Synopsys, Inc.

Jianfeng Luo

Charles C Chiang

Subarnarekha Sinha

Qing Su

Gang Y Chen

A method of improving a design rule fixing process comprises receiving an integrated circuit design, including layout elements, and identifying a plurality of design rule violations in the integrated circuit design. The process then identifies a plurality of possible actions, each action comprising fixing a design rule. The process then uses a deep learning algorithm to select an action, the action representing fixing of a particular design rule violation. The process then comprises applying a first patch, based on the order returning to step (b) to select a next patch to apply.

Circuit design including design rule violation correction utilizing patches based on deep reinforcement learning

A method, system or computer usable program product for preventing odd cycles caused by design modifications to a double patterning layout including utilizing a processor to identify a set of double patterning cycles in the layout for storage in a memory; receiving a set of design modifications to the layout; utilizing the processor to identify from the set of double patterning cycles a subset of double patterning cycles affected by the set of design modifications; utilizing the processor to identify from the set of design modifications a subset of design modifications which may cause odd cycles in the subset of double patterning cycles; and providing a notification of the subset of design modifications.

Preventing double patterning odd cycles

Graph analysis for double pattern lithography is described. Layout shapes are decomposed into rectangles and a vertex is provided for each rectangle. Double pattern spacing conflicts are determined and shown as edges for the graph analysis. Odd cycles are used to identify double pattern lithography violations. Cycles can be completed with the addition of edges between vertices where stitches have been included in the layout. Edges between touching shapes do not count toward the odd count in the cycles. Fixes are included by increasing space or by rerouting. A portion of the layout can be incrementally changed and a local update of the graph analysis performed. Correct by construction layout is implemented by avoiding certain odd cycle prone layout routings.

Routing analysis with double pattern lithography

One embodiment of the present invention provides a system that predicts manufacturing yield for a die within a semiconductor wafer. During operation, the system first receives a physical layout of the die. Next, the system partitions the die into an array of tiles. The system then computes systematic variations for a quality indicative value to describe a process parameter across the array of tiles based on the physical layout of the die. Next, the system applies a random variation for the quality indicative parameter to each tile in the array of tiles. Finally, the system obtains the manufacturing yield for the die based on both the systematic variations and the random variations.

Predicting IC manufacturing yield by considering both systematic and random intra-die process variations

The use of smooth post-ECP topography (instead of final chip topography) as an objective during dummy filling enables a computationally efficient model-based dummy filling solution for copper while maintaining solution quality. A layout can be divided into tiles and the 'case' of each tile identified. Exemplary cases can include conformal fill, over fill, super fill, or super/over fill (if the ECP model cannot distinguish between super and over fill cases). One or more undesired tile cases can be converted to a desired tile case. Then, a height difference between tiles can be minimized. Dummy features can be inserted in the layout to perform the conversion and to minimize the height difference between tiles. Minimizing the CMP-effective density difference between tiles with ECP considerations can be performed to further improve planarization.

Dummy filling technique for improved planarization of chip surface topography

A dimension of a conductive material in a semiconductor wafer is determined by a computer that treats as identical (a) volume of the conductive material which is proportional to an effective surface area of sidewalls of an insulative trench and (b) volume of the conductive material derived from geometry based on a predetermined amount by which width of a conductive trench (if present) in the conductive material differs from width of the insulative trench. In some embodiments, the computer computes the effective surface area as the product of trench depth and a layout parameter, either or both of which may be partially or wholly empirically determined from a test wafer containing several topographies. The computer computes the dimension assuming one topography and validates the assumption if a predetermined condition is met. If the condition is not met, the computer re-computes the dimension, assuming another topography.

Growing community of inventors

Foster City, CA, United States of America

Jianfeng Luo