Misam: Using ML in Dataflow Selection of Sparse-Sparse Matrix Multiplication

Sanjali Yadav, Bahar Asgari

Workshop Track: Machine Learning for System

Presentation: In-Person

Keywords: SPGEMM, Decision Trees, Reinforcement Learning, Heuristics

Presenter Full Name: Bahar Asgari

TL;DR: This paper presents a machine learning-based approach for adaptively selecting the most appropriate dataflow scheme for SpGEMM tasks with diverse sparsity patterns.

Presenter Email: [e-mail]

Abstract:

Sparse matrix-matrix multiplication (SpGEMM) is a critical operation in numerous fields, including scientific computing, graph analytics, and deep learning. These applications exploit the sparsity of matrices to reduce storage and computational demands. However, the irregular structure of sparse matrices poses significant challenges for performance optimization. Traditional hardware accelerators are tailored for specific sparsity patterns with fixed dataflow schemes—inner, outer, and row-wise—but often perform suboptimally when the actual sparsity deviates from these predetermined patterns. As the use of SpGEMM expands across various domains, each with distinct sparsity characteristics, the demand for hardware accelerators that can efficiently handle a range of sparsity patterns is increasing. This paper presents a machine learning-based approach for adaptively selecting the most appropriate dataflow scheme for SpGEMM
tasks with diverse sparsity patterns. By employing decision trees and deep reinforcement learning, we explore the potential of
these techniques to surpass heuristic-based methods in identifying optimal dataflow schemes. We evaluate our models by comparing
their performance with that of a heuristic, highlighting the strengths and weaknesses of each approach. Our findings suggest
that using machine learning for dynamic dataflow selection in hardware accelerators can provide upto 28× gains.

Presenter Bio: Bahar Asgari is an assistant professor in the Department of Computer Science, and the director of the Computer Architecture and Systems Lab (CASL) at the University of Maryland, College Park. Her research interests include but are not limited to domain-specific architecture design, near memory processing, and reconfigurable computing. Her proposed low-cost hardware accelerators that deal with essential challenges of sparse problems contribute to a widespread application domain from machine learning to scientific computing.

Paper Checklist Guidelines: I certify that all co-authors have validated the presented results and conclusions, and have read and commit to adhering to the Paper Checklist Guidelines, Call for Papers and Publication Ethics.

YouTube Link: https://youtu.be/y0JqhDQ1EOM

Workshop Registration: Yes, at least one of the authors has registered for the workshop (Two-Day Registration at minimum).

Submission Number: 8