Abstract: Predicting and counting repetitions of a physical activity includes capturing first sensor data, by a first magnetometer on a wearable device, a change in a magnetic field indicative of a ferromagnetic object moving in relation to the wearable device. One or more characteristics of a user motion are determined based on the first sensor data. A count of repetitions of the user motion are determined based on the one or more characteristics of the user motion, and a notification of the count of repetitions is generated.

Abstract: Systems and methods for efficient context switching in multithread processors are disclosed. A processing system comprises a direct memory access module configured to detect a preemption request generated by the scheduling circuit. Responsive to the preemption request, the direct memory access module determines whether execution of a first task from a plurality of tasks needs to be replaced by execution of a second task. When the replacement is necessitated, the module saves a first plurality of registers associated with the first task at a memory location transmitted by the scheduling circuit and queues the second task for execution. The memory location is transmitted by the scheduling circuit as part of the preemption request.

Abstract: Techniques are described for implementing selective activation and deactivation of a dynamically allocated subset of shader engines, such as based on application-based profile information and/or on an active system power configuration. Instructions for execution are received from an application associated with a first application profile. Based on the application profile, a quantity of activated shader engines in a plurality of shader engines is modified. The quantity of activated shader engines is further modified responsive to receiving additional instructions from a second application, and/or to receiving one or more indications of an altered active system power configuration.

Abstract: A processor includes a plurality of state registers and a command processor. The plurality of state registers is configured to maintain context states for a plurality of graphics contexts. The command processor includes a processing unit and a fixed-function hardware circuit. The processing unit is configured to place a plurality of graphics commands into a queue. The fixed-function hardware circuit is configured to monitor a graphics command stream output by the queue and detect a specified graphics command in the monitored graphics command stream. In response to the detected specified graphics command, the fixed-function hardware circuit is further configured to perform at least one graphics command management operation that includes one or more of a graphics context management operation or a graphics persistent state management operation.

Abstract: A processing device includes a hardware scheduler, an unmapped queue unit, and command processor, and a plurality of compute units. Responsive to a queue doorbell being an unmapped queue doorbell, the unmapped queue unit is configured to transmit a signal to the hardware scheduler indicating work has been placed into a queue currently unmapped to a hardware queue of the processing device. The hardware scheduler is configured to map the queue to a hardware queue of a plurality of hardware queues at the processing device in response to the signal. The command processor is configured to dispatch the work associated with the mapped queue to one or more compute units of the plurality of compute units.

Abstract: Methods and systems are disclosed for inline suspension of an accelerated processing unit (APU). Techniques include receiving a packet, including a mode of operation and commands to be executed by the APU; suspending execution of commands received in previous packets when the mode of operation is a suspension initiation mode; and executing, by the APU, the commands in the received packet. The execution of the suspended commands is restored when the mode of operation in a subsequently received packet is a suspension conclusion mode.

Abstract: Techniques for implementing accelerated draw indirect fetching are disclosed. A fetch accelerator enables streamlined data fetching by looping internally and filling a draw queue for a micro engine. By using a dedicated fetch accelerator rather than processing data fetches separately and individually using a conventional processor, significant processing overhead is eliminated and computational latency is reduced. Additionally, different types of aligned or unaligned data structures are usable with equivalent or nearly equivalent performance.

Abstract: Methods, devices, and systems for rendering primitives in a frame. During a visibility pass, state packets are processed to determine a register state, and the register state is stored in a memory device. During a rendering pass, the state packets are discarded and the register state is read from the memory device. In some implementations, a graphics pipeline is configured during the visibility pass based on the register state determined by processing the state packets, and the graphics pipeline is configured during the rendering pass based on the register state read from the memory device. In some implementations, replay control packets, draw packets, and the state packets, from a packet stream, are processed during the visibility pass; the draw packets are modified based on visibility information determined during the visibility pass; and the replay control packets and draw packets are processed, during the rendering pass.

Abstract: An electronic device may maintain a list of possible locations for the electronic device and a list of possible activities for the electronic device. The electronic device may gather sensor data and determine the location and the activity for the electronic device based on the sensor data. In response to detecting a change in the location and/or activity, the electronic device may obtain additional sensor data using at least one sensor that was previously turned off. Using the additional sensor data, the electronic device may make a determination to present content to the user. In response to detecting the change in the location and/or activity, the electronic device may increase a sampling rate (and power consumption) of at least one sensor.

