On-Chip Game and AI Engines for Local Real-Time ML Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing game and simulation engines, as well as AI processing, face inefficiencies due to reliance on CPUs, which are not optimized for AI tasks, and IPUs in servers lack privacy and require resource-intensive data transmission, necessitating improved AI processors for secure, high-speed processing of large data sets.

Innovation Solution

Integration of game and simulation engines with AI engines on a single chip using dedicated electronic circuitry, enabling direct data exchange and optimized processing through hardware interfaces, specifically tailored for tensor contraction operations and machine learning algorithms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Power

If AI processing is performed using CPUs or IPUs in servers, then computing power and data processing capability are improved, but resource consumption increases and security/privacy protection deteriorates

Engineering Contradiction:
Improvecomputing powerVSAvoidsecurity and privacy
Core Design Contradiction:
PowerVSReliability

Solution Approach 1:

The patent combines the game engine and AI engine into a single integrated system on a chip, merging previously separate processing functions. This integration allows AI processing to occur locally on the user device rather than requiring external server connections, thereby improving both computing efficiency and data security by keeping sensitive data on-device.

Inventive Principle:
Principle #5Merging (Combining)

2Productivity

If AI processing is performed using IPUs in servers, then machine learning capability is improved, but data transmission time and resource waste increase

Engineering Contradiction:
Improvemachine learning capabilityVSAvoiddata transmission time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent extracts the AI engine from external server infrastructure and implements it directly on the user device chip. This extraction eliminates the need for data to be transmitted to and from remote servers, removing the time loss associated with data transmission while maintaining advanced machine learning capabilities through on-device processing.

Inventive Principle:
Principle #2Taking out (Extraction)

3Adaptability or versatility

If software engines are executed on CPUs, then versatility and functionality are improved, but processing speed and real-time performance deteriorate

Engineering Contradiction:
ImprovefunctionalityVSAvoidprocessing speed
Core Design Contradiction:
Adaptability or versatilityVSSpeed

Solution Approach 1:

The patent replaces the software-based engine execution model with hardware-based engine implementations. By implementing the game engine and AI engine as dedicated hardware circuits rather than software running on general-purpose CPUs, the system achieves significantly faster processing speeds while maintaining full functionality, enabling real-time performance requirements to be met.

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

Data Source

PatentEP4480558B1Game engine and artificial intelligence engine on a chip
Publication Date: 2026.05.13 THE CALANY HLDG S.À.R L
  • EP4480558B1 patent drawingFigure 1A
  • EP4480558B1 patent drawingFigure 1B
  • EP4480558B1 patent drawingFigure 1C

AI summary

An electronic chip, a chip assembly, a computing device, and a method are described. The electronic chip comprises a plurality of processing cores and at least one hardware interface coupled to at least one of the one or more processing cores. At least one processing core implements a game engine and/or a simulation engine and at least one or more processing cores implements an artificial intelligence engine, whereby implementations are on-chip implementations in hardware by dedicated electronic circuitry. The at least one or more game and/or simulation engines performs tasks on sensory, generating data sets that are processed through machine learning algorithms by the hardwired artificial intelligence engine. The data sets processed by the hardwired artificial intelligence engine include at least contextual data and target data, wherein combining both data and processing by dedicated hardware results in enhanced machine learning processing.