Design Space Exploration (DSE) refers to systematic analysis and pruning of unwanted design points based on parameters of interest. While the term DSE can apply to any kind of system, we refer to electronic and embedded system design in this article.
Given the complex specification of electronic systems and the plethora of design choices ranging from the choice of components, number of components, operating modes of each of the components, connections between the components, choice of algorithm, etc.; design decisions need to be based on a systematic exploration process. However, the exploration process is complex because of a variety of ways in which the same functionality can be implemented. A tradeoff analysis between each of the implementation option based on a certain parameter of interest forms the basis of DSE. The parameter of interest could vary across systems, but the commonly used parameters are power, performance, and cost. Additional factors like size, shape, weight, etc. can be important for some handheld systems like cellphone and tablets. With growing usage of mobile devices, energy is also becoming a mainstream optimization parameter along with power and performance.
Owing to the complexity of the exploration process, researchers have proposed automated DSE where the exploration software is able to take decisions and comes up with the optimal solution. However, it is not possible to have an automated DSE for all kind of systems and hence there are semi-automated methods of DSE where the designer has to steer the tool after every iteration towards convergence. Since the exploration is a complex process which takes large computational time, researchers have developed exploration tools which can give an approximate analysis of the system behavior in a fraction of time compared to accurate analysis. Such tools are very important for quick comparison of design decisions and are becoming more important with increasing complexity of designs.
To simplify the complexity of DSE, researchers have been continuously striving to raise the abstractions of component and system definition to be able to cater to larger and complex systems. For example, instead of modeling a digital system at transistor or gate level, there have been attempts to use RTL or behavioral modeling. Further higher abstractions like SystemC or block diagram based modeling are also used depending on the system requirements. Modeling at higher abstractions allows fast exploration of various design choices for the lower level implementation.
The ability to operate on the space of design candidates makes DSE useful for many engineering tasks, such as rapid prototyping, optimization, and system integration.
See also
*
Computer experiment A computer experiment or simulation experiment is an experiment used to study a computer simulation, also referred to as an in silico system. This area includes computational physics, computational chemistry, computational biology and other similar ...
*
Design of experiment
A design is a plan or specification for the construction of an object or system or for the implementation of an activity or process or the result of that plan or specification in the form of a prototype, product, or process. The verb ''to design' ...
*
MULTICUBE
MULTICUBE ("Multi-objective Design Space Exploration of MultiProcessor-SoC Architectures for Embedded Multimedia Applications") is a Seventh Framework Programme (FP7) project aimed to define innovative methods for the design optimization of compu ...
*
Multifactor design of experiments software
Software that is used for designing factorial experiments plays an important role in scientific experiments and represents a route to the implementation of design of experiments procedures that derive from statistical and combinatorial theory. In ...
*
Probabilistic design
Probabilistic design is a discipline within engineering design. It deals primarily with the consideration of the effects of random variability upon the performance of an engineering system during the design phase. Typically, these effects are rela ...
*
Randomized block design
In the statistical theory of the design of experiments, blocking is the arranging of experimental units in groups (blocks) that are similar to one another. Blocking can be used to tackle the problem of pseudoreplication.
Use
Blocking reduces un ...
References
Design of experiments
Industrial engineering
Systems engineering
Quantitative research
Experiments
{{systemstheory-stub