English Version Русская версия

Zemliak Alexander
Puebla Autonomous University,Physics and Mathematics, Professor azemliak@fcfm.buap.mx

Principal Aspects of the Minimal-Time System Design Methodology

The problem of the computer time reduction for a large system design is one of the essential problems of the total quality design improvement. This problem has a special significance for the VLSI electronic circuit design. There are some powerful methods to reduce the necessary time for the system analysis like sparse matrix techniques and decomposition techniques. The progress in optimization technique favors the development of fast algorithms for the electronic circuit design too. Nevertheless, the time of the large-scale circuit analysis and the time of the optimization procedure increase when the network scale increases. Meanwhile, it is possible to reformulate the system design problem methodology to produce a set of different design strategies. The infinite number of the different design strategies is appeared in this case. The general design methodology was described on the basis of the control theory approach. The design process is formulated in this case as a dynamic controllable system. The main equations for the proposed approach include the special control functions that generalize the design problem. Optimal dependencies of the control functions give the possibility to reduce the total computer design time. Practical results of some electronic system design show that the traditional design strategy is not time-optimal and the potential computer time gain of the optimal design strategy increases when the size and complexity of the system increase. The problem of the time-optimal system design strategy construction is formulated as a typical problem for the functional minimization of the optimal control theory. This approach permits to use the specific methods of the control theory and opens the perspective to construct the time-optimal system design algorithm. This algorithm can be obtained on the basis of the control functions optimal selection. The optimal control functions dependency is the principal aspect in this case and it can be found on the basis of the special Lyapunov function of the design process.