From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757121Ab3KISUr (ORCPT ); Sat, 9 Nov 2013 13:20:47 -0500 Received: from unicorn.mansr.com ([81.2.72.234]:58729 "EHLO unicorn.mansr.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751325Ab3KISUm convert rfc822-to-8bit (ORCPT ); Sat, 9 Nov 2013 13:20:42 -0500 From: =?iso-8859-1?Q?M=E5ns_Rullg=E5rd?= To: Matt Sealey Cc: Stephen Boyd , "linux-arm-kernel\@lists.infradead.org" , "linux-kernel\@vger.kernel.org" , Jean-Christophe PLAGNIOL-VILLARD , Christopher Covington , Russell King - ARM Linux , =?iso-8859-1?Q?M=E5n?= =?iso-8859-1?Q?s_Rullg=E5rd?= , Rob Herring Subject: Re: [PATCH v2] ARM: Use udiv/sdiv for __aeabi_{u}idiv library functions References: <1383951632-6090-1-git-send-email-sboyd@codeaurora.org> Date: Sat, 09 Nov 2013 18:20:38 +0000 In-Reply-To: (Matt Sealey's message of "Sat, 9 Nov 2013 00:46:11 -0600") Message-ID: User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/24.3 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Matt Sealey writes: > BTW has there been any evaluation of the penalty for the extra > branching, or the performance hit for the ARMv7-without-division > cases? The branches themselves probably have minimal overhead. There will however be code to preserve call-clobbered registers (and move the values to/from r0/r1) that would not be needed if the div instructions were done inline (obviously such a kernel could only run on hardware with division support). -- Måns Rullgård mans@mansr.com