From mboxrd@z Thu Jan  1 00:00:00 1970
X-Msuck: nntp://news.gmane.org/gmane.linux.lib.musl.general/14711
Path: news.gmane.org!.POSTED.blaine.gmane.org!not-for-mail
From: Szabolcs Nagy <nsz@port70.net>
Newsgroups: gmane.linux.lib.musl.general
Subject: Re: [PATCH] math: optimize lrint on 32bit targets
Date: Mon, 23 Sep 2019 20:38:19 +0200
Message-ID: <20190923183818.GE22009@port70.net>
References: <20190921155234.GA22009@port70.net>
 <20190922204335.GC22009@port70.net>
 <20190923174029.GN9017@brightrain.aerifal.cx>
Reply-To: musl@lists.openwall.com
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Injection-Info: blaine.gmane.org; posting-host="blaine.gmane.org:195.159.176.226";
	logging-data="245457"; mail-complaints-to="usenet@blaine.gmane.org"
User-Agent: Mutt/1.10.1 (2018-07-13)
To: musl@lists.openwall.com
Original-X-From: musl-return-14727-gllmg-musl=m.gmane.org@lists.openwall.com Mon Sep 23 20:38:33 2019
Return-path: <musl-return-14727-gllmg-musl=m.gmane.org@lists.openwall.com>
Envelope-to: gllmg-musl@m.gmane.org
Original-Received: from mother.openwall.net ([195.42.179.200])
	by blaine.gmane.org with smtp (Exim 4.89)
	(envelope-from <musl-return-14727-gllmg-musl=m.gmane.org@lists.openwall.com>)
	id 1iCTEH-0011lj-Ad
	for gllmg-musl@m.gmane.org; Mon, 23 Sep 2019 20:38:33 +0200
Original-Received: (qmail 10159 invoked by uid 550); 23 Sep 2019 18:38:30 -0000
Mailing-List: contact musl-help@lists.openwall.com; run by ezmlm
Precedence: bulk
List-Post: <mailto:musl@lists.openwall.com>
List-Help: <mailto:musl-help@lists.openwall.com>
List-Unsubscribe: <mailto:musl-unsubscribe@lists.openwall.com>
List-Subscribe: <mailto:musl-subscribe@lists.openwall.com>
List-ID: <musl.lists.openwall.com>
Original-Received: (qmail 10141 invoked from network); 23 Sep 2019 18:38:30 -0000
Mail-Followup-To: musl@lists.openwall.com
Content-Disposition: inline
In-Reply-To: <20190923174029.GN9017@brightrain.aerifal.cx>
Xref: news.gmane.org gmane.linux.lib.musl.general:14711
Archived-At: <http://permalink.gmane.org/gmane.linux.lib.musl.general/14711>

* Rich Felker <dalias@libc.org> [2019-09-23 13:40:29 -0400]:
> On Sun, Sep 22, 2019 at 10:43:35PM +0200, Szabolcs Nagy wrote:
> > +long lrint(double x)
> > +{
> > +	uint32_t abstop = asuint64(x)>>32 & 0x7fffffff;
> > +	uint64_t sign = asuint64(x) & (1ULL << 63);
> > +
> > +	if (abstop < 0x41dfffff) {
> > +		/* |x| < 0x7ffffc00, no overflow */
> > +		double_t toint = asdouble(asuint64(1/EPS) | sign);
> > +		double_t y = x + toint - toint;
> > +		return (long)y;
> > +	}
> > +	return lrint_slow(x);
> > +}
> >  #else
> >  long lrint(double x)
> >  {
> 
> This code should be considerably faster than calling rint on 64-bit
> archs too, no? I wonder if it should be something like (untested,
> written inline here):

yeah i'd expect it to be a bit faster, but e.g. a
target may prefer sign?-1/EPS:1/EPS to 1/EPS|sign,
and you need a threshold check even if there is no
inexact overflow issue:

> long lrint(double x)
> {
> 	uint32_t abstop = asuint64(x)>>32 & 0x7fffffff;
> 	uint64_t sign = asuint64(x) & (1ULL << 63);
> 
> #if LONG_MAX < 1U<<53 && defined(FE_INEXACT)
> 	if (abstop >= 0x41dfffff) return lrint_slow(x);

#else
	if (abstop >= 0x43300000) return (long)x;
	/* |x| < 2^52 <= 1/EPS */

> #endif
> 	/* |x| < 0x7ffffc00, no overflow */
> 	double_t toint = asdouble(asuint64(1/EPS) | sign);
> 	double_t y = x + toint - toint;
> 	return (long)y;
> }

i can try to benchmark this (although on x86_64 and
aarch64 there is single instruction lrint so i can
only benchmark machines where this is not relevant).