Transfer-Tuning: Reusing Auto-Schedules for Efficient Tensor Program Code Generation

Gibson, P. and Cano, J. (2022) Transfer-Tuning: Reusing Auto-Schedules for Efficient Tensor Program Code Generation. In: 31st International Conference on Parallel Architectures and Compilation Techniques (PACT2022), Chicago, USA, 10-12 October 2022, (Accepted for Publication)

[img] Text
280380.pdf - Accepted Version
Restricted to Repository staff only

3MB

Abstract

No abstract available.

Item Type:Conference Proceedings
Keywords:Compute schedules, auto-tuning, DNNs, TVM, auto-scheduling, tensor programs, tensor compilers.
Status:Accepted for Publication
Refereed:Yes
Glasgow Author(s) Enlighten ID:Cano Reyes, Dr Jose and Gibson, Perry
Authors: Gibson, P., and Cano, J.
College/School:College of Science and Engineering
College of Science and Engineering > School of Computing Science
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record