[Mpi3-rma] Call for errata
Jim Dinan
dinan at mcs.anl.gov
Fri Feb 15 09:04:47 CST 2013
Hi Hubert,
I updated the proposed text in the ticket. Thanks for helping to fix this.
~Jim.
On 2/15/13 3:24 AM, Hubert Ritzdorf wrote:
> Hi Jim,
>
> This text is ok for me.
>
> Many thanks
>
> Hubert
>
>> -----Original Message-----
>> From: mpi3-rma-bounces at lists.mpi-forum.org [mailto:mpi3-rma-
>> bounces at lists.mpi-forum.org] On Behalf Of Jim Dinan
>> Sent: Wednesday, February 13, 2013 9:59 PM
>> To: mpi3-rma at lists.mpi-forum.org
>> Subject: Re: [Mpi3-rma] Call for errata
>>
>> Hi Hubert,
>>
>> Ok, I think I understand the problem -- I am parsing "fit in"
>> incorrectly. Hopefully the following text should correct the
>> misinterpretation of "fit in" and also correctly specify what data is
>> transferred from target to origin.
>>
>> p. 428, line 15-17 quoted:
>>
>> Accumulate origin_count elements of type origin_datatype from the origin
>> buffer (origin_addr) to the buffer at offset target_disp, in the target
>> window specified by target_rank and win, using the operation op and
>> return in the result buffer result_addr the content of the target
>>
>> OLD LINE 18:
>>
>> buffer before the accumulation.
>>
>> NEW LINE 18:
>>
>> buffer before the accumulation, specified by target_count and
>> target_datatype.
>>
>> p. 428, line 23-24, replace "fit in" with:
>>
>> target_datatype must not specify overlapping entries, and the target
>> buffer must *be contained within* the target window or in attached
>> memory in a dynamic window.
>>
>> Thanks again for your help,
>> ~Jim.
>>
>> On 2/1/13 4:24 AM, Hubert Ritzdorf wrote:
>>> Hi Jim,
>>>
>>> I agree to the semantics below.
>>> However, ticket 355 specifies
>>>
>>> -------
>>> In addition, there appears to be a typo in the current text
>> (s/target/origin/).
>>>
>>> Current text on p. 458, line 23-24:
>>>
>>> target_datatype must not specify overlapping entries, and the target
>> buffer
>>> must fit in the target window or in attached memory in a dynamic window.
>>>
>>> Suggested text:
>>>
>>> target_datatype must not specify overlapping entries, and the *origin*
>> buffer
>>> must fit in the target window or in attached memory in a dynamic window.
>>> ...
>>> -------
>>>
>>> I think, that the original text is correct and the suggested text is
>> incorrect.
>>> The original text corresponds to the text for MPI_GET. The target buffer
>>> must fit in the target window since the target data is transferred to
>> the origin's
>>> result buffer.
>>>
>>> Hubert
>>> ________________________________________
>>> From: mpi3-rma-bounces at lists.mpi-forum.org [mpi3-rma-bounces at lists.mpi-
>> forum.org] on behalf of Jim Dinan [dinan at mcs.anl.gov]
>>> Sent: Wednesday, January 30, 2013 6:35 PM
>>> To: mpi3-rma at lists.mpi-forum.org
>>> Subject: Re: [Mpi3-rma] Call for errata
>>>
>>> Hi Hubert,
>>>
>>> It's no bother; I appreciate your help in ensuring that we get this
>> right.
>>>
>>> I didn't fully follow your description below (maybe this is just
>>> terminology). The semantics that we mean to convey are:
>>>
>>> * The origin data (specified by origin buffer parameters) must fit in
>>> the target buffer.
>>> * The target data (specified by target buffer parameters) must fit in
>>> the origin's result buffer.
>>>
>>> Cheers,
>>> ~Jim.
>>>
>>> On 1/30/13 11:26 AM, Hubert Ritzdorf wrote:
>>>> Hi Jim,
>>>>
>>>> this is really hard to understand from the description.
