Neural Network PE Architecture With Depth-Wise Parallel Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing neural-network-processing architectures face inefficiencies in resource utilization due to limitations in depth-sequential processing, leading to underutilization of computing resources and reduced performance, especially in edge devices with power and packaging constraints.

Innovation Solution

Implementing depth-wise parallel processing techniques that allow for simultaneous processing of input portions at multiple depths, enhancing resource utilization and scalability by supporting both input and depth parallelism in neural-network architectures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If depth-sequential processing is used in neural-network-processing architectures, then device complexity is reduced and ease of manufacture is improved, but resource utilization deteriorates and productivity decreases

Engineering Contradiction:
Improveresource utilizationVSAvoidprocessing architecture complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The processing architecture is segmented into multiple processing element groups, where each group can independently process different depth portions of input data. This segmentation enables parallel processing of multiple depths simultaneously, improving resource utilization without requiring a complete redesign of the entire processing system.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces depth parallelism as an additional dimension of processing beyond traditional input parallelism. By organizing processing elements to handle different depth portions concurrently, the architecture transforms the processing paradigm from sequential depth handling to parallel depth handling, thereby improving productivity while maintaining manageable complexity through structured organization.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Productivity

If dedicated hardware accelerators are used for machine learning processing, then processing capacity and productivity are improved, but use of energy and device packaging requirements worsen

Engineering Contradiction:
Improveprocessing capacityVSAvoidpower consumption
Core Design Contradiction:
ProductivityVSUse of energy by moving object

Solution Approach 1:

The processing element groups are designed to be universal and reconfigurable, capable of handling different neural network operations and data formats. This multi-functionality allows the same hardware to process various machine learning tasks efficiently, improving processing capacity while reducing the need for specialized dedicated hardware that would consume more power and occupy more packaging space.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The architecture employs dynamic resource allocation where processing element groups can be activated or deactivated based on the specific processing requirements. This dynamic behavior allows the system to scale its processing capacity according to actual workload, avoiding the continuous power consumption of fully dedicated hardware accelerators while maintaining high productivity when needed.

Inventive Principle:
Principle #15Dynamics

3Device complexity

If data is moved across common data busses in accelerators, then device complexity is reduced, but use of energy increases and loss of time occurs due to latency

Engineering Contradiction:
Improvedata bus structureVSAvoidpower usage
Core Design Contradiction:
Device complexityVSLoss of energy

Solution Approach 1:

The patent implements local data storage and processing within each processing element group, reducing the need for frequent data transfers across common data busses. By keeping data locally where it is needed and enabling parallel processing, the architecture minimizes energy-consuming data movements while maintaining simple bus structures, thereby reducing power usage without significantly increasing device complexity.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4396726B1Parallel depth-wise processing architectures for neural networks
Publication Date: 2026.04.22 QUALCOMM INC
  • EP4396726B1 patent drawingFigure 1A~1C
  • EP4396726B1 patent drawingFigure 1D
  • EP4396726B1 patent drawingFigure 2

AI summary

Methods and apparatus for performing machine learning tasks, and in particular, to a neural-network-processing architecture and circuits for improved performance through depth parallelism. One example neural-network-processing circuit generally includes a plurality of groups of processing element (PE) circuits, wherein each group of PE circuits comprises a plurality of PE circuits configured to process in parallel an input at a plurality of depths.