While air cooling has served mainstream data centers for decades, liquid cooling has been the choice for high performance computing. As thermal demands grow in the era of accelerated GPU based AI computing, liquid cooling is not a choice but a necessity. Liquid cooling unlocks performance and sustainability benefits while enabling the move to rapidly increasing kilowatts per rack. With multiple architectures in play, choosing the right approach and ensuring it runs reliably is a challenge.

Selecting the appropriate liquid cooling architecture is more complicated than just accommodating thermal performance. It involves understanding the number of IT racks and rack densities, server configurations, water availability, heat rejection options, and cooling distribution configurations. All of these factors impact reliability and long-term performance.

To help you choose the right liquid cooling architecture, this whitepaper explores:

• Core elements of a data center liquid cooling architecture
• Existing heat rejection system options
• How to choose the best CDU form factor
• Evaluating the right facility heat rejection technologies