Publications
Detailed Information
Dataflow Mirroring: Architectural Support for Highly Efficient Fine-Grained Spatial Multitasking on Systolic-Array NPUs
Cited 14 time in
Web of Science
Cited 19 time in Scopus
- Authors
- Issue Date
- 2021
- Publisher
- IEEE
- Citation
- 2021 58TH ACM/IEEE DESIGN AUTOMATION CONFERENCE (DAC), pp.247-252
- Abstract
- We present dataflow mirroring, architectural support for low-overhead fine-grained systolic array allocation which overcomes the limitations of prior coarse-grained spatial-multitasking Neural Processing Unit (NPU) architectures. The key idea of dataflow mirroring is to reverse the dataflows of co-located Neural Networks (NNs) in horizontal and/or vertical directions, allowing allocation boundaries to be set between any adjacent rows and columns of a systolic array and supporting up to four-way spatial multitasking. Our detailed experiments using MLPerf NNs and a dataflow-mirroring-augmented NPU prototype which extends Google's TPU with dataflow mirroring shows that dataflow mirroring can significantly improve the multitasking performance by up to 46.4%.
- ISSN
- 0738-100X
- Files in This Item:
- There are no files associated with this item.
Related Researcher
- College of Engineering
- Department of Electrical and Computer Engineering
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.