Methods for evaluating and covering the design space during early design development

Abstract

This paper gives an overview of methods used for Design Space Exploration (DSE) at the system-and micro-architecture levels. The DSE problem is considered to be two orthogonal issues: (I) How could a single design point be evaluated, (II) how could the design space be covered during the exploration process? The latter question arises since an exhaustive exploration of the design space by evaluating every possible design point is usually prohibitive due to the sheer size of the design space. We therefore reveal trade-offs linked to the choice of appropriate evaluation and coverage methods. The designer has to balance the following issues: the accuracy of the evaluation, the time it takes to evaluate one design point (including the implementation of the evaluation model), the precision/granularity of the design space coverage, and last but not least the possibilities for automating the exploration process. We also list common representations of the design space and compare current system and micro-architecture level design frameworks. This review thus eases the choice of a decent exploration policy by providing a comprehensive survey and classification of recent related work. It is focused on System-on-a-Chip designs, particularly those used for network processors. These systems are heterogeneous in nature using multiple computation, communication, memory, and peripheral resources.Keywords: Design space exploration, design space pruning, system-level design, micro-architecture design, design frameworks, benchmarking, multi-objective search. NoteWe focus on related work which applies methods in the context of design space exploration. Discussing the theory of optimization methods and the fundamentals of design evaluation is beyond the scope of this survey.

Power Estimation of Time Variant SoCs with TAPES

“…[4] gives a broad overview of methods used in architecture exploration. These range from analytic approaches ( [5], [6]) to simulation based concepts.…”

Complexity enabled design space exploration

“…Different approaches for design space exploration have been proposed in the literature [2]. Some of these techniques include exhaustively covering the entire design space and randomly sampling the design space.…”

User-centric design space exploration for heterogeneous Network-on-Chip platforms

“…Although prior work for evaluating and covering the design space exists [8], the traditional design flow still can generate only one or a few platform configurations, the so-called application scenarios [21], belonging to the same Pareto curve trading off multiple objectives [13]. Therefore, even assuming perfect techniques for run-time optimization, such a platform can hardly meet all user needs ( Fig.…”