Title :
Stochastic interpolation model scheme for statistical circuit design
Author :
Lu, Jin-Qin ; Ogawa, Kimihiro ; Adachi, Takehiko ; Strojwas, Andrzej J.
Author_Institution :
Sony Corp., Atsugi, Japan
fDate :
30 May-2 Jun 1994
Abstract :
In this paper, a stochastic interpolation model (SIM) scheme is proposed to approximate circuit performances for statistical circuit design purpose. First, a parameter estimation technique for SIM construction is presented. Next, a sequential sampling strategy based on variance analysis is described to efficiently fit SIM with the least amount of sample data. Finally, the coefficient of variance is introduced as a new criterion for approximation accuracy check. The effectiveness of presented implementation scheme is demonstrated by several numerical examples as well as a statistical circuit analysis example
Keywords :
circuit CAD; circuit analysis computing; integrated circuit design; interpolation; parameter estimation; statistical analysis; approximation accuracy check; circuit performances; coefficient of variance; parameter estimation technique; sequential sampling strategy; statistical circuit analysis; statistical circuit design; stochastic interpolation model scheme; variance analysis; Circuit simulation; Circuit synthesis; Covariance matrix; Function approximation; Input variables; Interpolation; Parameter estimation; Polynomials; Sampling methods; Stochastic processes;
Conference_Titel :
Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on
Conference_Location :
London
Print_ISBN :
0-7803-1915-X
DOI :
10.1109/ISCAS.1994.408771
