RPython high-level synthesis

Radoslaw Cieszewski; Maciej Linczuk

doi:10.1117/12.2249143

28 September 2016 RPython high-level synthesis

Radoslaw Cieszewski, Maciej Linczuk

Proceedings Volume 10031, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2016; 100314O (2016) https://doi.org/10.1117/12.2249143
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2016, 2016, Wilga, Poland

Abstract

The development of FPGA technology and the increasing complexity of applications in recent decades have forced compilers to move to higher abstraction levels. Compilers interprets an algorithmic description of a desired behavior written in High-Level Languages (HLLs) and translate it to Hardware Description Languages (HDLs). This paper presents a RPython based High-Level synthesis (HLS) compiler. The compiler get the configuration parameters and map RPython program to VHDL. Then, VHDL code can be used to program FPGA chips. In comparison of other technologies usage, FPGAs have the potential to achieve far greater performance than software as a result of omitting the fetch-decode-execute operations of General Purpose Processors (GPUs), and introduce more parallel computation. This can be exploited by utilizing many resources at the same time. Creating parallel algorithms computed with FPGAs in pure HDL is difficult and time consuming. Implementation time can be greatly reduced with High-Level Synthesis compiler. This article describes design methodologies and tools, implementation and first results of created VHDL backend for RPython compiler.

Citation Download Citation

Radoslaw Cieszewski and Maciej Linczuk "RPython high-level synthesis", Proc. SPIE 10031, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2016, 100314O (28 September 2016); https://doi.org/10.1117/12.2249143

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

Includes PDF, HTML & Video, when available