Abstract: A system comprising an adapter plate to couple a plurality of different types of cooling manifolds to one or more racks in a datacenter is disclosed. Additionally, a system comprising an adapter plate to adaptively couple a cooling manifold to a plurality of different types of server racks is disclosed.

Abstract: Apparatuses, systems, and techniques provide a policy that can be executed to cause a machine to move. In at least one embodiment, a first policy layer is provided to cause the machine to execute a first motion that causes the machine to accelerate to reach an unbiased state. A second policy layer is provided to cause the machine to execute a second motion without influencing the unbiased state to be reached by machine. The policy can comprise the first and second policy layers.

Abstract: In various examples, computing system display settings may be configured automatically based at least on display illumination patterns. For example, a system(s) may determine one or more locations of one or more displays associated with a computing device based at least on image data depicting a user of the computing device. In some instances, the image data may be captured during a period of time in which the display(s) may be operating at one or more respective frequencies. During this period of time, the system(s) may cause the display(s) to operate at the respective frequency(ies), and the image data may depict one or more reflections of the display(s) off one or more portions of the user. The system(s) may then determine the location(s) of the display(s) based at least on correlating one or more frequencies associated with the reflection(s) to the respective frequency(ies) of the displays.

Abstract: In various examples, information may be received for a 3D model, such as 3D geometry information, lighting information, and material information. A machine learning model may be trained to disentangle the 3D geometry information, the lighting information, and/or material information from input data to provide the information, which may be used to project geometry of the 3D model onto an image plane to generate a mapping between pixels and portions of the 3D model. Rasterization may then use the mapping to determine which pixels are covered and in what manner, by the geometry. The mapping may also be used to compute radiance for points corresponding to the one or more 3D models using light transport simulation. Disclosed approaches may be used in various applications, such as image editing, 3D model editing, synthetic data generation, and/or data set augmentation.

Abstract: Apparatuses, systems, and techniques to indicate contextual information to be used by available logical processors. In at least one embodiment, one or more circuits are to perform an application programming interface (API) to indicate a first set of contextual information to be used by a first subset of available processors.

Abstract: Apparatuses, systems, and techniques for white balancing an image are presented. In at least one embodiment, a chromaticity-based weighting function is determined based at least on an estimated scene brightness of the image and applied to exclude or minimize the impact of large colored portions or objects within an image when estimating an illuminant color.

Abstract: A power arrangement and cooling system for electronic devices includes a processing unit electrically interconnected and disposed to a first side of a printed circuit board and a power converter electrically interconnected and disposed on a second side of the printed circuit board. The power converter includes a thermally conductive material layer that transfers heat generated by the power converter during operation away from the power converter toward a heatsink that is disposed adjacent the second side of the printed circuit board. Heat generated by the processing unit is absorbed by a heatsink disposed adjacent the first side of the printed circuit board. Power for the processing unit is provided, by the power converter, through a thickness of the printed circuit board.

Abstract: In various examples, systems and methods are disclosed relating to training machine learning models using human demonstration of segments of a task, where other segments of the task are performed by a planning method, such as a Task and Motion Planning (TAMP) system. A method may include segmenting a task to be performed by a robot into segments, determining a first set of instructions of a plurality of sets of instructions for operating the robot to perform a first objective of a first segment, determining that the plurality of sets of instructions is inadequate to perform a second objective of a second segment, receiving from a user device a second set of instructions for operating the robot for the second segment following an end of the first segment, and updating a machine learning model for controlling the robot using the second set of instructions for the second segment.

Abstract: In various examples, a hazard detection system fuses outputs from multiple sensors over time to determine a probability that a stationary object or hazard exists at a location. The system may then use sensor data to calculate a detection bounding shape for detected objects and, using the bounding shape, may generate a set of particles, each including a confidence value that an object exists at a corresponding location. The system may then capture additional sensor data by one or more sensors of the ego-machine that are different from those used to capture the first sensor data. To improve the accuracy of the confidences of the particles, the system may determine a correspondence between the first sensor data and the additional sensor data (e.g., depth sensor data), which may be used to filter out a portion of the particles and improve the depth predictions corresponding to the object.

Abstract: In various examples, a technique for slot filling includes receiving a natural language sentence from a user and identifying a first mention span included in the natural language sentence. The technique also includes determining, using a first machine learning model, that the first mention span is associated with a first slot class included in a set of slot classes based on a set of slot class descriptions corresponding to the set of slot classes.

