From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 48) id 51FCB3858004; Wed, 24 May 2023 08:42:02 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 51FCB3858004 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1684917722; bh=/geyOnseAztTjGDiuam8zhb0W/0LQfFxO+PMXfI9MyY=; h=From:To:Subject:Date:In-Reply-To:References:From; b=FRqfSOsMKuh/2gIgXCRomMpkHtQYo3AfoHjnyM6P2e0oMTuouh1q2x7yxBxWSH5wt GEO/+sTHKUrTJUaDyzHTXtW8aKCAvQCeVxPpJASK1Kwy02pYHpXJeCf+xSY10tLIhy X20NnWEhDrkHGeFHa3xZLsYiqhqrucC/f//WXiOk= From: "jbeulich at suse dot com" To: gcc-bugs@gcc.gnu.org Subject: [Bug target/100711] Miss optimization for pandn Date: Wed, 24 May 2023 08:42:00 +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: 12.0 X-Bugzilla-Keywords: missed-optimization X-Bugzilla-Severity: normal X-Bugzilla-Who: jbeulich at suse dot com X-Bugzilla-Status: RESOLVED X-Bugzilla-Resolution: FIXED 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: cc 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=3D100711 jbeulich at suse dot com changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |jbeulich at suse dot com --- Comment #8 from jbeulich at suse dot com --- Since the commit doesn't really explain it (maybe it's obvious to others, b= ut it isn't to me), may I ask why two splitters were introduced, yet then still not covering all possible modes? VI48_128 only covers two of the four possi= ble SSE2 modes, while VI124_AVX2 leaves out all DI-element-size ones as well as= all 512-bit ones. Shouldn't both be folded, using VI_AVX2 as the mode iterator? As an aside, it is also interesting that the 1st splitter uses TARGET_SSE without the corresponding testcase limiting itself to just SSE. When buildi= ng that testcase with SSE2 turned off, foo() uses shufps and andnps as expecte= d, but the splitter doesn't appear to come into play at all for bar(), when re= ally it is only the broadcast that needs synthesizing, while andnps can be used regardless of mode.=