The Multi-Processor Computing runtime (MPC) is a unified runtime targeting the MPI, OpenMP and PThread standards. One of its main specificity is the ability to run MPI Processes inside threads, being a thread-based MPI.
More information here: http://mpc.hpcframework.com
InHP@ct is a seminar-hosting initiative taking place at the Ter@tec Campus, encouraging people to share their HPC knowledge with an audience composed of experts and HPC technology aficionados. Workshops held at Ter@tec are also accessible through this resource.
For more information: http://inhpact.hpcframework.com
MALP is an online performance tracing tool aiming at overcoming common file-system limitations by relying on runtime coupling between running applications.
Compact views of parallel application behavior can be generated. Thanks to its web interface and interactive visualizations, a better understanding of its MPI behavior at scale is at your fingertips.
For more information: http://malp.hpcframework.com
JCHRONOSS is a test orchestrator for large test-suites, targeting HPC and other highly-scalable environments. The main purpose of this tool is to run a given workload over dedicated resources while keeping time to result as low as possible. Even if built with test-suites in mind, JCHRONOSS is not bound to test-cases and can handle a wide set of jobs.
For more information: http://pcvs.hpcframework.com
To extend validation support with HPC systems to build an scalable, portable and heterogeneous test-suite (relying over multiple distinct benchmarks, for instance), one may consider taking a deep look to another tool, named PCVS and reachable here: https://github.com/cea-hpc/pcvs
WI4MPI is a light translation framework between MPI constants and MPI objects from an MPI implementation to another one. Through two differents approaches (preload or interface), WI4MPI aims to leverage the adherence to a single MPI implementation between application compilation and runtime.
For more information: https://github.com/cea-hpc/wi4mpi