mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 900 + i); + *(vuint16mf2_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 500); + *(vuint32mf2_t*)(out + 500) = v; + } else if (n == 1) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 600); + *(vuint32mf2_t*)(out + 600) = v; + } else { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 700); + *(vuint32mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 900 + i); + *(vuint32mf2_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 500); + *(vuint32mf2_t*)(out + 500) = v; + } else if (n == 1) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 600); + *(vuint32mf2_t*)(out + 600) = v; + } else { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 700); + *(vuint32mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 900 + i); + *(vuint32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-28.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-28.c new file mode 100644 index 00000000000..c64572ec911 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-28.c @@ -0,0 +1,86 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 500); + *(vfloat32mf2_t*)(out + 500) = v; + } else if (n == 1) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 600); + *(vfloat32mf2_t*)(out + 600) = v; + } else { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 700); + *(vfloat32mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 900 + i); + *(vfloat32mf2_t*)(out + 900 + i) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + if (n == 0) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 500); + *(vfloat32mf2_t*)(out + 500) = v; + } else if (n == 1) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 600); + *(vfloat32mf2_t*)(out + 600) = v; + } else { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 700); + *(vfloat32mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 900 + i); + *(vfloat32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-3.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-3.c new file mode 100644 index 00000000000..b52cae3bb51 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-3.c @@ -0,0 +1,35 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 500); + *(vfloat32mf2_t*)(out + 500) = v; + } else if (n == 1) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 600); + *(vfloat32mf2_t*)(out + 600) = v; + } else { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 700); + *(vfloat32mf2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 900 + i); + *(vfloat32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-4.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-4.c new file mode 100644 index 00000000000..c61d38e1476 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-4.c @@ -0,0 +1,210 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool64_t v = *(vbool64_t*)(in + 500); + *(vbool64_t*)(out + 500) = v; + } else if (n == 1) { + vbool64_t v = *(vbool64_t*)(in + 600); + *(vbool64_t*)(out + 600) = v; + } else { + vbool64_t v = *(vbool64_t*)(in + 700); + *(vbool64_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool64_t v = *(vbool64_t*)(in + 900 + i); + *(vbool64_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool32_t v = *(vbool32_t*)(in + 500); + *(vbool32_t*)(out + 500) = v; + } else if (n == 1) { + vbool32_t v = *(vbool32_t*)(in + 600); + *(vbool32_t*)(out + 600) = v; + } else { + vbool32_t v = *(vbool32_t*)(in + 700); + *(vbool32_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool32_t v = *(vbool32_t*)(in + 900 + i); + *(vbool32_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool16_t v = *(vbool16_t*)(in + 500); + *(vbool16_t*)(out + 500) = v; + } else if (n == 1) { + vbool16_t v = *(vbool16_t*)(in + 600); + *(vbool16_t*)(out + 600) = v; + } else { + vbool16_t v = *(vbool16_t*)(in + 700); + *(vbool16_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool16_t v = *(vbool16_t*)(in + 900 + i); + *(vbool16_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool8_t v = *(vbool8_t*)(in + 500); + *(vbool8_t*)(out + 500) = v; + } else if (n == 1) { + vbool8_t v = *(vbool8_t*)(in + 600); + *(vbool8_t*)(out + 600) = v; + } else { + vbool8_t v = *(vbool8_t*)(in + 700); + *(vbool8_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool8_t v = *(vbool8_t*)(in + 900 + i); + *(vbool8_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool4_t v = *(vbool4_t*)(in + 500); + *(vbool4_t*)(out + 500) = v; + } else if (n == 1) { + vbool4_t v = *(vbool4_t*)(in + 600); + *(vbool4_t*)(out + 600) = v; + } else { + vbool4_t v = *(vbool4_t*)(in + 700); + *(vbool4_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool4_t v = *(vbool4_t*)(in + 900 + i); + *(vbool4_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool2_t v = *(vbool2_t*)(in + 500); + *(vbool2_t*)(out + 500) = v; + } else if (n == 1) { + vbool2_t v = *(vbool2_t*)(in + 600); + *(vbool2_t*)(out + 600) = v; + } else { + vbool2_t v = *(vbool2_t*)(in + 700); + *(vbool2_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool2_t v = *(vbool2_t*)(in + 900 + i); + *(vbool2_t*)(out + 900 + i) = v; + } +} + +void f7 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool1_t v = *(vbool1_t*)(in + 500); + *(vbool1_t*)(out + 500) = v; + } else if (n == 1) { + vbool1_t v = *(vbool1_t*)(in + 600); + *(vbool1_t*)(out + 600) = v; + } else { + vbool1_t v = *(vbool1_t*)(in + 700); + *(vbool1_t*)(out + 700) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool1_t v = *(vbool1_t*)(in + 900 + i); + *(vbool1_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m1,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 6 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O2" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-5.