ARC now provides a consulting service to assist researchers with deploying and running codes on HPC clusters such as Flux. The service assists with adapting scientific codes to parallel environments, making efficient use of HPC resources, scaling up codes, locating current and emerging performance bottlenecks, identifying hot spots, and parallelizing performance-critical parts.
Contact Alexander Gaenko <[email protected]> to set up an appointment for a high-level review of your code, including the computational methodology adopted, the operating system and/or platform the code was written for, the programming language(s) used, and the parallelization model used (e.g., MPI or OpenMP, if applicable). If the code exhibits performance or scalability problems, information documenting the behavior, e.g. whether the problematic code and/or use case is memory-, CPU- or I/O-bound, and the outcome of any performance improvements already attempted, should be provided as well.
ARC’s HPC consulting service provides short-term resolutions to code performance issues. If more sustained consultation is required, ARC will work with you on a support mechanism to facilitate a dedicated effort by our consulting team.