# US 2021/0232432 A1 · Reservation-based high-performance computing system and method

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0232432 A1
- Document ID: US20210232432A1
- Status: Published application
- Kind: A1
- Application number: 16/773,262
- Filed: 2020-01-27
- Published: 2021-07-29
- Earliest claimed: 2020-01-27
- Assignees: Raytheon Company
- Applicants: Raytheon Company
- Inventors: Douglas A. Meyer; John D. Stone; Dudley F. Spooner, II; Ryan L. Bird; Amzie L. McWhorter
- Web page: https://patentgrep.com/patent/US20210232432A1

## CPC

- G06F 9/5027: {the resource being a machine, e.g. CPUs, Servers, Terminals}
- G06F 9/5061: {Partitioning or combining of resources}
- G06F 9/4881: {Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method includes communicatively coupling a shared computing resource to core computing resources associated with a first project. The core computing resources associated with the first project are configured to use the shared computing resource to perform data processing operations associated with the first project. The method also includes reassigning the shared computing resource to a second project by (i) powering down the shared computing resource, (ii) disconnecting the shared computing resource from the core computing resources associated with the first project, (iii) communicatively coupling the shared computing resource to core computing resources associated with the second project, and (iv) powering up the shared computing resource. The core computing resources associated with the second project are configured to use the shared computing resource to perform data processing operations associated with the second project. The shared computing resource lacks non-volatile memory to store data related to the first and second projects.

## Claims

### Claim 1

A method comprising:
communicatively coupling a shared computing resource to core computing resources associated with a first project, the core computing resources associated with the first project configured to use the shared computing resource to perform data processing operations associated with the first project; and
reassigning the shared computing resource to a second project by:
powering down the shared computing resource;
disconnecting the shared computing resource from the core computing resources associated with the first project;
communicatively coupling the shared computing resource to core computing resources associated with the second project; and
powering up the shared computing resource, the core computing resources associated with the second project configured to use the shared computing resource to perform data processing operations associated with the second project;
wherein the shared computing resource lacks non-volatile memory to store data related to the first and second projects;
wherein the shared computing resource and the core computing resources associated with the first project collectively form at least part of a first computing cluster; and
wherein the shared computing resource and the core computing resources associated with the second project collectively form at least part of a second computing cluster.

### Claim 2 (depends on 1)

The method of claim 1, wherein:
the shared computing resource comprises volatile memory used to store the data related to the first and second projects; and
powering down the shared computing resource clears the volatile memory and prevents the data associated with the first project from being accessed by the core computing resources associated with the second project.

### Claim 3 (depends on 1)

The method of claim 1, wherein:
the shared computing resource comprises a diskless computing node; and
the core computing resources associated with the second project comprise at least one management server that provides boot information to the diskless computing node.

### Claim 4 (depends on 1)

The method of claim 1, wherein the core computing resources associated with the second project comprise at least one scratch server that at least one of: provides information to the shared computing resource and receives processing results from the shared computing resource.

### Claim 5 (depends on 4)

The method of claim 4, wherein the core computing resources associated with the second project further comprise at least one session server that permits users to submit and monitor processing jobs for execution by the second computing cluster and to access the processing results in the at least one scratch server.

### Claim 6 (depends on 1)

The method of claim 1, wherein:
the core computing resources associated with the second project comprise at least one management server that integrates the shared computing resource into a pool for use by the core computing resources associated with the second project;
the at least one management server comprises a job scheduler and a batch queueing system;
the job scheduler receives processing jobs submitted by users and provides the processing jobs to the batch queueing system; and
the batch queueing system assigns the processing jobs to particular computing resources including the shared computing resource for execution.

### Claim 7 (depends on 1)

The method of claim 1, wherein the core computing resources associated with the second project comprise at least one dedicated computing node that lacks non-volatile memory to store data related to the second project.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
storing processing results from the shared computing resource in a non-volatile storage in the core computing resources associated with the second project.

