SoC Neural Processor Optical Memory Integration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current microprocessor and memory devices lack the necessary speed, density, efficiency, and neuron-like capabilities required for advanced computing applications, necessitating the development of new system on chip (SoC) technologies that integrate microprocessors, neural processors, electronic memory devices, and optical memory devices with enhanced performance.

Innovation Solution

The development of SoC systems that electrically or optically couple microprocessors and neural processors with electronic and optical memory devices, utilizing phase transition materials, carbon nanotubes, and memristors to create high-performance building blocks for memory and processing units, including nanoscaled phase change and phase transition materials for improved memory devices and optical interfaces.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If current microprocessor and memory devices are used, then device complexity is maintained at conventional levels, but speed, density, and efficiency are insufficient for advanced computing applications

Engineering Contradiction:
Improveprocessing speedVSAvoiddevice complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The patent merges previously separate components (microprocessor, memory devices, optical interfaces) into an integrated system on chip. This integration allows multiple functions to coexist and interact within a single device, enabling higher processing speed and density while managing complexity through unified architecture design.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system on chip is designed with multi-functional capabilities, incorporating both electronic and optical memory devices, microprocessors, and neural processors in a single platform. This universal design allows the device to perform multiple computing functions simultaneously, improving overall speed and efficiency without requiring separate dedicated devices for each function.

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

2Quantity of substance

If conventional memory devices are used, then manufacturing processes are well-established, but density and storage capacity are insufficient for advanced applications

Engineering Contradiction:
Improvememory densityVSAvoidmanufacturing ease
Core Design Contradiction:
Quantity of substanceVSEase of manufacture

Solution Approach 1:

The patent incorporates optical memory devices that utilize optical fields and electromagnetic interactions, representing a dimensional shift from conventional electrical memory approaches. This enables higher density storage by exploiting additional physical dimensions and properties, achieving greater storage capacity while maintaining compatibility with established semiconductor manufacturing processes.

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

Solution Approach 2:

The system employs composite structures combining different memory technologies (electronic and optical memory devices) with distinct material properties. This composite approach allows each memory type to contribute its strengths, achieving high overall density while leveraging well-established manufacturing techniques for each component material.

Inventive Principle:
Principle #40Composite materials

3Adaptability or versatility

If traditional processing architectures are used, then device simplicity is maintained, but neuron-like capabilities and adaptability are lacking

Engineering Contradiction:
Improveneuron-like capabilitiesVSAvoidprocessing architecture complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent incorporates neural processors with dynamic, adaptive computing capabilities that can modify their processing behavior based on input patterns and learning requirements. This dynamic architecture enables neuron-like functionality, allowing the system to adapt to different computing tasks and improve performance through learning, rather than following fixed processing paths.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system implements feedback mechanisms through optical interfaces and interconnected memory-processor units, allowing information to circulate and be processed iteratively. This feedback capability is essential for neural-like computation, enabling the system to learn from past computations and adjust future processing, thereby achieving adaptability without requiring overly complex external control systems.

Inventive Principle:
Principle #23Feedback

4Speed

If electronic memory devices alone are used, then electrical coupling is simple, but speed and efficiency for certain applications are insufficient

Engineering Contradiction:
Improvedata access speedVSAvoidcoupling architecture complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The patent introduces optical memory devices and optical interfaces as intermediary components between processing units and memory storage. These optical intermediaries enable faster data access and transfer speeds by utilizing optical signal transmission, which can operate at higher frequencies than electrical signals, while the integrated design manages the added architectural complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system replaces conventional electrical coupling mechanisms with optical coupling for certain data transmission paths. This substitution uses electromagnetic optical fields instead of electrical currents, enabling higher speed data access and transfer while reducing interference and heat generation, with the complexity managed through integrated photonic components.

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

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

These SoC systems achieve increased speed, higher density, and efficiency, enabling neuron-like capabilities by integrating advanced memory and processing technologies, such as phase change materials and memristors, which enhance data storage and processing efficiency and adaptability.

Implementation Method 1

phase transition materials, carbon nanotubes, and memristors to create high-performance building blocks for memory and processing units, including nanoscaled phase change and phase transition materials for improved memory devices

Methodology Applied
Scientific EffectPhase transition: Phase Change

Implementation Method 2

carbon nanotubes, and memristors to create high-performance building blocks

Methodology Applied
Scientific EffectElectrical conduction: Conduction (electrical)

Implementation Method 3

optically coupling with an optical memory device

Methodology Applied
Scientific EffectOptical absorption: Absorption (EM radiation)

Data Source

PatentUS10803941B2System on chip (SoC) based on neural processor or microprocessor
Publication Date: 2020.10.13 CELERIS SYSTEMS INC
  • US10803941B2 patent drawing
  • US10803941B2 patent drawing
  • US10803941B2 patent drawing

AI summary

System on chips (SoCs) based on a microprocessor or a neural processor (e.g., brain-inspired processor) electrically coupled with electronic memory devices and/or optically coupled with an optical memory device, along with embodiment(s) of a building block (an element) of the microprocessor/neural processor, the electronic memory device and the optical memory device are disclosed. It should be noted that a microprocessor can be replaced by a graphical processor.