Abstract: In various examples, sensor data may be collected using one or more sensors of an ego-vehicle to generate a representation of an environment surrounding the ego-vehicle. The representation may include lanes of the roadway and object locations within the lanes. The representation of the environment may be provided as input to a longitudinal speed profile identifier, which may project a plurality of longitudinal speed profile candidates onto a target lane. Each of the plurality of longitudinal speed profiles candidates may be evaluated one or more times based on one or more sets of criteria. Using scores from the evaluation, a target gap and a particular longitudinal speed profile from the longitudinal speed profile candidates may be selected. Once the longitudinal speed profile for a target gap has been determined, the system may execute a lane change maneuver according to the longitudinal speed profile.

Abstract: One embodiment of a method for rendering one or more graphics images includes tracing one or more rays through a graphics scene; computing one or more surface normals associated with intersections of the one or more rays with one or more surfaces, where computing each surface normal includes: computing a plurality of intermediate surface normals associated with a plurality of adjacent voxels of a grid, and interpolating the plurality of intermediate surface normals; and rendering one or more graphics images based on the one or more surface normals.

Abstract: A technique for streaming and a client device that uses the technique are disclosed herein. The disclosed technique determines context complexity of streamed data and determines whether to discard or select the streamed data for a future reference frame based on the context complexity of the streamed data. The streamed data is discarded if the content complexity is higher than a content complexity threshold, and the streamed data is selected if the content complexity is not higher than a content complexity threshold. This is based on the realization that error propagation in the case of a less complex video sequence is not very bothersome to the end user experience whereas corruption will be very severe in cases of highly complex sequences.

Abstract: A level-shifting circuits utilizing storage cells for shifting signals low-to-high or high-to-low include control drivers with moving supply voltages. The moving supply voltages may power positive or negative supply terminals of the control drivers. The control drivers drive gates of common-source configured devices coupled to storage nodes of the storage cell.

Abstract: Stacked voltage domain level shifting circuits for shifting signals low-to-high or high-to-low include a storage cell and control drivers powered by a mid-range supply rail of the stacked voltage domain level shifting circuit, wherein the control drivers are coupled to drive common-source configured devices coupled to storage nodes of the storage cell.

Abstract: Stacked voltage domain level shifting circuits for shifting signals low-to-high or high-to-low include a storage cell powered by a mid-range supply rail of the stacked voltage domain level shifting circuit, and control drivers powered by moving supply voltages generated by the storage cell, wherein the control drivers coupled to drive gates of common-source configured devices coupled to storage nodes of the storage cell.

Abstract: In various examples, systems and methods are disclosed for generating and/or analyzing candidate paths for a multi-body vehicle—e.g., a tractor trailer truck—based on obstacle avoidance considerations and using an uncertainty representation for the vehicle. The uncertainty representation may correspond to a trailer portion of the multi-body vehicle to account for the variations in rotation of the trailer with respect to the tractor. As such, the uncertainty representation may be indicative of a probability that the trailer of the vehicle occupies locations and/or points in world space. This probability—combined with the probability of locations of actors in the environment—may be used to generate candidate paths that satisfy various constraints—e.g., a minimum stochastic distance—between the vehicle and the actor.

Abstract: A redundancy shut-off system for a datacenter liquid cooling system is disclosed. The redundancy shut-off system has a first ball valve located above a datacenter platform and coupling between a row manifold of a secondary cooling loop and a rack manifold of a rack, where the first ball valve provides redundancy to a second ball valve located below the datacenter platform.

Abstract: A three-dimensional (3D) object reconstruction neural network system learns to predict a 3D shape representation of an object from a video that includes the object. The 3D reconstruction technique may be used for content creation, such as generation of 3D characters for games, movies, and 3D printing. When 3D characters are generated from video, the content may also include motion of the character, as predicted based on the video. The 3D object construction technique exploits temporal consistency to reconstruct a dynamic 3D representation of the object from an unlabeled video. Specifically, an object in a video has a consistent shape and consistent texture across multiple frames. Texture, base shape, and part correspondence invariance constraints may be applied to fine-tune the neural network system. The reconstruction technique generalizes well—particularly for non-rigid objects.

Abstract: A multi-rank circuit system utilizing a shared IO channel includes a first stage of multiple selectors coupled to input multiple digital busses, and a second stage including one or more selectors coupled to receive outputs of the first stage of selectors and to individually select one of the outputs of the first stage of selectors to one or more control circuits for IO circuits of the ranks. The system switches one of the ranks to be an active rank on the shared IO channel, and operates the first stage of selectors to select one of the digital busses to the second stage of selectors in advance of switching a next active rank to the shared IO channel.

Abstract: A system, method, and apparatus of power management for computing systems are included herein that optimize individual frequencies of components of the computing systems using machine learning. The computing systems can be tightly integrated systems that consider an overall operating budget that is shared between the components of the computing system while adjusting the frequencies of the individual components. An example of an automated method of power management includes: (1) learning, using a power management (PM) agent, frequency settings for different components of a computing system during execution of a repetitive application, and (2) adjusting the frequency settings of the different components using the PM agent, wherein the adjusting is based on the repetitive application and one or more limitations corresponding to a shared operating budget for the computing system.