Abstract: A system includes a processing unit such as a GPU that itself includes a command processor configured to receive instructions for execution from a software application. A processor pipeline coupled to the processing unit includes a set of parallel processing units for executing the instructions in sets. A set manager is coupled to one or more of the processor pipeline and the command processor. The set manager includes at least one table for storing a set start time, a set end time, and a set execution time. The set manager determines an execution time for one or more sets of instructions of a first window of sets of instructions submitted to the processor pipeline. Based on the execution time of the one or more sets of instructions, a set limit is determined and applied to one or more sets of instructions of a second window subsequent to the first window.

Abstract: In example implementations, an apparatus is provided. The apparatus includes a plurality of microphones to record background sounds, a noise cancellation component to generate an inverted signal to negate the background sounds from an output signal, a memory to store sound patterns associated with known events, a speaker to output the output signal, and a processor. The processor is to compare a background sound of the background sounds to sound patterns stored in the memory, detect an event when the background sound matches a sound pattern and is coming from behind a user, and execute a corrective action to the output signal in response to the event being detected and the background sound coming from behind the user.

Abstract: A method of packet attribute confirmation includes receiving, at a command processor of a parallel processor, a command packet including a received packet attribute, such as a packet size, of the command packet. The command processor compares the received packet attribute of the command packet relative to an expected packet attribute of the command packet. The command processor passes one or more commands to a prefetch parser such that a summed total size of the one or more commands is equal to the received packet size of the command packet. The command processor passes, based at least on determining a match between the received packet size and the expected packet size, the received command packet to the prefetch parser. Otherwise, the command processor passes, based at least on determining a mismatch between the received packet size and the expected packet size, one or more no-operation instructions to the prefetch parser.

Abstract: An apparatus may identify each object of a set of objects included in a first location, wherein the set of objects includes at least one IoT device and at least one other object. The apparatus may determine a first set of attributes for the at least one IoT device. The apparatus may store registration information associated with the at least one IoT device, the registration information including a first identifier associated with the at least one IoT device and including the first set of attributes for the at least one IoT device. The apparatus may obtain an input. The apparatus may determine whether the input corresponds to the at least one IoT device based on the registration information associated with the at least one IoT device. The apparatus may control the at least one IoT device when the input corresponds to the at least one IoT device.

Abstract: An apparatus for optimizing a computational network is configure to receive an input at a first processing component. The first processing component may include at least a first programmable processing component and a second programmable processing component. The first programmable processing component is configured to compute a first nonlinear function and the second programmable processing component is configured to compute a second nonlinear function which is different than the second nonlinear function. The computational network which may be a recurrent neural network such as a long short-term memory may be operated to generate an inference based at least in part on outputs of the first programmable processing component and the second programmable processing component.

Abstract: Examples of machine learning model training are described herein. In some examples, a method may include training, on an apparatus, an encoder machine learning model or a context machine learning model. In some examples, the method may include training the encoder machine learning model or the context machine learning model using negative samples in a latent space from emote devices and a ground truth.

Abstract: Methods and systems are disclosed for inline suspension of an accelerated processing unit (APU). Techniques include receiving a packet, including a mode of operation and commands to be executed by the APU; suspending execution of commands received in previous packets when the mode of operation is a suspension initiation mode; and executing, by the APU, the commands in the received packet. The execution of the suspended commands is restored when the mode of operation in a subsequently received packet is a suspension conclusion mode.

Abstract: Examples of methods for controlling machine learning model structures are described herein. In some examples, a method includes controlling a machine learning model structure. In some examples, the machine learning model structure may be controlled based on an environmental condition. In some examples, the machine learning model structure may be controlled to control apparatus power consumption associated with a processing load of the machine learning model structure.

Abstract: A method of processing asynchronous event-driven input samples of a continuous time signal, includes calculating a convolutional output directly from the event-driven input samples. The convolutional output is based on an asynchronous pulse modulated (APM) encoding pulse. The method further includes interpolating output between events.

Abstract: In example implementations, a device is provided. The device includes a microphone, an event generator, a keyword detector, and a digital signal processor. The digital signal processor is in communication with the keyword detector. The microphone is to receive an audio signal. The event generator generates a pattern of events from the audio signal. The keyword detector detects a keyword based on the pattern of events generated by the event generator. In response to the keyword being detected, the digital signal processor is activated to analyze subsequent audio streams.

Abstract: A method of packet attribute confirmation includes receiving, at a command processor of a parallel processor, a command packet including a received packet attribute, such as a packet size, of the command packet. The command processor compares the received packet attribute of the command packet relative to an expected packet attribute of the command packet. The command processor passes one or more commands to a prefetch parser such that a summed total size of the one or more commands is equal to the received packet size of the command packet. The command processor passes, based at least on determining a match between the received packet size and the expected packet size, the received command packet to the prefetch parser. Otherwise, the command processor passes, based at least on determining a mismatch between the received packet size and the expected packet size, one or more no-operation instructions to the prefetch parser.