### Claim 9 (depends on 1)

The method of claim 1, wherein:
the shared computing resource comprises one of a plurality of shared computing resources in a first set of shared computing resources;
the method further comprises communicatively coupling the first set of shared computing resources and at least one additional set of shared computing resources to the core computing resources associated with the first project and the core computing resources associated with the second project; and
different sets of shared computing resources comprise different types of computing nodes.

### Claim 10 (depends on 1)

The method of claim 1, wherein the shared computing resource comprises at least one of: one or more servers and one or more graphics processing units.

### Claim 11

A system comprising:
a shared computing resource;
core computing resources associated with a first project and configured to use the shared computing resource to perform data processing operations associated with the first project; and
core computing resources associated with a second project and configured to use the shared computing resource to perform data processing operations associated with the second project;
wherein the shared computing resource is configured to be communicatively coupled to the core computing resources associated with the first project, powered down and disconnected from the core computing resources associated with the first project, and communicatively coupled to the core computing resources associated with the second project and powered up to reassign the shared computing resource;
wherein the shared computing resource lacks non-volatile memory to store data related to the first and second projects;
wherein the shared computing resource and the core computing resources associated with the first project collectively form at least part of a first computing cluster; and
wherein the shared computing resource and the core computing resources associated with the second project collectively form at least part of a second computing cluster.

### Claim 12 (depends on 11)

The system of claim 11, wherein:
the shared computing resource comprises volatile memory configured to store the data related to the first and second projects; and
the shared computing resource is configured such that powering down the shared computing resource clears the volatile memory and prevents the data associated with the first project from being accessed by the core computing resources associated with the second project.

### Claim 13 (depends on 11)

The system of claim 11, wherein:
the shared computing resource comprises a diskless computing node; and
the core computing resources associated with the second project comprise at least one management server configured to provide boot information to the diskless computing node.

### Claim 14 (depends on 11)

The system of claim 11, wherein the core computing resources associated with the second project comprise at least one scratch server configured to at least one of: provide information to the shared computing resource and receive processing results from the shared computing resource.

### Claim 15 (depends on 14)

The system of claim 14, wherein the core computing resources associated with the second project further comprise at least one session server configured to permit users to submit and monitor processing jobs for execution by the second computing cluster and to access the processing results in the at least one scratch server.

### Claim 16 (depends on 11)

The system of claim 11, wherein:
the core computing resources associated with the second project comprise at least one management server configured to integrate the shared computing resource into a pool for use by the core computing resources associated with the second project;
the at least one management server comprises a job scheduler and a batch queueing system;
the job scheduler is configured to receive processing jobs submitted by users and provide the processing jobs to the batch queueing system; and
the batch queueing system is configured to assign the processing jobs to particular computing resources including the shared computing resource for execution.

### Claim 17 (depends on 11)

The system of claim 11, wherein the core computing resources associated with the second project comprise at least one dedicated computing node that lacks non-volatile memory to store data related to the second project.

### Claim 18 (depends on 11)

The system of claim 11, wherein the core computing resources associated with the second project comprise a non-volatile storage configured to store processing results from the shared computing resource.

### Claim 19 (depends on 11)

The system of claim 11, wherein the shared computing resource comprises at least one of: one or more servers and one or more graphics processing units.

### Claim 20

A system comprising:
multiple sets of core computing resources associated with and dedicated to different projects, each set of core computing resources configured to perform data processing operations for the associated project; and
multiple shared computing resources each configured to be selectively assigned to one of the different projects and to perform data processing operations for the assigned project;
wherein each shared computing resource is configured to be communicatively coupled to the set of core computing resources associated with a first of the projects, powered down and disconnected from the set of core computing resources associated with the first project, and communicatively coupled to the set of core computing resources associated with a second of the projects and powered up to reassign the shared computing resource;
wherein each shared computing resource lacks non-volatile memory to store data related to the projects; and
wherein each set of core computing resources and the shared computing resources communicatively coupled to that set of core computing resources form of a computing cluster, each computing cluster being reconfigurable by changing the shared computing resources communicatively coupled to the set of core computing resources.
