Automated Programmatic Performance Analysis of Parallel Programs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929221258969088 |
|---|---|
| author | Cankur, Onur Tomar, Aditya Nichols, Daniel Scully-Allison, Connor Isaacs, Katherine E. Bhatele, Abhinav |
| author_facet | Cankur, Onur Tomar, Aditya Nichols, Daniel Scully-Allison, Connor Isaacs, Katherine E. Bhatele, Abhinav |
| contents | Developing efficient parallel applications is critical to advancing scientific development but requires significant performance analysis and optimization. Performance analysis tools help developers manage the increasing complexity and scale of performance data, but often rely on the user to manually explore low-level data and are rigid in how the data can be manipulated. We propose a Python-based API, Chopper, which provides high-level and flexible performance analysis for both single and multiple executions of parallel applications. Chopper facilitates performance analysis and reduces developer effort by providing configurable high-level methods for common performance analysis tasks such as calculating load imbalance, hot paths, scalability bottlenecks, correlation between metrics and CCT nodes, and causes of performance variability within a robust and mature Python environment that provides fluid access to lower-level data manipulations. We demonstrate how Chopper allows developers to quickly and succinctly explore performance and identify issues across applications such as AMG, Laghos, LULESH, Quicksilver and Tortuga. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_13150 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automated Programmatic Performance Analysis of Parallel Programs Cankur, Onur Tomar, Aditya Nichols, Daniel Scully-Allison, Connor Isaacs, Katherine E. Bhatele, Abhinav Distributed, Parallel, and Cluster Computing Performance Developing efficient parallel applications is critical to advancing scientific development but requires significant performance analysis and optimization. Performance analysis tools help developers manage the increasing complexity and scale of performance data, but often rely on the user to manually explore low-level data and are rigid in how the data can be manipulated. We propose a Python-based API, Chopper, which provides high-level and flexible performance analysis for both single and multiple executions of parallel applications. Chopper facilitates performance analysis and reduces developer effort by providing configurable high-level methods for common performance analysis tasks such as calculating load imbalance, hot paths, scalability bottlenecks, correlation between metrics and CCT nodes, and causes of performance variability within a robust and mature Python environment that provides fluid access to lower-level data manipulations. We demonstrate how Chopper allows developers to quickly and succinctly explore performance and identify issues across applications such as AMG, Laghos, LULESH, Quicksilver and Tortuga. |
| title | Automated Programmatic Performance Analysis of Parallel Programs |
| topic | Distributed, Parallel, and Cluster Computing Performance |
| url | https://arxiv.org/abs/2401.13150 |