Experiments with Parallelizing Tribology Simulations

Experiments with Parallelizing a Tribology Application

Different parallelization methods vary in their system requirements, programming styles, efficiency of exploring parallelism, and the application characteristics they can handle. Different applications can exhibit totally different performance gains depending on the parallelization method used. This paper compares OpenMP, MPI, and Strings( A distributed shared memory) for parallelizing a compli...

Comparing Various Parallelizing Approaches for Tribology

Different parallelization methods vary in their system requirements, programming styles, efficiency of exploring parallelism, and the application characteristics they can handle. For different situations, they can exhibit totally different performance gains. This paper compares OpenMP, MPI, and Strings for parallelizing a complicated tribology problem. The problem size and computing infrastruct...

Parallelizing OMNeT++ simulations using Xgrid

Experiments with auto - parallelizing 1 SPEC 2000 FP benchmarks

In this paper, we document the experimental work in our attempts to 7 automatically parallelize SPEC2000FP benchmarks for SMP machines. This is 8 not purely a research project. It was implemented within IBM’s software labo9 ratory in a commercial compiler infrastructure which implements OpenMP 2.0 10 specifications in both Fortran and C/C++. From the beginning, our emphasis is 11 on using simpl...

APPARC PCA5 Parallelizing Distinct Element Simulations

The parallelization of distinct element models is discussed with particular attention being paid to the problem of load balancing. One method for solving the load balancing problem through the use of a local, dynamic procedure is given and an implementation on the Cray-T3D and the Intel Paragon is described. The theoretical issues surrounding the load balancing problems are shown to map easily ...