An automatic test pattern generation-based circuit verification method, comprises: determining a to-be-detected first logic cone from a fan-out logic cone corresponding to the target line; determining, based on the first logic cone, a to-be-detected second logic cone from a fan-in logic cone corresponding to the target line; generating a first CNF based on the first logic cone and the second logic cone, and detecting the target line by using the first CNF to obtain a first detection result; and if the first logic cone is a partial region in the fan-out logic cone, and the first detection result meets a first specified condition corresponding to the first logic cone, determining a first verification result of the target line based on the first detection result.

One or more machine-learning models are trained and employed to predict test coverage and test data volume. Input features for the one or more machine-learning models comprise the test configuration features and the design complexity features. The training data are prepared by performing test pattern generation and circuit design analysis. The design complexity features may comprise testability, X-profiling, clock domains, power domains, design-rule-checking warnings, or any combination thereof.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a touchless testing platform employed to, for example, create automated testing scripts, sequence test cases, and implement determine defect solutions. In one aspect, a method includes the actions of receiving a log file that includes log records generated from a code base; processing the log file through a pattern mining algorithm to determine a usage pattern; generating a graphical representation based on an analysis of the usage pattern; processing the graphical representation through a machine learning algorithm to select a set of test cases from a plurality of test cases for the code base and to assign a priority value to each of the selected test cases; sequencing the set of test cases based on the priority values; and transmitting the sequenced set of test cases to a test execution engine.

A first score and a second score for each scan cell are first determined based on numbers of test cubes in a set of test cubes having a specified value of 1 and a specified value of 0 for the each scan cell, respectively. A ranking score for each test cube in the set of test cubes is then determined based on combining the first scores and the second scores corresponding to specified bits of the each test cube in the set of test cubes. Test cubes in the set of test cubes are merged according to a sequence based on the ranking scores in a test pattern generation process.

The operational mode information and the hold-toggle pattern for a flexible isometric test compression system may be determined based on the plurality of test cubes generated for a subset of the targeted faults, the predetermined size and toggle rate for the hold-toggle pattern, and the predetermined maximum number of device inputs for full-toggle scan chains. The operational mode information comprising information of the full-toggle scan chains may be determined based on reduced toggle ranges first and the hold-toggle pattern may then be determined using a relaxation method. Alternatively, the hold-toggle pattern and the full-toggle scan chains may be determined incrementally together.

Constant-output-value gates and buffer gates are determined for gates in a circuit design based on a hold-toggle pattern. The hold-toggle pattern determines in which shift clock cycles in a segment of consecutive shift clock cycles one or more scan chains receive bits based on corresponding bits of a test pattern or same bits as bits of previous shift clock cycles during a shift operation. Activation probabilities and observation probabilities are then determined for circuit nodes of the circuit design based at least in part on the constant-output-value gates and the buffer gates. Finally, test patterns are generated based on the activation probabilities and the observation probabilities.

A model is generated for predicting failures at the wafer production level. Input data from sensors is stored as an initial dataset, then data exhibiting excursions or useless impact is removed from the dataset. The dataset is converted into target features, where the target features are useful in predicting whether a wafer will be normal or not. A trade-off between positive and negative results is selected, and a plurality of predictive models are created. The final model is selected based on the trade-off criteria, and deployed

Provided is a generation device including: a test vector generation unit for selecting, for each of parameters to be included in a test vector, one value from among possible values for the parameter to generate test vectors whose combinations of values are different from each other; an extraction unit for extracting, as partial sequences each including one or more test vectors, portions of a series including the test vectors output by the test vector generation unit; and a test sequence generation unit for generating a test sequence based on the extracted partial sequences.

A method for evaluating tests for fabricated integrated circuit (IC) chips includes providing, design for fault injection (DfFI) instances of an IC design that characterize activatable states of controllable elements in an IC chip based on the IC design. The method also includes fault simulating the IC design a corresponding identified test suite to determine a signature for faults and simulating the IC design with the DfFI instances activated to determine a signature for the DfFI instances. The method includes generating a DfFI-fault equivalence dictionary based on a comparison of the signature of the faults and DfFI instances and generating tests for a fabricated IC chip based on the IC design. The method includes receiving test result data characterizing the tests being applied against the fabricated IC chip with the DfFI instances activated and analyzing the test result data to determine an ability of the tests to detect the faults.

A method for verifying an integrated circuit (IC) design described in a hardware description or hardware verification language (HDHVL) is provided. The method includes identifying connections between random variables and coverage areas of the IC design, as described in HDHVL code, the connections being identified by determining which coverage areas of the IC design will be influenced during simulation by which random variables. The method can further include storing the identified connections in a database, and using, by a processor, connections retrieved from the database to simulate and verify the coverage areas of the IC design.