Parallel algorithms development for programmable logic devices
Advances in Engineering Software
Parallel on-chip ciphers development for the third generation mobile telecommunication system
ACST'07 Proceedings of the third conference on IASTED International Conference: Advances in Computer Science and Technology
Higher-level hardware synthesis of the KASUMI algorithm
Journal of Computer Science and Technology
Parallel algorithms development for programmable devices with application from cryptography
International Journal of Parallel Programming
Synthesizing the F8 cryptographic algorithm for programmable devices
ACST '08 Proceedings of the Fourth IASTED International Conference on Advances in Computer Science and Technology
A denotational semantics for Handel-C
Formal methods and hybrid real-time systems
Hi-index | 0.00 |
Enormous improvements in efficiency can beachieved through exploiting parallelism and realizingimplementation in hardware. On the other hand, conventional methods for achieving these improvementsare traditionally costly, complex and error prone. Twosignifficant advances in the past decade have radicallychanged these perceptions. Firstly, the FPGA, whichgives us the ability to reconfigure hardware throughsoftware, dramatically reducing the costs of developing hardware implementations. Secondly, the languageHandel-C with primitive explicit parallelism which cancompile programs down to an FPGA. In this paper, webuild on these recent technological advances and presenta systematic approach of behavioural synthesis. Starting with an intuitive high level functional specificationof a problem, given without annotation of parallelism, the approach aims at deriving an efficient parallel implementation in Handel-C, which is subsequently compiled into a circuit implemented on reconfigurable hardware. Algebraic laws are systematically used for exposing implicit parallelism and transforming the specification into a collection of interacting components. Formal methods based on data refinement and a small library of higher order functions are then used to derive behavioural description in Handel-C of each component. A small case study illustrates the use of thisapproach.