Workshop: The 5th Annual Parallel Applications Workshop, Alternatives to MPI+X (PAW-ATM)
Event TypeWorkshop
Registration Categories
Heterogeneous Systems
Hierarchical Parallelism
Parallel Programming Languages and Models
Performance Portability
Scientific Computing
Session Formats
TimeMonday, 14 November 20228:30am - 5pm CST
DescriptionSupercomputers get faster and more complex every year. MPI, long the dominant model for distributed computation, has adapted by combining with models for intra-node parallelism (e.g. OpenMP, CUDA). These MPI+X hybrids offer performance but demand significant programmer effort to write, debug, and tune applications.

Alternatives to MPI+X are worth exploring as programmer productivity becomes a major component of the time to science. Alternatives include parallel programing languages (e.g. Chapel, Regent, Fortran 2018), general purpose libraries (e.g. Charm++, COMPSs, HPX, Legion, UPC++), and domain specific libraries (e.g. Arkouda, Dask, Spark). None are as widely used as MPI+X. So, it is hard for programmers to know which alternative models are appropriate for their application and for programming model developers to understand the opportunities for improvement.

Through discussion of specific applications, PAW-ATM brings together application experts and programming model developers to improve applications and models.

Workshop Website
8:30am - 8:32am CSTPAW-ATM – Opening Remarks
8:32am - 10:00am CSTPAW-ATM – Survey of Technologies for Developers of Parallel Applications
10:00am - 10:30am CSTPAW-ATM – Morning Break
10:30am - 10:52am CSTExtending OpenMP and OpenSHMEM for Efficient Heterogeneous Computing
10:52am - 11:14am CSTTask Fusion in Distributed Runtimes
11:14am - 11:37am CSTComposition of Algorithmic Building Blocks in Template Task Graphs
11:37am - 12:00pm CSTAsynchronous Workload Balancing through Persistent Work-Stealing and Offloading for a Distributed Actor Model Library
12:00pm - 1:30pm CSTPAW-ATM – Lunch Break
1:30pm - 2:18pm CSTPAW-ATM – Distinguished Speaker: The Convergence of Exascale Computing, Data Science, and Visualization toward Zero-Carbon Fuels for Power and Transportation
2:18pm - 2:38pm CSTGASNet-EX RMA Communication Performance on Recent Supercomputing Systems
2:38pm - 3:00pm CSTDesign and Performance Evaluation of UCX for Tofu-D Interconnect with OpenSHMEM-UCX on Fugaku
3:00pm - 3:30pm CSTPAW-ATM – Afternoon Break
3:30pm - 5:00pm CSTPAW-ATM – Panel Discussion
Back To Top Button