Abstract: An integrated circuit with specialized processing blocks are provided. A specialized processing block may be optimized for machine learning algorithms and may include a multiplier data path that feeds an adder data path. The multiplier data path may be decomposed into multiple partial product generators, multiple compressors, and multiple carry-propagate adders of a first precision. Results from the carry-propagate adders may be added using a floating-point adder of the first precision. Results from the floating-point adder may be optionally cast to a second precision that is higher or more accurate than the first precision. The adder data path may include an adder of the second precision that combines the results from the floating-point adder with zero, with a general-purpose input, or with other dot product terms. Operated in this way, the specialized processing block provides a technical improvement of greatly increasing the functional density for implementing machine learning algorithms.

Abstract: A system for handling errors in a neural network includes a neural network processor for executing a neural network associated with use of a vehicle. The neural network processor includes an error detector configured to detect a data error associated with execution of the neural network and a neural network controller configured to receive a report of the data error from the error detector. In response to receiving the report, the neural network controller is further configured to signal that a pending result of the neural network is tainted without terminating execution of the neural network.

Abstract: An integrated circuit with specialized processing blocks is provided. A specialized processing block may be optimized for machine learning algorithms and may include a multiplier data path that feeds an adder data path. The multiplier data path may be decomposed into multiple partial product generators, multiple compressors, and multiple carry-propagate adders of a first precision. Results from the carry-propagate adders may be added using a floating-point adder of the first precision. Results from the floating-point adder may be optionally cast to a second precision that is higher or more accurate than the first precision. The adder data path may include an adder of the second precision that combines the results from the floating-point adder with zero, with a general-purpose input, or with other dot product terms. Operated in this way, the specialized processing block provides a technical improvement of greatly increasing the functional density for implementing machine learning algorithms.

Abstract: An integrated circuit with specialized processing blocks is provided. A specialized processing block may be optimized for machine learning algorithms and may include a multiplier data path that feeds an adder data path. The multiplier data path may be decomposed into multiple partial product generators, multiple compressors, and multiple carry-propagate adders of a first precision. Results from the carry-propagate adders may be added using a floating-point adder of the first precision. Results from the floating-point adder may be optionally cast to a second precision that is higher or more accurate than the first precision. The adder data path may include an adder of the second precision that combines the results from the floating-point adder with zero, with a general-purpose input, or with other dot product terms. Operated in this way, the specialized processing block provides a technical improvement of greatly increasing the functional density for implementing machine learning algorithms.

Abstract: A system for handling errors in a neural network includes a neural network processor for executing a neural network associated with use of a vehicle. The neural network processor includes an error detector configured to detect a data error associated with execution of the neural network and a neural network controller configured to receive a report of the data error from the error detector. In response to receiving the report, the neural network controller is further configured to signal that a pending result of the neural network is tainted without terminating execution of the neural network.

Abstract: A Voltage Regulator Module (VRM) includes a first voltage rail circuit board oriented in a first plane having formed therein a first plurality of conductors and configured to produce a first rail voltage, a second voltage rail circuit board oriented in a second plane that is substantially parallel to the first plane having formed therein a second plurality of conductors and configured to produce a second rail voltage. The VRM also includes a first capacitor circuit board oriented in a third plane that is (substantially perpendicular to the first plane and a second capacitor circuit board oriented in a fourth plane that is substantially parallel to the third plane. The VRM includes a plurality of conductors intercoupling the first voltage rail circuit board, the first capacitor circuit board, the second voltage rail circuit board, and the second capacitor circuit board.

Abstract: A system for handling errors in a neural network includes a neural network processor for executing a neural network associated with use of a vehicle. The neural network processor includes an error detector configured to detect a data error associated with execution of the neural network and a neural network controller configured to receive a report of the data error from the error detector. In response to receiving the report, the neural network controller is further configured to signal that a pending result of the neural network is tainted without terminating execution of the neural network.

Abstract: A system for handling errors in a neural network includes a neural network processor for executing a neural network associated with use of a vehicle. The neural network processor includes an error detector configured to detect a data error associated with execution of the neural network and a neural network controller configured to receive a report of the data error from the error detector. In response to receiving the report, the neural network controller is further configured to signal that a pending result of the neural network is tainted without terminating execution of the neural network.

