Home
last modified time | relevance | path

Searched refs:rank (Results 1 – 8 of 8) sorted by relevance

/libCEED/examples/fluids/src/
H A Dmisc.c379 PetscMPIInt rank, comm_size; in PrintRunInfo() local
381 PetscCallMPI(MPI_Comm_rank(comm, &rank)); in PrintRunInfo()
469 if (!rank) PetscCall(PetscMalloc1(comm_size, &gather_buffer)); in PrintRunInfo()
472 if (!rank) { in PrintRunInfo()
485 if (!rank) { in PrintRunInfo()
509 if (rranks[i] == rank) continue; // Ignore same-part global->local transfers in PrintRunInfo()
514 if (iranks[i] == rank) continue; in PrintRunInfo()
520 if (!rank) { in PrintRunInfo()
534 if (!rank) { in PrintRunInfo()
545 if (!rank) { in PrintRunInfo()
[all …]
H A Dmat-ceed.c255 PetscMPIInt size, rank; in MatView_Ceed() local
267 PetscCallMPI(MPI_Comm_rank(PetscObjectComm((PetscObject)mat_ceed), &rank)); in MatView_Ceed()
268 if (rank != 0) PetscFunctionReturn(PETSC_SUCCESS); in MatView_Ceed()
279 PetscCall(PetscSNPrintf(rank_string, 16, "on Rank %d", rank)); in MatView_Ceed()
/libCEED/examples/solids/src/
H A Dmisc.c116 PetscMPIInt rank; in ViewSolution() local
121 MPI_Comm_rank(comm, &rank); in ViewSolution()
122 if (!rank) { in ViewSolution()
/libCEED/examples/fluids/
H A Dnavierstokes.c219 PetscMPIInt rank; in main() local
220 MPI_Comm_rank(comm, &rank); in main()
221 if (!rank) { in main()
H A Dindex.md253 where the term in parentheses is a rank-1 diffusivity tensor that has been pulled back to the refer…
437 …etric positive-definite rank 2 tensor defining the width of the filter, $\bm{D}$ is the filter wid…
/libCEED/examples/petsc/
H A DREADME.md39 … which will run a problem-size sweep of 600, 1200, 2400, 4800, 9600, 192000 FEM nodes per MPI rank.
H A Dbpsraw.c346 PetscMPIInt size, rank; in main() local
425 PetscCall(MPI_Comm_rank(comm, &rank)); in main()
426 for (int d = 0, rank_left = rank; d < dim; d++) { in main()
/libCEED/doc/sphinx/source/
H A DlibCEEDapi.md77 > - each unknown $i$ has exactly one copy, on exactly one processor, $rank(i)$
136 > - CSR matrix on each rank
182 Each MPI rank can use one or more {ref}`Ceed`s, and each {ref}`Ceed`, in turn, can represent one or…
183 The idea is that every MPI rank can use any logical device it is assigned at runtime.
185 Another choice could be to run 1 MPI rank on the whole node and use 5 {ref}`Ceed` objects: 1 managi…