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-5.c new file mode 100644 index 00000000000..f59b4eeacb1 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-5.c @@ -0,0 +1,167 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint8mf8_t v = *(vint8mf8_t*)(in + 500); + *(vint8mf8_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf8_t v = *(vint8mf8_t*)(in + 600); + *(vint8mf8_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf8_t v = *(vint8mf8_t*)(in + 900 + i); + *(vint8mf8_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint8mf4_t v = *(vint8mf4_t*)(in + 500); + *(vint8mf4_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf4_t v = *(vint8mf4_t*)(in + 600); + *(vint8mf4_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf4_t v = *(vint8mf4_t*)(in + 900 + i); + *(vint8mf4_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint8mf2_t v = *(vint8mf2_t*)(in + 500); + *(vint8mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf2_t v = *(vint8mf2_t*)(in + 600); + *(vint8mf2_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf2_t v = *(vint8mf2_t*)(in + 900 + i); + *(vint8mf2_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint16mf4_t v = *(vint16mf4_t*)(in + 500); + *(vint16mf4_t*)(out + 500) = v; + } else if (n == 1) { + vint16mf4_t v = *(vint16mf4_t*)(in + 600); + *(vint16mf4_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf4_t v = *(vint16mf4_t*)(in + 900 + i); + *(vint16mf4_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint16mf2_t v = *(vint16mf2_t*)(in + 500); + *(vint16mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint16mf2_t v = *(vint16mf2_t*)(in + 600); + *(vint16mf2_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf2_t v = *(vint16mf2_t*)(in + 900 + i); + *(vint16mf2_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint32mf2_t v = *(vint32mf2_t*)(in + 500); + *(vint32mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint32mf2_t v = *(vint32mf2_t*)(in + 600); + *(vint32mf2_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint32mf2_t v = *(vint32mf2_t*)(in + 900 + i); + *(vint32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-6.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-6.c new file mode 100644 index 00000000000..ac9ae26184a --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-6.c @@ -0,0 +1,167 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint8mf8_t v = *(vint8mf8_t*)(in + 500); + *(vint8mf8_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf8_t v = *(vint8mf8_t*)(in + 600); + *(vint8mf8_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf8_t v = *(vint8mf8_t*)(in + 900 + i); + *(vint8mf8_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint8mf4_t v = *(vint8mf4_t*)(in + 500); + *(vint8mf4_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf4_t v = *(vint8mf4_t*)(in + 600); + *(vint8mf4_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf4_t v = *(vint8mf4_t*)(in + 900 + i); + *(vint8mf4_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint8mf2_t v = *(vint8mf2_t*)(in + 500); + *(vint8mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint8mf2_t v = *(vint8mf2_t*)(in + 600); + *(vint8mf2_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf2_t v = *(vint8mf2_t*)(in + 900 + i); + *(vint8mf2_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint16mf4_t v = *(vint16mf4_t*)(in + 500); + *(vint16mf4_t*)(out + 500) = v; + } else if (n == 1) { + vint16mf4_t v = *(vint16mf4_t*)(in + 600); + *(vint16mf4_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf4_t v = *(vint16mf4_t*)(in + 900 + i); + *(vint16mf4_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vint16mf2_t v = *(vint16mf2_t*)(in + 500); + *(vint16mf2_t*)(out + 500) = v; + } else if (n == 1) { + vint16mf2_t v = *(vint16mf2_t*)(in + 600); + *(vint16mf2_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf2_t v = *(vint16mf2_t*)(in + 900 + i); + *(vint16mf2_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 500); + *(vuint32mf2_t*)(out + 500) = v; + } else if (n == 1) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 600); + *(vuint32mf2_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 900 + i); + *(vuint32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-7.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-7.c new file mode 100644 index 00000000000..832404d49cd --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-7.c @@ -0,0 +1,32 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 500); + *(vfloat32mf2_t*)(out + 500) = v; + } else if (n == 1) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 600); + *(vfloat32mf2_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 900 + i); + *(vfloat32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-8.