A power electronic circuit fault diagnosis method based on Extremely randomized trees (ET) and Stack Sparse auto-encoder (SSAE) algorithm includes the following. First, collect the fault signal and extract fault features. Then, reduce the dimensionality of fault features by calculating the importance value of all features using ET algorithm. A proportion of the features to be eliminated is determined, and a new feature set is obtained according the value of importance. Further extraction of fault features is carried by using SSAE algorithm, and hidden layer features of the last sparse auto-encoder are obtained as fault features after dimensionality reduction. Finally, the fault samples in a training set and a test set are input to the classifier for training to obtain a trained classifier. And mode identification, wherein the fault of the power electronic circuit is identified and located by the training classifier.

The signal toggling detection and correction circuit includes a flip-flop, a checker circuit, and a fault monitoring circuit that includes a restoration circuit. Based on faults such as soft errors and unintended bit toggles in the flip-flop, a flop output signal toggles. A set of checker signals outputted by the checker circuit may toggle based on toggling of the flop output signal and a restoration signal of the restoration circuit. Based on the toggling of at least one checker signal, the fault monitoring circuit determines whether the flip-flop or the checker circuit is faulty. When the checker circuit is faulty, the fault monitoring circuit corrects the toggling of at least one checker signal. When the flip-flop is faulty, the fault monitoring circuit corrects the toggling of one of the toggled flop output signal or the restoration signal and further corrects the toggled checker signal.

A method includes identifying state holding pipeline stages in a pipeline path of a design for test (DFT) of an integrated circuit design, splitting each pattern of a plurality of patterns into a first part and a second part, reformatting the plurality of patterns to generate another plurality of patterns such that the first part and the second part of each pattern of the plurality patterns are included in different patterns of the another plurality of patterns. The length of the first part is a function of a number of the identified pipeline stages.

A self-test system for PCIe and a method thereof are disclosed. In the system, a first circuit interconnect card and a second circuit interconnect card are inserted into CEM slots, respectively, and the first circuit interconnect card and the second circuit interconnect card are electrically connected to each other through a FFC, the central processing unit generates and provides differential signals to the first circuit interconnect card and the second circuit interconnect card; the first circuit interconnect card or the second circuit interconnect card provide differential signals to the second circuit interconnect card or the first circuit interconnect card through the first FFC interface and the second FFC interface, respectively, and the second circuit interconnect card or the first circuit interconnect card provides the differential signals to a central processing unit, so as to implement self-check for PCIe.

A method includes instantiating a simulation of an electronic design for a device under test (DUT) in hardware design language responsive to a user selection thereof. A subset of leaf nodes from a plurality of leaf nodes from the electronic design with input/output signaling of more than two values is identified. A hierarchical path for each leaf node of the plurality of leaf nodes of the electronic design for the DUT with respect to a testbench is calculated. A bypass module for the subset of leaf nodes is generated. The bypass module is generated in response to detecting presence of the subset of leaf nodes in the electronic design with input/output signaling of more than two values. The bypass module facilitates communication between the testbench and the subset of leaf nodes. Leaf nodes other than the subset of leaf nodes communicate with the testbench without communicating through the bypass module.

A system and method are disclosed for formulating a sequential equivalency problem for fault (non)propagation with minimal circuit logic duplication by leveraging information about the location and nature of a fault. The system and method further apply formal checking to safety diagnoses and efficiently models simple and complex transient faults.

To provide more test data during the manufacture of non-volatile memories and other integrated circuits, machine learning is used to generate virtual test values. Virtual test results are interpolated for one set of tests for devices on which the test is not performed based on correlations with other sets of tests. In one example, machine learning determines a correlation study between bad block values determined at die sort and photo-limited yield (PLY) values determined inline during processing. The correlation can be applied to interpolate virtual inline PLY data for all of the memory dies, allowing for more rapid feedback on the processing parameters for manufacturing the memory dies and making the manufacturing process more efficient and accurate. In another set of embodiments, the machine learning is used to extrapolate limited metrology (e.g., critical dimension) test data to all of the memory die through interpolated virtual metrology data values.

A debug system for debugging a logic design includes an adaptor and a debug station connected to the adaptor. The logic design includes a plurality of design modules. The adaptor is configured to receive an emulation output of the logic design. The emulation output includes a design snapshot of the logic design and input signals to the logic design that both are recorded during an emulation process of the logic design. The debug station is configured to generate, based on the emulation output and a netlist of a design module of the logic design, an emulation history of the design module.

The invention relates to a method, an apparatus and a non-transitory computer-readable storage medium for debugging a solid-state disk (SSD) device. The method is performed by a processing unit of a single-board personal computer (PC) when loading and executing a function of a runtime library, to include: receiving a request to drive a General-Purpose Input/Output (GPIO) interface (I/F), which includes a parameter required for completing a Joint Test Action Group (JTAG) command; issuing a first hardware instruction to the GPIO I/F to set a register corresponding to a GPIO test data input (TDI) pin according to the parameter carried in the request for emulating to issue the JTAG command to a solid-state disk (SSD) device, wherein the single-board PC is coupled to the SSD device through the GPIO I/F; issuing a second hardware instruction to the GPIO I/F to read a value of the register corresponding to the GPIO TDI pin; and replying with a completion message in response to the request.

The invention relates to an apparatus and a system for debugging a solid-state disk (SSD) device. The apparatus includes a Joint Test Action Group (JTAG) add-on board; and a Raspberry Pi. The Raspberry Pi includes a General-Purpose Input/Output (GPIO) interface (I/F), coupled to the JTAG add-on board; and a processing unit, coupled to the GPIO I/F. The processing unit is arranged operably to: simulate to issue a plurality of JTAG command through the GPIO I/F to the SSD device for dumping data generated by the SSD device during operation from the SSD device.