# US 2026/0093972 A1 · Layer-wise precision optimization in analog compute-in-memory accelerators

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

- Number: US 2026/0093972 A1
- Document ID: US20260093972A1
- Status: Published application
- Kind: A1
- Application number: 19/413,190
- Filed: 2025-12-09
- Published: 2026-04-02
- Earliest claimed: 2025-08-25
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Shamik Kundu; Arnab Raha; Richard Dorrance; Deepak Abraham Mathaikutty; Brent Carlton
- Web page: https://patentgrep.com/patent/US20260093972A1

## CPC

- G06N 3/065: Analogue means
- G06F 15/7821: {Tightly coupled to memory, e.g. computational memory, smart memory, processor in memory}
- G06N 3/063: using electronic means
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

It is not optimal to apply analog compute-in-memory circuitry (ACiM) for all layers of a neural network or to apply digital compute-in-memory (DCiM) circuitry for all layers of the neural network, due to the tradeoff between efficiency and precision. To address this challenge, a layer-wise offloading strategy can selectively execute neural network layers using either DCiM circuitry or ACIM circuitry based on signal and statistical sensitivity conditions. The approach leverages a combined heuristic, incorporating both the number of input channels meeting a signal sensitivity criterion and the statistical properties of the weight distribution meeting a statistical sensitivity criterion. Layers are allocated to DCiM when both conditions are satisfied, while layers are allocated to ACIM if either or both conditions are not met. The approach optimizes computational efficiency by dynamically assigning resources according to input characteristics and distributional metrics.

## Claims

### Claim 1

An apparatus for compiling a neural network model to be executed on a neural network accelerator, comprising:
a processor; and
a memory to store instructions, that when executed by the processor, cause the processor to:
receive information about a layer of the neural network model, wherein the information includes one or more of: a number of input channels of the layer, and a distribution of a plurality of weights of the layer;
based on the information, determine whether the layer is to be executed by a digital compute-in-memory (DCiM) circuitry of the neural network accelerator or an analog compute-in-memory circuitry (ACiM) of the neural network accelerator; and
generate one or more machine-readable configurations for the layer according to the determination.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the processor determines whether the layer is to be executed by the DCIM circuitry or the ACIM circuitry by:
determining whether the number of input channels meets a signal sensitivity condition.

### Claim 3 (depends on 2)

The apparatus of claim 2, wherein the signal sensitivity condition comprises the number of input channels crossing a threshold.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the processor determines whether the layer is to be executed by the DCiM circuitry or the ACIM circuitry by:
determining whether the distribution of the plurality of weights meets a statistical sensitivity condition.

### Claim 5 (depends on 4)

The apparatus of claim 4, wherein the statistical sensitivity condition comprises one or more of:
a standard deviation of the distribution crossing a critical threshold; and
a tailedness of the distribution crossing a confidence threshold.

### Claim 6 (depends on 5)

The apparatus of claim 5, wherein the tailedness comprises kurtosis of the distribution.

### Claim 7 (depends on 1)

The apparatus of claim 1, wherein the processor determines whether the layer is to be executed by the DCIM circuitry or the ACIM circuitry by:
determining the layer is to be executed by the DCiM circuitry based on the number of input channels meeting a signal sensitivity condition and the distribution of the plurality of weights meeting a statistical sensitivity condition.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the processor determines whether the layer is to be executed by the DCIM circuitry or the ACIM circuitry by:
determining the layer is to be executed by the ACIM circuitry based on the number of input channels not meeting a signal sensitivity condition and/or the distribution of the plurality of weights not meeting a statistical sensitivity condition.

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein the one or more machine-readable configurations for the layer comprise one or more flags to enable execution on the DCIM or the ACiM.

### Claim 10

One or more non-transitory computer-readable media storing instructions for compiling a neural network model to be executed on a neural network accelerator, that when executed by a processor, cause the processor to:
receive information about a layer of the neural network model, wherein the information includes one or more of: a number of input channels of the layer, and a distribution of a plurality of weights of the layer;
based on the information, determine whether the layer is to be executed by a digital compute-in-memory (DCiM) circuitry of the neural network accelerator or an analog compute-in-memory circuitry (ACiM) of the neural network accelerator; and
generate one or more machine-readable configurations for the layer according to the determination.

### Claim 11 (depends on 10)

The one or more non-transitory computer-readable media of claim 10, wherein the processor determines whether the layer is to be executed by the DCIM circuitry or the ACIM circuitry by:
determining whether the number of input channels meets a signal sensitivity condition.

### Claim 12 (depends on 11)

The one or more non-transitory computer-readable media of claim 11, wherein the signal sensitivity condition comprises the number of input channels crossing a threshold.

### Claim 13 (depends on 10)

The one or more non-transitory computer-readable media of claim 10, wherein determining whether the layer is to be executed by the DCiM circuitry or the ACIM circuitry comprises:
determining whether the distribution of the plurality of weights meets a statistical sensitivity condition.

### Claim 14 (depends on 13)

The one or more non-transitory computer-readable media of claim 13, wherein the statistical sensitivity condition comprises one or more of:
a standard deviation of the distribution crossing a critical threshold; and
a tailedness of the distribution crossing a confidence threshold.

### Claim 15 (depends on 14)

The one or more non-transitory computer-readable media of claim 14, wherein the tailedness comprises kurtosis of the distribution.

### Claim 16

A method for compiling a neural network model to be executed on a neural network accelerator:
receiving information about a layer of the neural network model, wherein the information includes one or more of: a number of input channels of the layer, and a distribution of a plurality of weights of the layer;
based on the information, determining whether the layer is to be executed by a digital compute-in-memory (DCiM) circuitry of the neural network accelerator or an analog compute-in-memory circuitry (ACiM) of the neural network accelerator; and
generating one or more machine-readable configurations for the layer according to the determination.

### Claim 17 (depends on 16)

The method of claim 16, wherein determining whether the layer is to be executed by the DCiM circuitry or the ACIM circuitry comprises:
determining whether the number of input channels meets a signal sensitivity condition.

### Claim 18 (depends on 16)

The method of claim 16, wherein determining whether the layer is to be executed by the DCiM circuitry or the ACIM circuitry comprises:
determining whether the distribution of the plurality of weights meets a statistical sensitivity condition.

### Claim 19 (depends on 16)

The method of claim 16, wherein determining whether the layer is to be executed by the DCiM circuitry or the ACIM circuitry comprises:
determining the layer is to be executed by the DCiM circuitry based on the number of input channels meeting a signal sensitivity condition and the distribution of the plurality of weights meeting a statistical sensitivity condition.

### Claim 20 (depends on 18)

The method of claim 18, wherein determining whether the layer is to be executed by the DCIM circuitry or the ACIM circuitry comprises:
determining the layer is to be executed by the ACIM circuitry based on the number of input channels not meeting a signal sensitivity condition and/or the distribution of the plurality of weights not meeting a statistical sensitivity condition.
