Widely parameterizable  high-level synthesis

Radoslaw Cieszewski; Krzysztof Pozniak; Ryszard Romaniuk; Maciej Linczuk

doi:10.1117/12.2502153

1 October 2018 Widely parameterizable high-level synthesis

Radoslaw Cieszewski, Krzysztof Pozniak, Ryszard Romaniuk, Maciej Linczuk

Author Affiliations +

Proceedings Volume 10808, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2018; 108084D (2018) https://doi.org/10.1117/12.2502153
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2018, 2018, Wilga, Poland

Abstract

In recent years, HLS compilers are gaining increasing popularity. This popularity is due to the fact that FPGA chips can achieve higher computing power than traditional CPUs in fine-grained algorithms. The greatest development of compilers were in recent years. Both commercial and open solutions are being developed. The most difficult part of compilers are algorithms responsible for converting code from a high high level of abstraction to low. In commercial solutions, these algorithms are closed as a "black box" and open solutions have implemented rather simple algorithms. The article presents an alternative, open solution of a high-level synthesis compiler (HLS) implemented in Python with its algorithms. The compiler, based on Python's high-level functional description, generates a configuration that allows the creation of a given structure in the FPGA system during the synthesis process. The article describes the design methods, tools and implementation of the developed Python-VHDL compiler with examples of its use.

Citation Download Citation

Radoslaw Cieszewski, Krzysztof Pozniak, Ryszard Romaniuk, and Maciej Linczuk "Widely parameterizable high-level synthesis", Proc. SPIE 10808, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2018, 108084D (1 October 2018); https://doi.org/10.1117/12.2502153

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE