Abstract: Embodiments herein describe a hardware accelerator that includes multiple power or clock domains. For example, the hardware accelerator can include an array of data processing engines (DPEs) where different subsets of the DPEs (e.g., different columns, rows, or blocks) are disposed in different power or clock domains within the hardware accelerator. When one or more subsets of the DPEs are idle (e.g., the hardware accelerator has not assigned any tasks to those DPEs), the accelerator can deactivate the corresponding power or clock domain (or domains), which deactivates the DPEs in those domains while the DPEs in the other power or clock domains remain operational. As such, idle DPEs can be deactivated to conserve energy while DPEs with work can remain operational.

Abstract: A system on chip is configured to operate within a thermal design power (TDP) envelope threshold and form factor (e.g., a TDP envelope and form factor associated with a 10 watt to 15 watt notebook or tablet). The system on chip includes a plurality of central processing unit (CPU) core complexes, each CPU core complex including a last level cache; a parallel processor including a plurality of shader arrays; and an inference processing unit (IPU) including a plurality of inference processing engines (IPEs).

Abstract: Embodiments herein describe a hardware accelerator that includes multiple power or clock domains. For example, the hardware accelerator can include data processing engines (DPEs) which include circuitry for performing acceleration tasks (e.g., artificial intelligence (AI) tasks, data encryption tasks, data compression tasks, and the like). The DPEs are interconnected to permit them to share data when performing the acceleration tasks. In addition to the DPEs, the hardware accelerator can include other circuitry such as an interconnect, a controller, address translation circuitry, etc. The DPEs may be in a first power or clock domain while the other circuitry is in a second power or clock domain. That way, when the DPEs are idle (e.g., the hardware accelerator currently has no tasks assigned to it), the first power or clock domain can be powered down while the second power or clock domain can remain powered.

Abstract: Embodiments herein describe integrating an accelerator into a same SoC (or same chip or IC) as a CPU. The SoC also includes a controller (e.g., a microcontroller) that orchestrates data processing engines (DPEs) in the accelerator. The controller (or orchestrator) receives a task from the CPU and then configures the DPEs to perform the task. For example, the controller may divide the task into a sequence of operations that are performed by one or more of the DPEs. The controller can then report back to the CPU when the task is complete.

Abstract: Embodiments herein describe a hardware accelerator that includes multiple power or clock domains. For example, the hardware accelerator can include an array of data processing engines (DPEs) where different subsets of the DPEs (e.g., different columns, rows, or blocks) are disposed in different power or clock domains within the hardware accelerator. When one or more subsets of the DPEs are idle (e.g., the hardware accelerator has not assigned any tasks to those DPEs), the accelerator can deactivate the corresponding power or clock domain (or domains), which deactivates the DPEs in those domains while the DPEs in the other power or clock domains remain operational. As such, idle DPEs can be deactivated to conserve energy while DPEs with work can remain operational.

Abstract: Embodiments herein describe integrating an AI accelerator into a same SoC (or same chip or IC) as a CPU. Thus, instead of relying on off-chip communication techniques, on-chip communication techniques such as an interconnect (e.g., a NoC) can be used to facilitate communication. This can result in faster communication between the AI accelerator and the CPU. Moreover, a tighter integration between the CPU and AI accelerator can make it easier for the CPU to offload AI tasks to the Al accelerator. In one embodiment, the AI accelerator includes address translation circuitry for translating virtual addresses used in the AI accelerator to physical addresses used to store the data.

Abstract: A dynamic hybrid residential threat detection method is disclosed. The method includes receiving, by a packet selector on a customer premises equipment (CPE), communication sessions and selecting and sending, by the packet selector, a predefined number of packets of the communication sessions to a CPE detection engine based on packet selection rules. The method also includes inspecting, by the CPE detection engine, the predefined number of packets of each communication session based on CPE detection rules that establish what type of inspection is to be performed by the CPE detection engine based at least in part on CPE resource constraints. The method further includes sending, by the packet selector, the predefined number of packets of at least some of the communication sessions to a cloud detection engine and blocking particular communication traffic on the CPE based on the inspection and/or an instruction from the cloud detection engine.

