Patents by Inventor Dominic Rajeev DIVAKARUNI

Dominic Rajeev DIVAKARUNI has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Fault-tolerant accelerator based inference service
    Patent number: 11960935
    Abstract: Implementations detailed herein include description of a computer-implemented method.
    Type: Grant
    Filed: June 27, 2018
    Date of Patent: April 16, 2024
    Assignee: Amazon Technologies, Inc.
    Inventors: Sudipta Sengupta, Poorna Chand Srinivas Perumalla, Dominic Rajeev Divakaruni, Nafea Bshara, Leo Parker Dirac, Bratin Saha, Matthew James Wood, Andrea Olgiati, Swaminathan Sivasubramanian
  • Attached accelerator based inference service
    Patent number: 11599821
    Abstract: Implementations detailed herein include description of a computer-implemented method. In an implementation, the method at least includes receiving an application instance configuration, an application of the application instance to utilize a portion of an attached accelerator during execution of a machine learning model and the application instance configuration including: an indication of the central processing unit (CPU) capability to be used, an arithmetic precision of the machine learning model to be used, an indication of the accelerator capability to be used, a storage location of the application, and an indication of an amount of random access memory to use.
    Type: Grant
    Filed: June 27, 2018
    Date of Patent: March 7, 2023
    Assignee: Amazon Technologies, Inc.
    Inventors: Sudipta Sengupta, Poorna Chand Srinivas Perumalla, Dominic Rajeev Divakaruni, Nafea Bshara, Leo Parker Dirac, Bratin Saha, Matthew James Wood, Andrea Olgiati, Swaminathan Sivasubramanian
  • Attached accelerator selection and placement
    Patent number: 11494621
    Abstract: Implementations detailed herein include description of a computer-implemented method.
    Type: Grant
    Filed: June 27, 2018
    Date of Patent: November 8, 2022
    Assignee: Amazon Technologies, Inc.
    Inventors: Sudipta Sengupta, Poorna Chand Srinivas Perumalla, Dominic Rajeev Divakaruni, Nafea Bshara, Leo Parker Dirac, Bratin Saha, Matthew James Wood, Andrea Olgiati, Swaminathan Sivasubramanian
  • Framework integration for instance-attachable accelerator
    Patent number: 11467835
    Abstract: Techniques for partitioning data flow operations between execution on a compute instance and an attached accelerator instance are described. A set of operations supported by the accelerator is obtained. A set of operations associated with the data flow is obtained. An operation in the set of operations associated with the data flow is identified based on the set of operations supported by the accelerator. The accelerator executes the first operation.
    Type: Grant
    Filed: November 23, 2018
    Date of Patent: October 11, 2022
    Assignee: Amazon Technologies, Inc.
    Inventors: Sudipta Sengupta, Poorna Chand Srinivas Perumalla, Jalaja Kurubarahalli, Samuel Oshin, Cory Pruce, Jun Wu, Eftiquar Shaikh, Pragya Agarwal, David Thomas, Karan Kothari, Daniel Evans, Umang Wadhwa, Mark Klunder, Rahul Sharma, Zdravko Pantic, Dominic Rajeev Divakaruni, Andrea Olgiati, Leo Dirac, Nafea Bshara, Bratin Saha, Matthew Wood, Swaminathan Sivasubramanian, Rajankumar Singh
  • Attached accelerator scaling
    Patent number: 11422863
    Abstract: Implementations detailed herein include description of a computer-implemented method. In an implementation, the method at least includes provisioning an application instance and portions of at least one accelerator attached to the application instance to execute a machine learning model of an application of the application instance; loading the machine learning model onto the portions of the at least one accelerator; receiving scoring data in the application; and utilizing each of the portions of the attached at least one accelerator to perform inference on the scoring data in parallel and only using one response from the portions of the accelerator.
    Type: Grant
    Filed: June 27, 2018
    Date of Patent: August 23, 2022
    Assignee: Amazon Technologies, Inc.
