LogoLogo
AI HubCommunityWebsite
  • Start Here
  • AI Hub
    • Overview
    • Quickstart
    • Teams
    • Device Farm
    • Browser Inference
    • Model Zoo
      • Hailo
      • Intel
      • MemryX
      • BrainChip
      • Google
      • DeGirum
      • Rockchip
    • View and Create Model Zoos
    • Model Compiler
    • PySDK Integration
  • PySDK
    • Overview
    • Quickstart
    • Installation
    • Runtimes and Drivers
      • Hailo
      • OpenVINO
      • MemryX
      • BrainChip
      • Rockchip
      • ONNX
    • PySDK User Guide
      • Core Concepts
      • Organizing Models
      • Setting Up an AI Server
      • Loading an AI Model
      • Running AI Model Inference
      • Model JSON Structure
      • Command Line Interface
      • API Reference Guide
        • PySDK Package
        • Model Module
        • Zoo Manager Module
        • Postprocessor Module
        • AI Server Module
        • Miscellaneous Modules
      • Older PySDK User Guides
        • PySDK 0.16.0
        • PySDK 0.15.2
        • PySDK 0.15.1
        • PySDK 0.15.0
        • PySDK 0.14.3
        • PySDK 0.14.2
        • PySDK 0.14.1
        • PySDK 0.14.0
        • PySDK 0.13.4
        • PySDK 0.13.3
        • PySDK 0.13.2
        • PySDK 0.13.1
        • PySDK 0.13.0
    • Release Notes
      • Retired Versions
    • EULA
  • DeGirum Tools
    • Overview
      • Streams
        • Streams Base
        • Streams Gizmos
      • Compound Models
      • Result Analyzer Base
      • Inference Support
  • DeGirumJS
    • Overview
    • Get Started
    • Understanding Results
    • Release Notes
    • API Reference Guides
      • DeGirumJS 0.1.3
      • DeGirumJS 0.1.2
      • DeGirumJS 0.1.1
      • DeGirumJS 0.1.0
      • DeGirumJS 0.0.9
      • DeGirumJS 0.0.8
      • DeGirumJS 0.0.7
      • DeGirumJS 0.0.6
      • DeGirumJS 0.0.5
      • DeGirumJS 0.0.4
      • DeGirumJS 0.0.3
      • DeGirumJS 0.0.2
      • DeGirumJS 0.0.1
  • Orca
    • Overview
    • Benchmarks
    • Unboxing and Installation
    • M.2 Setup
    • USB Setup
    • Thermal Management
    • Tools
  • Resources
    • External Links
Powered by GitBook

Get Started

  • AI Hub Quickstart
  • PySDK Quickstart
  • PySDK in Colab

Resources

  • AI Hub
  • Community
  • DeGirum Website

Social

  • LinkedIn
  • YouTube

Legal

  • PySDK EULA
  • Terms of Service
  • Privacy Policy

© 2025 DeGirum Corp.

On this page
  • Thermal Management Overview
  • Heatsink and Airflow Requirements
  • Example Calculation
  • Heatsink and Airflow Design Guidelines
  • Example M.2 2280 Heatsinks
  • Example heatsink installations
  • Testing and validation

Was this helpful?

  1. Orca

Thermal Management

This topic provides guidelines for heatsink and airflow solutions to ensure the Orca M.2 module operates within safe thermal limits.

PreviousUSB SetupNextTools

Last updated 2 months ago

Was this helpful?

Thermal Management Overview

The Orca M.2 module includes internal temperature monitoring and a frequency throttling mechanism to prevent overheating. To maintain optimal performance and prevent thermal throttling during intensive workloads, effective thermal management is crucial. If the module exceeds a preset high-temperature threshold, the firmware automatically reduces the operating frequency until the temperature returns to safe levels. This helps avoid damage due to insufficient heat dissipation.

For environments with high ambient temperatures or extended workloads, additional cooling solutions, such as heatsink and airflow, may be required to maintain optimal operating temperatures.

Heatsink and Airflow Requirements

Thermal dissipation can be approximated by the following the formula:

Ambient Temperature+W×RTJA<Maximum Operating Temperature\text{Ambient Temperature} + W \times R_{TJA} < \text{Maximum Operating Temperature} Ambient Temperature+W×RTJA​<Maximum Operating Temperature

Where:

  • \text{W}\: Power Dissipated by the Orca module (Watts)

  • RTJAR_{TJA}RTJA​: Thermal resistance from junction to ambient (°C/W)

  • Maximum Operating Temperature\text{Maximum Operating Temperature}Maximum Operating Temperature: Junction temperature limit

The total thermal resistance of RTJAR_{\text{TJA}}RTJA​ consists of:

  • RJCR_{JC}RJC​: Junction-to-case thermal resistance (0.3 °C/W)

  • RCHSR_{CHS}RCHS​: Case-to-heatsink thermal resistance (0.12 °C/W with thermal paste or pad)

  • RHSAR_{HSA}RHSA​: Heatsink-to-ambient thermal resistance

Example Calculation

Consider a scenario where the Orca module dissipates 3 W, the ambient temperature is 70 °C, and the recommended maximum operating temperature is 95 °C.

70\,^\circ\text{C} + 3\,\text{W} \times \left(0.3\,^\circ\text{C/W} + 0.12\,^\circ\text{C/W} + R_{HSA}\right) < 95\,^\circ\text{C}
R_{HSA} < 5.4\,^\circ\text{C/W}

A heatsink with thermal resistance lower than 5.4 °C/W is required to maintain safe operating temperatures. The user should select an appropriate combination of heatsink type, size, and airflow to ensure a thermal resistance of less than 5.4 °C/W for this example.

Heatsink and Airflow Design Guidelines

  • Material: Use aluminum or copper for optimal thermal conductivity.

  • Dimensions: Ensure the heatsink is appropriately sized for the M.2 2280 form factor (22 mm x 80 mm).

  • Attachment: Use thermal pads or thermal paste to enhance heat transfer between the module and heatsink.

    • Airflow:

      • In environments with limited airflow, a passive heatsink may be sufficient.

      • For more demanding applications, active cooling solutions (e.g., small fans or improved ventilation) are recommended. Optimize airflow direction and placement for maximum cooling efficiency.

Example M.2 2280 Heatsinks

Example heatsink installations

Testing and validation

  • Thermal Testing: Monitor the module’s temperature under typical workloads to validate the cooling solution.

  • Frequency Throttling: Observe any signs of frequency throttling, which may indicate inadequate cooling.

  • Long-Term Reliability: Keep the module within recommended temperature limits to prevent degradation and ensure stable, high-performance AI inference during extended or heavy workloads.

Solving for RHSAR_{HSA}RHSA​:

M.2 2280 heatsink with an active cooling fan
M.2 2280 passive heatsink
M.2 2280 passive heatsink with visible heat pipes