Abstract: A dynamic hybrid residential threat detection method is disclosed. The method includes receiving, by a packet selector on a customer premises equipment (CPE), communication sessions and selecting and sending, by the packet selector, a predefined number of packets of the communication sessions to a CPE detection engine based on packet selection rules. The method also includes inspecting, by the CPE detection engine, the predefined number of packets of each communication session based on CPE detection rules that establish what type of inspection is to be performed by the CPE detection engine based at least in part on CPE resource constraints. The method further includes sending, by the packet selector, the predefined number of packets of at least some of the communication sessions to a cloud detection engine and blocking particular communication traffic on the CPE based on the inspection and/or an instruction from the cloud detection engine.

Abstract: A dynamic cloud-based threat detection system is disclosed. The system comprises a network broker that receives communication sessions associated with communication device(s) via a network and selects and sends a predefined number of packets of each communication session to a detection based on packet selection rules. The communication device(s) comprises customer premises equipment (CPE) and/or a mobile communication device. The detection engine receives and inspects the predefined number of packets of each communication session and a governor that initiates blocking of particular communication traffic based on the inspection. The system also comprises a dynamic optimizer that monitors factor(s) and creates and sends updated packet rules to the network broker based on the monitoring. The network broker selects and sends a different predefined number of packets of each of a second plurality of communication sessions to the detection engine for inspection based on the updated packet selection rules.

Abstract: A method of dynamic residential threat detection is disclosed. The method includes a packet selection component on a customer premises equipment (CPE) sending a predefined number of packets of each of a plurality of communication sessions to a detection engine based on packet selection rules. The method also includes the detection engine on the CPE receiving and inspecting the predefined number of packets. The method further includes a dynamic optimizing component on the CPE monitoring one or more factors and creating and sending updated packet selection rules based on the monitored factor(s) to the packet selection component. The method additionally comprises the packet selection component sending a different predefined number of packets of each of a second plurality of communication sessions to the detection engine based on the updated packet selection rules. The method further includes the detection engine receiving and inspecting the different predefined number of packets.

Abstract: Systems and methods are provided herein for creating and building a model of a unique infrastructure, such as a parking structure. The model may be created through the identification of various triggers by a vehicle traversing the infrastructure. The triggers may include, for example, sensors or other devices capable of sensing the vehicle within the infrastructure. The triggers may also be information received from the vehicle itself. Based on the triggers, it may be inferred that various places exist throughout the infrastructure. For example, it may be inferred through two subsequent triggers that a place exists between the two triggers. The place may be added to the model of the infrastructure in between the two triggers. The model may continue to grow in this manner.

Abstract: An electronic device incorporating a liquid crystal display (LCD) screen comprises at least one at least one radio frequency (RF) antenna mounted behind a LCD panel of the LCD screen, and a processor. The RF antenna includes a directional transmit RF antenna that transmits an RF signal through the LCD panel to impinge on a human user, and includes a receive antenna configured to receive a RF signal reflected from tissue of the human user. The processor processes the reflected RF signal to generate a processed signal indicative of presence or absence of the human user, and responsive to the processed signal, controls an operating mode of the electronic device and/or enables control of the device by the human user.

Abstract: A dynamic hybrid residential threat detection method is disclosed. The method includes receiving, by a packet selector on a customer premises equipment (CPE), communication sessions and selecting and sending, by the packet selector, a predefined number of packets of the communication sessions to a CPE detection engine based on packet selection rules. The method also includes inspecting, by the CPE detection engine, the predefined number of packets of each communication session based on CPE detection rules that establish what type of inspection is to be performed by the CPE detection engine based at least in part on CPE resource constraints. The method further includes sending, by the packet selector, the predefined number of packets of at least some of the communication sessions to a cloud detection engine and blocking particular communication traffic on the CPE based on the inspection and/or an instruction from the cloud detection engine.

