hippylib.scheduling package¶

Submodules¶

hippylib.scheduling.collective module¶

class hippylib.scheduling.collective.MultipleSerialPDEsCollective(comm)[source]¶

Bases: object

Parallel reduction utilities when several serial systems of PDEs (one per process) are solved concurrently.

comm is mpi4py.MPI comm

allReduce(v, op)[source]¶: Case handled: - v is a scalar (float, int); - v is a numpy array (NOTE: v will be overwritten) - v is a dolfin.Vector (NOTE: v will be overwritten) Operation: op = "Sum" or “Avg” (case insentive).

rank()[source]¶

size()[source]¶

class hippylib.scheduling.collective.NullCollective[source]¶

Bases: object

No-overhead “Parallel” reduction utilities when a serial system of PDEs is solved on 1 process.

allReduce(v, op)[source]¶

rank()[source]¶

size()[source]¶

Module contents¶