The initialization and get/put functions have existed in our MPI
implementation on top of Puma portals for the Paragon and TeraFLOPS
machine for over two months. We have several ASCI users who are
in the process of porting their shmem codes from the T3D to our
MPI-2 one sided interface, which is essentially what was proposed
in the March 4th edition of the document. Our implementation
currently ignores the target counter argument to the put functions
(which will require a handler or something at the target), so I
voted against having this functionality at the last meeting.
I have documentation that is dated December '95 for an MPI-2 one sided
communications implementation that EPCC has done for the Cray T3D also.