Nvidia Patent Grants

Blower design for a graphics processing unit

Granted: June 25, 2024
Patent Number: 12022633
A graphics subsystem includes a printed circuit board (PCB), a blower, and a heat sink. A graphics processing unit (GPU) is integrated into the PCB. The PCB is shortened to occupy a portion of the width of the graphics subsystem. The heat sink is coupled to the PCB and/or GPU similarly occupies just a portion of the width of the graphics subsystem. The blower is disposed adjacent to the PCB and heat sink and configured to occupy the full height of the graphics subsystem. The blower is…

Ray tracing hardware acceleration with alternative world space transforms

Granted: June 25, 2024
Patent Number: 12020367
Enhanced techniques applicable to a ray tracing hardware accelerator for traversing a hierarchical acceleration structure are disclosed. The traversal efficiency of such hardware accelerators are improved, for example, by transforming a ray, in hardware, from the ray's coordinate space to two or more coordinate spaces at respective points in traversing the hierarchical acceleration structure. In one example, the hardware accelerator is configured to transform a ray, received from a…

Techniques for balancing workloads when parallelizing multiply-accumulate computations

Granted: June 25, 2024
Patent Number: 12020076
In various embodiments, a dispatch application performs multiply-accumulate (“MAC”) computations across parallel processing elements. In operation, the dispatch application determines a first quantity of iterations associated with a given MAC computation. The dispatch application determines a maximum number of tasks that can execute concurrently across a set of parallel processing elements. Subsequently, the dispatch application causes the maximum number of tasks to be executed…

Programmatically controlled data multicasting across multiple compute engines

Granted: June 25, 2024
Patent Number: 12020035
This specification describes a programmatic multicast technique enabling one thread (for example, in a cooperative group array (CGA) on a GPU) to request data on behalf of one or more other threads (for example, executing on respective processor cores of the GPU). The multicast is supported by tracking circuitry that interfaces between multicast requests received from processor cores and the available memory. The multicast is designed to reduce cache (for example, layer 2 cache)…

Routing connections in integrated circuits based on reinforcement learning

Granted: June 25, 2024
Patent Number: 12019967
The disclosure provides a general solution for determining connections between terminals of various types of circuits using machine learning (ML). A ML method that uses reinforcement learning (RL), such as deep RL, to determine and optimize routing of circuit connections using a game process is provided. In one example a method of determining routing connection includes: (1) receiving a circuit design having known terminal groups, (2) establishing terminal positions for the terminal…

Core off sleep mode with low exit latency

Granted: June 25, 2024
Patent Number: 12019498
An optimized power saving technique is described for a processor, such as, for example, a graphic processing unit (GPU), which includes one or more processing cores and at least one data link interface. According to the technique, the processor is operable in a low power mode in which power to the at least one processing core is off and power to the at least one data link interface is on. This technique provides reduced exit latencies compared to currently available approaches in which…

Transformation of joint space coordinates using machine learning

Granted: June 25, 2024
Patent Number: 12017352
Apparatuses, systems, and techniques to map coordinates in task space to a set of joint angles of an articulated robot. In at least one embodiment, a neural network is trained to map task-space coordinates to joint space coordinates of a robot by simulating a plurality of robots at various joint angles, and determining the position of their respective manipulators in task space.

Adaptive temporal image filtering for rendering realistic illumination

Granted: June 18, 2024
Patent Number: 12014460
Robust temporal gradients, representing differences in shading results, can be computed between current and previous frames in a temporal denoiser for ray-traced renderers. Backward projection can be used to locate matching surfaces, with the relevant parameters of those surfaces being carried forward and used for patching. Backward projection can be performed for each stratum in a current frame, a stratum representing a set of adjacent pixels. A pixel from each stratum is selected that…

In-row cooling unit with interchangeable heat exchangers

Granted: June 18, 2024
Patent Number: 12016154
Systems and methods for cooling a datacenter are disclosed. In at least one embodiment, an in-row cooling unit is located within a row of racks and between racks so that it can use an interchangeable heat exchanger (IHE) to receive a primary coolant and can use one or more flow controllers to provide a first part of the primary coolant to cool a secondary coolant that is to be distributed to at least one cold plate, and to provide a second part of the primary coolant to cool air to be…

