公开(公告)号：US20250029286A1

公开(公告)日：2025-01-23

申请号：US18223229

申请日：2023-07-18

Applicant: NVIDIA CORPORATION

Inventor： Siddha Ganju ,  Srikanth Cherukuri ,  Elad Mentovich ,  Yoram Zer ,  Ashrut Ambastha ,  Jeremy Rodriguez ,  Lior Ofer

IPC: G06T11/00 ,  H04L43/045

Abstract: Systems, methods, and computer program products are provided for datacenter visualization. An example method includes receiving a request for datacenter visualization that is associated with a plurality of datacenter computing components of a physical datacenter installation. The method includes determining one or more installation characteristics associated with the physical datacenter installation and determining one or more performance parameters associated with the physical datacenter installation based at least in part on the one or more installation characteristics. The method further includes generating the datacenter visualization for presentation to a user associated with the request. The datacenter visualization is a digital representation of the physical datacenter installation that further includes a visual representation of the performance parameters associated with the plurality of datacenter computing components.

公开(公告)号：US20250005214A1

公开(公告)日：2025-01-02

申请号：US18215290

申请日：2023-06-28

Applicant: Nvidia Corporation

Inventor： Siddha Ganju ,  Aastha Jhunjhunwala ,  Elad Mentovich ,  Ryan Albright ,  Srikanth Cherukuri

IPC: G06F30/13 ,  G06F30/27

Abstract: Systems, computer program products, and methods are described herein for intelligent intelligently designing and reconfiguring data centers. For example, a system may be an artificial-intelligence-based system for designing and reconfiguring data centers based on user inquiries. The system may receive inquiries from users requesting a design for a data center having particular performance characteristics (e.g., selected performance characteristics), changes to an existing design of a data center, information about a data center, and/or the like. The inquiries may be text-based or audio and in the form of natural language questions or commands. The system may use two machine learning models, namely a knowledge base model and a ranking model. The system may use the knowledge base model to determine solutions to user inquiries and then use the ranking model to determine rankings for the solutions.