DeepAI AI Chat
Log In Sign Up

DeepSoCS: A Neural Scheduler for Heterogeneous System-on-Chip (SoC) Resource Scheduling

05/15/2020
by   Tegg Taekyong Sung, et al.
Kwangwoon University
0

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.

READ FULL TEXT
05/15/2020

DeepSoCS: A Neural Scheduler for Heterogeneous System-on-Chip Resource Scheduling

In this paper, we present a novel scheduling solution for a class of Sys...
04/28/2021

SoCRATES: System-on-Chip Resource Adaptive Scheduling using Deep Reinforcement Learning

Deep Reinforcement Learning (DRL) is being increasingly applied to the p...
11/20/2017

Deep Reinforcement Learning for Multi-Resource Multi-Machine Job Scheduling

Minimizing job scheduling time is a fundamental issue in data center net...
04/27/2021

A Scalable and Reproducible System-on-Chip Simulation for Reinforcement Learning

Deep Reinforcement Learning (DRL) underlies in a simulated environment a...
03/05/2021

Learning to Schedule DAG Tasks

Scheduling computational tasks represented by directed acyclic graphs (D...
03/09/2021

Learning to Optimize DAG Scheduling in Heterogeneous Environment

Directed Acyclic Graph (DAG) scheduling in a heterogeneous environment i...