From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id 2DE4E3858C33; Wed, 19 Jul 2023 08:55:52 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 2DE4E3858C33 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1689756952; bh=7PzzoupsXHnynsBwk5+Eo4Y8x73hzJTmEc0wki8AN1o=; h=From:To:Subject:Date:In-Reply-To:References:From; b=cFE3d539pzrdONpx9jwc8ZodLyDfAhNWRXcUzAXJqcSOPJ82ESba0c6AnZClolSJA PS8aS+jNU/ixMUL7A6h2NFq9hx1T8hPCfES12+A1xTK1evARGDFqp58dIWbTS0v1RJ qn4St3wUIuHt+wenUR1A+TpMteB2fbyKhKpCsVqs= From: "rsandifo at gcc dot gnu.org" To: gcc-bugs@gcc.gnu.org Subject: [Bug target/110625] [AArch64] Vect: SLP fails to vectorize a loop as the reduction_latency calculated by new costs is too large Date: Wed, 19 Jul 2023 08:55:51 +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: missed-optimization X-Bugzilla-Severity: normal X-Bugzilla-Who: rsandifo at gcc dot gnu.org X-Bugzilla-Status: ASSIGNED X-Bugzilla-Resolution: X-Bugzilla-Priority: P3 X-Bugzilla-Assigned-To: rsandifo 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=3D110625 --- Comment #7 from rsandifo at gcc dot gnu.org --- The current issue rate framework was originally written for Neoverse V1 and Neoverse V2. For those cores, it wasn't necessary to make a distinction between scalar integer operations and scalar FP operations: the integer throughput and FP throughput were close enough for the difference not to matter. I think the problem is that the difference between integer throughput and FP throughput does matter for Neoverse N2. E.g. integer additions have a throughput of 4 a cycle whereas FP additions have a throughput of 2 a cycle. Currently the Neoverse N2 model uses a throughput of 4 =E2=80=9Cgeneral ops= =E2=80=9D for scalar code. However, when the loop consists entirely of loads, stores and FP operations, the limit should instead be 2.=