FORTRAN SOFTWARE CATALOG

Repository owner: DFTB+ Project (dftbplus)

mpifx

Typed modern Fortran MPI wrappers; single-process broadcast/reduction example.

Repository · Pinned source (1223bd515bf2) · Try in playground · Checked package example

GAMS classifications

About this package

Category
Parallel computing
License
BSD-2-Clause

Topics: collective-operations, communication, fortran, mpi, parallel-computing, wrappers

Classification scope and review notes

The upstream CMake library source list is generated with Fypp 3.2, with every generated file checksum locked in the recipe. The example exercises communicator initialization, real-vector broadcast, real and integer all-reduce and in-place maximum reduction on exactly one MPI process, checking API statuses and returned data. MPICH is pinned and UCX transports are limited to self/shared memory. This illustrates typed communication APIs, not parallel execution or speedup; point-to-point messaging, multiple processes and other wrappers are outside verification scope. Classification R covers the tested service routines.

Package dependencies

Resolved GitHub repositories used by the verified playground build, combining direct and indirect dependencies. This list does not describe internal module dependencies or native system libraries.

Required by this build

No additional GitHub package dependencies were recorded for this verified build.

Build record verified 2026-10-29.

Used by (0 selected packages)

No other selected build records this repository as a dependency. This is not a measure of usage outside the catalog.

Reviewed procedures

These mappings have pinned source evidence. A checked package example may exercise only some of them; source review is not a numerical benchmark.

mpifx_bcast / mpifx_allreduce / mpifx_allreduceip

Module: libmpifx_module

R

R: source-supported

Derivatives / callbacks: not applicable

The upstream CMake library source list is generated with Fypp 3.2, with every generated file checksum locked in the recipe. The example exercises communicator initialization, real-vector broadcast, real and integer all-reduce and in-place maximum reduction on exactly one MPI process, checking API statuses and returned data. MPICH is pinned and UCX transports are limited to self/shared memory. This illustrates typed communication APIs, not parallel execution or speedup; point-to-point messaging, multiple processes and other wrappers are outside verification scope. Classification R covers the tested service routines.

Pinned source: lib/mpifx_bcast.fpp · lib/mpifx_allreduce.fpp · lib/mpifx_comm.fpp

Author examples/tests: test/test_allreduce.f90 · test/test_bcast.f90