Search Results for "multi-threaded"

...It shows % completed, time remaining, time elapsed, number of threads, MPI_Rank(if any), CPU usage & speed (FPS). The FPS measures may be used in benchmarking, e.g. while optimizing HPC algorithms for performance. progrep supports both single-threaded and parallel (multicore/multinode - e.g. OpenMP/MPI) jobs. progrep can also report for jobs running on remote hosts, e.g. jobs running on Linux Clusters. progrep works in client-server model. The server can be installed in your simulation source code with only 4 extra lines (API). When the progrep command is invoked, it queries this server as a client. progrep does not interfere with or slow down your simulation when not invoked. ...

...Margetts, Three-dimensional cellular automata modelling of cleavage propagation across crystal boundaries in polycrystalline microstructures, Proc. Roy. Soc. A 471:20150039, DOI: http://dx.doi.org/10.1098/rspa.2015.0039. CASUP can be linked with FE (e.g. MPI FE library ParaFEM, http://parafem.org.uk) for a multi-scale multi-physics CA-FE framework. CASUP extensively uses Fortran 2008 and 2018 coarrays, as well as MPI, OpenMP and do concurrent. CASUP can be used with Cray, Intel and GCC/OpenCoarrays compilers. Scaling beyond 100,000 cores on Cray XC30 was demonstrated.

...The initial application is for FE simulation of elasto-plastic buckling of steel rods aimed at tuning the hardening model. Unix shell scripts are used extensively. High concurrency is achieved with parallel multi-start global search and with parallel MPI FE. Powell's BOBYQA or LINCOA are used (not included in this package). Automatic mesh generation of 3D cylinders is provided + automatic boundary conditions, all via Fortran and shell scripting.

Numerikus is an attempt to build a set of numerical libraries written in C/C++, Fortran, Java and C# for single processor and multi-core processors. It wil have from basic functions to Linear Algebra solvers and ODE's and PDE's methods.