Abstract: Techniques applicable to a ray tracing hardware accelerator for traversing a hierarchical acceleration structure with reduced false positive ray intersections are disclosed. The reduction of false positives may be based upon one or more of selectively performing a secondary higher precision intersection test for a bounding volume, identifying and culling bounding volumes that degenerate to a point, and parametrically clipping rays that exceed certain configured distance thresholds.
Type:
Grant
Filed:
September 16, 2022
Date of Patent:
January 14, 2025
Assignee:
NVIDIA CORPORATION
Inventors:
Gregory Muthler, John Burgess, Magnus Andersson, Ian Kwong, Edward Biddulph
Abstract: A receiver includes a multi-phase clock generator to generate phases of a clock signal and a global phase interpolator (PI) circuit coupled to the multi-phase clock generator and to clock and data recovery (CDR) circuitry. The global PI circuit generates initial-adjusted phases from the phases of the clock signal based on a control signal received from the CDR circuitry. A first local PI receives the initial-adjusted phases of the clock signal and applies a first fixed phase shift to the initial-adjusted phases to generate first final-adjusted phases of the clock signal that are useable to sample a first level of multiple levels of a pulse-amplitude-modulated (PAM) data stream.
Abstract: Apparatuses, systems, and techniques to determine position information for a gameplay session. In at least one embodiment, the position information is determined by at least matching features extracted from a mini-map to feature extracted from a map and determining a transformation matrix to be applied to a position within the mini-map.
Type:
Grant
Filed:
January 27, 2022
Date of Patent:
January 14, 2025
Assignee:
NVIDIA Corporation
Inventors:
Jim van Welzen, Suresh Yerva, Jonathan White, Shyam Raikar
Abstract: Systems and methods for cooling a datacenter are disclosed. In at least one embodiment, a fluid reservoir in a form-factor of at least one rack is provided, the fluid reservoir to store fluid, the fluid to be passed to a cold plate or an immersive-cooled server, and the fluid to be cooled by a secondary cooling loop or an air-cooling system.
Abstract: Techniques applicable to a ray tracing hardware accelerator for traversing a hierarchical acceleration structure with reduced false positive ray intersections are disclosed. The reduction of false positives may be based upon one or more of selectively performing a secondary higher precision intersection test for a bounding volume, identifying and culling bounding volumes that degenerate to a point, and parametrically clipping rays that exceed certain configured distance thresholds.
Type:
Grant
Filed:
September 16, 2022
Date of Patent:
January 14, 2025
Assignee:
NVIDIA CORPORATION
Inventors:
Gregory Muthler, John Burgess, Magnus Andersson, Ian Kwong, Edward Biddulph
Abstract: A system includes a device having a controller a plurality of finite state machines (FSMs). The device is to detect that one or more FSMs of the plurality of FSMs fails to satisfy a non-idle duration criterion during an operation, where the one or more FSM that fail to satisfy the non-idle duration criterion are associated with one or more errors. The device is to determine a location of the one or more FSMs that fail to satisfy the non-idle duration criterion. The device is to record the location of the one or more FSMs and the one or more errors, restore the one or more FSM to an idle state, and transmit an indication that the one or more FSMs failed to satisfy the non-idle duration criterion.
Type:
Grant
Filed:
July 7, 2022
Date of Patent:
January 14, 2025
Assignee:
NVIDIA Corporation
Inventors:
Leon Lixingyu, Prosenjit Chatterjee, Anshu Nadkarni
Abstract: A transceiver configured to communicate a burst of data bits and meta-data bits for the data bits includes data channels, auxiliary data channels, and at least one error correction channel. The transceiver includes an encoder that applies 11b7s encoding to a first number of the data bits to generate first PAM-3 symbols on some or all of the communication channels, and that applies 3b2s encoding to a second number of the data bits to generate second PAM-3 symbols on at least some of the communication channels.