Event information extraction from game logs using natural language processing

Granted: June 18, 2024
Patent Number: 12014547
In various examples, natural language processing may be performed on text generated by a game to extract one or more in-game events from the game. The system (e.g., a client device and/or server) may receive the text in the form of one or more strings generated by a game application. The system may then extract one or more in-game events from the text using natural language processing. The game may include the text in a message it sends to the system (e.g., using an Application…

Concurrent hash map updates

Granted: June 18, 2024
Patent Number: 12013844
Approaches in accordance with various embodiments can perform spatial hash map updates while ensuring the atomicity of the updates for arbitrary data structures. A hash map can be generated for a dataset where entries in the hash map may correspond to multiple independent values, such as pixels of an image to be rendered. Update requests for independent values may be received on multiple concurrent threads, but change requests for independent values corresponding to a hash map entry can…

Intersection pose detection in autonomous machine applications

Granted: June 18, 2024
Patent Number: 12013244
In various examples, live perception from sensors of a vehicle may be leveraged to generate potential paths for the vehicle to navigate an intersection in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputs—such as heat maps corresponding to key points associated with the intersection, vector fields corresponding to directionality, heading, and offsets with respect to lanes, intensity maps corresponding to widths of lanes,…

Communicating faults to an isolated safety region of a system on a chip

Granted: June 18, 2024
Patent Number: 12012125
In various examples, an integrated circuit includes first and second portions. The first portion includes a timer that starts when the first portion transmits at least one error signal to the second portion. The timer may reset when data corresponding to at least one fault has been cleared from the first portion. The first portion transmits a timeout error signal when the timer indicates at least a predetermined amount of time has elapsed. The second portion receives the at least one…

Energy efficient liquid-cooled datacenters

Granted: June 11, 2024
Patent Number: 12010819
Systems and methods for operating a datacenter are disclosed. In at least one embodiment, a power delivery system includes one or more fuel cells to provide a source of electrical power for a datacenter, where waste heat produced by a fuel cell is to be captured and provided to an absorption chiller to produce a cooled liquid for use in a cooling system for this datacenter.

Level-conversion circuits for signaling across voltage domains

Granted: June 11, 2024
Patent Number: 12009816
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.

Transposed sparse matrix multiply by dense matrix for neural network training

Granted: June 11, 2024
Patent Number: 12008475
Machine learning systems that implement neural networks typically operate in an inference mode or a training mode. In the training mode, inference operations are performed to help guide the training process. Inference mode operation typically involves forward propagation and intensive access to certain sparse matrices, encoded as a set of vectors. Back propagation and intensive access to transposed versions of the same sparse matrices provide training refinements. Generating a transposed…

Machine learning-based seatbelt detection and usage recognition using fiducial marking

Granted: June 11, 2024
Patent Number: 12005855
Systems and methods for machine learning based seatbelt position detection and classification. A number of fiducial markers are placed on a vehicle seatbelt. A camera or other sensor is placed within the vehicle, to capture images or other data relating positions of the fiducial markers when the seatbelt is in use. One or more models such as machine learning models may then determine the spatial positions of the fiducial markers from the captured image information, and determine the worn…

Cloud execution of audio/video compositing applications

Granted: June 11, 2024
Patent Number: 12005363
In various examples, applications may be executed on remote computing devices to composite and broadcast gameplay with video and audio data. Systems and methods are disclosed that distribute, between and among various computing devices, processing of tasks including rendering of gameplay, composition of various types of data, and broadcasting of composited data. The tasks may be executed on computing devices that are remote to a client device, such as a virtual machine, GPU, server,…

Protecting against resets by untrusted software during cryptographic operations

Granted: June 4, 2024
Patent Number: 12001592
Apparatuses, systems, and techniques for handling faults by a direct memory access (DMA) engine. When a DMA engine detects an error associated with an encryption or decryption operation, the DMA engine reports the error to a CPU, which may be executing an untrusted software directing a DMA operation, and the secure processor. The DMA engine waits for clearance from the secure processor before responding to further directions from the potentially untrusted software.

Future trajectory predictions in multi-actor environments for autonomous machine

Granted: June 4, 2024
Patent Number: 12001958
In various examples, past location information corresponding to actors in an environment and map information may be applied to a deep neural network (DNN)—such as a recurrent neural network (RNN)—trained to compute information corresponding to future trajectories of the actors. The output of the DNN may include, for each future time slice the DNN is trained to predict, a confidence map representing a confidence for each pixel that an actor is present and a vector field representing…