Ray Tracing Core MIMD Architecture Pipeline Efficiency

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current 3D graphic technologies require separate high-performance processors for ray tracing, which is computationally intensive and inefficient, especially in simulating realistic light effects like reflection, refraction, and shading.

Innovation Solution

A ray tracing core with a setup processing unit, ray generation unit, and multiple T&I units using MIMD architecture, which generates eye rays and shading rays, and performs intersection tests within a unified pipeline architecture to enhance processing efficiency and reduce computational load.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Power

If a separate high-performance processor is used for ray tracing, then the computational capability for light effects simulation is improved, but the device complexity and processing efficiency deteriorate

Engineering Contradiction:
Improvecomputational capabilityVSAvoidprocessor structure
Core Design Contradiction:
PowerVSDevice complexity

Solution Approach 1:

The patent merges the ray tracing processing unit into the existing graphics processing pipeline, combining ray generation, T&I testing, and shading functions within a unified processor structure. This integration eliminates the need for separate high-performance processors while maintaining computational capability for light effects simulation.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The ray tracing processing unit is designed with multi-functionality, handling eye ray generation, shading ray generation, T&I testing, and shading calculations within a single processor. This universal design reduces device complexity by eliminating dedicated separate processors for each function.

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

2Reliability

If traditional ray tracing processing is used, then light effects simulation is achieved, but the processing time and computational load increase

Engineering Contradiction:
Improvelight effects simulation qualityVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The ray tracing process is segmented into distinct functional units: ray generation unit, T&I unit, and shading unit. Each unit processes specific tasks independently and efficiently, reducing overall processing time while maintaining simulation quality. The segmentation allows parallel processing of multiple rays simultaneously.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The setup processing unit performs preliminary actions by pre-calculating and storing intersection information in advance. This preliminary preparation reduces the computational load during actual ray tracing operations, significantly decreasing processing time while preserving light effects simulation accuracy.

Inventive Principle:
Principle #10Preliminary action

3Productivity

If multiple processing units are added to increase processing speed, then the productivity is improved, but the device complexity and synchronization overhead increase

Engineering Contradiction:
Improveprocessing speedVSAvoidpipeline architecture
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent introduces a control unit as an intermediary that manages multiple processing units through a unified pipeline architecture. This control unit coordinates data flow and synchronization between processing units, reducing complexity overhead while maintaining high processing speed through efficient resource management.

Inventive Principle:
Principle #24Intermediary (Mediator)

4Measurement precision

If intersection testing accuracy is improved, then the measurement precision is improved, but the computational load and processing time increase

Engineering Contradiction:
Improveintersection testing accuracyVSAvoidcomputational load
Core Design Contradiction:
Measurement precisionVSPower

Solution Approach 1:

The setup processing unit performs preliminary intersection testing and pre-calculates potential hit points before detailed T&I processing. This preliminary action filters out non-intersecting rays early, maintaining high intersection testing accuracy while significantly reducing the computational load on the main processing units.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS9965889B2Ray tracing core and ray tracing chip having the same
Publication Date: 2018.05.08 SILICONARTS TECHNOLOGY US INC
  • US9965889B2 patent drawing
  • US9965889B2 patent drawing
  • US9965889B2 patent drawing

AI summary

A ray tracing core includes a ray generation unit and a plurality of T&I (Traversal & Intersection) units with MIMD (Multiple Instruction stream Multiple Data stream) architecture. The ray generation unit generates at least one eye ray based on an eye ray generation information. The eye ray generation information includes a screen coordinate value. Each of the plurality of T&I units receives the at least one eye ray and checks whether there exists a triangle intersected with the received at least one eye ray. The triangle configures a space.