MTT maintenance/deployment on ECP platforms [Poster]
Abstract not provided.
Engineering topics
Publications and source records attributed to Pritchard, Jr., Howard Porter.
Abstract not provided.
Abstract not provided.
Scientific workflows increasing in complexity. Elastic workflows promise improved application and system performance.
Abstract not provided.
Abstract not provided.
Further work for this milestone confirmed that using ECP Gitlab CI does not work with PR based work flow used by the Open MPI.
This report provides an update on the current design, implementation, and usage of bueno, a Python framework enabled by container technology that supports gradations of reproducibility for wellprovenanced benchmarking of sequential and parallel programs. The ultimate goal of the bueno project is to provide convenient access to mechanisms that aid in the automated generation, collection, and dissemination of data relevant for experimental reproducibility in computer system benchmarking.
Pagosa is a 3 dimensional, multi-material shock wave physics code that uses a structured cartesian mesh.
This presentation gives an update on Cloverleaf performance on A64FX. The backend stalls we reported previously have since been found to be very sensitive to compiler optimization level, at least for CCE. The unrolling and jamming that CCE does with –O3 makes a big difference. Unfortunately we get wrong answers for some of the test cases and need to use –hflex_mp=rigorous to get the 960x960 test to pass. This compiler option disables a lot of the optimizations needed for good performance on A64FX.
The presentation was targeted to Riken/SNL collaborators.
Topics covered in the presentation include: Primary causes of current performance on KNL/Haswell processers; compiler discussion; array-syntax; compiler-option/code modifications; and, performance results.