Abstract: A method and apparatus for post-silicon repair of on-die networks is disclosed. In one embodiment, an integrated circuit includes a first network node of an on-chip network configured to couple each of a plurality of functional units to at least one other one of the plurality of functional units. The first network node includes a plurality of ports. Each of the plurality of ports includes a plurality of multiplexers configured to substitute a spare channel of the network node into the network responsive to a test determining that another one of a plurality of channels is defective.

Abstract: A method and apparatus for post-silicon repair of on-die networks is disclosed. In one embodiment, an integrated circuit includes a first network node of an on-chip network configured to couple each of a plurality of functional units to at least one other one of the plurality of functional units. The first network node includes a plurality of ports. Each of the plurality of ports includes a plurality of multiplexers configured to substitute a spare channel of the network node into the network responsive to a test determining that another one of a plurality of channels is defective.

Abstract: Embodiments of a device (such as a computer system or a circuit tester), a method, and a computer-program product (i.e., software) for use with the device are described. These systems and processes may be used to statistically characterize interdependencies between sub-circuits in an integrated circuit (which are referred to as ‘aggressor-victim relationships’). In particular, statistical relationships between the aggressors and victims are determined from values of a performance metric (such as clock speed) when the integrated circuit fails for a group of state-change difference vectors. Using these statistical relationships, a worst-case sub-group of the state-change difference vectors, such as the worst-case sub-group, is selected. This sub-group can be used to accurately test the integrated circuit.

Abstract: An integrated circuit configured for at-speed scan testing of memory arrays. The integrated circuit includes a scan chain having a plurality of serially coupled scan elements, wherein a subset of the plurality of scan elements are coupled to provide signals to a memory array. Each scan element of the subset of the plurality of scan elements includes a flip flop having a data input, and a data output coupled to a corresponding input of the memory array, and selection circuitry configured to, in an operational mode, couple a data path to the data input, and further configured to, in a scan mode, couple to the data input one of a scan input, the data output, and a complement of the data output. The scan elements of the subset support at-speed testing of a memory array coupled thereto.

Abstract: An integrated circuit configured for at-speed scan testing of memory arrays. The integrated circuit includes a scan chain having a plurality of serially coupled scan elements, wherein a subset of the plurality of scan elements are coupled to provide signals to a memory array. Each scan element of the subset of the plurality of scan elements includes a flip flop having a data input, and a data output coupled to a corresponding input of the memory array, and selection circuitry configured to, in an operational mode, couple a data path to the data input, and further configured to, in a scan mode, couple to the data input one of a scan input, the data output, and a complement of the data output. The scan elements of the subset support at-speed testing of a memory array coupled thereto.

Abstract: Embodiments of a device (such as a computer system or a circuit tester), a method, and a computer-program product (i.e., software) for use with the device are described. These systems and processes may be used to statistically characterize interdependencies between sub-circuits in an integrated circuit (which are referred to as ‘aggressor-victim relationships’). In particular, statistical relationships between the aggressors and victims are determined from values of a performance metric (such as clock speed) when the integrated circuit fails for a group of state-change difference vectors. Using these statistical relationships, a worst-case sub-group of the state-change difference vectors, such as the worst-case sub-group, is selected. This sub-group can be used to accurately test the integrated circuit.