Automated compiling targetting FPGAs

This dissertation explores the algorithmic opportunities offered by the high-level synthesis of digital synchronous circuits targeting Programmable Active Memories. We present the implementation of an experimental compiler toolchain which automatically compiles a reconfigurable circuit from its high-level specification. The circuit description is written in DSL (Design Source Language) which is rooted in the Jazz functional programming language. DSL can describe any digital synchronous circuit. DSL can then simulate, synthetize and execute the hardware routine on a Programmable Active Memory. The compiler proceeds in stages from the DSL source-code in order synthetize the circuit from its high-level specification. Each compiler stage generates annotations which specify circuit properties down to a synthetizable form. Most annotations are generated automatically. Manual annotations are part of the syntax of DSL, and can be used by an experienced designer to specify circuit details through source guidance. DSL automatically generates the hardware and software interfaces needed for speedy communication between the circuit and its host. The whole system is thus a fully automatic hardware accelerator for software applications described in DSL. It has been tested on a strong set of algorithms, including a lossless codec, digital dithering algorithms, motion estimation and Harris feature point extraction.

Data and Resources

Additional Info

Field Value
Source https://theses.hal.science/tel-00807973
Author Note, Jean-Baptiste
Maintainer CCSD
Last Updated May 11, 2026, 16:44 (UTC)
Created May 11, 2026, 16:44 (UTC)
Identifier NNT: 2007PA066483
Language fr
Rights https://about.hal.science/hal-authorisation-v1/
contributor Algorithmique Matérielle ; École normale supérieure - Paris (ENS-PSL) ; Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)
creator Note, Jean-Baptiste
date 2007-10-31T00:00:00
harvest_object_id 33195ebd-712c-4074-a112-3419bace3569
harvest_source_id 3374d638-d20b-4672-ba96-a23232d55657
harvest_source_title test moissonnage SELUNE
metadata_modified 2025-08-12T00:00:00
set_spec type:THESE