Abstract: A dynamic cloud-based threat detection system is disclosed. The system comprises a network broker that receives communication sessions associated with communication device(s) via a network and selects and sends a predefined number of packets of each communication session to a detection based on packet selection rules. The communication device(s) comprises customer premises equipment (CPE) and/or a mobile communication device. The detection engine receives and inspects the predefined number of packets of each communication session and a governor that initiates blocking of particular communication traffic based on the inspection. The system also comprises a dynamic optimizer that monitors factor(s) and creates and sends updated packet rules to the network broker based on the monitoring. The network broker selects and sends a different predefined number of packets of each of a second plurality of communication sessions to the detection engine for inspection based on the updated packet selection rules.

Abstract: A method of dynamic residential threat detection is disclosed. The method includes a packet selection component on a customer premises equipment (CPE) sending a predefined number of packets of each of a plurality of communication sessions to a detection engine based on packet selection rules. The method also includes the detection engine on the CPE receiving and inspecting the predefined number of packets. The method further includes a dynamic optimizing component on the CPE monitoring one or more factors and creating and sending updated packet selection rules based on the monitored factor(s) to the packet selection component. The method additionally comprises the packet selection component sending a different predefined number of packets of each of a second plurality of communication sessions to the detection engine based on the updated packet selection rules. The method further includes the detection engine receiving and inspecting the different predefined number of packets.

Abstract: Vehicle parking monitoring systems and methods are disclosed herein. An example method can include receiving images from a camera of a parking spot, each of the images being time stamped, determining presence of a vehicle in the images, placing a bounding area around a region of interest of the vehicle, the region of interest including no personally identifiable information, retaining the bounding area and discarding a remainder of the images, and determining when the vehicle is no longer present based on a change in the bounding area of the images.

Abstract: A mobile communication device-based corneal topography system includes an illumination system, an imaging system, a topography processor, an image sensor, and a mobile communication device. The illumination system is configured to generate an illumination pattern reflected off a cornea of a subject. The imaging system is coupled to an image sensor to capture an image of the reflected illumination pattern. A topography processor is coupled to the image sensor to process the image of the reflected illumination pattern. The mobile communications device includes a display, the mobile communications device is operatively coupled to the image sensor. The mobile communications device includes a mobile communications device (MCD) processor. A housing at least partially encloses one or more of the illumination system, the imaging system, or the topography processor.

Abstract: A mobile communication device-based corneal topography system includes an illumination system, an imaging system, a topography processor, an image sensor, and a mobile communication device. The illumination system is configured to generate an illumination pattern reflected off a cornea of a subject. The imaging system is coupled to an image sensor to capture an image of the reflected illumination pattern. A topography processor is coupled to the image sensor to process the image of the reflected illumination pattern. The mobile communications device includes a display, the mobile communications device is operatively coupled to the image sensor. The mobile communications device includes a mobile communications device (MCD) processor. A housing at least partially encloses one or more of the illumination system, the imaging system, or the topography processor.

Abstract: A mobile communication device-based corneal topography system includes an illumination system, an imaging system, a topography processor, an image sensor, and a mobile communication device. The illumination system is configured to generate an illumination pattern reflected off a cornea of a subject. The imaging system is coupled to an image sensor to capture an image of the reflected illumination pattern. A topography processor is coupled to the image sensor to process the image of the reflected illumination pattern. The mobile communications device includes a display, the mobile communications device is operatively coupled to the image sensor. The mobile communications device includes a mobile communications device (MCD) processor. A housing at least partially encloses one or more of the illumination system, the imaging system, or the topography processor.

Abstract: A mobile communication device-based corneal topography system includes an illumination system, an imaging system, a topography processor, an image sensor, and a mobile communication device. The illumination system is configured to generate an illumination pattern reflected off a cornea of a subject. The imaging system is coupled to an image sensor to capture an image of the reflected illumination pattern. A topography processor is coupled to the image sensor to process the image of the reflected illumination pattern. The mobile communications device includes a display, the mobile communications device is operatively coupled to the image sensor. The mobile communications device includes a mobile communications device (MCD) processor. A housing at least partially encloses one or more of the illumination system, the imaging system, or the topography processor.