Message-passing interface

W. Gropp, E. Lusk and A. Skjellum, Using MPI Portable Parallel Programming with Message-Passing Interface, Scientific and Engineering Computation series, 1994. 

Figure 2 Speedup for CISD test calculations on CO using the public domain PVM message passing interface.

We show in Figs. 2 and 3 the speed up for a Davidson iteration obtained with the PVM [17] ( Parallel Virtual Machine ) and PVMe [18] ( PVM enhanced ) message passing interfaces respectively. Speed-up factors are here relative to the sequential version of the program (n=l), and the theoretical mciximum has been defined according to the expression s n) — n — I appropriate to the used master/slave model. 

Information and resources relating to the Message Passing Interface (MPI) project is available at http //www.netlib.org/mpi/. ... 

Due to the nature of FFT, or spectral transforms in general, parallelization of the solver is more suited to a shared memory architecture than to the Message Passing Interface approach. Further, since the most time-consuming portion of the code deals with calculating the RHS of the equation, we choose to apply a single threaded library for ODE solvers (gsl in our case) and only parallelize the calculation of derivatives needed in the ODE solver. 

The message-passing interface (MPI) standardization effort has produced a draft of a proposed standard interface.More than 40 research institutes and computer hardware and software vendors are participating in this international effort. 

LAM/MPl (2004) Local Area Multicomputer Message Passing Interface -... 

MPICH (2004) Message Passing Interface CHameleon - Homepage... 

The scaling of the model performance with the number of processors is usually better with message passing programming (MPI message passing interface) than with a compiler parallelized code (Open MP) for relatively small problems. However, the preference of the different programming techniques is under debate. 

The major task undertaken as a part of the code development efforts during the past year was implementation of the Message Passing Interface (MPI) such that the code could be run on parallel computers. This is a very important step, as the intensity of the planned simulations makes it impossible to generate the results using only a single processor. 

The Message-Passing Interface (MPI) is the primary mechanism used for explicit message-passing in scientific computing applications. This appendix briefly discusses some of fhe most commonly used MPI routines. 

---