Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

Subject: Re: [OMPI users] Bug MPI_Iscatter
From: George Bosilca (bosilca_at_[hidden])
Date: 2013-11-22 20:01:05


On Nov 23, 2013, at 01:18 , Pierre Jolivet <jolivet_at_[hidden]> wrote:

> George,
>
> On Nov 22, 2013, at 5:21 AM, George Bosilca <bosilca_at_[hidden]> wrote:
>
>> Pierre,
>>
>> On Nov 22, 2013, at 02:39 , Pierre Jolivet <jolivet_at_[hidden]> wrote:
>>
>>> George,
>>> I completely agree that the code I sent was a good example of what NOT to do with collective and non-blocking communications, so I’m sending a better one.
>>> 1. I’m setting MPI_DATATYPE_NULL only on non-root processes. The root has a real datatype. Why should both match when using MPI_IN_PLACE ?
>>
>> Because it is a strong requirement of the MPI standard: the typemap of a send should be matched by its corresponding receive. Otherwise, it is legal to raise an exception of type MPI_ERR_TYPE.
>>
>>> 2-3-4. Yes, all these points are valid, this is of course just a minimalist example.
>>>
>>> My question is, if you are indeed saying that it is not a OpenMPI bug, what is the rationale for changing the behavior between MPI_Scatter and MPI_Iscatter when it comes down to the send type on non-root processes.
>>
>> Different algorithms implemented by different people. Some of them are more robust, while others less. In this case Scatter translate the count = 0 to a message length = 0, while the Iscatter always look for the extent of the datatype.
>>
>>> I don’t see any remark on that matter on the MPI 3.0 documentation.
>>
>> Indeed, and there is at least one example where MPI_DATATYPE_NULL is explicitly used for calls where the datatype does not matter (4.23 as an example). Horrible!!!
>
> That’s what I don’t get, why are you saying it’s horrible ? It is clearly written in the spec. that the data type is only significant at root (for Scatter), and that Iscatter is nothing else than a nonblocking variant of Scatter (so the value should also be significant only at root).

Because this is mixing two concepts: non-existence and non-significance.

> Moreover, there is at least one thing that is wrong in the sources:
> 1) in ompi/mca/coll/libnbc/nbc_igather.c, line 55 should read:
> if (MPI_SUCCESS != res) { printf("MPI Error in MPI_Comm_size() (%i)\n", res); return res; }
> instead of:
> if (MPI_SUCCESS != res) { printf("MPI Error in MPI_Comm_rank() (%i)\n", res); return res; }
>
> And I still have a hard time believing that the test line 56 in ompi/mca/coll/libnbc/nbc_igather.c — if (rank == root) — is not missing in ompi/mca/coll/libnbc/nbc_iscatter.c line 58, but I guess I will have to trust you on this one.

A patch has been submitted (r29736). Thanks for the bug report.

  George.

