Abstract: A method for exposing a pattern in an area on a surface using a charged particle beam lithography is disclosed and includes inputting an original set of exposure information for the area. The area comprises a plurality of pixels, and the original set of exposure information comprises dosages for the plurality of pixels in the area. A backscatter is calculated for a sub area of the area based on the original set of exposure information including the dosages for the plurality of pixels in the area. An increase in dosage for at least one pixel in a plurality of pixels in the sub area is determined, in a location where the backscatter of the sub area is below a pre-determined threshold, thereby increasing the backscatter of the sub area.

Abstract: Disclosed is an apparatus and method for controlling step charging of a secondary battery. A charging control unit determines a SOC, an OCV and a polarization voltage of the secondary battery, determines an OCV deviation corresponding to a difference between the OCV and a predefined minimum OCV value, determines a correction factor corresponding to the polarization voltage and the OCV deviation, determines a look-up SOC by correcting the SOC according to the correction factor, determines the magnitude of a charging current corresponding to the look-up SOC, and provides the determined charging current to a charging device.

Abstract: A tractor battery charging module includes a compartment where a portable battery for a handheld battery power tool may be stored and connected to a tractor electrical system. The tractor electrical system charges the portable handheld tool battery in a first mode when the tractor ignition is on, and the portable handheld tool battery recharges the tractor battery in a second mode when the tractor ignition is off. The first mode includes a step up converter to convert the tractor electrical system voltage to the portable battery voltage, and the second mode includes a step down converter to convert the portable handheld tool battery voltage to the tractor electrical system voltage.

Abstract: One or more processors determine a predicted sorting bin of a semiconductor device, based on measurement and test data performed on the semiconductor device subsequent to a current metallization layer. A current predicted sorting bin and a target sorting bin are determined by a machine learning model for the semiconductor device; the target bin include higher performance semiconductor devices than the predicted sorting bin. The model determines a performance level improvement attainable by adjustments made to process parameters of subsequent metallization layers of the semiconductor device. Adjustments to process parameters are generated, based on measurement and test data of the current metallization layer of semiconductor device, and the adjustment outputs for the process parameters of the subsequent metallization layers of the semiconductor device are made available to the one or more subsequent metallization layer processes by a feed-forward mechanism.

Abstract: In accordance with at least one aspect of this disclosure, a failure detection system for an integrated circuit component includes an integrated circuit component configured to connect to a circuit board, a first sensor operatively connected to sense and output a signal indicative of an actual current output of the component in a first state, and a second sensor operatively connected to sense and output a signal indicative of an actual condition of the component in the first state. A logic module can be configured to output a component failed state signal based at least in part on the signal indicative of the actual current output of the component in the first state and the signal indicative of the actual condition of the component in the first state.

Abstract: In some embodiments, logic stored on a computer-readable medium, in response to execution, causes a computing system to conduct an inverse design process to generate a plurality of segmented designs corresponding to a plurality of device specifications, determine at least one highly impactful design area based on the plurality of segmented designs; and designate the at least one highly impactful design area as a static design area. In some embodiments, a product line comprising a plurality of physical devices is provided. Each physical device of the plurality of physical devices includes a design region that includes a static design area and a customized design area. The static design area for each physical device is the same for each physical device of the plurality of physical devices, and the customized design area for each physical device is different for each physical device of the plurality of physical devices.

Abstract: For each defect in a set of defects, the defect may be associated with a defect attribute constructed from a set of computer-aided design (CAD) identifiers associated with polygons in an integrated circuit (IC) design that overlap with a defect area of the defect. Next, the set of defects may be segregated into defect groups based on the associated defect attributes. The defect groups may be used to perform additional processing on the set of defects.

Abstract: A method includes storing a base model generated using base data and receiving training data generated by compiling circuit designs. The method also includes generating, using the training data, a tuned model and generating, using the training data and the base data, a hybrid model. The method further includes receiving a selected cost function and biasing the base model, the tuned model, and the hybrid model using the selected cost function.

Abstract: A computer-implemented method, a machine learning system, and non-transitory computer-readable storage medium for designing electrical circuits are provided. In the method input data, comprising an indication of a plurality of connections including a first and second connection is processed to generate a representation of the electrical circuit. Routes for the first and second connections are determined using an iterative process that includes defining one or more orders in which to determine routes for the first and second connections. A Sequential Monte Carlo process is used to perform a look ahead search of each defined order by generating simulations in respect of routes to be determined for the connections in the orders, the Sequential Monte Carlo process being guided by a neural network. A connection is selected and a route for the selected connection is determined. The representation is updated by providing an action selection signal representing the determined route.

Abstract: A method includes tracing from an observation point in a circuit to an input of the circuit to produce a cone of influence that includes a plurality of components of the circuit. The plurality of components is connected at a plurality of nodes in the cone of influence and the plurality of components includes a plurality of logic elements. The method also includes, for each node of the plurality of nodes, determining an observability probability that a logical high or low value at a corresponding node propagates to the observation point. The method further includes determining a weighted soft error probability for each logic element of the plurality of logic elements and determining a weighed soft error failure mode distribution for the cone of influence.