>>>>
>>>> Nevertheless, the target buffer must fit into the target window (such
>> as in MPI_GET),
>>>> not the origin buffer. And the origin buffer must fit into the target
>> buffer.
>>>>
>>>> Sorry to bother you
>>>>
>>>> Hubert
>>>> ________________________________________
>>>> From: mpi3-rma-bounces at lists.mpi-forum.org [mpi3-rma-bounces at lists.mpi-
>> forum.org] on behalf of Jim Dinan [dinan at mcs.anl.gov]
>>>> Sent: Wednesday, January 30, 2013 5:12 PM
>>>> To: mpi3-rma at lists.mpi-forum.org
>>>> Subject: Re: [Mpi3-rma] Call for errata
>>>>
>>>> Hi Hubert,
>>>>
>>>> For Get_accumulate, the origin buffer parameters specify how much data
>>>> is accumulated at the target, and the target buffer parameters specify
>>>> how much data will be received into the result buffer. These semantics
>>>> do not change, based on which operation is used. This is what we are
>>>> trying to clarify with the new text in #355.
>>>>
>>>> ~Jim.
>>>>
>>>> On 1/29/13 2:24 PM, Hubert Ritzdorf wrote:
>>>>> Hi Jim,
>>>>>
>>>>> you are right. Datatypes created by
>> MPI_TYPE_CREATE_F90_{INTEGER,REAL,COMPLEX}
>>>>> are defined as predefined nevertheless they are handles. MPI_WCHAR was
>> only a joke to
>>>>> a previous discussion.
>>>>>
>>>>> I think ticket 355 doesn't clarify this. It doesn't specify that
>> target_count items of target_datatype
>>>>> are transferred if MPI_NO_OP is specified. It says only something
>> about (minimal/maximal) size of buffers
>>>>> nothing about the items transferred and is independent of MPI_NO_OP.
>>>>> You could interpret it that always target_count items of
>> target_datatype are returned to
>>>>> the result buffer independent on origin_count and origin datatype
>> (even if op is not MPI_NO_OP).
>>>>>
>>>>> I think that it is much more clear for the reader if ticket 250
>> specifies:
>>>>>
>>>>> When MPI_NO_OP is specified as the operation, the origin buffer
>> arguments are ignored
>>>>> and target_count elements of type target_datatype are returned from
>> the buffer at offset target_disp
>>>>> to result buffer result_addr.
>>>>>
>>>>> Best regards
>>>>>
>>>>> Hubert
>>>>>
>>>>> ________________________________________
>>>>> From: mpi3-rma-bounces at lists.mpi-forum.org [mpi3-rma-
>> bounces at lists.mpi-forum.org] on behalf of Jim Dinan [dinan at mcs.anl.gov]
>>>>> Sent: Monday, January 28, 2013 11:51 PM
>>>>> To: mpi3-rma at lists.mpi-forum.org
>>>>> Subject: Re: [Mpi3-rma] Call for errata
>>>>>
>>>>> Hi Hubert,
>>>>>
>>>>> Please correct me if I'm wrong, but as far as I can tell, every type
>>>>> that is internal to the MPI implementation (including Fortran and pair
>>>>> types) are "predefined".
>>>>>
>>>>> The F90 types are described as predefined in the standard (pg. 617-
>> 618).
>>>>>
>>>>> MPI_WCHAR is also predefined (pg. 665).
>>>>>
>>>>> Tables 3.x say "predefined" in the table caption.
>>>>>
>>>>> This wording was copied from the original MPI_Accumulate text in MPI
>>>>> 2.2, so if predefined is not all-encompassing, we may not be able to
>> fix
>>>>> this as an erratum.
>>>>>
>>>>> Re: Ticket 350 -- I think we fixed this with ticket 355. Could you
>> take
>>>>> a look at that ticket and see if this clears up your concerns?
