AEx

Automated High-Level Synthesis of Compiler Programmable Co-Processors

Journal Article (2023)
Author(s)

Alex Hirvonen (Tampere University)

Topi Leppänen (Tampere University)

Kari Hepola (Tampere University)

Joonas Multanen (Tampere University)

Joost Hoozemans (TU Delft - Computer Engineering)

Pekka Jaäskelaïnen (Tampere University)

Research Group
Computer Engineering
Copyright
© 2023 Alex Hirvonen, Topi Leppänen, Kari Hepola, Joonas Multanen, J.J. Hoozemans, Pekka Jääskeläinen
DOI related publication
https://doi.org/10.1007/s11265-023-01841-3
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 Alex Hirvonen, Topi Leppänen, Kari Hepola, Joonas Multanen, J.J. Hoozemans, Pekka Jääskeläinen
Research Group
Computer Engineering
Issue number
9
Volume number
95
Pages (from-to)
1051-1065
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Modern High Level Synthesis (HLS) tools succeed well in their engineering productivity goal, but still require toolset and target technology specific modifications to the source code to guide the process towards an efficient implementation. Furthermore, their end result is a fixed function accelerator with limited field and runtime flexibility. In this paper we describe the status of AEx, a novel work-in-progress HLS tool developed in the FitOptiVis ECSEL JU project. AEx is based on automated exploration of architectures using a flexible and lightweight parallel co-processor template. We compare its current performance in CHStone C-language benchmarks to the state of the art FPGA HLS tool Vitis, provide ASIC implementation numbers, and identify the main remaining toolset features that are expected to dramatically further improve the performance. The potential is explored with a hand-optimized case study that shows only 1.64x performance slowdown with the programmable co-processor in comparison to the fixed function Vitis HLS result.