A Deep Reinforcement Learning Framework for Architectural Exploration: A Routerless NoC Case Study

Machine learning applied to architecture design presents a promising opportunity with broad applications. Recent deep reinforcement learning (DRL) techniques, in particular, enable efficient exploration in vast design spaces where conventional design strategies may be inadequate. This paper proposes...

Full description

Saved in:
Bibliographic Details
Main Authors: Lin, Ting-Ru, Penney, Drew, Pedram, Massoud, Chen, Lizhong
Format: Conference Proceeding
Language:English
Subjects:
Complexity theory
Computer architecture
Learning (artificial intelligence)
Machine learning
network-on-chip
routerless
Space exploration
Throughput
Wiring
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine learning applied to architecture design presents a promising opportunity with broad applications. Recent deep reinforcement learning (DRL) techniques, in particular, enable efficient exploration in vast design spaces where conventional design strategies may be inadequate. This paper proposes a novel deep reinforcement framework, taking routerless networks-on-chip (NoC) as an evaluation case study. The new framework successfully resolves problems with prior design approaches, which are either unreliable due to random searches or inflexible due to severe design space restrictions. The framework learns (near-)optimal loop placement for routerless NoCs with various design constraints. A deep neural network is developed using parallel threads that efficiently explore the immense routerless NoC design space with a Monte Carlo search tree. Experimental results show that, compared with conventional mesh, the proposed deep reinforcement learning (DRL) routerless design achieves a 3.25x increase in throughput, 1.6x reduction in packet latency, and 5x reduction in power. Compared with the state-of-the-art routerless NoC, DRL achieves a 1.47x increase in throughput, 1.18x reduction in packet latency, 1.14x reduction in average hop count, and 6.3% lower power consumption.
ISSN:2378-203X
DOI:10.1109/HPCA47549.2020.00018