Abstract:
Disclosed is a cascode configuration that moves the gate of the cascode substantially without delay relative to an output node by capacitively coupling the latter onto the cascode gates. The passive coupling eliminates the need for actively driving the gates of the cascode. In some embodiments, the only circuitry needed on the cascode gate may be a biasing circuit that limits the swing on the cascode gate between Vmax and 2×Vmax, where Vmax is a transistor device rating.
Abstract:
Techniques are provided for using one or more machine learning systems to process input data including image data. The input data including the image data can be obtained, and at least one machine learning system can be applied to at least a portion of the image data to determine at least one color component value for one or more pixels of at least the portion of the image data. Based on application of the at least one machine learning system to at least the portion of the image data, output image data for a frame of output image data can be generated. The output image data includes at least one color component value for one or more pixels of the frame of output image data. Application of the at least one machine learning system causes the output image data to have a reduced dimensionality relative to the input data.
Abstract:
Techniques are provided for using one or more machine learning systems to process input data including image data. The input data including the image data can be obtained, and at least one machine learning system can be applied to at least a portion of the image data to determine at least one color component value for one or more pixels of at least the portion of the image data. Based on application of the at least one machine learning system to at least the portion of the image data, output image data for a frame of output image data can be generated. The output image data includes at least one color component value for one or more pixels of the frame of output image data. Application of the at least one machine learning system causes the output image data to have a reduced dimensionality relative to the input data.
Abstract:
A low standby power DC-DC converter can be powered down during standby mode. The DC-DC converter can be periodically awakened between sleep cycles to check if the output voltage needs to be recharged (refreshed). The duration of the sleep cycles can be varied to accommodate for changing load conditions that would affect the output voltage.
Abstract:
Reliability of a buck power stage may be enhanced by extending the maximum input voltage able to be withstood in the disabled (non-switching) state. During device qualification/testing, a power management unit (PMU) in the disabled state may have its input node subjected to greater than a maximum input voltage permitted for reliability (Vmax). Under such conditions, a force voltage (Vforce) may be selectively applied to the PMU switching node in the disabled state. For a given input voltage (VIN), this reduces voltage across the non-switching transistors of the power stage (and hence the resulting stress) to below Vmax. In certain embodiments, the Vforce applied to the switching node is of a fixed magnitude. In other embodiments, the Vforce applied to the switching node is of a magnitude varying with input voltage. Embodiments may be particularly suited to implement power management for a System-On-Chip (SoC).
Abstract:
Disclosed is a cascode configuration that moves the gate of the cascode substantially without delay relative to an output node by capacitively coupling the latter onto the cascode gates. The passive coupling eliminates the need for actively driving the gates of the cascode. In some embodiments, the only circuitry needed on the cascode gate may be a biasing circuit that limits the swing on the cascode gate between Vmax and 2×Vmax, where Vmax is a transistor device rating.
Abstract:
Techniques are provided for using one or more machine learning systems to process input data including image data. The input data including the image data can be obtained, and at least one machine learning system can be applied to at least a portion of the image data to determine at least one color component value for one or more pixels of at least the portion of the image data. Based on application of the at least one machine learning system to at least the portion of the image data, output image data for a frame of output image data can be generated. The output image data includes at least one color component value for one or more pixels of the frame of output image data. Application of the at least one machine learning system causes the output image data to have a reduced dimensionality relative to the input data.
Abstract:
Reliability of a buck power stage may be enhanced by extending the maximum input voltage able to be withstood in the disabled (non-switching) state. During device qualification/testing, a power management unit (PMU) in the disabled state may have its input node subjected to greater than a maximum input voltage permitted for reliability (Vmax). Under such conditions, a force voltage (Vforce) may be selectively applied to the PMU switching node in the disabled state. For a given input voltage (VIN), this reduces voltage across the non-switching transistors of the power stage (and hence the resulting stress) to below Vmax. In certain embodiments, the Vforce applied to the switching node is of a fixed magnitude. In other embodiments, the Vforce applied to the switching node is of a magnitude varying with input voltage. Embodiments may be particularly suited to implement power management for a System-On-Chip (SoC).