Effective Compression Modeling for Packaged Integrated Circuit with Compressive Sensing

Abstract

In this paper, the compressive sensing theory is applied to the integrated circuit compression modeling. The microprocessor chip is divided into a number of dense micro-regions, and the temperature information of each region in a certain time domain is collected to form a temperature parameter matrix of the time domain and the region. The high-dimensional temperature parameter matrix is mapped to the low-dimensional space by principal component analysis to obtain the critical point temperature of the chip. By observing the critical point temperature, the chip can be used to recover the temperature parameter of the dense distribution. This is the compression modeling method of integrated circuit chips, which is of great significance for the early warning and protection of integrated circuit reliability. The experiment compares the effects of the compressed sensing modeling method and the traditional modeling method. The experimental results show that the recovery efficiency and accuracy of the model are improved by nearly 1.5 times.