[Mpi3-rma] request-based ops

Jeff Hammond jhammond at alcf.anl.gov
Fri Jun 14 12:56:34 CDT 2013


"The completion of an MPI_RACCUMULATE operation indicates that the
origin buffer is free to be updated. It does not indicate that the
operation has completed at the target window."

How does waiting on this request give me the same behavior as IWIN_FLUSH?

Jeff

On Fri, Jun 14, 2013 at 12:23 PM, Jim Dinan <james.dinan at gmail.com> wrote:
> Jeff,
>
> How would iwin_flush be different in practice from doing nothing?  I can
> give you a trivial implementation that does nothing until you wait on the
> request, at which point I call blocking win_flush.  With my implementor hat
> on, I would view this function as a performance hint that indicates to the
> implementation that you will want to complete all operations thus far and
> none after.  Given a high quality implementation that actually makes
> background progress on one-sided communications, this should be unnecessary
> and I would probably implement it as above.  If you want to only complete
> specific operations, the request generating functions are available.
>
>  ~Jim.
>
>
>
> On Fri, Jun 14, 2013 at 11:09 AM, Jeff Hammond <jhammond at alcf.anl.gov>
> wrote:
>>
>> Yes, I was making a disingenuous argument to push back against the
>> fallacy that iwin_flush is not required.
>>
>> Jeff
>>
>> On Fri, Jun 14, 2013 at 10:25 AM, Jim Dinan <james.dinan at gmail.com> wrote:
>> > Hey now, blocking doesn't mean that MPI /must/ block, it only means that
>> > it
>> > /can/ block.  Blocking and synchronizing are certainly not the same;
>> > Ssend
>> > synchronizes, which is a stronger semantic than blocking.
>> >
>> >  ~Jim.
>> >
>> >
>> > On Wed, Jun 12, 2013 at 5:07 PM, Jeff Hammond <jhammond at alcf.anl.gov>
>> > wrote:
>> >>
>> >> Sure, let's separate these issues.  I think Pirate RMA (RRPUT,
>> >> RRACCUMULATE and RRRGET_ACCUMULATE) is a more _local_ solution in the
>> >> MPI standard sense :-)
>> >>
>> >> SEND is also a nonblocking operation because the implementation can
>> >> always buffer the data and return before the remote RECV is posted.
>> >> Only SSEND is blocking if one asserts that blocking is equivalent to
>> >> "requires remote agency to complete".
>> >>
>> >> So basically, I completely agree with the Forum back-pushers that
>> >> IWIN_FLUSH etc. are as useful as ISEND.
>> >>
>> >> Jeff
>> >>
>> >> On Wed, Jun 12, 2013 at 4:58 PM, Pavan Balaji <balaji at mcs.anl.gov>
>> >> wrote:
>> >> >
>> >> > The push-back at the Forum was that WIN_FLUSH and WIN_UNLOCK are
>> >> > local
>> >> > operations (in MPI's definition of local), so they are already
>> >> > nonblocking.
>> >> > I was not at the Forum.  I pointed out to Wesley after he returned
>> >> > that
>> >> > they
>> >> > are only local in the simple case where no one else is holding the
>> >> > lock.
>> >> > Otherwise they are not.
>> >> >
>> >> > Further, the proposal is not only about WIN_FLUSH and WIN_UNLOCK.  It
>> >> > was
>> >> > for a long list of blocking functions: COMM_ACCEPT, COMM_CONNECT,
>> >> > WIN_FENCE,
>> >> > WIN_COMPLETE, WIN_WAIT, WIN_UNLOCK, WIN_FLUSH, WIN_FLUSH_LOCAL,
>> >> > WIN_FLUSH_ALL, WIN_FLUSH_LOCAL_ALL, ...  The point was that MPI
>> >> > should
>> >> > deal
>> >> > with concepts, not specific function exceptions. Nonblocking
>> >> > communication
>> >> > is one such concept, and it should be valid for all operations (that
>> >> > are
>> >> > not
>> >> > local).
>> >> >
>> >> > FWIW, my proposal was only to add nonblocking variants to blocking
>> >> > calls.
>> >> > Adding extra per-op remote completion requests is a separate issue
>> >> > and
>> >> > should not be mixed with this.  I personally think it's useful (in
>> >> > fact,
>> >> > my
>> >> > original proposal for RPUT/RGET equivalents had it), but that's still
>> >> > a
>> >> > separate issue.
>> >> >
>> >> >  -- Pavan
>> >> >
>> >> >
>> >> > On 06/12/2013 09:41 AM, Jeff Hammond wrote:
>> >> >>
>> >> >> So Wes was telling me about IWIN_FLUSH yesterday (this function is a
>> >> >> great idea, btw) and the alternative of adding double-request RPUT
>> >> >> and
>> >> >> RACCUMULATE that provide a request for both local and remote
>> >> >> completion.  By induction, this would imply a triple-request
>> >> >> RGET_ACCUMULATE operation, which I also think is a good idea.  It's
>> >> >> really silly to have to wait for the result buffer to be ready to
>> >> >> reuse the origin buffer in RGET_ACCUMULATE.  It seems that many
>> >> >> implementations will be able to send the entire origin buffer a
>> >> >> nontrivial amount of time before the result comes back, particularly
>> >> >> if the remote side doesn't have hardware-based progress and the data
>> >> >> has to wait in a network buffer.
>> >> >>
>> >> >> I'm sorry that I missed the last day of the Forum in San Jose.  I
>> >> >> didn't know these operations were on the table.  They sound like a
>> >> >> great idea to me.
>> >> >>
>> >> >> Jeff
>> >> >>
>> >> >
>> >> > --
>> >> > Pavan Balaji
>> >> > http://www.mcs.anl.gov/~balaji
>> >>
>> >>
>> >>
>> >> --
>> >> Jeff Hammond
>> >> Argonne Leadership Computing Facility
>> >> University of Chicago Computation Institute
>> >> jhammond at alcf.anl.gov / (630) 252-5381
>> >> http://www.linkedin.com/in/jeffhammond
>> >> https://wiki.alcf.anl.gov/parts/index.php/User:Jhammond
>> >> ALCF docs: http://www.alcf.anl.gov/user-guides
>> >> _______________________________________________
>> >> mpi3-rma mailing list
>> >> mpi3-rma at lists.mpi-forum.org
>> >> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma
>> >
>> >
>> >
>> > _______________________________________________
>> > mpi3-rma mailing list
>> > mpi3-rma at lists.mpi-forum.org
>> > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma
>>
>>
>>
>> --
>> Jeff Hammond
>> Argonne Leadership Computing Facility
>> University of Chicago Computation Institute
>> jhammond at alcf.anl.gov / (630) 252-5381
>> http://www.linkedin.com/in/jeffhammond
>> https://wiki.alcf.anl.gov/parts/index.php/User:Jhammond
>> ALCF docs: http://www.alcf.anl.gov/user-guides
>> _______________________________________________
>> mpi3-rma mailing list
>> mpi3-rma at lists.mpi-forum.org
>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma
>
>
>
> _______________________________________________
> mpi3-rma mailing list
> mpi3-rma at lists.mpi-forum.org
> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma



-- 
Jeff Hammond
Argonne Leadership Computing Facility
University of Chicago Computation Institute
jhammond at alcf.anl.gov / (630) 252-5381
http://www.linkedin.com/in/jeffhammond
https://wiki.alcf.anl.gov/parts/index.php/User:Jhammond
ALCF docs: http://www.alcf.anl.gov/user-guides



More information about the mpiwg-rma mailing list