Neural Network Layer Scheduling for Accelerator Idle-Time Reduction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing neural network execution systems face challenges in efficiently utilizing hardware resources due to idle times and tail latencies caused by unsynchronized execution of tasks across different neural networks, leading to suboptimal performance and throughput.

Innovation Solution

A method and device that perform layer-wise scheduling of neural network models based on estimated idle times of operation and memory access resources, allowing for real-time queuing and execution in an accelerator to minimize idle times and maximize resource utilization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If memory block prefetching is used to reduce memory bandwidth idleness, then memory bandwidth utilization is improved, but processing element array idleness increases when prefetching is not enough to resolve compute block dependencies

Engineering Contradiction:
Improvememory bandwidth utilizationVSAvoidprocessing element array idle time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent implements dynamic scheduling that adjusts memory block prefetching strategies based on real-time compute block dependency status. When compute blocks are ready, prefetching is intensified; when dependencies block execution, the system dynamically switches to compute block merging to keep processing elements busy, thus resolving the contradiction between memory bandwidth utilization and processing element utilization.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent merges multiple memory blocks and compute blocks together in a unified scheduling framework. By combining memory block prefetching with compute block merging, the system ensures that when memory operations complete, compute blocks are ready to immediately utilize the processed data, eliminating processing element idle time while maintaining high memory bandwidth utilization.

Inventive Principle:
Principle #5Merging (Combining)

2Productivity

If compute block merging is applied to improve processing element array utilization, then processing element utilization is improved, but on-chip memory footprint increases

Engineering Contradiction:
Improveprocessing element array utilizationVSAvoidon-chip memory footprint
Core Design Contradiction:
ProductivityVSVolume of stationary object

Solution Approach 1:

The patent employs dynamic scheduling that adapts compute block merging intensity based on current on-chip memory availability. When memory pressure is high, the system reduces merging size; when memory is available, it increases merging to maximize processing element utilization, thus dynamically balancing utilization and memory footprint.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the parameter of compute block size dynamically based on system state. By adjusting block size parameters according to memory availability and workload characteristics, the system achieves high processing element utilization without excessively increasing on-chip memory footprint beyond acceptable thresholds.

Inventive Principle:
Principle #35Parameter changes

3Productivity

If multiple neural network models are executed in parallel to improve throughput, then system throughput is improved, but resource scheduling complexity increases

Engineering Contradiction:
Improvesystem throughputVSAvoidresource scheduling complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the scheduling problem into independent per-layer decisions rather than attempting to schedule entire models at once. Each layer is scheduled independently based on its own idle time characteristics, which simplifies the scheduling algorithm while still achieving high parallel throughput across multiple neural network models.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent uses idle time as a key parameter to simplify scheduling decisions. By calculating and comparing idle times for different layers across multiple models, the system makes straightforward scheduling choices that maximize throughput without requiring complex scheduling algorithms, thus managing multiple models efficiently.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3985507B1Electronic device and method with scheduling
Publication Date: 2025.12.03 SAMSUNG ELECTRONICS CO LTD
  • EP3985507B1 patent drawingFigure 1a
  • EP3985507B1 patent drawingFigure 1b
  • EP3985507B1 patent drawingFigure 2

AI summary

A scheduler, a method of operating the scheduler, and an electronic device including the scheduler are disclosed. The method of operating the scheduler configured to determine a model to be executed in an accelerator includes receiving one or more requests for execution of a plurality of models to be independently executed in the accelerator, and performing layer-wise scheduling on the models based on an idle time occurring when a candidate layer which is a target for the scheduling in each of the models is executed in the accelerator