Open MPI User's Mailing List Archives

Subject: Re: [OMPI users] Blocking communication a thread better thenasynchronous progress?
From: Jeff Squyres (jsquyres_at_[hidden])
Date: 2009-08-20 08:52:48

• Next message: Jean Potsam: "[OMPI users] problem with installing openmp 1.3"
• Previous message: Jeff Squyres: "Re: [OMPI users] OpenMPI extremely slow with progress threads"
• In reply to: tomek: "[OMPI users] Blocking communication a thread better then asynchronous progress?"
• Next in thread: tomek: "Re: [OMPI users] Blocking communication a thread better thenasynchronous progress?"
• Reply: tomek: "Re: [OMPI users] Blocking communication a thread better thenasynchronous progress?"

On Aug 20, 2009, at 5:14 AM, tomek wrote:

> Is doing blocking communication in a separate thread better then
> asynchronous progress?
> (At least as a workaround until the proper implementation gets
> improved)
>

At the moment, yes. OMPI's asynchronous progress is "loosely
tested" (at best).

OMPI's threading support is somewhat stable for some devices (e.g.,
not OpenFabrics-based networks), but it's still somewhat new, so
feedback would be welcome here.

Per my other mail, depending on your network/etc., you might get
asynchronous behavior using non-blocking MPI functions.

-- 
Jeff Squyres
jsquyres_at_[hidden]

• Next message: Jean Potsam: "[OMPI users] problem with installing openmp 1.3"
• Previous message: Jeff Squyres: "Re: [OMPI users] OpenMPI extremely slow with progress threads"
• In reply to: tomek: "[OMPI users] Blocking communication a thread better then asynchronous progress?"
• Next in thread: tomek: "Re: [OMPI users] Blocking communication a thread better thenasynchronous progress?"
• Reply: tomek: "Re: [OMPI users] Blocking communication a thread better thenasynchronous progress?"