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-8.c new file mode 100644 index 00000000000..6f29253b3b7 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-8.c @@ -0,0 +1,194 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool64_t v = *(vbool64_t*)(in + 500); + *(vbool64_t*)(out + 500) = v; + } else if (n == 1) { + vbool64_t v = *(vbool64_t*)(in + 600); + *(vbool64_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool64_t v = *(vbool64_t*)(in + 900 + i); + *(vbool64_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool32_t v = *(vbool32_t*)(in + 500); + *(vbool32_t*)(out + 500) = v; + } else if (n == 1) { + vbool32_t v = *(vbool32_t*)(in + 600); + *(vbool32_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool32_t v = *(vbool32_t*)(in + 900 + i); + *(vbool32_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool16_t v = *(vbool16_t*)(in + 500); + *(vbool16_t*)(out + 500) = v; + } else if (n == 1) { + vbool16_t v = *(vbool16_t*)(in + 600); + *(vbool16_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool16_t v = *(vbool16_t*)(in + 900 + i); + *(vbool16_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool8_t v = *(vbool8_t*)(in + 500); + *(vbool8_t*)(out + 500) = v; + } else if (n == 1) { + vbool8_t v = *(vbool8_t*)(in + 600); + *(vbool8_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool8_t v = *(vbool8_t*)(in + 900 + i); + *(vbool8_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool4_t v = *(vbool4_t*)(in + 500); + *(vbool4_t*)(out + 500) = v; + } else if (n == 1) { + vbool4_t v = *(vbool4_t*)(in + 600); + *(vbool4_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool4_t v = *(vbool4_t*)(in + 900 + i); + *(vbool4_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool2_t v = *(vbool2_t*)(in + 500); + *(vbool2_t*)(out + 500) = v; + } else if (n == 1) { + vbool2_t v = *(vbool2_t*)(in + 600); + *(vbool2_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool2_t v = *(vbool2_t*)(in + 900 + i); + *(vbool2_t*)(out + 900 + i) = v; + } +} + +void f7 (int8_t * restrict in, int8_t * restrict out, int n) +{ + if (n == 0) { + vbool1_t v = *(vbool1_t*)(in + 500); + *(vbool1_t*)(out + 500) = v; + } else if (n == 1) { + vbool1_t v = *(vbool1_t*)(in + 600); + *(vbool1_t*)(out + 600) = v; + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool1_t v = *(vbool1_t*)(in + 900 + i); + *(vbool1_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m1,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m1,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]\s+\.L[0-9][0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-9.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-9.c new file mode 100644 index 00000000000..7b0924de69e --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_bb_prop-9.c @@ -0,0 +1,230 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint8mf8_t v = *(vint8mf8_t*)(in + 500); + *(vint8mf8_t*)(out + 500) = v; + break; + } + case 1:{ + vint8mf8_t v = *(vint8mf8_t*)(in + 500); + *(vint8mf8_t*)(out + 500) = v; + break; + } + default:{ + vint8mf8_t v = *(vint8mf8_t*)(in + 700); + *(vint8mf8_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf8_t v = *(vint8mf8_t*)(in + 900 + i); + *(vint8mf8_t*)(out + 900 + i) = v; + } +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint8mf4_t v = *(vint8mf4_t*)(in + 500); + *(vint8mf4_t*)(out + 500) = v; + break; + } + case 1:{ + vint8mf4_t v = *(vint8mf4_t*)(in + 500); + *(vint8mf4_t*)(out + 500) = v; + break; + } + default:{ + vint8mf4_t v = *(vint8mf4_t*)(in + 700); + *(vint8mf4_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf4_t v = *(vint8mf4_t*)(in + 900 + i); + *(vint8mf4_t*)(out + 900 + i) = v; + } +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint8mf2_t v = *(vint8mf2_t*)(in + 500); + *(vint8mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vint8mf2_t v = *(vint8mf2_t*)(in + 500); + *(vint8mf2_t*)(out + 500) = v; + break; + } + default:{ + vint8mf2_t v = *(vint8mf2_t*)(in + 700); + *(vint8mf2_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf2_t v = *(vint8mf2_t*)(in + 900 + i); + *(vint8mf2_t*)(out + 900 + i) = v; + } +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint16mf4_t v = *(vint16mf4_t*)(in + 500); + *(vint16mf4_t*)(out + 500) = v; + break; + } + case 1:{ + vint16mf4_t v = *(vint16mf4_t*)(in + 500); + *(vint16mf4_t*)(out + 500) = v; + break; + } + default:{ + vint16mf4_t v = *(vint16mf4_t*)(in + 700); + *(vint16mf4_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf4_t v = *(vint16mf4_t*)(in + 900 + i); + *(vint16mf4_t*)(out + 900 + i) = v; + } +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint16mf2_t v = *(vint16mf2_t*)(in + 500); + *(vint16mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vint16mf2_t v = *(vint16mf2_t*)(in + 500); + *(vint16mf2_t*)(out + 500) = v; + break; + } + default:{ + vint16mf2_t v = *(vint16mf2_t*)(in + 700); + *(vint16mf2_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf2_t v = *(vint16mf2_t*)(in + 900 + i); + *(vint16mf2_t*)(out + 900 + i) = v; + } +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + switch (n) + { + case 0:{ + vint32mf2_t v = *(vint32mf2_t*)(in + 500); + *(vint32mf2_t*)(out + 500) = v; + break; + } + case 1:{ + vint32mf2_t v = *(vint32mf2_t*)(in + 500); + *(vint32mf2_t*)(out + 500) = v; + break; + } + default:{ + vint32mf2_t v = *(vint32mf2_t*)(in + 700); + *(vint32mf2_t*)(out + 700) = v; + break; + } + } + + for (int i = 0 ; i < n * n; i++) + out[i] = out[i] + out[i]; + + for (int i = 0 ; i < n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) + out[i] = out[i] * out[i]; + + for (int i = 0 ; i < n * n * n * n; i++) { + vint32mf2_t v = *(vint32mf2_t*)(in + 900 + i); + *(vint32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 2 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ +/* { dg-final { scan-assembler-times {add\ta[0-7],a[0-7],a[0-7]\s+\.L[0-9][0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" no-opts "-O1" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-1.