    Inventors: Sudipta Sengupta, Poorna Chand Srinivas Perumalla, Dominic Rajeev Divakaruni, Nafea Bshara, Leo Parker Dirac, Bratin Saha, Matthew James Wood, Andrea Olgiati, Swaminathan Sivasubramanian
  • Model adaptation
    Patent number: 11423283
    Abstract: Techniques for model adaptation are described. For example, a method of receiving a call to provide either a model variant or a model variant profile of a deep learning model, the call including desired performance of the deep learning model, a deep learning model identifier, and current edge device characteristics; comparing the received current edge device characteristics to available model variants and profiles based on the desired performance of the deep learning model to generate or select a model variant or profile, the available model variants and profiles determined by the model identifier; and sending the generated or selected model variant or profile to the edge device to use in inference is detailed.
    Type: Grant
    Filed: March 22, 2018
    Date of Patent: August 23, 2022
    Assignee: Amazon Technologies, Inc.
    Inventors: Hagay Lupesko, Dominic Rajeev Divakaruni, Jonathan Esterhazy, Sandeep Krishnamurthy, Vikram Madan, Roshani Nagmote, Naveen Mysore Nagendra Swamy, Yao Wang
  • ATTACHED ACCELERATOR BASED INFERENCE SERVICE
    Publication number: 20200004596
    Abstract: Implementations detailed herein include description of a computer-implemented method. In an implementation, the method at least includes receiving an application instance configuration, an application of the application instance to utilize a portion of an attached accelerator during execution of a machine learning model and the application instance configuration including: an indication of the central processing unit (CPU) capability to be used, an arithmetic precision of the machine learning model to be used, an indication of the accelerator capability to be used, a storage location of the application, and an indication of an amount of random access memory to use.
    Type: Application
    Filed: June 27, 2018
    Publication date: January 2, 2020
    Inventors: Sudipta SENGUPTA, Poorna Chand Srinivas PERUMALLA, Dominic Rajeev DIVAKARUNI, Nafea BSHARA, Leo Parker DIRAC, Bratin SAHA, Matthew James WOOD, Andrea OLGIATI, Swaminathan SIVASUBRAMANIAN
  • ATTACHED ACCELERATOR SELECTION AND PLACEMENT
    Publication number: 20200005124
    Abstract: Implementations detailed herein include description of a computer-implemented method.
    Type: Application
    Filed: June 27, 2018
    Publication date: January 2, 2020
    Inventors: Sudipta SENGUPTA, Poorna Chand Srinivas PERUMALLA, Dominic Rajeev DIVAKARUNI, Nafea BSHARA, Leo Parker DIRAC, Bratin SAHA, Matthew James WOOD, Andrea OLGIATI, Swaminathan SIVASUBRAMANIAN
  • ATTACHED ACCELERATOR SCALING
    Publication number: 20200004597
    Abstract: Implementations detailed herein include description of a computer-implemented method.
    Type: Application
    Filed: June 27, 2018
    Publication date: January 2, 2020
    Inventors: Sudipta SENGUPTA, Poorna Chand Srinivas PERUMALLA, Dominic Rajeev DIVAKARUNI, Nafea BSHARA, Leo Parker DIRAC, Bratin SAHA, Matthew James WOOD, Andrea OLGIATI, Swaminathan SIVASUBRAMANIAN
  • FAULT-TOLERANT ACCELERATOR BASED INFERENCE SERVICE
    Publication number: 20200004595
    Abstract: Implementations detailed herein include description of a computer-implemented method.
    Type: Application
    Filed: June 27, 2018
    Publication date: January 2, 2020
    Inventors: Sudipta SENGUPTA, Poorna Chand Srinivas PERUMALLA, Dominic Rajeev DIVAKARUNI, Nafea BSHARA, Leo Parker DIRAC, Bratin SAHA, Matthew James WOOD, Andrea OLGIATI, Swaminathan SIVASUBRAMANIAN