Abstract: A display device includes an array of LEDs, an array of LCD pixels, and a display controller that compensates for one or more sources of color variation in light produced by the LEDs having multiple color components that change differently as a function of distance. The display controller can determine a variation of a received color value from a color of light emitted by a given LED at a given LCD pixel based on the distance between the given LCD pixel and the given LED, and determine an accumulated color value that includes the variation and multiple other corresponding variations of other received color values of light emitted by multiple other emitters determined based on respective distances from the given LCD pixel. The display controller configures the given LCD pixel to filter light that is received from the LEDs in a manner that reduces or eliminates the color variation.

Abstract: In various embodiments, a comparison circuit compares voltages within an integrated circuit. The comparison circuit includes a comparison capacitor, an inverter, and multiple switches. A first terminal of the comparison capacitor is coupled to both a first terminal of a first switch and a first terminal of a second switch. A second terminal of the comparison capacitor is coupled to both a first terminal of a third switch and an input of the inverter. An output of the inverter is coupled to both a second terminal of the third switch and a first terminal of a fourth switch. A second terminal of the fourth switch is coupled to a first terminal of a fifth switch and a first output of the comparison circuit. At least a portion of the switches are turned on during a comparison model and are turned off during a reset mode.

Abstract: A latent code defined in an input space is processed by the mapping neural network to produce an intermediate latent code defined in an intermediate latent space. The intermediate latent code may be used as appearance vector that is processed by the synthesis neural network to generate an image. The appearance vector is a compressed encoding of data, such as video frames including a person's face, audio, and other data. Captured images may be converted into appearance vectors at a local device and transmitted to a remote device using much less bandwidth compared with transmitting the captured images. A synthesis neural network at the remote device reconstructs the images for display.

Abstract: High definition maps for autonomous vehicles are very high resolution and detailed, and hence require storage of a great deal of data. A vehicle computing system provides multi-layered caching makes this data usable in a system that requires very low latency on every operation. The system determines which routes are most likely to be driven in the near future by the car, and ensures that the route is cached on the vehicle before beginning the route. The system provides efficient formats for moving map data from server to car and for managing the on-car disk. The system further provides real-time accessibility of nearby map data as the car moves, while providing data access at optimal speeds.

Abstract: In various examples, at least partial control of a vehicle may be transferred to a control system remote from the vehicle. Sensor data may be received from a sensor(s) of the vehicle and the sensor data may be encoded to generate encoded sensor data. The encoded sensor data may be transmitted to the control system for display on a virtual reality headset of the control system. Control data may be received by the vehicle and from the control system that may be representative of a control input(s) from the control system, and actuation by an actuation component(s) of the vehicle may be caused based on the control input.

Abstract: The disclosure introduces polar stroking for representing paths. A system, method, and apparatus are disclosed for representing and rendering stroked paths employing polar stroking. In one example, a method of approximating a path is provided that includes: (1) evaluating, in parallel, multiple links of a path, wherein each link of the multiple links is evaluated in steps based on tangent angle changes of the link, and (2) providing a polar stroked representation of the path employing the steps. A computing system for rendering is also provided. In one example, the computing system includes one or more processing units to perform one or more operations including generating, in parallel, a polar stroked representation of individual links of a path, and rendering a stroked tessellation of the path based on the polar stroked representations of the individual links.

Abstract: In a streaming cache, multiple, dynamically sized tracking queues are employed. Request tracking information is distributed among the plural tracking queues to selectively enable out-of-order memory request returns. A dynamically controlled policy assigns pending requests to tracking queues, providing for example in-order memory returns in some contexts and/or for some traffic and out of order memory returns in other contexts and/or for other traffic.

Abstract: In various examples, a test system is provided for executing built-in-self-test (BIST) on integrated circuits deployed in the field. The integrated circuits may include a first device and a second device, the first device having direct access to external memory, which stores test data, and the second device having indirect access to the external memory by way of the first device. In addition to providing a mechanism to permit the first device and the second device to run test concurrently, the hardware and software may reduce memory requirements and runtime associated with running the test sequences, thereby making real-time BIST possible in deployment. Furthermore, some embodiments permit a single external memory image to cater to different SKU configurations.

Abstract: Generation of synthetic speech from an input text sequence may be difficult when durations of individual phonemes forming the input text sequence are unknown. A predominantly parallel process may model speech rhythm as a separate generative distribution such that phoneme duration may be sampled at inference. Additional information such as pitch or energy may also be sampled to provide improved diversity for synthetic speech generation.

Abstract: In various examples, systems and methods of the present disclosure combine open and closed dialog systems into an intelligent dialog management system. A text query may be processed by a natural language understanding model trained to associate the text query with a domain tag, intent classification, and/or input slots. Using the domain tag, the natural language understanding model may identify information in the text query corresponding to input slots needed for answering the text query. The text query and related information may then be passed to a dialog manager to direct the text query to the proper domain dialog system. Responses retrieved from the domain dialog system may be provided to the user via text output and/or via a text to speech component of the dialog management system.