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-1.c new file mode 100644 index 00000000000..ca501e0e1a1 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-1.c @@ -0,0 +1,239 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -O3 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void fn3 (void); + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vbool64_t v = *(vbool64_t*)(in + 900 + i); + *(vbool64_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool64_t v = *(vbool64_t*)(in + 900 + i); + *(vbool64_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool64_t v = *(vbool64_t*)(in + 900 + i); + *(vbool64_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool64_t v = *(vbool64_t*)(in + 900 + i); + *(vbool64_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool64_t v = *(vbool64_t*)(in + 900 + i); + *(vbool64_t*)(out + 900 + i) = v; + } + +} + +int f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vbool32_t v = *(vbool32_t*)(in + 900 + i); + *(vbool32_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool32_t v = *(vbool32_t*)(in + 900 + i); + *(vbool32_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool32_t v = *(vbool32_t*)(in + 900 + i); + *(vbool32_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool32_t v = *(vbool32_t*)(in + 900 + i); + *(vbool32_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool32_t v = *(vbool32_t*)(in + 900 + i); + *(vbool32_t*)(out + 900 + i) = v; + } + +} + +int f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vbool16_t v = *(vbool16_t*)(in + 900 + i); + *(vbool16_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool16_t v = *(vbool16_t*)(in + 900 + i); + *(vbool16_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool16_t v = *(vbool16_t*)(in + 900 + i); + *(vbool16_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool16_t v = *(vbool16_t*)(in + 900 + i); + *(vbool16_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool16_t v = *(vbool16_t*)(in + 900 + i); + *(vbool16_t*)(out + 900 + i) = v; + } + +} + +int f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vbool8_t v = *(vbool8_t*)(in + 900 + i); + *(vbool8_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool8_t v = *(vbool8_t*)(in + 900 + i); + *(vbool8_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool8_t v = *(vbool8_t*)(in + 900 + i); + *(vbool8_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool8_t v = *(vbool8_t*)(in + 900 + i); + *(vbool8_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool8_t v = *(vbool8_t*)(in + 900 + i); + *(vbool8_t*)(out + 900 + i) = v; + } + +} + +int f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vbool4_t v = *(vbool4_t*)(in + 900 + i); + *(vbool4_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool4_t v = *(vbool4_t*)(in + 900 + i); + *(vbool4_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool4_t v = *(vbool4_t*)(in + 900 + i); + *(vbool4_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool4_t v = *(vbool4_t*)(in + 900 + i); + *(vbool4_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool4_t v = *(vbool4_t*)(in + 900 + i); + *(vbool4_t*)(out + 900 + i) = v; + } + +} + +int f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vbool2_t v = *(vbool2_t*)(in + 900 + i); + *(vbool2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool2_t v = *(vbool2_t*)(in + 900 + i); + *(vbool2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool2_t v = *(vbool2_t*)(in + 900 + i); + *(vbool2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool2_t v = *(vbool2_t*)(in + 900 + i); + *(vbool2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool2_t v = *(vbool2_t*)(in + 900 + i); + *(vbool2_t*)(out + 900 + i) = v; + } + +} + +int f7 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vbool1_t v = *(vbool1_t*)(in + 900 + i); + *(vbool1_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool1_t v = *(vbool1_t*)(in + 900 + i); + *(vbool1_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vbool1_t v = *(vbool1_t*)(in + 900 + i); + *(vbool1_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool1_t v = *(vbool1_t*)(in + 900 + i); + *(vbool1_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vbool1_t v = *(vbool1_t*)(in + 900 + i); + *(vbool1_t*)(out + 900 + i) = v; + } + +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m1,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m1,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m4,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 1 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]\s+\.L[0-9][0-9][0-9]\:\s+vlm\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 4 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-2.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-2.c new file mode 100644 index 00000000000..69cc50f0219 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-2.c @@ -0,0 +1,207 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -O3 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void fn3 (void); + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf8_t v = *(vint8mf8_t*)(in + 900 + i); + *(vint8mf8_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf8_t v = *(vint8mf8_t*)(in + 900 + i); + *(vint8mf8_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf8_t v = *(vint8mf8_t*)(in + 900 + i); + *(vint8mf8_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf8_t v = *(vint8mf8_t*)(in + 900 + i); + *(vint8mf8_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf8_t v = *(vint8mf8_t*)(in + 900 + i); + *(vint8mf8_t*)(out + 900 + i) = v; + } + +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf4_t v = *(vint8mf4_t*)(in + 900 + i); + *(vint8mf4_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf4_t v = *(vint8mf4_t*)(in + 900 + i); + *(vint8mf4_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf4_t v = *(vint8mf4_t*)(in + 900 + i); + *(vint8mf4_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf4_t v = *(vint8mf4_t*)(in + 900 + i); + *(vint8mf4_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf4_t v = *(vint8mf4_t*)(in + 900 + i); + *(vint8mf4_t*)(out + 900 + i) = v; + } + +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf2_t v = *(vint8mf2_t*)(in + 900 + i); + *(vint8mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf2_t v = *(vint8mf2_t*)(in + 900 + i); + *(vint8mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf2_t v = *(vint8mf2_t*)(in + 900 + i); + *(vint8mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf2_t v = *(vint8mf2_t*)(in + 900 + i); + *(vint8mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vint8mf2_t v = *(vint8mf2_t*)(in + 900 + i); + *(vint8mf2_t*)(out + 900 + i) = v; + } + +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf4_t v = *(vint16mf4_t*)(in + 900 + i); + *(vint16mf4_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf4_t v = *(vint16mf4_t*)(in + 900 + i); + *(vint16mf4_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf4_t v = *(vint16mf4_t*)(in + 900 + i); + *(vint16mf4_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf4_t v = *(vint16mf4_t*)(in + 900 + i); + *(vint16mf4_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf4_t v = *(vint16mf4_t*)(in + 900 + i); + *(vint16mf4_t*)(out + 900 + i) = v; + } + +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf2_t v = *(vint16mf2_t*)(in + 900 + i); + *(vint16mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf2_t v = *(vint16mf2_t*)(in + 900 + i); + *(vint16mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf2_t v = *(vint16mf2_t*)(in + 900 + i); + *(vint16mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf2_t v = *(vint16mf2_t*)(in + 900 + i); + *(vint16mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vint16mf2_t v = *(vint16mf2_t*)(in + 900 + i); + *(vint16mf2_t*)(out + 900 + i) = v; + } + +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vint32mf2_t v = *(vint32mf2_t*)(in + 900 + i); + *(vint32mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vint32mf2_t v = *(vint32mf2_t*)(in + 900 + i); + *(vint32mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vint32mf2_t v = *(vint32mf2_t*)(in + 900 + i); + *(vint32mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vint32mf2_t v = *(vint32mf2_t*)(in + 900 + i); + *(vint32mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vint32mf2_t v = *(vint32mf2_t*)(in + 900 + i); + *(vint32mf2_t*)(out + 900 + i) = v; + } + +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-3.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-3.c new file mode 100644 index 00000000000..3a350486cee --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-3.c @@ -0,0 +1,207 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -O3 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void fn3 (void); + +void f (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 900 + i); + *(vuint8mf8_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 900 + i); + *(vuint8mf8_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 900 + i); + *(vuint8mf8_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 900 + i); + *(vuint8mf8_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf8_t v = *(vuint8mf8_t*)(in + 900 + i); + *(vuint8mf8_t*)(out + 900 + i) = v; + } + +} + +void f2 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 900 + i); + *(vuint8mf4_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 900 + i); + *(vuint8mf4_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 900 + i); + *(vuint8mf4_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 900 + i); + *(vuint8mf4_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf4_t v = *(vuint8mf4_t*)(in + 900 + i); + *(vuint8mf4_t*)(out + 900 + i) = v; + } + +} + +void f3 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 900 + i); + *(vuint8mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 900 + i); + *(vuint8mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 900 + i); + *(vuint8mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 900 + i); + *(vuint8mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + 900 + i); + *(vuint8mf2_t*)(out + 900 + i) = v; + } + +} + +void f4 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 900 + i); + *(vuint16mf4_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 900 + i); + *(vuint16mf4_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 900 + i); + *(vuint16mf4_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 900 + i); + *(vuint16mf4_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + 900 + i); + *(vuint16mf4_t*)(out + 900 + i) = v; + } + +} + +void f5 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 900 + i); + *(vuint16mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 900 + i); + *(vuint16mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 900 + i); + *(vuint16mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 900 + i); + *(vuint16mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + 900 + i); + *(vuint16mf2_t*)(out + 900 + i) = v; + } + +} + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 900 + i); + *(vuint32mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 900 + i); + *(vuint32mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 900 + i); + *(vuint32mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 900 + i); + *(vuint32mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vuint32mf2_t v = *(vuint32mf2_t*)(in + 900 + i); + *(vuint32mf2_t*)(out + 900 + i) = v; + } + +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle8\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf4,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle16\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9][0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-4.