[mpich-devel] Possible problem with accfence1 test

[Zhao, Xin]

Hi Nathan, Jeff,

We are aware of this bug and it is recently fixed in mpich/master. Could you try tonight’s mpich nightly snapshot (http://www.mpich.org/static/downloads/nightly/master/mpich/) ?

Thanks,
Xin

________________________________________
From: Jeff Hammond [jeff.science at gmail.com]
Sent: Tuesday, February 24, 2015 5:56 PM
To: devel at mpich.org
Subject: Re: [mpich-devel] Possible problem with accfence1 test

Rajeev pointed out offline that I cannot read. He said it nicely, but that doesn't mean I'm not a bleeping idiot.

Sorry for my epic fail. I hate stupid people, especially when it's me.

Jeff

Sent from my iPhone

> On Feb 24, 2015, at 1:32 PM, Nathan Hjelm <hjelmn at lanl.gov> wrote:
>
>
> Hey, I am looking that the accfence1 test in MPICH and I think the tests
> is invalid. The test attempts to execute an MPI_Accumulate with different
> datatypes for the origin and destination. The problem is that the test
> violates MPI 3.0 § 11.3.4 p. 426 1-4:
>
>
> Each datatype argument must be a predefined datatype or a derived
> datatype, where all basic components are of the same predefined
> datatype. Both datatype arguments must be constructed from the same
> predefined datatype. The operation op applies to elements of that
> predefined type.
>
>
> I see no wording in the standard that says this restriction does not
> apply when the operator is MPI_REPLACE. The test is correct if the
> operation is changed from MPI_Accumulate to MPI_Put.
>
> If the test is correct then it might make sense to make it explicit in
> the standard that the datatype restriction does not apply to MPI_REPLACE.
>
> -Nathan
> _______________________________________________
> To manage subscription options or unsubscribe:
> https://lists.mpich.org/mailman/listinfo/devel
_______________________________________________
To manage subscription options or unsubscribe:
https://lists.mpich.org/mailman/listinfo/devel