From owner-freebsd-hackers@FreeBSD.ORG Sun Jun 7 16:44:19 2015 Return-Path: Delivered-To: freebsd-hackers@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id CDF80FBB for ; Sun, 7 Jun 2015 16:44:19 +0000 (UTC) (envelope-from davide.italiano@gmail.com) Received: from mail-qk0-x22b.google.com (mail-qk0-x22b.google.com [IPv6:2607:f8b0:400d:c09::22b]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 874E4176F for ; Sun, 7 Jun 2015 16:44:19 +0000 (UTC) (envelope-from davide.italiano@gmail.com) Received: by qkhq76 with SMTP id q76so66873764qkh.2 for ; Sun, 07 Jun 2015 09:44:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:sender:in-reply-to:references:date:message-id:subject :from:to:cc:content-type; bh=O2+DfmSP4jfRLxodknwoMEXMYNjbUz74Av/2fo1c+tY=; b=rJAuJXBOUej6jvt4WpwKD8MsP6lKrBCsfFIF93y4W8Iru9XeVFgGl6LW/5slXgdXyQ Xy+DbNJ+R91uy+QEZTY7wRh0Yf5HjMs8EIq69Gd/3GLFul1odNQ8TSu1Vfuim5w+oWxO ErgqJfbNfJHJOGisWPFQy4+ULpoX/CEDld2OUOnwFKdtLdVda/KWGzs6ANCBEEvHSPCX Ar15FN+Wd/QZbN1Bd1Ek9LoijNe1MhP5Qlbj50v4lBBaQ54MndLX3Zfx9V4B9IDhjWE0 QlHrPl4L/xOkIcyd7FLc7JR+tUBjdsr4ywiaDtWw9Zy0ZSsjZl5CojO4XA+WigMPSGmU fTlw== MIME-Version: 1.0 X-Received: by 10.140.145.202 with SMTP id 193mr15684402qhr.43.1433695458648; Sun, 07 Jun 2015 09:44:18 -0700 (PDT) Sender: davide.italiano@gmail.com Received: by 10.96.106.234 with HTTP; Sun, 7 Jun 2015 09:44:18 -0700 (PDT) In-Reply-To: References: <20150607081315.7c0f09fb@B85M-HD3-0.alogt.com> <5573EA5E.40806@selasky.org> <20150607195245.62dc191f@B85M-HD3-0.alogt.com> <20150607135453.GH2499@kib.kiev.ua> Date: Sun, 7 Jun 2015 09:44:18 -0700 X-Google-Sender-Auth: NDJ9u3YLOJXje3zKAYM74EO0tmc Message-ID: Subject: Re: allow ffs & co. a binary search From: Davide Italiano To: Konstantin Belousov Cc: Erich Dollansky , Hans Petter Selasky , "freebsd-hackers@freebsd.org" Content-Type: text/plain; charset=UTF-8 X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Jun 2015 16:44:20 -0000 On Sun, Jun 7, 2015 at 9:37 AM, Davide Italiano wrote: > On Sun, Jun 7, 2015 at 6:54 AM, Konstantin Belousov wrote: >> On Sun, Jun 07, 2015 at 07:52:45PM +0800, Erich Dollansky wrote: >>> What I saw is that all CPUs except ARM uses the software version [of ffs]. >> >> Without quantifiers, this statement is not true. i386 libc function ffs(3) >> uses bsfl instruction to do the job. Compilers know about ffs(3) and friends >> as well, so e.g. gcc 5.1.0 generates the following code for the given >> fragment: >> return (ffs(x) + 1); >> is translated to >> 0: 0f bc c7 bsf %edi,%eax >> 3: ba ff ff ff ff mov $0xffffffff,%edx >> 8: 0f 44 c2 cmove %edx,%eax >> b: 83 c0 02 add $0x2,%eax >> (arg in %edi, result in %eax). >> >> I wrote a patch for amd64 libc long time ago to convert ffs/fls etc to use >> of the bitstring instruction, but Bruce Evans argued that this would be >> excessive. Your patch is excessive for the similar reasons. >> >> My guess is that significantly clever compiler would recognize a pattern >> used by native ffs implementation and automatically use bitstring >> instructions. E.g., this already happens with popcnt and recent >> gcc/clang, I am just lazy to verify ffs. >> _______________________________________________ >> freebsd-hackers@freebsd.org mailing list >> http://lists.freebsd.org/mailman/listinfo/freebsd-hackers >> To unsubscribe, send any mail to "freebsd-hackers-unsubscribe@freebsd.org" > > Clang trunk to the best of my knowledgde hasn't a way to recognize > ffs() pattern. > http://llvm.org/docs/doxygen/html/LoopIdiomRecognize_8cpp_source.html > I can't comment about gcc as long as I'm not familiar with the implementation. > > -- > Davide > > "There are no solved problems; there are only problems that are more > or less solved" -- Henri Poincare Also, FWIW, for the fragment provided by Kostik, clang seems to generate more instructions than gcc does, I'll bring this upstream. 0: 0f bc c7 bsf %edi,%eax 3: b9 20 00 00 00 mov $0x20,%ecx 8: 0f 45 c8 cmovne %eax,%ecx b: 83 c1 02 add $0x2,%ecx e: 85 ff test %edi,%edi 10: b8 01 00 00 00 mov $0x1,%eax 15: 0f 45 c1 cmovne %ecx,%eax -- Davide "There are no solved problems; there are only problems that are more or less solved" -- Henri Poincare