Jeff Hammond

The blocking case is feasible. The nonblocking case requires crazy stuff, maybe generalized requests.

There are at least 3 cases to consider, where we assume the buffer is a non-contiguous subarray. ## Vector case The datatype argument corresponds to an element of the array...

The project is maintained (bugs will be fixed) but not developed (features will not be added). Once the feature set I proposed made it into MPI 4.0, I moved on...

yes, allowing others to borrow what they need from BigMPI and integrate into their own projects to avoid another dependency was an explicit design goal. `BigMPI_Factorize_count` is not strictly necessary...

You are a co-author of a paper that contains the following: > Unfortunately, nonblocking v-collectives cannot be implemented by using the aforementioned approaches. _In the case of the neighborhood collective...

Unfortunately, generalized requests are useless without threads. This is a well-known flaw. I think it is covered in http://www.mcs.anl.gov/~thakur/papers/grequest-redesign.pdf. If not there, then I look up the details, but the...

No, that's the problem with generalized requests. If you create one then wait on it, it will hang forever unless there is a thread driving progress out-of-band. And you probably...

Please add a new one, possibly derived from the ALLTOALLW (renamed to NEIGHBORHOOD_ALLTOALLW I guess) case. That way it's easy to compare them and there is a work around if...

Nope, CMake is being stupid and (1) failing to use the MPI wrapper scripts, (2) detecting the wrong compilers for the MPI implementation. `/opt/mpich/dev/intel/` is MPICH compiled with the Intel...

The build fails and it also appears to be invoking `configure`, for reasons I do not understand. ```sh jrhammon-mac01:build-cmake jrhammon$ make [ 2%] Generating ../../src/bigmpiconf.h autoreconf: Entering directory `.' autoreconf:...