Re: [PATCH 1/8] add lib/gcd.c

linux-mips

Re: [PATCH 1/8] add lib/gcd.c

To:	James Cloos <cloos@jhcloos.com>
Subject:	Re: [PATCH 1/8] add lib/gcd.c
From:	Alan Cox <alan@lxorguk.ukuu.org.uk>
Date:	Sat, 13 Jun 2009 16:28:02 +0100
Cc:	linux-kernel@vger.kernel.org, "Linux-MIPS" <linux-mips@linux-mips.org>, Florian Fainelli <florian@openwrt.org>, Andrew Morton <akpm@linux-foundation.org>, Takashi Iwai <tiwai@suse.de>, Ralf Baechle <ralf@linux-mips.org>
In-reply-to:	<m38wjwz5ur.fsf@lugabout.jhcloos.org>
Original-recipient:	rfc822;linux-mips@linux-mips.org
References:	<200906041615.10467.florian@openwrt.org> <m38wjwz5ur.fsf@lugabout.jhcloos.org>
Sender:	linux-mips-bounce@linux-mips.org

> Would the binary gcd algorithm not be a better fit for the kernel?
> 
> It avoids division, using only shifts and subtraction:

Time them both and see. I suspect on a lot of processors the divide based
one now wins. We also have fls() and ffs() which may mean some platforms
can implement the first two loops even better.

Could well be the shift based one is better for some processors only.

[More with this subject...]

<Prev in Thread]	Current Thread	[Next in Thread>
[PATCH 1/8] add lib/gcd.c, Florian Fainelli Re: [PATCH 1/8] add lib/gcd.c, Sergei Shtylyov Re: [PATCH 1/8] add lib/gcd.c, Sergei Shtylyov Re: [PATCH 1/8] add lib/gcd.c, Florian Fainelli Re: [PATCH 1/8] add lib/gcd.c, Joe Perches Re: [PATCH 1/8] add lib/gcd.c, Andrew Morton Re: [PATCH 1/8] add lib/gcd.c, Andrew Morton Re: [PATCH 1/8] add lib/gcd.c, James Cloos Re: [PATCH 1/8] add lib/gcd.c, Alan Cox <= Re: [PATCH 1/8] add lib/gcd.c, James Cloos Re: [PATCH 1/8] add lib/gcd.c, James Cloos

Previous by Date:	Re: [PATCH 1/8] add lib/gcd.c, James Cloos
Next by Date:	Re: [PATCH 1/8] add lib/gcd.c, James Cloos
Previous by Thread:	Re: [PATCH 1/8] add lib/gcd.c, James Cloos
Next by Thread:	Re: [PATCH 1/8] add lib/gcd.c, James Cloos
Indexes:	[Date] [Thread] [Top] [All Lists]