Abstract: A receiver device includes detection logic, an error counter, and an interrupt logic. The detection logic is to receive a first set of data frames and detect one or more frame errors in the first set of data frames. The error counter is to store a number of the one or more frame errors detected in the first set of data frames. The interrupt logic can be coupled to the error counter. The interrupt logic is to specify a period and compare the number of the one or more frame errors with a threshold number of frame errors during the period, where the interrupt logic is to indicate an interrupt responsive to the number of the one or more frame errors detected within the period satisfying the threshold number of frame errors.

Abstract: A game cloud server, a method of operating a cloud server, and a method of playing a game on a game cloud server are disclosed. In one example, the game cloud server includes: (1) one or more processing units that virtually supports different gaming applications according to a gaming operating mode, and (2) an operating mode selector that is coupled to the one or more processing units and has (2A) a virtual fusing register that selects the gaming operating mode for executing the different virtually supported gaming applications, and (2B) a security processor that enables a secure virtual fusing based on documented security files authorizing selection of the gaming operating mode, separately from executing an operating system of the one or more processing units, wherein the gaming operating mode is a reconfigurable operating mode selectable from at least one signed license file of the documented security files.

Abstract: A processing unit can include a performance monitor for monitoring the performance of the processing unit and associated sub-units. The performance monitor includes a logic analyzer, and implements a state machine via state machine data entries stored in a memory associated with the performance monitor. A state machine data entry includes output signals associated with state transitions. The output signals include a next state and a trigger to the logic analyzer. The performance monitor implements logic circuits that determine, based on input signals and the state machine data entries, the next state to transition and associated output signals. If a state transition includes a trigger to the logic analyzer, the trigger is transmitted to the logic analyzer. In response to the trigger, the logic analyzer assembles and samples input signals and stores the sampled input signals into the memory associated with the performance monitor, overwriting the state machine data entries.

Abstract: In various examples, an extensible network traffic engineering platform monitors network traffic and application performance to dynamically update network ingress and egress communication paths for increasing performance of the application—such as a cloud gaming application, a cloud virtual reality (VR) application, and/or another high performance application types. Pluggable, distributed, application-centric network monitors, policy engines, and network configurators are implemented at the edge to detect degraded network and application performance and dynamically update network routing to account for the same.

Abstract: A system and method for an on-demand shuttle, bus, or taxi service able to operate on private and public roads provides situational awareness and confidence displays. The shuttle may include ISO 26262 Level 4 or Level 5 functionality and can vary the route dynamically on-demand, and/or follow a predefined route or virtual rail. The shuttle is able to stop at any predetermined station along the route. The system allows passengers to request rides and interact with the system via a variety of interfaces, including without limitation a mobile device, desktop computer, or kiosks. Each shuttle preferably includes an in-vehicle controller, which preferably is an AI Supercomputer designed and optimized for autonomous vehicle functionality, with computer vision, deep learning, and real time ray tracing accelerators. An AI Dispatcher performs AI simulations to optimize system performance according to operator-specified system parameters.

Abstract: Systems and methods are described for rendering complex surfaces or geometry. In at least one embodiment, neural signed distance functions (SDFs) can be used that efficiently capture multiple levels of detail (LODs), and that can be used to reconstruct multi-dimensional geometry or surfaces with high image quality. An example architecture can represent complex shapes in a compressed format with high visual fidelity, and can generalize across different geometries from a single learned example. Extremely small multi-layer perceptrons (MLPs) can be used with an octree-based feature representation for the learned neural SDFs.

Abstract: This disclosure presents an assisted driving vehicle system, including autonomous, semi-autonomous, and technology assisted vehicles, that can share sensor data among two or more controllers. A sensor can have one communication channel to a controller, thereby saving cabling and circuitry costs. The data from the sensor can be sent from one controller to another controller to enable redundancy and backup in case of a system failure. Sensor data from more than one sensor can be aggregated at one controller prior to the aggregated sensor data being communicated to another controller thereby saving bandwidth and reducing transmission times. The sharing of sensor data can be enabled through the use of a sensor data distributor, such as a converter, repeater, or a serializer/deserializer set located as part of the controller and communicatively coupled to another such device in another controller using a data interface communication channel.

Abstract: In various embodiments, a software program uses hardware features of a parallel processor to checkpoint a context associated with an execution of a software application on the parallel processor. The software program uses a preemption feature of the parallel processor to cause the parallel processor to stop executing instructions in accordance with the context. The software program then causes the parallel processor to collect state data associated with the context. After generating a checkpoint based on the state data, the software program causes the parallel processor to resume executing instructions in accordance with the context.

Abstract: One embodiment of a computer-implemented method for decompressing a compressed texture block includes identifying a first texel included in a plurality of texels, wherein the plurality of texels forms at least a portion of a compressed texture block; determining a first location within the compressed texel block that corresponds to the first texel; and extracting the first texel from the first location without decompressing any of the other texels included in the plurality of texels.