Abstract: In certain embodiments, a method includes the following steps. An engineering change order (ECO) is for fixing a violation of a target constraint on a target netlist of an integrated circuit. A constraint on a related netlist of the integrated circuit is identified. The identified constraint is adversely affected by fixing the violation of the target constraint. A processor concurrently modifies the target netlist to fix the violation of the target constraint and modifies the related netlist to prevent violation of the adversely affected constraint.

Abstract: Methods, systems, and computer programs are presented for determining the recipe for manufacturing a semiconductor with the use of machine learning (ML) to accelerate the definition of recipes. One general aspect includes a method that includes an operation for performing experiments for processing a component, each experiment controlled by a recipe, from a set of recipes, that identifies parameters for manufacturing equipment. The method further includes an operation for performing virtual simulations for processing the component, each simulation controlled by one recipe from the set of recipes. An ML model is obtained by training an ML algorithm using experiment results and virtual results from the virtual simulations. The method further includes operations for receiving specifications for a desired processing of the component, and creating, by the ML model, a new recipe for processing the component based on the specifications.

Abstract: Certain aspects are directed to apparatus and techniques for estimating parasitic information associated with routing of a design using a pre-route version of the design. One example method generally includes determining one or more output features using a machine learning model based on a pre-route version of a design of an integrated circuit, where the one or more output features include a density map providing an estimate of a density of elements associated with a routed version of the design. The method also includes estimating parasitic information associated with the design based on the one or more output features, and outputting the parasitic information.

Abstract: The independent claims of the present disclosure signify a concise description of embodiments. An electronic structure based on complementary-field effect transistor (CFET) architecture is disclosed. The electronic structure comprises an n-channel metal-oxide-semiconductior (NMOS) gate-all-around (GAA) channel in a first layer, and p-channel metal-oxide-semiconductor (PMOS) GAA channel in a second layer. The PMOS GAA channel is wider compared to the NMOS GAA channel. The first layer is above the second layer and separated by a dielectric layer.

Abstract: When designing circuits to meet certain constraint requirements, it is challenging to determine whether a given circuit design will meet the constraints. A designer at an early stage of the circuit design (e.g., synthesis or placement) may have limited information to rely on in order to determine whether the eventual circuit, or some design variation thereof, will satisfy those constraints without fully designing the circuit. The approaches described herein use a machine learning (ML) model to predict, based on features of partial circuit designs at early stages of the design flow, whether the full circuit is likely to meet the constraints. Additionally, the disclosed approaches allow for the ranking of various circuit designs or design implementations to determine best candidates to proceed with the full design.

Abstract: A storage device is provided including an interface circuit configured to receive application information from a host; a field programmable gate array (FPGA); a neural processing unit (NPU); and a central processing unit (CPU) configured to select a hardware image from among a plurality of hardware images stored in a memory using the application information, and reconfigure the FPGA using the selected hardware image. The NPU is configured to perform an operation using the reconfigured FPGA.

Abstract: A method comprises receiving an integrated circuit (IC) design file and determining, by one or more processors, dose information from the IC design file. The method further comprises determining, by the one or more processors, a mask vector file from the IC design file, and converting, by the one or more processors, the dose information to a vector file format. Further, the method comprises outputting the dose information in the vector file format and the mask vector file to a mask writer device.

Abstract: Systems and methods for measuring quantum states of qubits with more than two levels are provided. A method can include, for a plurality of shuffling sequences, applying, by a quantum computer, one or more quantum gates to the one or more qubits to execute a quantum algorithm; applying, by the quantum computer, a shuffling sequence to the one or more qubits; and measuring, using a readout apparatus, the state of the one or more qubits to determine a readout state. The method can further include determining, by a classical computer or the quantum computer, an average occupation for one or more of the quantum states of the one or more qubits using the readout states for each of the shuffling sequences. The readout states can correspond to a state in a subset of the quantum states of the one or more qubits.

Abstract: A design support device includes an operation reception unit that receives an operation from a user, a program creation unit that creates a ladder program in accordance with the operation received by the operation reception unit, and a circuit block extraction unit that extracts a circuit block from the ladder program when the circuit block is formed and a predetermined condition is satisfied. The circuit block is formed by detecting that one end of a circuit including a plurality of program elements is connected to one of two power rails included in the ladder program and that another end of the circuit is connected to another one of the two power rails. Further, there is a circuit block memory that stores configuration information of the circuit block extracted by the circuit block extraction unit. There is also a notification unit.

Abstract: A non-transitory computer-readable recording medium storing a timing library creation program of causing a computer to execute processing, the processing including: extracting, from a delay variation database that stores delay variation values of gates included in circuit design data, a delay variation value, out of the delay valuation values matching to characteristics which are characteristics of one of signal paths in the circuit design data and which include a threshold voltage, a drive force, and a number of gate stages of the signal path; calculating an extended delay variation coefficient based on the extracted delay variation value and the characteristics; and creating, based on a basic timing library in which the delay variation value is not reflected and the extended delay variation coefficient, an extended timing library in which the delay variation value is reflected.