Processor Circuit Neural Network Voltage Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current processor circuits require excessive voltage margins to ensure operation, leading to unnecessary power consumption due to manual experimentation-based voltage determination, which is inefficient and inaccurate.

Innovation Solution

A processor circuit incorporating a neural network circuit that detects various variation factors affecting operating voltage, using a control signal and detection results to determine a suitable operating voltage, thereby reducing the need for excessive voltage margins.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a voltage margin is added to the minimum allowable voltage to ensure proper operation, then the reliability of the circuit is improved, but the power consumption increases

Engineering Contradiction:
Improvecircuit operation reliabilityVSAvoidpower consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent implements dynamic voltage adjustment by using a neural network circuit that continuously monitors multiple variation factors (temperature, voltage, frequency, process characteristics) and dynamically determines the optimal operating voltage. This replaces the static voltage margin approach with a dynamic system that adjusts voltage in real-time based on actual operating conditions, maintaining reliability while minimizing power consumption.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the operating voltage parameter based on detected variation factors. The neural network circuit processes inputs including temperature, voltage, frequency, and process characteristics to determine the optimal voltage setting. This parameter adjustment allows the system to operate at the minimum necessary voltage under favorable conditions while ensuring proper operation when variation factors indicate higher voltage is needed.

Inventive Principle:
Principle #35Parameter changes

2Ease of manufacture

If manual experimentation is used to determine voltage margin, then the implementation is simple, but the precision of voltage determination is insufficient

Engineering Contradiction:
Improveimplementation simplicityVSAvoidvoltage determination accuracy
Core Design Contradiction:
Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent replaces the manual experimentation process with an automated neural network-based electronic system. Instead of human operators performing trial-and-error voltage adjustments, the system uses detection circuits and a neural network circuit to automatically measure variation factors and determine optimal voltage. This substitution significantly improves measurement precision while the automated nature maintains ease of implementation.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-determination of operating voltage through the neural network circuit that automatically processes detection results from multiple sensors and outputs the optimal voltage setting without external intervention. This self-service capability eliminates the need for manual experimentation while achieving high precision voltage determination through continuous monitoring and analysis of variation factors.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS20230060855A1Processor circuit and non-transitory computer readable medium
Publication Date: 2023.03.02 REALTEK SEMICON CORP
  • US20230060855A1 patent drawing
  • US20230060855A1 patent drawing
  • US20230060855A1 patent drawing

AI summary

A processor circuit includes a processor, N detection circuits and a neural network circuit. The processor is configured to provide a control signal. The control signal indicates an operational status of the processor. The N detection circuits are configured to detect N different types of variation factors affecting an operating voltage of the processor respectively, and accordingly generate N detection results respectively. N is an integer greater than one. The neural network circuit, coupled to the processor and the N detection circuits, is configured to determine the operating voltage of the processor according to the control signal and the N detection results.