Holistic Performance Analysis for Asynchronous Many-Task Runtimes
Omri Mor, George Bosilca, Marc Snir · 2024
Due to increasingly heterogeneous computing resources and complex application logic, there has been a renewed interest in Asynchronous Many-Task (AMT) computation runtimes. However, AMT scheduling is typically nondeterministic, and their task dependency graphs are complex and irregular, making it difficult to identify performance bottlenecks using current performance tools and analysis methodologies. This paper presents a new performance analysis methodology and a performance sampling tool that combines data from both computation and communication to support this methodology. The tool is integrated with the PaRSEC runtime. To illustrate the approach, the performance analysis of HiCMA, a state-of-the-art tile-based low-rank Cholesky factorization package, was conducted. The analysis identified bottlenecks in both the PaRSEC runtime and the application itself and suggested changes necessary to overcome them. After implementing the changes, there was up to a$1.45\times$speedup in time-to-solution when strong-scaling the application.