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-4.c new file mode 100644 index 00000000000..178036f780b --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_call-4.c @@ -0,0 +1,39 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -O3 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void fn3 (void); + +void f6 (int8_t * restrict in, int8_t * restrict out, int n) +{ + for (int i = 0 ; i < n * n * n * n; i++) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 900 + i); + *(vfloat32mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 900 + i); + *(vfloat32mf2_t*)(out + 900 + i) = v; + } + fn3 (); + + for (int i = 0 ; i < n * n * n * n; i++) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 900 + i); + *(vfloat32mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 900 + i); + *(vfloat32mf2_t*)(out + 900 + i) = v; + } + fn3 (); + for (int i = 0 ; i < n * n * n * n; i++) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + 900 + i); + *(vfloat32mf2_t*)(out + 900 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]\s+\.L[0-9]\:\s+vle32\.v\s+(?:v[0-9]|v[1-2][0-9]|v3[0-1]),0\s*\((?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7])\)} 5 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_complex_loop-1.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_complex_loop-1.c new file mode 100644 index 00000000000..c5962e5a385 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_complex_loop-1.c @@ -0,0 +1,52 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int32_t * restrict in, int32_t * restrict out, size_t n, size_t m, int cond) +{ + for (size_t i = 0; i < n; i++) + { + if (i % 2) { + + if (cond) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + i + 2000); + *(vfloat32mf2_t*)out = v; + } else { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + i + 3000); + *(vfloat32mf2_t*)out = v; + } + + for (size_t j = 0; j < m; j += 1) { + if (j % 2 == 0) { + vint8mf8_t v = *(vint8mf8_t*)(in + i + j + 100); + *(vint8mf8_t*)out = v; + } else { + vint8mf8_t v = *(vint8mf8_t*)(in + i + j + 200); + *(vint8mf8_t*)out = v; + } + } + + if (cond) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + i + 7000); + *(vuint16mf4_t*)out = v; + } else { + vuint16mf4_t v = *(vuint16mf4_t*)(in + i + 8000); + *(vuint16mf4_t*)out = v; + } + } else { + if (cond) { + vint8mf8_t v = *(vint8mf8_t*)(in + i + 4000); + *(vint8mf8_t*)out = v; + } else { + vint8mf8_t v = *(vint8mf8_t*)(in + i + 5000); + *(vint8mf8_t*)out = v; + } + + vbool64_t v = *(vbool64_t*)(in + i + 300); + *(vbool64_t*)out = v; + } + } +} + +/* { dg-final { scan-assembler-times {vsetvli} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_complex_loop-2.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_complex_loop-2.c new file mode 100644 index 00000000000..9ec4879dade --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_complex_loop-2.c @@ -0,0 +1,56 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int32_t * restrict in, int32_t * restrict out, size_t n, size_t m, int cond) +{ + for (size_t i = 0; i < n; i++) + { + if (i % 2) { + + if (cond) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + i + 2000); + *(vfloat32mf2_t*)(out + i + 2000) = v; + } else { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + i + 3000); + *(vfloat32mf2_t*)(out + i + 3000) = v; + } + + for (size_t j = 0; j < m; j += 1) { + if (j % 2 == 0) { + vint8mf8_t v = *(vint8mf8_t*)(in + i + j + 100); + *(vint8mf8_t*)(out + i + j + 100) = v; + } else { + vint8mf8_t v = *(vint8mf8_t*)(in + i + j + 200); + *(vint8mf8_t*)(out + i + j + 200) = v; + } + } + + if (cond) { + vuint16mf4_t v = *(vuint16mf4_t*)(in + i + 7000); + *(vuint16mf4_t*)(out + i + 7000) = v; + } else { + vuint16mf4_t v = *(vuint16mf4_t*)(in + i + 8000); + *(vuint16mf4_t*)(out + i + 8000) = v; + } + } else { + if (cond) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + i + 4000); + *(vuint16mf2_t*)(out + i + 4000) = v; + } else { + vuint16mf2_t v = *(vuint16mf2_t*)(in + i + 5000); + *(vuint16mf2_t*)(out + i + 5000) = v; + } + + vbool1_t v = *(vbool1_t*)(in + i + 300); + *(vbool1_t*)(out + i + 300) = v; + } + } +} + +/* { dg-final { scan-assembler-times {vsetvli} 5 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-not {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-1.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-1.c new file mode 100644 index 00000000000..dff5437da72 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-1.c @@ -0,0 +1,23 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int32_t * restrict in, int32_t * restrict out, size_t n, size_t cond, size_t cond2) +{ + for (size_t i = 0; i < n; i++) + { + if (i != cond) { + vint8mf8_t v = *(vint8mf8_t*)(in + i + 100); + *(vint8mf8_t*)(out + i + 100) = v; + } else { + vbool1_t v = *(vbool1_t*)(in + i + 400); + *(vbool1_t*)(out + i + 400) = v; + } + } +} + +/* { dg-final { scan-assembler-times {vsetvli} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {\.L[0-9]+:\s+vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9]+} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+j\s+\.L[0-9]+} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-10.