Welcome to Avnet Heat Sink for Kria K26
The Avnet Heat Sink for Kria K26 is designed specifically for the AMD-Xilinx Kria K26 system on module (SOM). The heat sink mounts directly to the heat spreader plate that comes standard on the K26 SOM. This solution is “turn key” as it includes the mounting hardware as well as the interface “gap” material preinstalled on the heat sink.
The Avnet Heat Sink for Kria K26 is designed to provide passive relief for designs up to 10W in room temperature (approximately 26C) applications. Designed with flexibility in mind, mounting holes in the heat sink allow for the addition of a standard 50x50mm fan. The addition of a fan provides maximum thermal relief capability allowing for higher power and higher ambient temperature operation. Power and environmental parameters should be considered when selecting your solution. Whether passive or active, Avnet's heat sink for Kria K26 has you covered!
image

Technical Specification

Click on the images to enlarge

Front View
Front Image
Front Top View
Front Top View
Left Angle View
Left Angle View
Right Angle View
Right Angle View
Top View
Top View
Pins View
Pins View
Back View
Back View
Bottom View
Bottom View

Technical Documents

Product Brief

Related Blog Posts
  • Azure Sphere Medical Measurement Reference Design (Part 1)

    Medical DisclaimerThis example does not provide medical advice or diagnostic data.  It is intended for informational purposes only. It is not a substitute for professional medical diagnostics, measurements, advice, diagnosis or treatment.  ...
  • Accelerating PetaLinux BSP Build Time

    Have you ever wished that your PetaLinux project didn't take so long to build?  Have you ever wanted a way to make the build happen faster? Alas!  There are simple steps to follow to accelerate your PetaLinux project build times. ...
  • Benchmarking Machine Learning on Avnet's MaaXBoard

    Update: Want to see how well benchmarking performs on the MaaXBoard Mini? Updated results including the MaaXBoard Mini are HERE.  IntroductionIn the past two years, Machine Learning at the edge has proliferated. With more machine learning models...