Dynamic c-slow pipelining for HLS

Jianyi Cheng, John Wickerson, George A. Constantinides

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

Abstract

In high-level synthesis (HLS), loop pipelining allows multiple iterations of a loop to be executed concurrently. The start time of the operations in each iteration can be determined either at compile time (static pipelining) or at run time (dynamic pipelining). There has been recent interest in dynamic pipelining, as it can overcome the conservatism of static analysis, potentially achieving better performance.In order to ensure correctness in the presence of memory dependences, existing state-of-the-art dynamic pipelining algorithms schedule control flow between basic blocks in the original program order even if they allow pipelining of data flow. This allows source code to be compiled compositionally, 'stitching together' the resulting hardware components to produce the final hardware design. However, this approach can result in suboptimal throughput.In this paper we propose a technique to statically determine a set of possible memory-legal control flows for nested loops, together with a scheduler component able to select from that set efficiently at run time, enabling dynamic execution of control as a C-slow pipeline. An empirical evaluation on a range of applications suggests that by using this approach, we can obtain 2.9× speedup with 7% area overhead compared to a dynamic scheduling approach with sequential control flow.
Original languageEnglish
Title of host publication2022 IEEE 30th Annual International Symposium on Field-Programmable Custom Computing Machines
PublisherInstitute of Electrical and Electronics Engineers
ISBN (Electronic)9781665483322
ISBN (Print)9781665483339
DOIs
Publication statusPublished - 3 Jun 2022
Event30th IEEE International Symposium on Field-Programmable Custom Computing Machines - New York, United States
Duration: 15 May 202218 May 2022

Publication series

NameProceedings of the IEEE International Symposium on Field-Programmable Custom Computing Machines
PublisherInstitute of Electrical and Electronics Engineers
ISSN (Print)2576-2613
ISSN (Electronic)2576-2621

Conference

Conference30th IEEE International Symposium on Field-Programmable Custom Computing Machines
Abbreviated titleFCCM 2022
Country/TerritoryUnited States
CityNew York
Period15/05/2218/05/22

Fingerprint

Dive into the research topics of 'Dynamic c-slow pipelining for HLS'. Together they form a unique fingerprint.

Cite this