POLSCA: Polyhedral high-level synthesis with compiler transformations

Ruizhe Zhao*, Jianyi Cheng, Wayne Luk*, George A. Constantinides

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Polyhedral optimization can parallelize nested affine loops for high-level synthesis (HLS), but polyhedral tools are HLS-agnostic and can worsen performance. Moreover, HLS tools require user directives which can produce unreadable polyhedral-transformed code. To address these two challenges, we present POLSCA, a compiler framework that improves polyhedral HLS workflow by automatic code transformation. POLSCA decomposes a design before polyhedral optimization to balance code complexity and parallelism, while revising memory interfaces of polyhedral-transformed code to make partitioning explicit for HLS tools; it enables designs to benefit more easily from polyhedral optimization. Experiments on Polybench/C show that POLSCA designs are 1.5 times faster on average compared with baseline designs generated directly from applying HLS on C code.
Original languageEnglish
Title of host publication2022 32nd International Conference on Field-Programmable Logic and Applications
PublisherInstitute of Electrical and Electronics Engineers
Pages235-242
Number of pages8
ISBN (Electronic)9781665473903
ISBN (Print)9781665473910
DOIs
Publication statusPublished - 13 Feb 2023
Event32nd International Conference on Field-Programmable Logic and Applications - Belfast, United Kingdom
Duration: 29 Aug 20222 Sept 2022

Publication series

NameProceedings of the International Conference on Field-Programmable Logic and Applications
PublisherInstitute of Electrical and Electronics Engineers
ISSN (Print)1946-147X
ISSN (Electronic)1946-1488

Conference

Conference32nd International Conference on Field-Programmable Logic and Applications
Abbreviated titleFPL 2022
Country/TerritoryUnited Kingdom
CityBelfast
Period29/08/222/09/22

Keywords / Materials (for Non-textual outputs)

  • compiler
  • high-level synthesis
  • polyhedral model

Fingerprint

Dive into the research topics of 'POLSCA: Polyhedral high-level synthesis with compiler transformations'. Together they form a unique fingerprint.

Cite this