petsc-3.4.5 2014-06-29
KSPPIPECG
Pipelined conjugate gradient method. There method has only a single non-blocking reduction per iteration, compared to 2 blocking for standard CG. The
non-blocking reduction is overlapped by the matrix-vector product and preconditioner application.
See also KSPPIPECR, where the reduction is only overlapped with the matrix-vector product.
Level
beginner
Notes
MPI configuration may be necessary for reductions to make asynchronous progress, which is important for performance of pipelined methods.
See the FAQ on the PETSc website for details.
Contributed by
Pieter Ghysels, Universiteit Antwerpen, Intel Exascience lab Flanders
Reference
P. Ghysels and W. Vanroose, "Hiding global synchronization latency in the preconditioned Conjugate Gradient algorithm",
Submitted to Parallel Computing, 2012.
See Also
KSPCreate(), KSPSetType(), KSPPIPECR, KSPGROPPCG, KSPPGMRES, KSPCG, KSPCGUseSingleReduction()
Level:none
Location:src/ksp/ksp/impls/cg/pipecg/pipecg.c
Index of all KSP routines
Table of Contents for all manual pages
Index of all manual pages