Message-ID: <457CEC0F.2030206@anagramm.de>
Date: Mon, 11 Dec 2006 06:26:39 +0100
From: Clemens Koller <clemens.koller@anagramm.de>
User-Agent: Thunderbird 1.5.0.8 (Windows/20061025)
MIME-Version: 1.0
To: Adrian Bunk <bunk@stusta.de>
CC: Folkert van Heusden <folkert@vanheusden.com>, linux-kernel@vger.kernel.org
Subject: Re: optimalisation for strlcpy (lib/string.c)
References: <20061210212350.GC30197@vanheusden.com> <20061210231305.GG10351@stusta.de>
In-Reply-To: <20061210231305.GG10351@stusta.de>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1104
Lines: 39

Hi, Adrian & Friends!

>> Like the other patch (by that other person), I think it is faster to not
>> do a strlen first.

There are PowerPC architectures, where a strlen is a matter of a single
instruction of the CPU.

Quote: "PowerPC 405 and 440 instruction sets offer the powerful
Determine Left-Most Zero Byte (DLMZB) instruction."

That's propably hard to beat.

So, if we really want to speed up these things, we should write
code which helps the compiler get that optimized instructions for
us - by improving the code of strlen() i.e.

Reference:
http://www-03.ibm.com/chips/power/powerpc/newsletter/sep2003/ppc_process_at_work2.html

Greets,

Clemens Koller
_______________________________
R&D Imaging Devices
Anagramm GmbH
Rupert-Mayer-Str. 45/1
81379 Muenchen
Germany

http://www.anagramm-technology.com
Phone: +49-89-741518-50
Fax: +49-89-741518-19

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/