Abstract: Methods and systems are described in some examples for changing the traversal of an acceleration data structure in a highly dynamic query-specific manner, with each query specifying test parameters, a test opcode and a mapping of test results to actions. In an example ray tracing implementation, traversal of a bounding volume hierarchy by a ray is performed with the default behavior of the traversal being changed in accordance with results of a test performed using the test opcode and test parameters specified in the ray data structure and another test parameter specified in a node of the bounding volume hierarchy. In an example implementation a traversal coprocessor is configured to perform the traversal of the bounding volume hierarchy.
Type:
Grant
Filed:
September 21, 2023
Date of Patent:
January 14, 2025
Assignee:
NVIDIA CORPORATION
Inventors:
Samuli Laine, Timo Aila, Tero Karras, Gregory Muthler, William P. Newhall, Jr., Ronald C Babich, Jr., Craig Kolb, Ignacio Llamas, John Burgess
Abstract: The present technology augments the GPU compute model to provide system-provided data marshalling characteristics of graphics pipelining to increase efficiency and reduce overhead. A simple scheduling model based on scalar counters (e.g., semaphores) abstract the availability of hardware resources. Resource releases can be done programmatically, and a system scheduler only needs to track the states of such counters/semaphores to make work launch decisions. Semantics of the counters/semaphores are defined by an application, which can use the counters/semaphores to represent the availability of free space in a memory buffer, the amount of cache pressure induced by the data flow in the network, or the presence of work items to be processed.
Type:
Grant
Filed:
March 17, 2021
Date of Patent:
January 14, 2025
Assignee:
NVIDIA Corporation
Inventors:
Yury Uralsky, Henry Moreton, Matthijs de Smedt, Lei Yang
Abstract: The present disclosure relates to determining a first illumination level corresponding to an area based at least on a first illumination detection obtained using a first illumination detector corresponding to a machine. A second illumination level corresponding to the area may be determined based at least on a second illumination detection obtained using a second illumination detector corresponding to the machine. Based at least on the first illumination level and the second illumination level, a scene illumination state of the area may be determined. Based at least on the scene illumination state, one or more lights of the machine may be controlled.
Type:
Grant
Filed:
August 16, 2023
Date of Patent:
January 7, 2025
Assignee:
NVIDIA CORPORATION
Inventors:
Keerthi Raj Nagaraja, Arjun Gupta, Abhishek Bajpayee, Kivanc Temel, Dylan Doblar, Sai Krishnan Chandrasekar, Yu Wang
Abstract: A multi-format graphics process unit (GPU) docking board is disclosed. The multi-format GPU docking board includes a first switch to enable communication between a first format (GPU) board and a second format GPU board, and a second switch to enable communication between a central processing unit (CPU) and the first format GPU board and between the CPU and the second format GPU board.
Type:
Grant
Filed:
July 31, 2020
Date of Patent:
January 7, 2025
Assignee:
Nvidia Corporation
Inventors:
Xiaozhuo Cai, Shuanghu Yan, Hao Zhu, Dinghai Yi
Abstract: One or more embodiments of the present disclosure relate to generating RADAR (RAdio Detection And Ranging) point clouds based on RADAR data obtained from one or more RADAR sensors disposed on one or more ego-machines. In these or other embodiments, the RADAR point clouds may be communicated to a distributed map system that is configured to generate map data based on the RADAR point clouds. In some embodiments of the present disclosure, certain compression operations may be performed on the RADAR point clouds to reduce the amount of data that is communicated from the ego-machines to the map system.
Type:
Grant
Filed:
March 21, 2022
Date of Patent:
January 7, 2025
Assignee:
NVIDIA CORPORATION
Inventors:
Amir Akbarzadeh, Andrew Carley, Birgit Henke, Si Lu, Ivana Stojanovic, Jugnu Agrawal, Michael Kroepfl, Yu Sheng, David Nister, Enliang Zheng, Niharika Arora
Abstract: Systems and methods for a datacenter cooling system are disclosed. In at least one embodiment, a thermal test vehicle (TTV) includes an air-cooled heat element associated with a plurality of fins to enable air cooling of a TTV and includes a liquid-cooled heat trace associated with a cold plate to enable liquid cooling of a TTV, where an air-cooled heat element and a liquid-cooled heat trace generate heat to enable separate or concurrent testing of air cooling and liquid cooling in a datacenter cooling system.
