[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <alpine.LFD.1.10.0804281757340.3261@apollo.tec.linutronix.de>
Date: Mon, 28 Apr 2008 17:58:44 +0200 (CEST)
From: Thomas Gleixner <tglx@...utronix.de>
To: Alexander van Heukelum <heukelum@...tmail.fm>
cc: Linus Torvalds <torvalds@...ux-foundation.org>,
Harvey Harrison <harvey.harrison@...il.com>,
Ingo Molnar <mingo@...e.hu>,
Andrew Morton <akpm@...ux-foundation.org>,
LKML <linux-kernel@...r.kernel.org>,
David Miller <davem@...emloft.net>
Subject: Re: [PATCH] bitops: simplify generic bit finding functions
On Mon, 28 Apr 2008, Alexander van Heukelum wrote:
> > See patch below. It gives back the 1400 bytes on SPARC64 and other
> > platforms that have no instruction for find bit.
>
> Hi,
>
> I, personally, see this patch as a stopgap measure. The real problem
> is that the generic __ffs is inlined and ends up generating a lot
> of instructions.
>
> Until the generic implementation of __ffs is fixed not to be an
> enormous inline function, this seems to be a reasonable thing
> to do, though it's a shame that the optimization is now default-
> off for architectures with a good implementation of __ffs.
Yup, it hasn't been there before and we explicitely enable it on
x86. If there are other archs which have a good one it's a nobrainer
to enable it.
Thanks,
tglx
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists