HyDra: Hybrid Task Mapping Application Framework for NOC-Based MPSoCs
Multiprocessor System-On-Chip (MPSoCs) with Networks-on-Chip (NoCs) has been proposed to address the communication challenges in modern dynamic applications. One of the key aspects of design exploration in NoC-based MPSoC is application mapping, which is critical for the parallel execution of multip...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10132481/ |
| _version_ | 1797812854030598144 |
|---|---|
| author | Waqar Amin Fawad Hussain Sheraz Anjum Sharoon Saleem Waqar Ahmad Mubashir Hussain |
| author_facet | Waqar Amin Fawad Hussain Sheraz Anjum Sharoon Saleem Waqar Ahmad Mubashir Hussain |
| author_sort | Waqar Amin |
| collection | DOAJ |
| description | Multiprocessor System-On-Chip (MPSoCs) with Networks-on-Chip (NoCs) has been proposed to address the communication challenges in modern dynamic applications. One of the key aspects of design exploration in NoC-based MPSoC is application mapping, which is critical for the parallel execution of multiple applications. However, mapping for dynamic workloads becomes challenging due to the unpredictable arrival times of applications and the availability of resources. In this work, we propose a hybrid task mapping approach, HyDra, that combines design-time mapping and efficient runtime remapping to reduce communication and energy costs. The proposed approach generates multiple application mappings during the design phase by minimizing latency, energy, and communication costs. The diverse mapping possibilities produced at design time consider multiple performance metrics. However, we cannot predict the arrival time of applications and the availability of resources at design time. To further optimize the MPSoC performance, our dynamic mapping phase re-configures the design time mappings based on the runtime availability of resources and applications. The simulation results show that HyDra reduces communication costs by 14% while using 15% less energy for small and large NoCs compared to state-of-the-art task mapping techniques. Furthermore, our approach provides an average of 19% reduction in end-to-end latency for applications. Our hybrid task allocation and scheduling approach effectively addresses communication issues in NoC-based MPSoCs for dynamic workloads. HyDra achieves improved performance by combining design-time and runtime mapping, providing a promising solution for future MPSoC design. |
| first_indexed | 2024-03-13T07:44:35Z |
| format | Article |
| id | doaj.art-296ec24a8d704f8f99067a121d98713a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T07:44:35Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-296ec24a8d704f8f99067a121d98713a2023-06-02T23:00:18ZengIEEEIEEE Access2169-35362023-01-0111523095232610.1109/ACCESS.2023.327950110132481HyDra: Hybrid Task Mapping Application Framework for NOC-Based MPSoCsWaqar Amin0https://orcid.org/0000-0002-9006-6251Fawad Hussain1https://orcid.org/0000-0002-7819-5990Sheraz Anjum2https://orcid.org/0000-0002-0199-2553Sharoon Saleem3Waqar Ahmad4https://orcid.org/0000-0003-1171-1249Mubashir Hussain5https://orcid.org/0000-0001-8965-5174Department of Computer Engineering, University of Engineering and Technology at Taxila, Taxila, PakistanDepartment of Computer Engineering, University of Engineering and Technology at Taxila, Taxila, PakistanDepartment of Computer Science, COMSATS University Islamabad, Wah Campus, Wah Cantt, PakistanDepartment of Computer Engineering, University of Engineering and Technology at Taxila, Taxila, PakistanDepartment of Computer Engineering, University of Engineering and Technology at Taxila, Taxila, PakistanSchool of Information Technology, King’s Own Institute, Sydney, AustraliaMultiprocessor System-On-Chip (MPSoCs) with Networks-on-Chip (NoCs) has been proposed to address the communication challenges in modern dynamic applications. One of the key aspects of design exploration in NoC-based MPSoC is application mapping, which is critical for the parallel execution of multiple applications. However, mapping for dynamic workloads becomes challenging due to the unpredictable arrival times of applications and the availability of resources. In this work, we propose a hybrid task mapping approach, HyDra, that combines design-time mapping and efficient runtime remapping to reduce communication and energy costs. The proposed approach generates multiple application mappings during the design phase by minimizing latency, energy, and communication costs. The diverse mapping possibilities produced at design time consider multiple performance metrics. However, we cannot predict the arrival time of applications and the availability of resources at design time. To further optimize the MPSoC performance, our dynamic mapping phase re-configures the design time mappings based on the runtime availability of resources and applications. The simulation results show that HyDra reduces communication costs by 14% while using 15% less energy for small and large NoCs compared to state-of-the-art task mapping techniques. Furthermore, our approach provides an average of 19% reduction in end-to-end latency for applications. Our hybrid task allocation and scheduling approach effectively addresses communication issues in NoC-based MPSoCs for dynamic workloads. HyDra achieves improved performance by combining design-time and runtime mapping, providing a promising solution for future MPSoC design.https://ieeexplore.ieee.org/document/10132481/Hybrid application mappingmultiprocessorsnetwork-on-chipparticle swarm optimizationsimulated annealingtask graph for free |
| spellingShingle | Waqar Amin Fawad Hussain Sheraz Anjum Sharoon Saleem Waqar Ahmad Mubashir Hussain HyDra: Hybrid Task Mapping Application Framework for NOC-Based MPSoCs IEEE Access Hybrid application mapping multiprocessors network-on-chip particle swarm optimization simulated annealing task graph for free |
| title | HyDra: Hybrid Task Mapping Application Framework for NOC-Based MPSoCs |
| title_full | HyDra: Hybrid Task Mapping Application Framework for NOC-Based MPSoCs |
| title_fullStr | HyDra: Hybrid Task Mapping Application Framework for NOC-Based MPSoCs |
| title_full_unstemmed | HyDra: Hybrid Task Mapping Application Framework for NOC-Based MPSoCs |
| title_short | HyDra: Hybrid Task Mapping Application Framework for NOC-Based MPSoCs |
| title_sort | hydra hybrid task mapping application framework for noc based mpsocs |
| topic | Hybrid application mapping multiprocessors network-on-chip particle swarm optimization simulated annealing task graph for free |
| url | https://ieeexplore.ieee.org/document/10132481/ |
| work_keys_str_mv | AT waqaramin hydrahybridtaskmappingapplicationframeworkfornocbasedmpsocs AT fawadhussain hydrahybridtaskmappingapplicationframeworkfornocbasedmpsocs AT sherazanjum hydrahybridtaskmappingapplicationframeworkfornocbasedmpsocs AT sharoonsaleem hydrahybridtaskmappingapplicationframeworkfornocbasedmpsocs AT waqarahmad hydrahybridtaskmappingapplicationframeworkfornocbasedmpsocs AT mubashirhussain hydrahybridtaskmappingapplicationframeworkfornocbasedmpsocs |