Abstract: A distributed deep neural net (DNN) utilizing a distributed, tile-based architecture implemented on a semiconductor package. The package includes multiple chips, each with a central processing element, a global memory buffer, and processing elements. Each processing element includes a weight buffer, an activation buffer, and multiply-accumulate units to combine, in parallel, the weight values and the activation values.

Abstract: Packet flows between a transmitter and a receiver in an unreliable and unordered switched packet network may be established as a result of receiving a second packet comprising a second memory operation on a memory address. The transmission of memory load command packets followed by memory store command packets in the packet flow may be serialized, and a synchronization operation may be executed between the transmitter and the receiver when a packet count at the receiver satisfies a number of data packets in the packet flow.

Abstract: In various examples, a deep neural network (DNN) is trained—using image data alone—to accurately predict distances to objects, obstacles, and/or a detected free-space boundary. The DNN may be trained with ground truth data that is generated using sensor data representative of motion of an ego-vehicle and/or sensor data from any number of depth predicting sensors—such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. The DNN may be trained using two or more loss functions each corresponding to a particular portion of the environment that depth is predicted for, such that—in deployment—more accurate depth estimates for objects, obstacles, and/or the detected free-space boundary are computed by the DNN. In some embodiments, a sampling algorithm may be used to sample depth values corresponding to an input resolution of the DNN from a predicted depth map of the DNN at an output resolution of the DNN.

Abstract: Data bits are encoded in an eleven bit seven pulse amplitude modulated three-level (PAM-3) symbol format on a plurality of data channels and two auxiliary data channels, and one or more of a cyclic redundancy check (CRC) value, a poison value, and a severity value are encoded as PAM-3 symbols on an error correction channel.

Abstract: Determining the occlusions or shadows for an area light within a scene is difficult, especially realistic shadowing in large and dynamic scenes. The disclosure provides an adaptive occlusion sampling process that uses voxel cone tracing to distribute the voxel tracing cones on the surface of area lights to obtain samples for shadowing in computer generated images or scenes. A method of adaptive occlusion sampling from a rectangular area light is disclosed that can be used to provide realistic shadowing in a computer generated scene. A process to compute a shadow of an area light within a scene is also disclosed herein that includes obtaining samples, employing voxel cone tracing, from a light surface of the area light based on sample points of a sampling grid created from sample patterns that are based on a determined number of cones.

Abstract: A generative adversarial neural network (GAN) learns a particular task by being shown many examples. In one scenario, a GAN may be trained to generate new images including specific objects, such as human faces, bicycles, etc. Rather than training a complex GAN having a predetermined topology of features and interconnections between the features to learn the task, the topology of the GAN is modified as the GAN is trained for the task. The topology of the GAN may be simple in the beginning and become more complex as the GAN learns during the training, eventually evolving to match the predetermined topology of the complex GAN. In the beginning the GAN learns large-scale details for the task (bicycles have two wheels) and later, as the GAN becomes more complex, learns smaller details (the wheels have spokes).

Abstract: One embodiment of a method for computing a texture color includes tracing a ray cone through a graphics scene, determining a curvature of a first surface within the graphics scene at a point where the ray cone hits the first surface based on differential barycentric coordinates associated with the point, determining, based on the curvature of the first surface, a width of the ray cone at a subsequent point where the ray cone hits a second surface within the graphics scene, and computing a texture color based on the width of the ray cone.

Abstract: A device includes feed-forward clock circuitry to provide a receiver (RX) clock to a sampler circuit that samples a data lane of a set of RX data lanes, the feed-forward clock circuitry having a temperature-induced delay. The device also includes an RX phase-locked loop (PLL) coupled between the feed-forward clock circuitry and the sampler circuit. The RX PLL includes a phase interpolator positioned in a feedback path of the RX PLL. The phase interpolator has a negative delay that matches the temperature-induced delay of the feed-forward clock circuitry to cause the sampler circuit to cancel out the common noise shared between the feed-forward clock circuitry and the data lane.

Abstract: In various examples, a trigger signal may be received that is indicative of a vehicle maneuver to be performed by a vehicle. A recommended vehicle trajectory for the vehicle maneuver may be determined in response to the trigger signal being received. To determine the recommended vehicle trajectory, sensor data may be received that represents a field of view of at least one sensor of the vehicle. A value of a control input and the sensor data may then be applied to a machine learning model(s) and the machine learning model(s) may compute output data that includes vehicle control data that represents the recommended vehicle trajectory for the vehicle through at least a portion of the vehicle maneuver. The vehicle control data may then be sent to a control component of the vehicle to cause the vehicle to be controlled according to the vehicle control data.

Abstract: In one embodiment, a system determines pixel data from a pair of regions of an image generated by an imaging device, the pair of regions includes a first region and a second region, where the first region includes a first plurality of pixels and the second region includes a second plurality of pixels. The system determines a plurality of pixel pairs of the image, where a pixel pair includes a first pixel from the first plurality of pixels and a second pixel from the second plurality of pixels. The system calculates a plurality of contrasts based on the plurality of pixel pairs, where a contrast is calculated between the first pixel and the second pixel. The system determines a contrast distribution based on the plurality of contrasts. The system calculates a value representative of a capability of the imaging device to detect contrast based on the contrast distribution.