# US 2026/0099779 A1 · Techniques for layer fusion group selection in deep learning compilers

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

- Number: US 2026/0099779 A1
- Document ID: US20260099779A1
- Status: Published application
- Kind: A1
- Application number: 18/910,130
- Filed: 2024-10-09
- Published: 2026-04-09
- Earliest claimed: 2024-10-09
- Assignees: Mediatek Inc.
- Applicants: Mediatek Inc.
- Inventors: Nien-En Lee; Tsung-Han Lin
- Web page: https://patentgrep.com/patent/US20260099779A1

## CPC

- G06Q 10/0631: Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q 10/0633: Workflow analysis
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may be a compiler. The compiler obtains data size of operations in a model graph corresponding to the workflow. The model graph includes multiple operations and an execution order of the operations. The compiler determines one or more operation fusion groups based on data sizes of adjacent operations and a storage capacity of one or more target memories, the intermediate data generated during processing by each operation fusion group is not transferred outside a corresponding target memory. The compiler updates the model graph based on the determined one or more operation fusion groups.

## Claims

### Claim 1

A method of scheduling a workflow, comprising:
obtaining data sizes of operations in a model graph corresponding to the workflow, wherein the model graph includes multiple operations and an execution order of the operations;
determining one or more operation fusion groups based on data sizes of adjacent operations and a storage capacity of one or more target memories, wherein intermediate data generated during processing by each operation fusion group is not transferred outside a corresponding target memory; and
updating the model graph based on the determined one or more operation fusion groups.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
sorting edges in the model graph based on data sizes associated with the edges; and
selecting edges for fusion in descending order of the data sizes.

### Claim 3 (depends on 1)

The method of claim 1, wherein determining the one or more operation fusion groups comprises:
identifying an edge in the model graph representing a largest data transfer among edges that are not in a fusion group;
attempting to fuse operations connected by the identified edge into a fusion group for a first target memory; and
if fusion is not possible for the first target memory, attempting to fuse the operations into a fusion group for a lower level memory.

### Claim 4 (depends on 1)

The method of claim 1, wherein the one or more target memories comprises at least one of an L1 memory and an L2 memory in a memory hierarchy.

### Claim 5 (depends on 1)

The method of claim 1, wherein updating the model graph comprises:
merging operations in each fusion group into a single entity within the model graph.

### Claim 6 (depends on 1)

The method of claim 1, wherein the workflow comprises a convolutional neural network.

### Claim 7 (depends on 1)

The method of claim 1, wherein determining the one or more operation fusion groups comprises iteratively selecting edges and attempting to fuse operations connected by the selected edges until all edges have been considered.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
generating a schedule for executing the workflow based on the determined one or more operation fusion groups, wherein the schedule specifies an execution order for the operations within each fusion group and a memory level assigned to each fusion group.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
evaluating a remaining memory capacity in one target memory after forming a fusion group; and
attempting to include additional operations in the fusion group based on the remaining memory capacity.

### Claim 10

An apparatus for scheduling a workflow, comprising:
a memory; and
at least one processor coupled to the memory and configured to:
obtain, data sizes of operations in a model graph corresponding to the workflow, wherein the model graph includes multiple operations and an execution order of the operations;
determine, one or more operation fusion groups based on data sizes of adjacent operations and a storage capacity of one or more target memories, wherein intermediate data generated during processing by each operation fusion group is not transferred outside a corresponding target memory; and
update, the model graph based on the determined one or more operation fusion groups.

### Claim 11 (depends on 10)

The apparatus of claim 10, wherein the processor further configured to:
sort edges in the model graph based on data sizes associated with the edges; and
select edges for fusion in descending order of the data sizes.

### Claim 12 (depends on 10)

The apparatus of claim 10, wherein to determine the one or more operation fusion groups, the at least one processor is further configured to:
identify an edge in the model graph representing a largest data transfer among edges that are not in a fusion group;
attempt to fuse operations connected by the identified edge into a fusion group for a first target memory; and
if fusion is not possible for the first target memory, attempt to fuse the operations into a fusion group for a lower level memory.

### Claim 13 (depends on 10)

The apparatus of claim 10, wherein the one or more target memories comprises at least one of an L1 memory and an L2 memory in a memory hierarchy.

### Claim 14 (depends on 10)

The apparatus of claim 10, wherein to update the model graph, the at least one processor is further configured to:
merging operations in each fusion group into a single entity within the model graph.

### Claim 15 (depends on 10)

The apparatus of claim 10, wherein the workflow comprises a convolutional neural network.

### Claim 16 (depends on 10)

The apparatus of claim 10, wherein to determine the one or more operation fusion groups, the at least one processor is further configured to iteratively select edges and attempt to fuse operations connected by the selected edges until all edges have been considered.

### Claim 17 (depends on 10)

The apparatus of claim 10, wherein the processor is further configured to:
generate a schedule for executing the workflow based on the determined one or more operation fusion groups, wherein the schedule specifies an execution order for the operations within each fusion group and a memory level assigned to each fusion group.

### Claim 18 (depends on 10)

The apparatus of claim 10, wherein the processor is further configured to:
evaluate a remaining memory capacity in one target memory after forming a fusion group; and
attempt to include additional operations in the fusion group based on the remaining memory capacity.

### Claim 19

A computer-readable medium storing computer executable code for scheduling a workflow, comprising code to:
obtain, data sizes of operations in a model graph corresponding to the workflow, wherein the model graph includes multiple operations and an execution order of the operations;
determine, one or more operation fusion groups based on data sizes of adjacent operations and a storage capacity of one or more target memories, wherein intermediate data generated during processing by each operation fusion group is not transferred outside a corresponding target memory; and
update, the model graph based on the determined one or more operation fusion groups.

### Claim 20 (depends on 19)

The computer-readable medium of claim 19, further comprising code to:
sort edges in the model graph based on data sizes associated with the edges; and
select edges for fusion in descending order of the data sizes.
