From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id 915413858430; Wed, 17 Jan 2024 01:38:44 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 915413858430 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1705455524; bh=4KWMHoqiW9ZfoETKORulx8yT+uccN7p92r6CoRmOYlM=; h=From:To:Subject:Date:In-Reply-To:References:From; b=s7Wb6IMEl0xF1EHOfj6wc3vvmhXLMvsj1R3kUQpi77SPirX13JalfTA1+oOFdNgbV b60CqvxuFCDyU9DIbsTlbVMZP+HrV/20IEhvwGecI1cSURFdijCsvrWXrOYmMFRfDO v2CjYHVWhmf1lYjxjfJKDmVWUX0fzo4MQVlhgH7o= From: "juzhe.zhong at rivai dot ai" To: gcc-bugs@gcc.gnu.org Subject: [Bug target/113431] [14] RISC-V rv64gcv vector: Runtime mismatch at -O3 Date: Wed, 17 Jan 2024 01:38:44 +0000 X-Bugzilla-Reason: CC X-Bugzilla-Type: changed X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: gcc X-Bugzilla-Component: target X-Bugzilla-Version: 14.0 X-Bugzilla-Keywords: wrong-code X-Bugzilla-Severity: normal X-Bugzilla-Who: juzhe.zhong at rivai dot ai X-Bugzilla-Status: UNCONFIRMED X-Bugzilla-Resolution: X-Bugzilla-Priority: P3 X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: Message-ID: In-Reply-To: References: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/ Auto-Submitted: auto-generated MIME-Version: 1.0 List-Id: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D113431 --- Comment #4 from JuzheZhong --- a[0][1] seems to be undefined value. And the test seems to trigger undefined behavior. I just checked ARM SVE and RVV. The vectorized IR is totally the same and I don't see anything obviously wr= ong in RVV assembler. https://godbolt.org/z/jz866Kfsv Hi, Andrew. Could you confirm it whether ARM SVE has the same behavior as R= VV? That is, with vectorized, return 1, whereas no vectorized, return 0;=