Two-phase cooling helps maximise AI performance

  • Saturday, 2nd May 2026 Posted 18 hours ago in by Phil Alsop
Shahar Belkin, Chief Evangelist at ZutaCore, explains how the company’s OmniTherm™ cold plate enables waterless two-phase cooling for manufacturers building servers with the NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs in a single-slot PCIe form factor - supporting full-power operation in standard enterprise and AI cloud server environments. OmniTherm enables a transition to two-phase liquid cooling without introducing water inside the server. The single-slot design allows operators to increase accelerator density in standard server architectures while capturing heat into a liquid loop, reducing reliance on extreme fan speeds that can create excessive noise, waste power and cause challenging operating conditions in the data centre.
Adhum Carter Wolde-Lule, Director at Prism Power Group, highlights the fact that switchgear is fast...
Sean Burke, CEO at Enteligent, positions 800V DC to 50V DC as the ‘missing piece’ in AI data...
Keith Norman, Chief Marketing & Sustainability Officer of Lyten, explains the reasons behind the...
Drew Gravitt is Senior Director of Distributed Generation & Microgrid Sales at Mission Critical...
Ryan Parker, Phononic's President & COO, discusses the data centre thermal management challenge,...
Thiri Shwesin Aung, founder and CEO of Nyxium, discusses how she and co-founder, Paul Seurin, have...
Aleksandar Grbić, Global Data Center Solutions Manager, Hitachi Energy, discusses how the...
Laura Allwood, now a fully qualified Project Manager at Arcadis, outlines her journey from...