Work

TeAAL: A Declarative Framework for Modeling Sparse Tensor Accelerators

Year: 2023

Type: conference-paper

Abstract: Over the past few years, the explosion in sparse tensor algebra workloads has led to a corresponding rise in domain-specific accelerators to service them. Due to the irregularity present in sparse tensors, these accelerators employ a wide variety of novel solutions to achieve good performance. At the same time, prior work on design-flexible sparse accelerator modeling does not express this full range of design features, making it difficult to understand the impact of each design choice and compare or extend the state-of-the-art.

Source: Proceedings of the ... annual International Symposium on Microarchitecture/Proceedings of the annual International Symposium on Microarchitecture

DOI: 10.1145/3613424.3623791

Authors: Nandeeka Nayak, Toluwanimi O. Odemuyiwa, Shubham Ugare, Christopher Fletcher, Michael Pellauer, Joel Emer

Institutions: University of Illinois Urbana-Champaign, University of California, Davis, Nvidia (United States), Massachusetts Institute of Technology

Language: English

Topic: Parallel Computing and Optimization Techniques

Subfield: Hardware and Architecture

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funders: National Science Foundation, Microsoft Research, Defense Advanced Research Projects Agency, University of Illinois at Urbana-Champaign

Awards: G433856850, CAREER: Fortifying Leaky Hardware Interfaces with Distinguishability Set Architectures, G7891557237