Asynchronous Many-Task Systems and Applications
Description
This book constitutes the refereed proceedings of the 4th International Workshop on Asynchronous Many-Task Systems and Applications, WAMTA 2026, held in Garching, Germany, during February 16-18, 2026.
The 12 full papers and 2 Short papers included in this book were carefully reviewed and selected from 18 submissions. They focus on the advantages and challenges of task-based programming on modern and future HPC systems.
More details
Content
.- Exploring Performance-Productivity Trade-offs in AMT Runtimes: A Task Bench Study of Itoyori, ItoyoriFBC, HPX, and MPI.
.- From Promts to Performance: Evaluating LLMs for Task-based Parallel Code Generation.
.- GPU-Resident Gaussian Process Regression Leveraging Asynchronous Tasks with HPX.
.- Silent Data Corruption Protection through Efficient Task Replication.
.- Managing Explicit Communications Within a Sequential Task Flow Paradigm.
.- Hierarchical Scheduling for Composable Affinity-Aware Policies in Task-Based Runtimes.
.- First Experiments to Evaluate the Relevance of Task-based Runtime Systems to Implement Large Language Model Applications.
.- Abstract communicators for task based runtime systems.
.- Leveraging PaRSEC for Task-Based Heterogeneous Computing in Python and Julia.
.- Dynamic Resource Management with Charm++ using Dynamic Processes with PSets.
.- Finding Conservation Laws of Large Dynamical Systems with Tasks and Futures: A Case Study in Utilizing Dynamic Data Dependencies.
.- Merging Parameterized Task Graphs in PaRSEC Through JDF Composition with LLM Assistance.
.- Multiresolution Analysis using Data-Flow Programming.
.- Using C++ Generators in Dataflow Broadcast.