End-to-end Mapping in Heterogeneous Systems Using Graph Representation Learning

04/25/2022
by   Yao Xiao, et al.
0

To enable heterogeneous computing systems with autonomous programming and optimization capabilities, we propose a unified, end-to-end, programmable graph representation learning (PGL) framework that is capable of mining the complexity of high-level programs down to the universal intermediate representation, extracting the specific computational patterns and predicting which code segments would run best on a specific core in heterogeneous hardware platforms. The proposed framework extracts multi-fractal topological features from code graphs, utilizes graph autoencoders to learn how to partition the graph into computational kernels, and exploits graph neural networks (GNN) to predict the correct assignment to a processor type. In the evaluation, we validate the PGL framework and demonstrate a maximum speedup of 6.42x compared to the thread-based execution, and 2.02x compared to the state-of-the-art technique.

READ FULL TEXT
research
01/21/2021

Boost then Convolve: Gradient Boosting Meets Graph Neural Networks

Graph neural networks (GNNs) are powerful models that have been successf...
research
04/25/2023

Performance Optimization using Multimodal Modeling and Heterogeneous GNN

Growing heterogeneity and configurability in HPC architectures has made ...
research
01/16/2023

PIGEON: Optimizing CUDA Code Generator for End-to-End Training and Inference of Relational Graph Neural Networks

Relational graph neural networks (RGNNs) are graph neural networks (GNNs...
research
07/16/2023

MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deployment

Graph Neural Networks (GNNs) are becoming increasingly popular for visio...
research
02/01/2022

Molecular Graph Representation Learning via Heterogeneous Motif Graph Construction

We consider feature representation learning problem of molecular graphs....
research
11/24/2022

End-to-end Wind Turbine Wake Modelling with Deep Graph Representation Learning

Wind turbine wake modelling is of crucial importance to accurate resourc...
research
10/28/2020

StencilFlow: Mapping Large Stencil Programs to Distributed Spatial Computing Systems

Spatial computing devices have been shown to significantly accelerate st...

Please sign up or login with your details

Forgot password? Click here to reset