Systems and Methods for Solving Computational Problems Using High-Performance Computing

Patent metadata

Field	Value
Publication number	US-2025390548-A1
Application number	US-202519237576-A
Country	US
Kind code	A1
Filing date	Jun 13, 2025
Priority date	Jun 24, 2024
Publication date	Dec 25, 2025
Grant date	—

Abstract

Systems and methods for solving computational problems using high-performance computing (HPC) are described herein. An example system receives a request from a computing device indicating a computational problem. The example system applies a supervisor model to the computational problem to generate (i) a workflow and (ii) a set of code, and an HPC agent of the example system determines a respective HPC environment satisfying computing resource requirements of the set of code. A computing agent of the example system executes the set of code within the respective HPC environment to generate an output associated with solving the computational problem, wherein the HPC agent controls execution of the set of code by the computing agent according to the workflow. The example system also applies the supervisor model to the output to generate a solution to the computational problem and provide the solution to a computing device.

First claim

What is claimed:

1 . A system comprising:
one or more processors; one or more memories; a supervisor model, stored on the one or more memories, trained using model training data to provide respective solutions to computational problems, including generating (i) workflows and (ii) code for solving the computational problems; a high-performance computing (HPC) agent stored on the one or more memories and configured to determine one or more HPC environments for executing the code according to the workflows; a computing agent stored on the one or more memories and configured to execute the code in the one or more HPC environments; and the one or more memories storing instructions that, when executed by the one or more processors, cause the system to:
receive, from a computing device, a request indicating a computational problem,
apply the supervisor model to the computational problem to generate (i) a workflow and (ii) a set of code,
determine, by the HPC agent, a respective HPC environment of the one or more HPC environments satisfying computing resource requirements of the set of code;
execute, by the computing agent, the set of code within the respective HPC environment to generate an output associated with solving the computational problem, wherein the HPC agent controls execution of the set of code by the computing agent according to the workflow,
apply the supervisor model to the output to generate a solution to the computational problem, and
provide, to the computing device, the solution.

2 . The system of claim 1 , further comprising:
a plurality of domain-specific models stored on the one or more memories trained using respective domain-specific training data to provide solutions to respective domain-specific computational problems; and the instructions, when executed by the one or more processors, further cause the system to:
determine a domain associated with the computational problem, and
select, based upon the domain, a domain-specific model of the plurality of domain-specific models, wherein the supervisor model includes the domain-specific model.

3 . The system of claim 2 , wherein one or more of the plurality of domain-specific models are multi-modal models.

4 . The system of claim 2 , wherein the domain is selected from a group consisting of: physics, chemistry, biology, density functional theory, engineering, neuroscience, combustion, astrophysics, and materials science.

5 . The system of claim 1 , wherein the supervisor model includes a large language model (LLM).

6 . The system of claim 5 , wherein the LLM is a pre-trained LLM fine-tuned using computational science training data to generate and/or understand computational science concepts.

7 . The system of claim 1 , wherein the model training data includes one or more of: computational simulation data, computational workflows, computational code, multi-modal computational data, multi-fidelity computational data, or computational experimental data.

8 . The system of claim 1 , wherein one or more of:
the HPC environment includes an exascale computer; or the computing resource requirements include one or more of: processor requirements, memory requirements, code compatibility, or node characteristics.

9 . The system of claim 2 , wherein at least a portion of the one or more memories stores data associated with solving the computational problem and is accessible to one or more of the supervisor model, the HPC agent, the computing agent, or the plurality of domain-specific models.

10 . The system of claim 1 , wherein the computing agent is further configured to one or more of: test the code, troubleshoot the code, generate new code, or optimize the code for a specific HPC environment.

11 . The system of claim 1 , wherein the request is a prompt.

12 . The system of claim 1 , further comprising:
a validation agent stored on the one or more memories and configured to validate the output of the code; and instructions that, when executed by the one or more processors, cause the system to:
validate, by a validation agent configured to validate the output of the code, the code; and
perform, by the validation agent, a corrective action responsive to the output failing validation.

13 . The system of claim 12 , wherein the corrective action includes one or more of re-executing the code, debugging the code, or selecting a different HPC environment.

14 . The system of claim 1 , further comprising instructions that, when executed by the one or more processors, further cause the system to:
determine a fidelity of the solution to the computational problem; and responsive to the fidelity not exceeding threshold fidelity, generating an alternate workflow and/or alternate code to solve the computational problem.

15 . The system of claim 1 , further comprising instructions that, when executed by the one or more processors, further cause the system to:
obtain HPC information indicating computing resources of the one or more HPC environments,
wherein to determine, by the HPC agent, the respective HPC environment satisfying computing resource requirements of the set of code is based at least in part upon the HPC information.

16 . The system of claim 15 , wherein the computing resources include one or more of: processor characteristics, memory characteristics, bandwidth, size, availability, or cost.

17 . A method comprising:
receiving, by one or more processors from a computing device, a request indicating a computational problem; applying, by the one or more processors, a supervisor model trained using model training data to the computational problem to generate (i) a workflow and (ii) a set of code; determining, by a high-performance computing (HPC) agent configured to determine one or more HPC environments for executing code according to workflows, a respective HPC environment of one or more HPC environments satisfying computing resource requirements of the set of code; executing, by a computing agent configured to execute the code in the one or more HPC environments, the set of code within the respective HPC environment to generate an output associated with solving the computational problem,
wherein the HPC agent controls execution of the set of code by the computing agent according to the workflow;
applying, by the one or more processors, the supervisor model to the output to generate a solution to the computational problem; and providing, by the one or more processors to the computing device, the solution.

18 . The method of claim 17 , further comprising:
determining, by the one or more processors, a domain associated with the computational problem; and selecting, by the one or more processors, based upon the domain, a domain-specific model of a plurality of domain-specific models trained using respective domain-specific training data to provide solutions to respective domain-specific computational problems, wherein the supervisor model includes the domain-specific model.

19 . The method of claim 17 , further comprising:
validating, by a validation agent configured to validate the output of the code, the code; and performing, by the validation agent, a corrective action responsive to the output failing validation.

20 . A tangible machine-readable medium comprising instructions that, when executed by one or more processors, cause a machine to at least:
receive from a computing device, a request indicating a computational problem; apply a supervisor model trained using mode

Assignees

• Univ Michigan

Inventors

• Viswanathan Venkatasubramanian
• Zhu Shang
• Duraisamy Karthik

Classifications

• G06F8/30

  Creation or generation of source code · CPC title

• G06F17/11 Primary

  for solving equations {, e.g. nonlinear equations, general mathematical optimization problems (optimization specially adapted for a specific administrative, business or logistic context G06Q10/04)} · CPC title