Title: Demonstrating the performance, flexibility and programmability of the hardware architecture of systemic computation modelling cancer growth
Authors: Christos Sakellariou; Peter J. Bentley
Addresses: Department of Computer Science, University College London, London, UK ' Department of Computer Science, University College London, London, UK
Abstract: Systemic computation (SC) is a bio-inspired computational paradigm designed to model the behaviour of natural systems and processes. It adopts a holistic view, meaning that apart from a sum of its constituents, the definition of a system should also include the interaction of its elements. SC implies an unconventional massively parallel computer architecture. However, existing software implementations have been limited in terms of performance, flexibility and programmability. This paper extends previous work which introduced the first hardware systemic computation implementation using FPGAs. We present various software enhancements, resulting in a complete and efficient SC programming platform. An SC application modelling the effect of genetic abnormalities and therapeutic approaches on tumour development is demonstrated, confirming that the suggested general-purpose platform performance, flexibility and programmability advantages over a dedicated software model.
Keywords: systemic computation; programming platforms; field programmable gate arrays; FPGA; ternary content addressable memory; TCAM; cancer modelling; bio-inspired computation; hardware architecture; performance; flexibility; programmability; genetic abnormalities; therapeutic approaches; tumour development; cancer growth modelling; cancer treatment; massively parallel computer architecture.
International Journal of Bio-Inspired Computation, 2015 Vol.7 No.6, pp.345 - 360
Received: 09 Dec 2013
Accepted: 25 May 2014
Published online: 26 Nov 2015 *