[Mpi-forum] MPI_Count

Darius Buntinas buntinas at mcs.anl.gov
Mon Jan 25 16:01:03 CST 2010

"at least 64 bits" means that in 2074 (when we need 128bits as per 
Mark's estimation) you'll need to check for overflow when using the 
"old" mpi implementations that still use 64bit counts.


On 01/25/2010 03:43 PM, Rajeev Thakur wrote:
> We could still use MPI_Count and specify that it must be at least 64 bit.
> Rajeev
>> -----Original Message-----
>> From: mpi-forum-bounces at lists.mpi-forum.org
>> [mailto:mpi-forum-bounces at lists.mpi-forum.org] On Behalf Of
>> Darius Buntinas
>> Sent: Monday, January 25, 2010 3:34 PM
>> To: Main MPI Forum mailing list
>> Subject: Re: [Mpi-forum] MPI_Count
>> I liked Mark's suggestion.  Using MPI_Count rather than
>> explicitly fixing the size means the user has to check for overflow.
>> Did the person state what the portability issues with int64_t
>> could be?
>>    Is there a C "basic type" that would be compatible with a
>> fortran INTEGER*8?  BTW, we already added stdint datatypes to MPI 2.2.
>> -d
>> On 01/25/2010 03:04 PM, Jeff Squyres wrote:
>>> On Jan 24, 2010, at 9:21 PM, Snir, Marc wrote:
>>>> I would suggest to use explicitly 64 bit integers as the
>> type of count in the new functions. I.e., int64_t in C and
>> INTEGER(KIND=8) in Fortran. Both types are part of the
>> (C/Fortran) standard.
>>> FWIW, I mentioned the above point on the MPI3 Fortran WG
>> mailing list and got this reply:
>>>> Please do not touch any of the<stdint.h>   stuff with a bargepole!
>>>> Stick to the basic types and MPI type names.
>>>> There are many different ways where<stdint.h>   integers cause
>>>> portability, efficiency and other problems.  Inter alia,
>> the current
>>>> revision of C is thinking of changing them in ways that could be
>>>> incompatible with old code, and they are semantically incompatible
>>>> with Fortran and many other languages in several respects.
>>>> MPI_count gives the opportunity to evade any such chaos, whether
>>>> introduced by the standard or an implementation.
>> _______________________________________________
>> mpi-forum mailing list
>> mpi-forum at lists.mpi-forum.org
>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum
> _______________________________________________
> mpi-forum mailing list
> mpi-forum at lists.mpi-forum.org
> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum

More information about the mpi-forum mailing list