Accéder au contenu.
Menu Sympa

starpu-devel - Re: [Starpu-devel] pthread_rwlock_t-related failures on Darwin.

Objet : Developers list for StarPU

Archives de la liste

Re: [Starpu-devel] pthread_rwlock_t-related failures on Darwin.


Chronologique Discussions 
  • From: Samuel Thibault <samuel.thibault@ens-lyon.org>
  • To: Cyril Roelandt <cyril.roelandt@inria.fr>
  • Cc: "starpu-devel@lists.gforge.inria.fr" <starpu-devel@lists.gforge.inria.fr>
  • Subject: Re: [Starpu-devel] pthread_rwlock_t-related failures on Darwin.
  • Date: Mon, 3 Sep 2012 00:10:13 +0200
  • List-archive: <http://lists.gforge.inria.fr/pipermail/starpu-devel>
  • List-id: "Developers list. For discussion of new features, code changes, etc." <starpu-devel.lists.gforge.inria.fr>

Cyril Roelandt, le Mon 03 Sep 2012 00:06:28 +0200, a écrit :
> On 09/02/2012 09:51 PM, Samuel Thibault wrote:
> >Cyril Roelandt, le Fri 31 Aug 2012 23:27:37 +0200, a écrit :
> >>Does anyone understand what's going on here ?
> >
> >Well, I'd simply say that Darwin sucks here :) And we then have to
> >cope with it by dynamically initializing the two tag_global_rwlock and
> >progression_hook_rwlock locks from starpu_init().
> >
>
> Doing that properly is gonna be a pain in the ass.

Why? The application is not supposed to call starpu_* functions before
starpu_init, and starpu_init already has a "call-once" guard.

Samuel





Archives gérées par MHonArc 2.6.19+.

Haut de le page