Design Space Exploration Of Systems Research Articles

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

This paper gives an overview of methods used for design space exploration (DSE) of micro-architectures and systems. The DSE problem generally considers two orthogonal issues: (I) How can a single design point be evaluated, (II) how can the design space be covered during the exploration process? The latter question arises since an exhaustive exploration of the design space is usually prohibitive due to the sheer size of the design space. We explain 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 summarize common representations of the design space and compare current system and micro-architecture level design frameworks. This review 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.

Advanced AI Search Techniques in Modern Digital Circuit Synthesis

Progress in microelectronic technology is extremely fast and it is outstripping the designers' abilities to make use of the created opportunities. Development and application of new more suitable design methods and tools is therefore very important for the modern system industry. This paper shows the importance of the AI search techniques for the circuits and systems design space exploration, explains what sorts of search techniques are useful for this aim, and discusses the place, role and way of use of these techniques in circuit and system design. In particular, the paper explains the importance and usage of the heuristic search techniques for the automatic construction and selection of the most promising solutions to the circuit synthesis problems. The discussion and conclusions of the paper are illustrated with examples of three effective and efficient search algorithms, and experimental results from their application to two important circuit synthesis problems. The knowledge presented in the paper combines numerous valuable concepts of modern system engineering and artificial intelligence, and forms a base for further research and application of the AI search techniques to design of complex circuits and systems.

Behavioral simulation for analog system design verification

Synthesis of analog circuits is an emergent field, with efforts focused at the cell level. With the growing trend of mixed ASIC designs that contain significant portions of analog sections, compatible design methodologies in the analog domain are necessary to complement those in the digital domain. The synthesis process requires an associated verification process to ensure that the designs meet performance specifications at the onset. In this paper we present a behavioral simulation methodology for analog system design verification and design space exploration. The verification task integrates with analog system-level synthesis for an integrated synthesis-verification process that avoids expensive post synthesis simulation by invoking external simulators. Thus rapid redesign at the architectural level can be undertaken for design parameter variation and during optimization. The verification suite is composed of a repertoire of analysis modes that include time and frequency domain analysis, sensitivity analysis and distortion analysis. Besides verification of design specifications, these analysis modes are also used to generate metrics for comparison of various architectural choices that could realize a given set of specifications. The implementation is in the form of a behavioral simulator, ARCHSIM. >

Advanced digital receiver principles and technologies for PCS

The synergy between digital radio communications and VLSI signal processing is revolutionizing the design of wireless terminals. Driving this synergy are certain fundamental paradigms in modern communication theory, digital signal processing, and VLSI design. The authors discuss the modern centers-of-gravity model, which they believe is emerging as the basis for the successful design and implementation of advanced digital communication systems. Central to this model are design principles that enable engineers to systematically derive digital receiver structures and explore algorithm and architecture trade-offs using sophisticated tools. Digital signal processing technology is critical in the implementation of these digital receiver structures efficiently. Finally, CAD tools for digital communications system design and design space exploration are shown to be of crucial importance in the efficient execution of these designs. >