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-10.c new file mode 100644 index 00000000000..697b093f69f --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-10.c @@ -0,0 +1,27 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int32_t * restrict in, int32_t * restrict out, size_t n, size_t m, size_t cond, size_t cond2) +{ + for (size_t i = 0; i < n; i++) + { + if (i != cond) { + vbool16_t v = *(vbool16_t*)(in + i + 400); + *(vbool16_t*)(out + i + 400) = v; + for (int j = 0; j < m; j++) { + vuint8mf2_t v = *(vuint8mf2_t*)(in + i + 100 + j); + *(vuint8mf2_t*)(out + i + 100 + j) = v; + } + } else if (i == cond2) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + i + 200); + *(vuint16mf2_t*)(out + i + 200) = v; + } else { + vint8mf8_t v = *(vint8mf8_t*)(in + i + 100); + *(vint8mf8_t*)(out + i + 100) = v; + } + } +} + +/* { dg-final { scan-assembler-times {vsetvli} 5 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-11.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-11.c new file mode 100644 index 00000000000..6ad2dc3f237 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-11.c @@ -0,0 +1,24 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int32_t * restrict in, int32_t * restrict out, size_t n, size_t m, size_t cond, size_t cond2) +{ + for (int i = 0; i < n; i++) { + vint8mf8_t v = *(vint8mf8_t*) (in + i + 1); + *(vint8mf8_t*) (out + i + 1) = v; + } + for (int i = 0; i < n; i++) { + vfloat32mf2_t v = *(vfloat32mf2_t*) (in + i + 2); + *(vfloat32mf2_t*) (out + i + 2) = v; + } + for (int i = 0; i < n; i++) { + vfloat32mf2_t v; + *(vfloat32mf2_t*) (out + i + 3) = v; + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+zero,\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli} 2 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-12.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-12.c new file mode 100644 index 00000000000..c01f4b4acae --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-12.c @@ -0,0 +1,39 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f2 (int32_t * restrict in, int32_t * restrict in2, int32_t * restrict out, int32_t * restrict out2, size_t n, size_t m, size_t cond, size_t cond2) +{ + for (int i = 0; i < n; i++){ + out2[i] = in2[i] + out[i]; + } + for (int i = 0; i < n; i++){ + out[i] = in[i] & out2[i]; + } + for (int i = 0; i < n; i++){ + out2[i] = out[i] * out2[i]; + } + for (size_t i = 0; i < n; i++) + { + if (i > cond) { + if (cond2) { + for (int j = 0; j < m; j++) { + vint8mf8_t v2 = *(vint8mf8_t*)(in2 + i + 100 + j); + *(vint8mf8_t*)(out2 + i + 100 + j) = v2; + } + } else { + for (int j = 0; j < m; j++) { + vfloat32mf2_t v3 = *(vfloat32mf2_t*)(in2 + i + 300 + j); + *(vfloat32mf2_t*)(out2 + i + 100 + j) = v3; + } + } + } else { + vbool64_t v = *(vbool64_t*)(in + i + 400); + *(vbool64_t*)(out + i + 400) = v; + } + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-2.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-2.c new file mode 100644 index 00000000000..d14f9ba34a1 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-2.c @@ -0,0 +1,23 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int32_t * restrict in, int32_t * restrict out, size_t n, size_t cond, size_t cond2) +{ + for (size_t i = 0; i < n; i++) + { + if (i == cond) { + vint8mf8_t v = *(vint8mf8_t*)(in + i + 100); + *(vint8mf8_t*)(out + i + 100) = v; + } else { + vbool1_t v = *(vbool1_t*)(in + i + 400); + *(vbool1_t*)(out + i + 400) = v; + } + } +} + +/* { dg-final { scan-assembler-times {vsetvli} 3 { target { no-opts "-O0" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]\s+\.L[0-9]+} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]\s+j\s+\.L[0-9]+} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-3.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-3.c new file mode 100644 index 00000000000..1ba0234788a --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-3.c @@ -0,0 +1,30 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f2 (int32_t * restrict in, int32_t * restrict in2, int32_t * restrict out, int32_t * restrict out2, size_t n, size_t m, size_t cond, size_t cond2) +{ + for (size_t i = 0; i < n; i++) + { + if (i > cond) { + if (cond2) { + for (int j = 0; j < m; j++) { + vint8mf8_t v2 = *(vint8mf8_t*)(in2 + i + 100 + j); + *(vint8mf8_t*)(out2 + i + 100 + j) = v2; + } + } else { + for (int j = 0; j < m; j++) { + vfloat32mf2_t v3 = *(vfloat32mf2_t*)(in2 + i + 300 + j); + *(vfloat32mf2_t*)(out2 + i + 100 + j) = v3; + } + } + } else { + vbool64_t v = *(vbool64_t*)(in + i + 400); + *(vbool64_t*)(out + i + 400) = v; + } + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-4.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-4.c new file mode 100644 index 00000000000..c86af9d3907 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-4.c @@ -0,0 +1,29 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int32_t * restrict in, int32_t * restrict out, size_t n, size_t cond, size_t cond2) +{ + for (size_t i = 0; i < n; i++) + { + if (i == cond) { + vint8mf8_t v = *(vint8mf8_t*)(in + i + 100); + *(vint8mf8_t*)(out + i + 100) = v; + } else if (i == cond2) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + i + 200); + *(vfloat32mf2_t*)(out + i + 200) = v; + } else { + vbool1_t v = *(vbool1_t*)(in + i + 400); + *(vbool1_t*)(out + i + 400) = v; + } + } +} + + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]\s+\.L[0-9]:+} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli} 5 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ + diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-5.