[Mpi3-rma] Proposal 1 discussion points for next telecon

Pavan Balaji balaji at mcs.anl.gov
Mon Oct 25 23:35:54 CDT 2010


On 10/25/2010 10:58 PM, Torsten Hoefler wrote:
> Hi Pavan,
>> This proposal doesn't have an atomic GET operation.
>>
>> MPI_ACCUMULATE with MPI_REPLACE is an atomic PUT.
>>
>> MPI_GET_ACCUMULATE with MPI_NO_OP does not work as an atomic GET as it
>> does not take more than 1 count, or non-predefined datatypes.
> Correct, we had count>1 and ddts in an earlier version and changed it
> after heated discussions about buffering. I forgot to add it to the
> discussion items.  I have no huge problems to allow ddts and counts>1,
> however, I believe Brian and Keith were against it.
>
> We should see if an advice to users/implementers that MPI_NO_OP is a
> special case that doesn't require buffering and that all other
> operations might be really really slow with large data.
>
> Please consider this item 7 on the discussion list!

Yes, I remember the discussion and it is a valid argument -- it was with 
respect to buffering requirements because of retransmissions (for 
reliability).

Note that I'm not proposing that MPI_GET_ACCUMULATE be made more 
generic. I'm just saying that we need a (possible separate) function to 
do atomic GETs. However, if MPI_GET_ACCUMULATE is not as generic as GET, 
it should be given a different name (though, if you want to discuss 
names later, that's fine).

  -- Pavan

-- 
Pavan Balaji
http://www.mcs.anl.gov/~balaji



More information about the mpiwg-rma mailing list