# US 2026/0089202 A1 · Reliably forwarding endpoint processing unit computations through a network fabric

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

- Number: US 2026/0089202 A1
- Document ID: US20260089202A1
- Status: Published application
- Kind: A1
- Application number: 19/227,462
- Filed: 2025-06-04
- Published: 2026-03-26
- Earliest claimed: 2024-09-21
- Assignees: Delos Data Inc.
- Applicants: Delos Data Inc.
- Inventors: Daniel P. Daly; Edward V. E. Doe; Alain J. E. Gravel
- Web page: https://patentgrep.com/patent/US20260089202A1

## CPC

- H04L 45/24: Multipath
- G06F 9/4881: {Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues}
- G06F 9/5027: {the resource being a machine, e.g. CPUs, Servers, Terminals}
- G06F 9/5083: {Techniques for rebalancing the load in a distributed system}
- G06F 9/547: {Remote procedure calls [RPC]; Web services}
- H04L 45/123: {Evaluation of link metrics (techniques for monitoring network metrics H04L43/08)}
- H04L 47/33: using forward notification
- H04L 67/10: in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46)
- H04L 67/1001: for accessing one among a plurality of replicated servers
- H04L 67/60: Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources (admission control or resource allocation H04L47/70)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Some embodiments provide a method of executing a distributed application with multiple endpoint processing units (EPUs) that perform computations for the distributed application. The EPUs are connected through a network having multiple network elements. The method iteratively provides instructions to the EPUs to perform computations associated with the distributed application. The method stores a result of each EPU computation at the EPU until the result has been forwarded to a destination in the network and a confirmation has been received that the result has successfully been received at its destination in the network.

## Claims

### Claim 1

A method of executing a distributed application with a plurality of endpoint processing units (EPUs) that perform computations for the distributed application, the EPUs connected through a network comprising a plurality of network elements, the method comprising:
iteratively providing instructions to the EPUs to perform computations associated with the distributed application; and
storing a result of each EPU computation at the EPU until the result has been forwarded to a destination in the network and a confirmation has been received that the result has successfully been received at its destination in the network.

### Claim 2 (depends on 1)

The method of claim 1, wherein the EPUs are graphics processing units (GPUs).

### Claim 3 (depends on 2)

The method of claim 2, wherein storing the result at each GPU comprises configuring each GPU to store the result of each computation in a memory of the GPU until the result has been forwarded to the result's destination in the network and the confirmation has been received that the result has successfully been received at its destination in the network.

### Claim 4 (depends on 3)

The method of claim 3, wherein configuring each GPU comprises configuring a process operating on the GPU to discard each stored computation result from the GPU memory after receiving confirmation that the result has successfully been received at its destination in the network.

### Claim 5 (depends on 4)

The method of claim 4, configuring each GPU further comprises configuring the process operating on the GPU to notify a network interface of the GPU each time that the GPU completes a computation and stores the result of the computation in the GPU memory, for the network interface to retrieve the result from the GPU memory and forward through the network to the result's destination.

### Claim 6 (depends on 5)

The method of claim 5 further comprising configuring each GPU's network interface with forwarding records that specify the network interface's forwarding of the GPU's results through the network.

### Claim 7 (depends on 5)

The method of claim 5 further comprising configuring each GPU's network interface to notify the GPU's process that the result of a GPU's computation has successfully been received at its destination in the network.

### Claim 8 (depends on 1)

The method of claim 1, wherein for each result, the confirmation is received as an acknowledgment from the destination that the result has been completely received at the destination.

### Claim 9 (depends on 8)

The method of claim 8, wherein for each result, the acknowledgment is sent from a network interface that connects the destination to the network.

### Claim 10 (depends on 9)

The method of claim 9 further comprising:
configuring a network interface of each GPU to send each result of each computation of the GPU as a plurality of segments in payloads of data messages in a data message flow, each segment sent with a segment identifier;
configuring the network interface of each destination to use the segment identifiers of each data message flow for each result to determine when the destination network interface has received all the segments of the result, and to send the acknowledgment for the result after determining that all segments of the result have been received.

### Claim 11 (depends on 10)

The method of claim 10 further comprising configuring the network interface of each destination to identify any segment that has not been received for the network interface of a GPU that was a source of the result to retransmit the identified segment, said retransmission making forwarding of the GPU computation results through the network reliable as the retransmission ensures that the forwarded computation results are fully received at their destinations before being discarded.

### Claim 12 (depends on 1)

The method of claim 1 further comprising configuring each EPU to discard each stored result after the confirmation has been received for the result.

### Claim 13 (depends on 12)

The method of claim 12, wherein by discarding the result only after the confirmation is received for the result, the result does not get lost or does not have to be maintained at one or more intermediate nodes in the network.

### Claim 14 (depends on 1)

The method of claim 1 further comprising:
for a first result computed by a first EPU, configuring a network interface of the first EPU that connects the first EPU with the network to forward the first result to a first destination in the network after receiving a first notification that the first result has been stored in a memory of the first EPU;
for a second result computed by the first EPU, configuring the first EPU's network interface to forward the second result to a second destination in the network only after (i) receiving a second notification that the second result has been stored in first EPU's memory and (ii) after receiving the second notification, requesting and then receiving scheduling parameters for governing at least one of timing or rate of the forwarding of the second result through the network to the second destination.

### Claim 15

A non-transitory machine readable medium storing a program that when executed by a processor reliably forwards results of a graphics processing unit (GPU) through a network that connects a plurality of GPUs, the program comprising sets of instructions for:
detecting that the particular GPU has performed a computation that has produced a result stored in a memory of the GPU; and
maintaining the result in the particular GPU's memory until the result has been forwarded to a destination in the network and a confirmation has been received that the result has successfully been received at its destination in the network.

### Claim 16 (depends on 15)

The non-transitory machine readable medium of claim 15, wherein the program further comprises a set of instructions for discarding the stored result from the particular GPU's memory after receiving confirmation that the result has successfully been received at its destination in the network.

### Claim 17 (depends on 15)

The non-transitory machine readable medium of claim 15, wherein the program is a driver or kernel process executed by the particular GPU or a control unit processor of the particular GPU.

### Claim 18 (depends on 15)

The non-transitory machine readable medium of claim 15, wherein the program further comprises a set of instructions for communicating with a network interface of the particular GPU to direct the network interface to forward the result and to receive confirmation from the network interface that the result has been successfully received at the destination.

### Claim 19 (depends on 18)

The non-transitory machine readable medium of claim 18, wherein the network interface is configured (i) to send the result as a plurality of segments in payloads of data messages in a data message flow, each segment sent with a segment identifier, and (ii) to provide the confirmation after receiving a confirmation from the destination that each segment has been received at the destination.