>>>>>
>>>>> https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/355
>>>>>
>>>>> Thanks for your detailed feedback!
>>>>> ~Jim.
>>>>>
>>>>> On 1/28/13 1:04 PM, Hubert Ritzdorf wrote:
>>>>>> Hi,
>>>>>>
>>>>>> Page 429, Line 41-42 specifies for MPI_Fetch_and_op:
>>>>>>
>>>>>> The datatype argument must be a predefined datatype.
>>>>>>
>>>>>> I think it should be:
>>>>>>
>>>>>> The datatype argument must be a predefined or MPI basic datatype (cf.
>> Section 5.9.2 on page 176).
>>>>>>
>>>>>> Reasons:
>>>>>>
>>>>>> (*) This would be consistent to the reduce functions and
>> MPI_Compare_and_swap
>>>>>> and would allow handles returned by
>> MPI_TYPE_CREATE_F90_INTEGER,
>>>>>> MPI_TYPE_CREATE_F90_REAL, or MPI_TYPE_F90_COMPLEX.
>>>>>> (which are currently excluded since they are not
>> predefined).
>>>>>>
>>>>>> (*) MPI_Compare_and_swap accepts handles created by
>>>>>> MPI_TYPE_CREATE_F90_INTEGER (they are contained in Fortran
>> integer category).
>>>>>>
>>>>>> (*) This proposed change support also atomic gets of MPI_WCHAR.
>>>>>>
>>>>>>
>>>>>> Additionally, on Page 430, Line 39:
>>>>>> predefined datatypes
>>>>>> should be replaced by
>>>>>> basic datatypes
>>>>>> since Section 5.9.2 defines the MPI basic datatypes and not the
>> predefined
>>>>>> datatypes (which are defined in Tables 3.x).
>>>>>>
>>>>>> Ticket 350 (MPI_NO_OP in new accumulate functions, origin buffer
>> arguments are ignored) should also
>>>>>> state that the number of entries transferred is defined by
>> target_count
>>>>>>
>>>>>> Hubert
>>>>>>
>>>>>> ________________________________________
>>>>>> From: mpi3-rma-bounces at lists.mpi-forum.org [mpi3-rma-
>> bounces at lists.mpi-forum.org] on behalf of Jim Dinan [dinan at mcs.anl.gov]
>>>>>> Sent: Monday, January 28, 2013 4:54 PM
>>>>>> To: MPI 3.0 Remote Memory Access working group
>>>>>> Subject: [Mpi3-rma] Call for errata
>>>>>>
>>>>>> Hi All,
>>>>>>
>>>>>> We are assembling the list of RMA errata to be voted on at the March
>>>>>> meeting. Currently, we have tickets #347, #348, #350, and #355 (I'm
>>>>>> working on official wording for these changes and will circulate it
>> soon).
>>>>>>
>>>>>> Are there any other errata items that should be included on the
>> agenda
>>>>>> for the upcoming meeting?
>>>>>>
>>>>>> Thanks,
>>>>>> ~Jim.
>>>>>> _______________________________________________
>>>>>> mpi3-rma mailing list
>>>>>> mpi3-rma at lists.mpi-forum.org
>>>>>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma
>>>>>>
>>>>>>
>>>>>> Click
>> https://www.mailcontrol.com/sr/cqZpjZJWCcHGX2PQPOmvUsQN7C0BBstkddyjT4P!KFP
>> MxAFFaa8ieyScSFKfD4GCvgRNeNI84u45W2BPFL9JFA== to report this email as
>> spam.
>>>>>>
>>>>>> _______________________________________________
>>>>>> 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
>>>>>
>>>>> _______________________________________________
>>>>> 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
>>>>
>>>> _______________________________________________
>>>> 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
>>>
>>> _______________________________________________
>>> 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
>>
>>
>> _______________________________________________
>> mpi3-rma mailing list
>> mpi3-rma at lists.mpi-forum.org
>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma
More information about the mpiwg-rma
mailing list