[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [mpi-21] ABI (was: Call for MPI 2.2 and 3.0...)

To: mpi-21@xxxxxxxxxxxxx
Subject: Re: [mpi-21] ABI (was: Call for MPI 2.2 and 3.0...)
From: Greg Lindahl <lindahl@xxxxxxx>
Date: Wed, 5 Dec 2007 11:32:24 -0800
Delivered-to: mpifrm-mpi-21-outgoing@mailbouncer.mcs.anl.gov
Delivered-to: mpifrm-mpi-21@mailbouncer.mcs.anl.gov
In-reply-to: <007901c83775$06542be0$860add8c@mcs.anl.gov>
References: <mp64xtryhGbQ.rSj4xqNx@smtp.gmail.com> <5ECAB1304A8B5B4CB3F9D6C01E4E21A2D3B655@swsmsx413.ger.corp.intel.com> <20071205191905.GA25173@bx9.net> <007901c83775$06542be0$860add8c@mcs.anl.gov>
Reply-to: mpi-21@xxxxxxxxxxxxx
Sender: owner-mpi-21@xxxxxxxxxxxxx
User-agent: Mutt/1.5.13 (2006-08-11)

On Wed, Dec 05, 2007 at 01:28:33PM -0600, Rajeev Thakur wrote:

> More than holes in the standard, it is because people (sometimes
> unknowingly) assume things not guaranteed by the standard, e.g., code that
> relies on MPI_Send being  nonblocking or MPI_Get being blocking. So it's
> more often user error.

I understand this. However, we have to collect data before we figure
out what to discard.

-- greg

References:
- Re: [mpi-21] ABI (was: Call for MPI 2.2 and 3.0...)
  - From: William Yu
- RE: [mpi-21] ABI (was: Call for MPI 2.2 and 3.0...)
  - From: Supalov, Alexander
- Re: [mpi-21] ABI (was: Call for MPI 2.2 and 3.0...)
  - From: Greg Lindahl
- RE: [mpi-21] ABI (was: Call for MPI 2.2 and 3.0...)
  - From: Rajeev Thakur

Prev by Date: RE: [mpi-21] ABI (was: Call for MPI 2.2 and 3.0...)
Next by Date: RE: [mpi-21] ABI (was: Call for MPI 2.2 and 3.0...)
Previous by thread: RE: [mpi-21] ABI (was: Call for MPI 2.2 and 3.0...)
Next by thread: RE: [mpi-21] ABI (was: Call for MPI 2.2 and 3.0...)
Index(es):
- Date
- Thread