From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from gate.crashing.org (gate.crashing.org [63.228.1.57]) by sourceware.org (Postfix) with ESMTP id E6D4D3858D37 for ; Thu, 14 Jul 2022 22:05:16 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org E6D4D3858D37 Authentication-Results: sourceware.org; dmarc=none (p=none dis=none) header.from=kernel.crashing.org Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=kernel.crashing.org Received: from gate.crashing.org (localhost.localdomain [127.0.0.1]) by gate.crashing.org (8.14.1/8.14.1) with ESMTP id 26EM4GKM021212; Thu, 14 Jul 2022 17:04:16 -0500 Received: (from segher@localhost) by gate.crashing.org (8.14.1/8.14.1/Submit) id 26EM4FAq021209; Thu, 14 Jul 2022 17:04:15 -0500 X-Authentication-Warning: gate.crashing.org: segher set sender to segher@kernel.crashing.org using -f Date: Thu, 14 Jul 2022 17:04:15 -0500 From: Segher Boessenkool To: Michael Meissner , gcc-patches@gcc.gnu.org, "Kewen.Lin" , David Edelsohn , Peter Bergner , Will Schmidt Subject: Re: [GCC 12 backport] Disable generating load/store vector pairs for block copies. Message-ID: <20220714220415.GX25951@gate.crashing.org> References: <20220714211214.GW25951@gate.crashing.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4.2.3i X-Spam-Status: No, score=-3.2 required=5.0 tests=BAYES_00, JMQ_SPF_NEUTRAL, KAM_DMARC_STATUS, SPF_HELO_PASS, SPF_PASS, TXREP, T_SCC_BODY_TEXT_LINE autolearn=no 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: , X-List-Received-Date: Thu, 14 Jul 2022 22:05:18 -0000 On Thu, Jul 14, 2022 at 05:49:57PM -0400, Michael Meissner wrote: > On Thu, Jul 14, 2022 at 04:12:14PM -0500, Segher Boessenkool wrote: > > You never posted the trunk version of this, so that never was approved > > either. > > I did post the trunk version on June 10th, and your only comment was fix the > commit message, which I thought I did in the commit. I did not approve the patch. Of course not, I didn't even get as far as reading it. You should have fixed it and sent again, I did not approve anything. > > > + if (TARGET_MMA && TARGET_EFFICIENT_UNALIGNED_VSX > > > + && rs6000_tune != PROCESSOR_POWER10) > > > rs6000_isa_flags |= OPTION_MASK_BLOCK_OPS_VECTOR_PAIR; > > > else > > > rs6000_isa_flags &= ~OPTION_MASK_BLOCK_OPS_VECTOR_PAIR; > > > > The TARGET_MMA in that should not be there. Please fix that (that > > probably needs more changes). > > All of the movoo and movxo support require TARGET_MMA as does the code in > rs6000-string.cc that could possibly generate load/store vector pair. And all that is wrong and should be fixed. > To > remove the check here would mean also fixing all of the vector load and store > pairs in mma.md. That is wha I said, yes,. > > This statement does the opposite of what the comment says. > > > > Please fix this. On trunk, first. This is the core problem with this patch: it is simply wrong. It is a very roundabout way of saying "only enable vector pairs if -mcpu=power10 but -mtune=somethingelse". Which is not a sensible thing to do, and not what the comment says either. Segher