Abstract: In various examples, systems and methods are disclosed relating to aligning images into frames of a first video using at least one first temporal attention layer of a neural network model. The first video has a first spatial resolution. A second video having a second spatial resolution is generated by up-sampling the first video using at least one second temporal attention layer of an up-sampler neural network model, wherein the second spatial resolution is higher than the first spatial resolution.
Type:
Grant
Filed:
March 10, 2023
Date of Patent:
January 7, 2025
Assignee:
NVIDIA Corporation
Inventors:
Karsten Julian Kreis, Robin Rombach, Andreas Blattmann, Seung Wook Kim, Huan Ling, Sanja Fidler, Tim Dockhorn
Abstract: In various examples, a method includes computing a current keyframe, the current keyframe being representative of an area around an autonomous vehicle at a current time based on map data. The method includes transforming a preceding keyframe to a coordinate frame of the autonomous vehicle at a first time prior to completing computation of the current keyframe to generate a first world model frame. The method includes transforming the preceding keyframe to the coordinate frame of the autonomous vehicle at a second time after the first time and prior to completing computation of the current keyframe to generate a second world model frame.
Type:
Grant
Filed:
March 10, 2022
Date of Patent:
January 7, 2025
Assignee:
NVIDIA CORPORATION
Inventors:
Akash Chandra Shekar, Matthew Ashman, Vaibhav Thukral
Abstract: In various examples, methods may include receiving first data transmitted from a second component and second data transmitted from the second component during a first time period. The first data may be transmitted via a first data lane and the second data may be transmitted via a second data lane. The method may include receiving de-skew symbols at an interval from the second component via the first data lane and via the second data lane during the first time period. The method may include compensating for a first skew introduced to a first propagation of the first data across the first data lane and a second skew introduced to a second propagation of the second data across the second data lane using the de-skew symbols received during the first time period.
Type:
Grant
Filed:
July 15, 2022
Date of Patent:
January 7, 2025
Assignee:
NVIDIA CORPORATION
Inventors:
Padmanabham Patki, Nisha Bhushan, Kiran Kumar Dash, Arpit Gupta, Chung-Hong Lai, Michael Alan Ditty
Abstract: In various examples, to support training a deep neural network (DNN) to predict a dense representation of a 3D surface structure of interest, a training dataset is generated using a simulated environment. For example, a simulation may be run to simulate a virtual world or environment, render frames of virtual sensor data (e.g., images), and generate corresponding depth maps and segmentation masks (identifying a component of the simulated environment such as a road). To generate input training data, 3D structure estimation may be performed on a rendered frame to generate a representation of a 3D surface structure of the road. To generate corresponding ground truth training data, a corresponding depth map and segmentation mask may be used to generate a dense representation of the 3D surface structure.
Type:
Grant
Filed:
October 28, 2021
Date of Patent:
January 7, 2025
Assignee:
NVIDIA Corporation
Inventors:
Kang Wang, Yue Wu, Minwoo Park, Gang Pan
Abstract: Systems and methods for cooling a computer environment are disclosed. In at least one embodiment, one or more neural networks can be used to determine one or more temperature control settings associated with one or more servers.
Abstract: A method includes obtaining first user input identifying at least one LIDAR point in a set of LIDAR points associated with an object in an image, and obtaining second user input identifying the object in the image. The method may also include generating a constraint on a relationship between a LIDAR sensor used to capture the set of LIDAR points and a camera used to capture the image. The method may additionally include reducing a cost associated with the LIDAR point being inconsistent with the object in the image subject to the constraint.
Abstract: Apparatuses, systems, and techniques are presented to reduce noise in audio. In at least one embodiment, one or more neural networks are used to determine a noise signal in one or more speech signals.