Dynamic Hardware Binary Translator for ρ-VEX

Master Thesis (2019)
Author(s)

A.E. Ntasios (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

J.S.S.M. Wong – Mentor (TU Delft - Computer Engineering)

AJ van Genderen – Graduation committee member (TU Delft - Computer Engineering)

Przemyslaw Pawelczak – Graduation committee member

Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright
© 2019 Angelos Ntasios
More Info
expand_more
Publication Year
2019
Language
English
Copyright
© 2019 Angelos Ntasios
Graduation Date
11-04-2019
Awarding Institution
Delft University of Technology
Project
['ρ-VEX']
Programme
['Computer Engineering']
Faculty
Electrical Engineering, Mathematics and Computer Science
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

The last years, there has been a increasing trend in embedded system and FPGA im-plementations for greater flexibility and also, a rising adaptation of heterogeneous plat-forms. These platforms often include FPGAs and embedded cores side by side.ρ-VEXcore, developed and maintained by the Computer Engineering group of TU Delft, is aVLIW processor mostly developed on FPGAs. On the other hand, popular embeddedarchitectures include the established ARM architecture and the newly rising RISC-Varchitecture. In order for these architectures to communicate with theρ-VEX core, atranslation procedure has to be established. In this thesis, a hardware dynamic binarytranslator was designed, able to translate on-the-fly ARM and RISCV instructions toρ-VEX instructions. The translator will enable heterogeneous platforms to be developedand also allow pre-compiled binaries for one (ARM/RISC-V) architecture to be directlyported in another one (ρ-VEX). This thesis provides a design process that focuses ontwo approaches: first is the minimization of the overhead resulting from the transla-tion procedure, and the second is the minimization of the hardware alterations and/orhardware additions. These design choices were examined in theρ-VEX core simulator.The simulations show that for overhead minimization, the resulting overhead can be aslow as 1% for the RISC-V with focusing on the overhead minimization, and as high as1024% with ARM and hardware minimization in mind.

Files

Thesis.pdf
(pdf | 1.02 Mb)
License info not available