As the manufacturing process continuously shrinks, how to accurately estimate routability at placement is becoming increasingly important. In addition to extracting local features, this article innovatively constructs an adjacency matrix to represent the connection relationship among tiles, which can reflect the placement quality more comprehensively. To effectively map local features of tiles to the corresponding adjacency matrix, a graph neural network is employed. This trained model is used to predict short violations at the placement stage. Experimental results demonstrate the proposed method can achieve better binary classification quality for designs with severe shorts and outperforms in inductive learning than available machine learning frameworks.

Current image compression algorithms based on transforms can achieve ideal performance for natural images, but do not do well with synthetic aperture radar (SAR) images. We propose a learned compression framework with pyramidal features and quality enhancement to fully exploit the redundancy among image pixels and to improve the compression bitrate and reconstruction quality. Based on the variational autoencoder (VAE) architecture, pyramidal decomposition is performed at the first autoencoder to extract both global and coarse feature maps. The latent distribution is modeled by the second hyperprior autoencoder with a single-Gaussian model for more accurate and flexible entropy estimation. Universal quantization is applied to consolidate the entropy estimation accuracy of the hyperprior network. To further improve reconstruction quality, a residual dense network (RDN) is adopted to fully capture local and global features. Experimental results demonstrate that the proposed framework provides a better rate-distortion tradeoff than standard codecs such as JPEG, JPEG2000, and learning-based methods on both the Sandia and ICEYE datasets.

There are two problems with the traditional lithium battery voltage sampling circuit based on operational amplifier voltage conversion: First, the use of more high-voltage MOS transistor in the operational amplifier leads to the reduction of detection accuracy; Second, there is a current path from battery positive to the ground during voltage detection, and the detection current from the positive pole is also inconsistent. It leads to the imbalance of each battery after the end of the detection. This paper proposes a multi-cell battery-management-system voltage sampling circuit that uses the super source follower structure for battery positive voltage pretreatment and ordinary source follower for battery negative voltage pretreatment. The circuit ensures that the upper and lower voltage difference of the operational amplifier is within the low voltage range of a battery voltage and the input transistor gate-source voltage of the operational amplifier, which avoids the use of high-voltage MOS transisitor. At the same time, the detection current is provided by all series batteries, and there is no current outflow at the positive and negative, ensures balance of the battery. The simulation test is carried out under the conditions of 0.35umBCD process, ss, tt, ff process angle and temperature 27 °C, and the circuit function is normal. The positive and negative current of the battery is less than 1fA, and the voltage sampling max error is 1.4mV.