DeepSoCS: A Neural Scheduler for Heterogeneous System-on-Chip (SoC) Resource Scheduling
In this paper, we present a novel scheduling solution for a class of System-on-Chip (SoC) systems where heterogeneous chip resources (DSP, FPGA, GPU, etc.) must be efficiently scheduled for continuously arriving hierarchical jobs with their tasks represented by a directed acyclic graph. Traditionall...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/9/6/936 |
| _version_ | 1797566087317946368 |
|---|---|
| author | Tegg Taekyong Sung Jeongsoo Ha Jeewoo Kim Alex Yahja Chae-Bong Sohn Bo Ryu |
| author_facet | Tegg Taekyong Sung Jeongsoo Ha Jeewoo Kim Alex Yahja Chae-Bong Sohn Bo Ryu |
| author_sort | Tegg Taekyong Sung |
| collection | DOAJ |
| description | In this paper, we present a novel scheduling solution for a class of System-on-Chip (SoC) systems where heterogeneous chip resources (DSP, FPGA, GPU, etc.) must be efficiently scheduled for continuously arriving hierarchical jobs with their tasks represented by a directed acyclic graph. Traditionally, heuristic algorithms have been widely used for many resource scheduling domains, and Heterogeneous Earliest Finish Time (HEFT) has been a dominating state-of-the-art technique across a broad range of heterogeneous resource scheduling domains over many years. Despite their long-standing popularity, HEFT-like algorithms are known to be vulnerable to a small amount of noise added to the environment. Our Deep Reinforcement Learning (DRL)-based SoC Scheduler (DeepSoCS), capable of learning the “best” task ordering under dynamic environment changes, overcomes the brittleness of rule-based schedulers such as HEFT with significantly higher performance across different types of jobs. We describe a DeepSoCS design process using a real-time heterogeneous SoC scheduling emulator, discuss major challenges, and present two novel neural network design features that lead to outperforming HEFT: (i) hierarchical job- and task-graph embedding; and (ii) efficient use of real-time task information in the state space. Furthermore, we introduce effective techniques to address two fundamental challenges present in our environment: delayed consequences and joint actions. Through an extensive simulation study, we show that our DeepSoCS exhibits the significantly higher performance of job execution time than that of HEFT with a higher level of robustness under realistic noise conditions. We conclude with a discussion of the potential improvements for our DeepSoCS neural scheduler. |
| first_indexed | 2024-03-10T19:21:46Z |
| format | Article |
| id | doaj.art-5ec28a4377e84b7fbe88bb2f21f39877 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T19:21:46Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-5ec28a4377e84b7fbe88bb2f21f398772023-11-20T02:53:41ZengMDPI AGElectronics2079-92922020-06-019693610.3390/electronics9060936DeepSoCS: A Neural Scheduler for Heterogeneous System-on-Chip (SoC) Resource SchedulingTegg Taekyong Sung0Jeongsoo Ha1Jeewoo Kim2Alex Yahja3Chae-Bong Sohn4Bo Ryu5Department of Electronics and Communications Engineering, Kwangwoon University, Seoul 01897, KoreaDepartment of Computer Science and Engineering, Chungnam National University, Daejeon 34134, KoreaDepartment of Computing, Imperial College London, London SW7 2AZ, UKEpiSys Science, Poway, CA 92064, USADepartment of Electronics and Communications Engineering, Kwangwoon University, Seoul 01897, KoreaEpiSys Science, Poway, CA 92064, USAIn this paper, we present a novel scheduling solution for a class of System-on-Chip (SoC) systems where heterogeneous chip resources (DSP, FPGA, GPU, etc.) must be efficiently scheduled for continuously arriving hierarchical jobs with their tasks represented by a directed acyclic graph. Traditionally, heuristic algorithms have been widely used for many resource scheduling domains, and Heterogeneous Earliest Finish Time (HEFT) has been a dominating state-of-the-art technique across a broad range of heterogeneous resource scheduling domains over many years. Despite their long-standing popularity, HEFT-like algorithms are known to be vulnerable to a small amount of noise added to the environment. Our Deep Reinforcement Learning (DRL)-based SoC Scheduler (DeepSoCS), capable of learning the “best” task ordering under dynamic environment changes, overcomes the brittleness of rule-based schedulers such as HEFT with significantly higher performance across different types of jobs. We describe a DeepSoCS design process using a real-time heterogeneous SoC scheduling emulator, discuss major challenges, and present two novel neural network design features that lead to outperforming HEFT: (i) hierarchical job- and task-graph embedding; and (ii) efficient use of real-time task information in the state space. Furthermore, we introduce effective techniques to address two fundamental challenges present in our environment: delayed consequences and joint actions. Through an extensive simulation study, we show that our DeepSoCS exhibits the significantly higher performance of job execution time than that of HEFT with a higher level of robustness under realistic noise conditions. We conclude with a discussion of the potential improvements for our DeepSoCS neural scheduler.https://www.mdpi.com/2079-9292/9/6/936heterogeneous resource schedulingdeep reinforcement learningneural networkssystem on chip |
| spellingShingle | Tegg Taekyong Sung Jeongsoo Ha Jeewoo Kim Alex Yahja Chae-Bong Sohn Bo Ryu DeepSoCS: A Neural Scheduler for Heterogeneous System-on-Chip (SoC) Resource Scheduling Electronics heterogeneous resource scheduling deep reinforcement learning neural networks system on chip |
| title | DeepSoCS: A Neural Scheduler for Heterogeneous System-on-Chip (SoC) Resource Scheduling |
| title_full | DeepSoCS: A Neural Scheduler for Heterogeneous System-on-Chip (SoC) Resource Scheduling |
| title_fullStr | DeepSoCS: A Neural Scheduler for Heterogeneous System-on-Chip (SoC) Resource Scheduling |
| title_full_unstemmed | DeepSoCS: A Neural Scheduler for Heterogeneous System-on-Chip (SoC) Resource Scheduling |
| title_short | DeepSoCS: A Neural Scheduler for Heterogeneous System-on-Chip (SoC) Resource Scheduling |
| title_sort | deepsocs a neural scheduler for heterogeneous system on chip soc resource scheduling |
| topic | heterogeneous resource scheduling deep reinforcement learning neural networks system on chip |
| url | https://www.mdpi.com/2079-9292/9/6/936 |
| work_keys_str_mv | AT teggtaekyongsung deepsocsaneuralschedulerforheterogeneoussystemonchipsocresourcescheduling AT jeongsooha deepsocsaneuralschedulerforheterogeneoussystemonchipsocresourcescheduling AT jeewookim deepsocsaneuralschedulerforheterogeneoussystemonchipsocresourcescheduling AT alexyahja deepsocsaneuralschedulerforheterogeneoussystemonchipsocresourcescheduling AT chaebongsohn deepsocsaneuralschedulerforheterogeneoussystemonchipsocresourcescheduling AT boryu deepsocsaneuralschedulerforheterogeneoussystemonchipsocresourcescheduling |