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-5.c new file mode 100644 index 00000000000..34c40d46466 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-5.c @@ -0,0 +1,32 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int32_t * restrict in, int32_t * restrict out, size_t n, size_t cond, size_t cond2) +{ + for (size_t i = 0; i < n; i++) + { + if (i == cond) { + vint8mf8_t v = *(vint8mf8_t*)(in + i + 100); + *(vint8mf8_t*)(out + i + 100) = v; + } else if (i == cond2) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + i + 200); + *(vfloat32mf2_t*)(out + i + 200) = v; + } else if (i == (cond2 - 1)) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + i + 300); + *(vuint16mf2_t*)(out + i + 300) = v; + } else { + vbool1_t v = *(vbool1_t*)(in + i + 400); + *(vbool1_t*)(out + i + 400) = v; + } + } +} + +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} 4 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]\s+\.L[0-9]:+} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli} 7 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ + diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-6.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-6.c new file mode 100644 index 00000000000..a009aadeecd --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-6.c @@ -0,0 +1,26 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int32_t * in, int32_t * out, int n, int cond) +{ + if (cond) { + vint32mf2_t v = *(vint32mf2_t*) (in + 100); + *(vint32mf2_t*) (out + 100) = v; + } else { + vint16mf2_t v = *(vint16mf2_t*) (in + 200); + *(vint16mf2_t*) (out + 200) = v; + } + + for (int i = 0; i < n; i++) { + vint8mf8_t v = *(vint8mf8_t*) (in + 300 + i); + *(vint8mf8_t*) (out + 300 + i) = v; + } +} + +/* { dg-final { scan-assembler-times {\.L[0-9]+:\s+vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]\s+\.L[0-9]+:} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {\.L[0-9]+:\s+vle8\.v} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e32,\s*mf2,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli} 3 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-7.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-7.c new file mode 100644 index 00000000000..12ec25d5264 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-7.c @@ -0,0 +1,26 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int32_t * restrict in, int32_t * restrict out, size_t n, size_t cond, size_t cond2) +{ + for (size_t i = 0; i < n; i++) + { + if (i != cond) { + vbool1_t v = *(vbool1_t*)(in + i + 400); + *(vbool1_t*)(out + i + 400) = v; + } else if (i == cond2) { + vfloat32mf2_t v = *(vfloat32mf2_t*)(in + i + 200); + *(vfloat32mf2_t*)(out + i + 200) = v; + } else { + vint8mf8_t v = *(vint8mf8_t*)(in + i + 100); + *(vint8mf8_t*)(out + i + 100) = v; + } + } +} + +/* { dg-final { scan-assembler-times {vsetvli} 4 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {j\s+\.L[0-9]+\s+\.L[0-9]+:\s+vlm\.v} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-8.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-8.c new file mode 100644 index 00000000000..a7c9829c646 --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-8.c @@ -0,0 +1,27 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int32_t * restrict in, int32_t * restrict out, size_t n, size_t cond, size_t cond2) +{ + for (size_t i = 0; i < n; i++) + { + if (i != cond) { + vbool1_t v = *(vbool1_t*)(in + i + 400); + *(vbool1_t*)(out + i + 400) = v; + } else if (i == cond2) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + i + 200); + *(vuint16mf2_t*)(out + i + 200) = v; + } else { + vint8mf8_t v = *(vint8mf8_t*)(in + i + 100); + *(vint8mf8_t*)(out + i + 100) = v; + } + } +} + +/* { dg-final { scan-assembler-times {vsetvli} 5 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {j\s+\.L[0-9]+\s+\.L[0-9]+:\s+vlm\.v} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*m8,\s*t[au],\s*m[au]} 3 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e8,\s*mf8,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ +/* { dg-final { scan-assembler-times {vsetvli\s+(?:ra|[sgtf]p|t[0-6]|s[0-9]|s10|s11|a[0-7]),\s*zero,\s*e16,\s*mf2,\s*t[au],\s*m[au]} 1 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */ diff --git a/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-9.c b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-9.c new file mode 100644 index 00000000000..bd6d552b22e --- /dev/null +++ b/gcc/testsuite/gcc.target/riscv/rvv/vsetvl/vlmax_conflict-9.c @@ -0,0 +1,27 @@ +/* { dg-do compile } */ +/* { dg-options "-march=rv32gcv -mabi=ilp32 -fno-tree-vectorize" } */ + +#include "riscv_vector.h" + +void f (int32_t * restrict in, int32_t * restrict out, size_t n, size_t m, size_t cond, size_t cond2) +{ + for (size_t i = 0; i < n; i++) + { + if (i != cond) { + vbool1_t v = *(vbool1_t*)(in + i + 400); + *(vbool1_t*)(out + i + 400) = v; + for (int j = 0; j < m; j++) { + vint32mf2_t v = *(vint32mf2_t*)(in + i + 100 + j); + *(vint32mf2_t*)(out + i + 100 + j) = v; + } + } else if (i == cond2) { + vuint16mf2_t v = *(vuint16mf2_t*)(in + i + 200); + *(vuint16mf2_t*)(out + i + 200) = v; + } else { + vint8mf8_t v = *(vint8mf8_t*)(in + i + 100); + *(vint8mf8_t*)(out + i + 100) = v; + } + } +} + +/* { dg-final { scan-assembler-times {vsetvli} 7 { target { no-opts "-O0" no-opts "-O1" no-opts "-Os" no-opts "-funroll-loops" no-opts "-g" } } } } */