From mboxrd@z Thu Jan 1 00:00:00 1970 Path: news.gmane.io!.POSTED.blaine.gmane.org!not-for-mail From: Andrea Corallo via "Emacs development discussions." Newsgroups: gmane.emacs.devel Subject: Re: On elisp running native - Update 12 Date: Mon, 28 Sep 2020 17:21:13 +0000 Message-ID: References: <83o8uegykm.fsf@gnu.org> <74dd94a9-28cb-a5fd-dbc7-ab21009834ad@cs.ucla.edu> <87pn66ornr.fsf@gmail.com> <87v9fxyj5k.fsf@gmail.com> Reply-To: Andrea Corallo Mime-Version: 1.0 Content-Type: text/plain Injection-Info: ciao.gmane.io; posting-host="blaine.gmane.org:116.202.254.214"; logging-data="34108"; mail-complaints-to="usenet@ciao.gmane.io" User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/28.0.50 (gnu/linux) Cc: Andrea Corallo via "Emacs development discussions." , Eli Zaretskii , Stefan Monnier , rms@gnu.org To: Caio Henrique Original-X-From: emacs-devel-bounces+ged-emacs-devel=m.gmane-mx.org@gnu.org Mon Sep 28 19:26:00 2020 Return-path: Envelope-to: ged-emacs-devel@m.gmane-mx.org Original-Received: from lists.gnu.org ([209.51.188.17]) by ciao.gmane.io with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.92) (envelope-from ) id 1kMwuW-0008k4-Jq for ged-emacs-devel@m.gmane-mx.org; Mon, 28 Sep 2020 19:26:00 +0200 Original-Received: from localhost ([::1]:51182 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1kMwuV-0008LD-FL for ged-emacs-devel@m.gmane-mx.org; Mon, 28 Sep 2020 13:25:59 -0400 Original-Received: from eggs.gnu.org ([2001:470:142:3::10]:46962) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1kMwq0-0003Sj-Q3 for emacs-devel@gnu.org; Mon, 28 Sep 2020 13:21:20 -0400 Original-Received: from mx.sdf.org ([205.166.94.24]:50584) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1kMwpy-0006wT-MX; Mon, 28 Sep 2020 13:21:20 -0400 Original-Received: from mab (ma.sdf.org [205.166.94.33]) by mx.sdf.org (8.15.2/8.14.5) with ESMTP id 08SHLDjM008522; Mon, 28 Sep 2020 17:21:13 GMT In-Reply-To: <87v9fxyj5k.fsf@gmail.com> (Caio Henrique's message of "Mon, 28 Sep 2020 13:12:55 -0300") Received-SPF: pass client-ip=205.166.94.24; envelope-from=akrl@sdf.org; helo=mx.sdf.org X-detected-operating-system: by eggs.gnu.org: First seen = 2020/09/28 10:51:09 X-ACL-Warn: Detected OS = ??? X-Spam_score_int: -18 X-Spam_score: -1.9 X-Spam_bar: - X-Spam_report: (-1.9 / 5.0 requ) BAYES_00=-1.9, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: emacs-devel@gnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: "Emacs development discussions." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: emacs-devel-bounces+ged-emacs-devel=m.gmane-mx.org@gnu.org Original-Sender: "Emacs-devel" Xref: news.gmane.io gmane.emacs.devel:256624 Archived-At: Caio Henrique writes: > Andrea Corallo writes: > >> We may add it tho, but I think would be more beneficial to >> expose first aref aset and see what we can generate with the GCC >> vectorizer. > > Does that mean that native elisp would be able to use SSE, AVX etc? I must say I'm very ignorant regarding the X86 GCC backend so I'm not sure which instructions (if any) can be generated with autovectorization there. I've got the idea as these days I had to put my hands in the vectorizer trying to improve it looking at Aarch64 SVE as output. Andrea