Algorithms for scheduling task-based applications onto heterogeneous many-core architectures
In this paper we present an Integer Linear Programming (ILP) formulation and two non-iterative heuristics for scheduling a task-based application onto a heterogeneous many-core architecture. Our ILP formulation is able to handle different application performance targets, e.g., low execution time, lo...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2015
|
| Online Access: | http://hdl.handle.net/1721.1/100009 https://orcid.org/0000-0001-8253-7714 |
| _version_ | 1826216239564849152 |
|---|---|
| author | Kinsy, Michel A. Devadas, Srinivas |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Kinsy, Michel A. Devadas, Srinivas |
| author_sort | Kinsy, Michel A. |
| collection | MIT |
| description | In this paper we present an Integer Linear Programming (ILP) formulation and two non-iterative heuristics for scheduling a task-based application onto a heterogeneous many-core architecture. Our ILP formulation is able to handle different application performance targets, e.g., low execution time, low memory miss rate, and different architectural features, e.g., cache sizes. For large size problem where the ILP convergence time may be too long, we propose a simple mapping algorithm which tries to spread tasks onto as many processing units as possible, and a more elaborate heuristic that shows good mapping performance when compared to the ILP formulation. We use two realistic power electronics applications to evaluate our mapping techniques on full RTL many-core systems consisting of eight different types of processor cores. |
| first_indexed | 2024-09-23T16:44:31Z |
| format | Article |
| id | mit-1721.1/100009 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:44:31Z |
| publishDate | 2015 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1000092022-10-03T07:58:56Z Algorithms for scheduling task-based applications onto heterogeneous many-core architectures Kinsy, Michel A. Devadas, Srinivas Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Devadas, Srinivas In this paper we present an Integer Linear Programming (ILP) formulation and two non-iterative heuristics for scheduling a task-based application onto a heterogeneous many-core architecture. Our ILP formulation is able to handle different application performance targets, e.g., low execution time, low memory miss rate, and different architectural features, e.g., cache sizes. For large size problem where the ILP convergence time may be too long, we propose a simple mapping algorithm which tries to spread tasks onto as many processing units as possible, and a more elaborate heuristic that shows good mapping performance when compared to the ILP formulation. We use two realistic power electronics applications to evaluate our mapping techniques on full RTL many-core systems consisting of eight different types of processor cores. 2015-11-23T17:50:19Z 2015-11-23T17:50:19Z 2014-09 Article http://purl.org/eprint/type/ConferencePaper 978-1-4799-6233-4 978-1-4799-6232-7 http://hdl.handle.net/1721.1/100009 Kinsy, Michel A., and Srinivas Devadas. “Algorithms for Scheduling Task-Based Applications onto Heterogeneous Many-Core Architectures.” 2014 IEEE High Performance Extreme Computing Conference (HPEC) (September 2014). https://orcid.org/0000-0001-8253-7714 en_US http://dx.doi.org/10.1109/HPEC.2014.7040977 Proceedings of the 2014 IEEE High Performance Extreme Computing Conference (HPEC) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) Other univ. web domain |
| spellingShingle | Kinsy, Michel A. Devadas, Srinivas Algorithms for scheduling task-based applications onto heterogeneous many-core architectures |
| title | Algorithms for scheduling task-based applications onto heterogeneous many-core architectures |
| title_full | Algorithms for scheduling task-based applications onto heterogeneous many-core architectures |
| title_fullStr | Algorithms for scheduling task-based applications onto heterogeneous many-core architectures |
| title_full_unstemmed | Algorithms for scheduling task-based applications onto heterogeneous many-core architectures |
| title_short | Algorithms for scheduling task-based applications onto heterogeneous many-core architectures |
| title_sort | algorithms for scheduling task based applications onto heterogeneous many core architectures |
| url | http://hdl.handle.net/1721.1/100009 https://orcid.org/0000-0001-8253-7714 |
| work_keys_str_mv | AT kinsymichela algorithmsforschedulingtaskbasedapplicationsontoheterogeneousmanycorearchitectures AT devadassrinivas algorithmsforschedulingtaskbasedapplicationsontoheterogeneousmanycorearchitectures |