>
> You should probably specify somewhere that you differ from the standard for that function, other MPI implementations don’t have this limitation, c.f.http://pic.dhe.ibm.com/infocenter/zos/v1r12/index.jsp?topic=%2Fcom.ibm.zos.r12.fomp200%2Fipezps0025.htm or http://trac.mpich.org/projects/mpich/browser/src/mpi/coll/iscatter.c#L601
>
> Pierre
>
>> George.
>>
>>>
>>> Thanks.
>>>
>>> #include <mpi.h>
>>>
>>> int main(int argc, char** argv) {
>>> int taskid, ntasks;
>>> MPI_Init(&argc, &argv);
>>> MPI_Request rq;
>>>
>>> MPI_Comm_rank(MPI_COMM_WORLD,&taskid);
>>> MPI_Comm_size(MPI_COMM_WORLD,&ntasks);
>>> double* r;
>>> int l = 0;
>>> // This will run fine. MPI_DOUBLE
>>> if(taskid > 0)
>>> MPI_Iscatter(NULL, 0, MPI_DOUBLE, r, l, MPI_DOUBLE, 0, MPI_COMM_WORLD, &rq);
>>> else
>>> MPI_Iscatter(r, l, MPI_DOUBLE, MPI_IN_PLACE, 0, MPI_DATATYPE_NULL, 0, MPI_COMM_WORLD, &rq);
>>> MPI_Wait(&rq, MPI_STATUS_IGNORE);
>>> // This will run fine. MPI_DATATYPE_NULL
>>> if(taskid > 0)
>>> MPI_Scatter(NULL, 0, MPI_DATATYPE_NULL, r, l, MPI_DOUBLE, 0, MPI_COMM_WORLD);
>>> else
>>> MPI_Scatter(r, l, MPI_DOUBLE, MPI_IN_PLACE, 0, MPI_DATATYPE_NULL, 0, MPI_COMM_WORLD);
>>> // This will not run fine. MPI_DATATYPE_NULL
>>> if(taskid > 0)
>>> MPI_Iscatter(NULL, 0, MPI_DATATYPE_NULL, r, l, MPI_DOUBLE, 0, MPI_COMM_WORLD, &rq);
>>> else
>>> MPI_Iscatter(r, l, MPI_DOUBLE, MPI_IN_PLACE, 0, MPI_DATATYPE_NULL, 0, MPI_COMM_WORLD, &rq);
>>> MPI_Wait(&rq, MPI_STATUS_IGNORE);
>>> MPI_Finalize();
>>> }
>>>
>>> On Nov 21, 2013, at 4:34 PM, George Bosilca <bosilca_at_[hidden]> wrote:
>>>
>>>> Pierre,
>>>> There are several issues with the code you provided.
>>>>
>>>> 1. You can’t use an MPI_DATATYPE_NULL as the send datatype, not even when count is zero. At least the root must provide a real datatype. In fact the type signature of the send message (datatype and count) should match the type signature of the receiving datatype.
>>>>
>>>> 2. I know your count is zero, and no data will be transmitted but your code is difficult to read and understand.
>>>>
>>>> 3. MPI_Iscatter is a collective communication. As such all processes in the associated communicator (MPI_COMM_WORLD in your case) must participate to the collective. Thus, calling MPI_Iscatter only where tasked > 0 is incorrect (you explicitly excluded 0).
>>>>
>>>> 4. From the MPI standard perspective your example is not correct, as you are not allowed to call MPI_Finalize while there are messages pending. Now, Open MPI tolerate this, but it is clearly not standard behavior.
>>>>
>>>> #include <mpi.h>
>>>>
>>>> int main(int argc, char** argv)
>>>> {
>>>> int taskid, ntasks;
>>>> MPI_Init(&argc, &argv);
>>>> MPI_Request rq;
>>>> MPI_Comm_rank(MPI_COMM_WORLD,&taskid);
>>>> MPI_Comm_size(MPI_COMM_WORLD,&ntasks);
>>>> double r;
>>>> int l = 0;
>>>>
>>>> MPI_Iscatter(NULL, 0, MPI_DOUBLE, &r, l, MPI_DOUBLE, 0, MPI_COMM_WORLD, &rq);
>>>> MPI_Wait(&rq, MPI_STATUS_IGNORE);
>>>>
>>>> MPI_Finalize();
>>>> }
>>>>
>>>> George.
>>>>
>>>>
>>>> On Nov 21, 2013, at 23:19 , Pierre Jolivet <jolivet_at_[hidden]> wrote:
>>>>
>>>>> Hello,
>>>>> The following code doesn’t execute properly :
>>>>> #include <mpi.h>
>>>>>
>>>>> int main(int argc, char** argv) {
>>>>> int taskid, ntasks;
>>>>> MPI_Init(&argc, &argv);
>>>>> MPI_Request rq;
>>>>>
>>>>> MPI_Comm_rank(MPI_COMM_WORLD,&taskid);
>>>>> MPI_Comm_size(MPI_COMM_WORLD,&ntasks);
>>>>> double* r;
>>>>> int l = 0;
>>>>> if(taskid > 0)
>>>>> MPI_Iscatter(NULL, 0, MPI_DATATYPE_NULL, r, l, MPI_DOUBLE, 0, MPI_COMM_WORLD, &rq);
>>>>> MPI_Finalize();
>>>>> }
>>>>>
>>>>> Outcome:
>>>>> *** An error occurred in MPI_Type_extent
>>>>> *** MPI_ERR_TYPE: invalid datatype
>>>>>
>>>>> Hotfix: change MPI_DATATYPE_NULL to something else.
>>>>>
>>>>> Thanks for a quick fix.
>>>>> _______________________________________________
>>>>> users mailing list
>>>>> users_at_[hidden]
>>>>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>>>
>>>> _______________________________________________
>>>> users mailing list
>>>> users_at_[hidden]
>>>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>>
>>> _______________________________________________
>>> users mailing list
>>> users_at_[hidden]
>>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>
>> _______________________________________________
>> users mailing list
>> users_at_[hidden]
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>
> _______________________________________________
> users mailing list
> users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/users