Abstract: In one embodiment, a system receives 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, 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. 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. The system determines a reduction in contrast detectability of the imaging device based on the value.

Abstract: Apparatuses, systems, and techniques are described to determine locations of objects using images including digital representations of those objects. In at least one embodiment, a gaze of one or more occupants of a vehicle is determined independently of a location of one or more sensors used to detect those occupants.

Abstract: In various examples, apparatuses, systems, and techniques to perform offline image signal processing of source image data to generate target image data. In at least one embodiment, data collection using exposure and calibration setting of an image sensor is performed to generate source image data, which is then processed by using offline image signal processing to generate target data.

Abstract: Systems and methods for cooling a datacenter are disclosed. In at least one embodiment, a cold plate includes an evaporator to remove heat from at least one computing device using a two-phase fluid and using a buffer to perform flow stabilization represented by different volumes or different flow rates of a two-phase fluid that is enabled to flow between an evaporator and a condensing or compressor unit located external to a cold plate.

Abstract: The disclosure provides a signaling link that overcomes or at least reduces the limitations of RC-dominated signaling wires, improving both the bandwidth and the power consumption of signaling circuits. Both an AC and a DC signaling link are disclosed. In one example, a signaling link is provided that includes: (1) a transmitter including a passive equalizer, (2) an over-terminated receiver, and (3) a lossy channel having a first end connected to the passive equalizer and a second end connected to the receiver, wherein the lossy channel has a channel characteristic impedance that is lower than a terminating impedance of the passive equalizer and a termination impedance of the receiver.

Abstract: Apparatuses, systems, and techniques including APIs to enable one or more fifth generation new radio (5G-NR) network components to write, read, send, transmit, load, or otherwise obtain packaging, synchronization, and/or management information. For example, a processor comprising one or more circuits to perform an application programming interface (API) to cause fifth generation new radio (5G-NR) packaging, synchronization, or management information to be indicated to one or more accelerators.

Abstract: In various examples, perception-based parking assistance systems and methods for an ego-machine are presented. Example embodiments may determine a location of a real-world parking strip relative to an ego-machine and an associated parking rule for the parking strip. A virtual parking strip and one or more virtual parking signs may be generated based at least in part on one or more detected features in an environment of the ego-machine and a tracked motion of the ego machine, and the virtual parking strip may be used to track parking strip locations and associated parking rules. The virtual parking strips and associated rules may be relied upon by an ego-machine to determine parking locations and/or to navigate into a suitable parking spot.

Abstract: Various embodiments include techniques for storing data in a repurposed cache memory in a computing system. The disclosed techniques include a system level cache controller that processes a memory operation for a processing unit. The controller and the processing unit communicate over a network-on-chip. To process the memory operation, the controller selects a repurposed cache memory from a pool of active cache memories associated with processing units that are inoperable and/or are in a low-power state. To select the repurposed cache memory, the controller generates a candidate vector that identifies the position of the requesting processing unit relative to the controller. The candidate vector enables the controller in selecting a repurposed cache memory that is, for example, on the shortest path between the processing unit and the controller. These techniques result in a lower latency, and improved memory performance, relative to prior conventional techniques.

Abstract: Disclosed are systems and techniques for efficient real-time codec encoding of video files. In one embodiment, the techniques include obtaining a first plurality of motion vectors of a first resolution, generating a second plurality of motion vectors of a second resolution, and calculating a first cost of the motion vector using a first cost function of a first size. The techniques include selecting a subset of motion vectors of the second plurality of motion vectors, calculating a second cost using a second cost function of a second size, and generating a plurality of combined motion vectors based on the subset of motion vectors. The techniques include calculating a third cost using the second cost function of the second size, selecting a final motion vector, and generating, based on the selected final motion vector, a block of predicted pixels that approximates a block of source pixels of an image frame.

Abstract: In various examples, techniques for performing software code verification are described. Systems and methods are disclosed for generating, using intermediate code and user input, a call graph that represents source code for software. For instance, the call graph represents at least functions (e.g., internal functions, external functions, etc.) associated with the software, calls (e.g., direct calls, call pointers, etc.) between the functions, and register information associated with the functions (e.g., variables used by the functions, assembly code used by the functions, etc.). The systems and methods may further use the call graph to perform software code verification by verifying rules from design specifications for the software and/or rules from various certification standards.