Automated High-Level Synthesis Design Modularization via E-Graph Anti-Unification
High-Level Synthesis (HLS) tools have greatly boosted hardware development productivity in the past decades, but still have a fundamental limitation: HLS is powerful in designing accelerators, not architectures – each individual design will be synthesized into independent hardware, and any possible hardware sharing must be done manually and explicitly.This is especially a problem when applied to rapidly evolving and diverse ML models, which significantly limits the practicality of HLS.
To address this limitation, we propose a novel framework to automatically identify the shared hardware modules among an input set of HLS programs. The framework leverages pattern anti-unification with e-graph exploration to identify the shared hardware. These hardware modules form the foundation of an accelerator architecture, balancing between the optimality for dedicated accelerators and the flexibility to handle diverse workloads. We automatically identify common modules over various datapaths, including fundamental ML operators such as Matrix Multiplication. Our framework can achieve up to a 46.1% reduction in the total area of hardware executing a group of designs.
Tue 17 JunDisplayed time zone: Seoul change
10:30 - 12:00 | |||
10:30 20mTalk | eqsat: An Equality Saturation Dialect for Non-destructive Rewriting EGRAPHS Jules Merckx Ghent University, Alexandre Lopoukhine University of Cambridge, Samuel Coward Imperial College London, UK / Intel Corporation, Jianyi Cheng University of Edinburgh, UK, Bjorn De Sutter Ghent University, Belgium , Tobias Grosser University of Cambridge Pre-print | ||
10:50 20mTalk | Hatching Theory Instantiations with Yardbird EGRAPHS Cole Vick University of Texas at Austin, Samuel Thomas The University of Texas at Austin, Texas, USA | ||
11:10 20mTalk | Automated High-Level Synthesis Design Modularization via E-Graph Anti-Unification EGRAPHS Andy Wanna Georgia Institute of Technology, Cong "Callie" Hao Georgia Institute of Technology, Theo Drane AMD |