ImpEDE: A multidimensional design-space exploration framework for biomedical-implant processors

Abstract

Abstract-The demand for biomedical implants keeps increasing. However, most of the current implant design methodologies involve custom-ASIC design. The SiMS project aims to change this process and make implant design more modular, flexible, faster and extensible. The most recent work within the SiMS context provides ImpEDE, a framework based on a multiobjective genetic algorithm, for automatic exploration of the design space of implant processors. The framework provides the processor designer with a Pareto front through which informed decisions can be made about specific implant families after analyzing their particular tradeoffs and requirements. A highly efficient, parallelized version of the genetic algorithm is also used to evolve the front and has as its objectives the optimization of power, performance and area. In addition, we illustrate the extensibility of our framework by modifying it to include a case study of a synthetic implant application with hard realtime deadlines.

ImpBench revisited: An extended characterization of implant-processor benchmarks

“…As evaluation framework for our characterization, we have employed ImpEDE, a previously proposed, GA-based, multiobjective, DSE framework for investigating Pareto-optimal implant-processor alternatives [13]. An overview of the framework is shown in Fig.…”

“…have been 6 In a real-world optimization problem like ours, the true Pareto front is not known. Therefore, we make the reasonable assumption (and have verified to the best of our equipment's capabilities in [13]) that the aggregate front P * reached after 200 generations matches the true Pareto front P ,i.e. |P * − P | ≈ 0.…”

“…Since its release, it has been put to good use in exploring efficient implant processors [10], [11] and in the work of others [12]. In this paper, we primarily attempt to expand the original characterization study with extensive, new results acquired through use of ImpEDE, a genetic-algorithm-(GA)-based, design-space exploration (DSE) framework [13]. Through using ImpEDE, we effectively investigate the sensitivity of different processor attributes (e.g.…”

“…Values denoted with 'VAR' indicate adjustable parameters by the GA. For complete parameter ranges refer to[13].…”