Abstract: An integrated circuit with specialized processing blocks is provided. A specialized processing block may be optimized for machine learning algorithms and may include a multiplier data path that feeds an adder data path. The multiplier data path may be decomposed into multiple partial product generators, multiple compressors, and multiple carry-propagate adders of a first precision. Results from the carry-propagate adders may be added using a floating-point adder of the first precision. Results from the floating-point adder may be optionally cast to a second precision that is higher or more accurate than the first precision. The adder data path may include an adder of the second precision that combines the results from the floating-point adder with zero, with a general-purpose input, or with other dot product terms. Operated in this way, the specialized processing block provides a technical improvement of greatly increasing the functional density for implementing machine learning algorithms.

Abstract: The new and distinct threadleaf coreopsis plant, Coreopsis verticillata plant named ‘Zesty Zinger’, with linear, foliage of bright-green, numerous flowers with ray petals with ray petals dark magenta lightening to ivory tips, blooming over a prolonged season from mid-summer until early fall. The new plant is useful as a specimen landscape plant, mass planting, container plant and cut flower.

Abstract: A method includes allocating a first single-cycle instruction to a first pipeline that picks single-cycle instructions for execution in program order. The method further includes marking at least one source register of the first single-cycle instruction as ready for execution in the first pipeline in response to all older single-cycle instructions allocated to the first pipeline being ready and eligible to be picked for execution. An apparatus includes a decoder to decode a first single-cycle instruction and to allocate the first single-cycle instruction to a first pipeline. The apparatus further includes a scheduler to pick single-cycle instructions for execution by the first pipeline in program order and to mark at least one source register of the first single-cycle instruction as ready for execution in the first pipeline in response to determining that all older single-cycle instructions allocated to the first pipeline are ready and eligible.

Abstract: A new and distinct cultivar of ornamental Miscanthus sinensis plant named ‘Encore’ useful in the landscape en masse, small group or single specimen with dense upright culms and arching foliage having dark green color and near-white midribs. The flower habit is open and at varying heights creating a rounded dome outline beginning in early fall with repeat flush about two to three weeks later, and effective through the winter.

Abstract: The new and distinct cultivar of ornamental bee balm plant named Monarda didyma ‘Pardon My Lavender’ has short, compact, branching stems and tight clumping habit, medium to dark green, numerous light lavender-pink flowers with excellent coverage and foliage highly resistant to powdery mildew.

Abstract: A new and distinct cultivar of ornamental Miscanthus sinensis plant named ‘Encore’ useful in the landscape en masse, small group or single specimen with dense upright culms and arching foliage having dark green color and near-white midribs. The flower habit is open and at varying heights creating a rounded dome outline beginning in early fall with repeat flush about two to three weeks later, and effective through the winter.

Abstract: The new and distinct cultivar of ornamental grass named Panicum virgatum ‘Apache Rose’ with gray-green foliage that develops rosy-red flushed tips in the fall, upright and compact habit with dense culms and airy panicles of rosy-red, suitable as a potted plant, for multi-seasonal interest mass or specimen landscaping, and for cut flower arrangements.

Abstract: The new and distinct cultivar of ornamental, winter-hardy, blue fescue plant, Festuca glauca ‘Blue Whiskers’, with highly-vigorous, clumps of tight, full, rounded habit of strong stems and foliage, consistent flower coverage, intensely silver-blue, linear, evergreen foliage retained throughout the year, upright habit of strong erect stems, long flowering season of large, densely-arranged, lavender-blue flowers on short branched stems.

Abstract: The new and distinct cultivar of ornamental bee balm plant named Monarda didyma ‘Pardon My Cerise’ has short, compact, basally branching stems, medium to dark green foliage with slight tinting of greyed purple, numerous large cerise-colored flowers creating excellent flower coverage and strong foliar resistance to powdery mildew.

Abstract: The new and distinct threadleaf coreopsis plant, Coreopsis verticillata plant named ‘Zesty Zinger’, with linear, foliage of bright-green, numerous flowers with ray petals with ray petals dark magenta lightening to ivory tips, blooming over a prolonged season from mid-summer until early fall. The new plant is useful as a specimen landscape plant, mass planting, container plant and cut flower.

Abstract: A new and distinct cultivar of Oleander plant named ‘ATXNOKHP’, characterized by its relatively compact, upright to somewhat outwardly spreading plant habit; freely branching habit; dark green-colored leaves; freely flowering habit; dark red purple-colored flowers; and good garden performance.