This is the mail archive of the binutils@sourceware.org mailing list for the binutils project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: overhead of bfd_{get,put}*()

From: "H.J. Lu" <hjl dot tools at gmail dot com>
To: Ian Lance Taylor <iant at google dot com>
Cc: David Miller <davem at davemloft dot net>, binutils at sourceware dot org
Date: Tue, 23 Feb 2010 09:33:42 -0800
Subject: Re: overhead of bfd_{get,put}*()
References: <20100222.173858.90782430.davem@davemloft.net> <mcraav0djrc.fsf@dhcp-172-17-9-151.mtv.corp.google.com>

On Tue, Feb 23, 2010 at 8:00 AM, Ian Lance Taylor <iant@google.com> wrote:
> David Miller <davem@davemloft.net> writes:
>
>> The top offenders were, surprisingly for me, bfd_getb64(),
>> bfd_putb64() and bfd_getb_signed_64(). ?And it's not because they
>> touch memory, it's the byte loads and shift/or dance they do.
>
> This is exactly why gold does its complex template dance: to avoid
> that overhead.
>
> Those functions will hit unaligned data in some cases.
>
> Ian
>

We can define host specific bfd_{get,put}*() to optimize for
hosts which don't require strict alignment for integers.

-- 
H.J.

Follow-Ups:
- Re: overhead of bfd_{get,put}*()
  - From: Joseph S. Myers

References:
- overhead of bfd_{get,put}*()
  - From: David Miller
- Re: overhead of bfd_{get,put}*()
  - From: Ian Lance Taylor

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]