What is it about?
This article presents a new suite of parallel benchmarks. The focus of these benchmarks is not to evaluate systems, but parallel programming models instead. Altogether there are 13 benchmarks implemented in the C programming language. The parallel programming models used in each benchmark are OpenMP, PThreads, MPI-1, and MPI-2. The suite is publicly available.
Featured Image
Why is it important?
There is still no comprehensive tool for this purpose.
Read the Original
This page is a summary of: PAMPAR: A new parallel benchmark for performance and energy consumption evaluation, Concurrency and Computation Practice and Experience, October 2019, Wiley,
DOI: 10.1002/cpe.5504.
You can read the full text:
Contributors
The following have contributed to this page
