Steve,
I like this new proposal. As for the order of execution between
the complete_fn and a posted handler routine, I would prefer to state
either:
"The order is unspecified by MPI. However, a good quality
implementation will always use the same order (handler routine first
and complete_fn second, or vice-versa)." (This way, the behavior
for any given implementation is predictable. However, a portable
program should not rely on any order).
or:
"The order is the following: posted handler routine first and complete_fn
second." (Since the handler is associated with a specific request and
the complete_fn with a GR=meta-request, it seems more natural to me
to start with the handler routine first, and then proceed with the
complete_fn).
Another possible choice is to say that posting a handler to a request
associated
with a GR, substitutes the complete_fn for that given request (that
specific
instantiation of the GR), and therefore the order issue is irrelevant.
I think we should have a discussion of the pros and cons of each
alternative.
Jean-Pierre
(Embedded
image moved lederman @ cs.wisc.edu
to file: 12/05/96 12:03 PM
PIC10075.PCX)
To: mpi-external @ mcs.anl.gov
cc: (bcc: Jean-Pierre Prost/Watson/IBM Research)
Subject: new generalized request
proposal
--0__=gjYK5981AQeqerRq68GbbYM3ZXQ3miw7Sci9xRbtq2HbK6Vfg8wBotZx
Taking into account the responses from my previous mail and comments
made before SC96, I will now outline my proposal for generalized
requests (GR). I hope it is cleaner and defines the semantics better.
I would like to see what comments people have now so I can hopefully
write it up once. The terminology I use for null, inactive, and
active handle are from the MPI-1 definitions.
GR only have a nonblocking (nonpersistent) form. A template for a GR
is made with MPI_GR_INIT(start_fn, push_fn, complete_fn, cancel_fn,
MPI_Gr *gr_req). This is like the current MPI_META_REQUEST_CREATE but
the extra_state is removed and it returns a request that is a new type
of handle instead of an MPI_Request. Since the gr_req is never used
in MPI_START, MPI_WAIT/TEST, etc. this should make error detection a
little easier. The gr_req is never used directly in an active GR so
it is always "inactive" and you can start it as many times as you want.
A GR is started with
MPI_GR_BEGIN(MPI_Gr gr_req, extra_state, MPI_Request *req).
This starts the GR and returns a standard MPI request. req is active
when MPI_GR_BEGIN returns and causes start_fn to be called. push_fn can go
on later in the "background". Note that extra_state is given here so
you can have unique values for each instantiation of the GR.
MPI_MARK_REQUEST_COMPLETE(MPI_Request req) internally marks the GR as
done. The only type of req allowed in this call is one from an
MPI_GR_BEGIN (i.e., can't do a regular MPI_Request). The req is still
active when this is done.
MPI_WAIT/TEST(req, status) will return true/complete on the GR if
MPI_MARK_REQUEST_COMPLETE has been called. This causes the
complete_fn to be called with the status provided. complete_fn will
finish before wait/test returns. On return, req is deallocated and
the handle is null by setting it to MPI_REQUEST_NULL. By definition
the req is now "inactive".
MPI_GR_FREE(MPI_Gr *gr_req) marks gr_req for deallocation and makes the
handle null by setting it to MPI_GR_NULL. In the MPI way, you can do
this even if there are GR what are outstanding that were created from
this template.
As with pt-to-pt you can do a MPI_CANCEL(req) on a req that is a GR.
As with pt-to-pt you still need to do a test/wait on req. Advice to
users is that since complete_fn gets called at the test/wait, you need
to see if req has been cancelled if that matters.
You can mark a GR for deallocation and cause the handle to become null
(MPI_NULL_REQUEST) by calling MPI_REQUEST_FREE(req). The req may
still be active. It will become inactive after
MPI_MARK_REQUEST_COMPLETE finishes. Advice to impl: The complete_fn
can and must be called after MPI_MARK_REQUEST_COMPLETE even if the req
has been freed. The status supplied to complete_fn is MPI_STATUS_NULL
in this case.
Interaction with handlers: If a handler and the complete_fn are both
elegible to execute (for example, the GR finishes while a wait is
active on the GR and a handler is attached to the GR) then MPI makes
no statement about the order in which they will execute. If someone
thinks we need to specify order and has a proposal I am open to this.
Geneal advice: If callbacks in GR (or handlers) change the state of MPI
handles (such as freeing a request), care must be taken that the "main
thread" of code will not generate errors due to this change.
Clarification to MPI-1: To help avoid errors from asynchronous
changes, MPI_CANCEL will accept the null handle MPI_REQUEST_NULL.
When this happens, MPI_CANCEL will simply return without generating an
error.
##########################################
Jean-Pierre Prost
IBM T.J. Watson Research Center
PO Box 218
Yorktown Heights, NY 10598
USA
Phone: (914) 945 3225 - Fax: (914) 945 2141
Lotus Notes: Jean-Pierre Prost @ IBM Research
Internet: jpprost@watson.ibm.com
URL: http://www.research.ibm.com/people/p/prost/
##########################################
--0__=gjYK5981AQeqerRq68GbbYM3ZXQ3miw7Sci9xRbtq2HbK6Vfg8wBotZx
Content-type: application/octet-stream;
name="PIC10075.PCX"
Content-transfer-encoding: base64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--0__=gjYK5981AQeqerRq68GbbYM3ZXQ3miw7Sci9xRbtq2HbK6Vfg8wBotZx--