公开(公告)号：US10885256B1

公开(公告)日：2021-01-05

申请号：US16781110

申请日：2020-02-04

申请人： Hong Kong Applied Science and Technology Research Institute Company, Limited

发明人： Yuan Lei ,  Chenyue Ma

IPC分类号： G06F30/392 ,  G06F30/398 ,  G06F30/31

摘要： An existing layout of an Integrated Circuit (IC) is migrated to two or more target layouts for different semiconductor processes with different design rules. The existing layout file is parsed for data items such as boundaries, paths, text, and cell instances to generate a layout database file with a text format. A layout engineer selects functions from a layout design toolkit and writes reusable code with these functions. Placement functions can specify relative locations to other data items that are dependent on the design rules. Routing functions allow interconnect to be re-routed after placements are adjusted for various target design rules. An analog layout expertise integrator replaces some of the data items in the layout database file with the reusable code to generate a reusable layout database. A layout generator compiles the reusable layout database and converts it to multiple target layouts for multiple design rules.

公开(公告)号：US11176447B2

公开(公告)日：2021-11-16

申请号：US16011787

申请日：2018-06-19

申请人： Hong Kong Applied Science and Technology Research Institute Company, Limited

发明人： Yuan Lei ,  Xiao Huo

IPC分类号： G06N3/063 ,  G06N3/08 ,  G06N3/10

摘要： A deep neural network models semiconductor devices. Measurements of test transistors are gathered into training data including gate and drain voltages and transistor width and length, and target data such as the drain current measured under the input conditions. The training data is converted by an input pre-processor that can apply logarithms of the inputs or perform a Principal Component Analysis (PCA). Rather than use measured drain current as the target when training the deep neural network, a target transformer transforms the drain current into a transformed drain current, such as a derivative of the drain current with respect to gate or drain voltages, or a logarithm of the derivative. Weights in the deep neural network are adjusted during training by comparing the deep neural network's output to the transformed drain current and generating a loss function that is minimized over the training data.