This is the mail archive of the libc-alpha@sources.redhat.com mailing list for the glibc 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: [patch] hp-timing for powerpc64

From: Benjamin Herrenschmidt <benh at kernel dot crashing dot org>
To: Ulrich Drepper <drepper at redhat dot com>
Cc: Paul Mackerras <paulus at samba dot org>, Matthieu Castet <castet dot matthieu at free dot fr>, libc-alpha at sources dot redhat dot com
Date: Mon, 20 Jun 2005 14:24:46 +1000
Subject: Re: [patch] hp-timing for powerpc64
References: <42B280A4.7050605@free.fr> <42B3966D.2030402@redhat.com> <17076.1865.189468.938214@cargo.ozlabs.ibm.com> <42B43934.5030000@redhat.com>

On Sat, 2005-06-18 at 08:09 -0700, Ulrich Drepper wrote:
> Paul Mackerras wrote:
> 
> > Do we use rdtsc on x86 machines?  If not rdtsc, what do we use?
> 
> Yes, we do, but at least it means that each unit is one cycle of t he
> CPU which then can be translated into seconds.  From what I know this
> isn't the case with mftb, where different implementations increment the
> counter differently.

Note that the vDSO page hast the calibration infos... So with vDSO
enabled kernels either he could just use gettimeofday (which is really
fast) or I could add some additional routine to the vDSO for 2.6.13 that
returns the timebase calibration if you think that is useful for the
generically.

Ben.

References:
- [patch] hp-timing for powerpc64
  - From: Matthieu Castet
- Re: [patch] hp-timing for powerpc64
  - From: Ulrich Drepper
- Re: [patch] hp-timing for powerpc64
  - From: Paul Mackerras
- Re: [patch] hp-timing for powerpc64
  - From: Ulrich Drepper

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