Reinforcement Learning Approach for Mapping Applications to Dataflow-Based Coarse-Grained Reconfigurable Array

05/26/2022
by   Andre Xian Ming Chang, et al.
9

The Streaming Engine (SE) is a Coarse-Grained Reconfigurable Array which provides programming flexibility and high-performance with energy efficiency. An application program to be executed on the SE is represented as a combination of Synchronous Data Flow (SDF) graphs, where every instruction is represented as a node. Each node needs to be mapped to the right slot and array in the SE to ensure the correct execution of the program. This creates an optimization problem with a vast and sparse search space for which finding a mapping manually is impractical because it requires expertise and knowledge of the SE micro-architecture. In this work we propose a Reinforcement Learning framework with Global Graph Attention (GGA) module and output masking of invalid placements to find and optimize instruction schedules. We use Proximal Policy Optimization in order to train a model which places operations into the SE tiles based on a reward function that models the SE device and its constraints. The GGA module consists of a graph neural network and an attention module. The graph neural network creates embeddings of the SDFs and the attention block is used to model sequential operation placement. We show results on how certain workloads are mapped to the SE and the factors affecting mapping quality. We find that the addition of GGA, on average, finds 10 schedules in terms of total clock cycles taken and masking improves reward obtained by 20

READ FULL TEXT

page 1

page 9

research
04/11/2023

Variations of Squeeze and Excitation networks

Convolutional neural networks learns spatial features and are heavily in...
research
03/24/2020

Joint Optimization of Spectrum and Energy Efficiency Considering the C-V2X Security: A Deep Reinforcement Learning Approach

Cellular vehicle-to-everything (C-V2X) communication, as a part of 5G wi...
research
02/26/2021

Iterative SE(3)-Transformers

When manipulating three-dimensional data, it is possible to ensure that ...
research
04/12/2021

Equivariant geometric learning for digital rock physics: estimating formation factor and effective permeability tensors from Morse graph

We present a SE(3)-equivariant graph neural network (GNN) approach that ...
research
02/06/2022

Learning Synthetic Environments and Reward Networks for Reinforcement Learning

We introduce Synthetic Environments (SEs) and Reward Networks (RNs), rep...
research
10/23/2020

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks

Graph neural networks (GNNs) have emerged as a powerful tool for learnin...

Please sign up or login with your details

Forgot password? Click here to reset