-
AWS Data Center Energy
Amazon's 2024 Sustainability Report highlights energy and emissions performance across its global operations, with Amazon Web Services (AWS) data centres recording improved efficiency despite a rise in absolute emissions for Amazon. AWS is building data centers to support the next generation of artificial intelligence (AI) innovation and customers' evolving needs. The company confirms its target to achieve net zero carbon. AWS is the world's most comprehensive and broadly adopted cloud offering, with millions of global users depending on it every day. This article delves into AWS's initiatives, surprising statistics, and success stories and provides actionable steps for organizations to become more sustainable.
-
Is liquid cooling for AI servers done by immersing them directly in liquid
In two-phase immersion cooling, a server is dunked into a vat of liquid. The liquid actively boils next to the heat-producing components, cooling them in the process. Liquid cooling is becoming a. Liquid cooling is a thermal management technology that directly addresses the immense heat generated by high-power AI servers like NVIDIA DGX systems. Cold Plate Liquid Cooling, often referred to as Direct-to-Chip (DLC), remains the most mature and widely deployed liquid cooling approach. The Cray-2 supercomputer, deployed in 1985, was famously immersed in. A single server rack packed with the latest NVIDIA GPUs can now consume over 100,000 watts of power—equivalent to the air conditioning load of 30 homes running simultaneously. Trying to cool this with traditional fans is like pointing a small desk fan at an erupting volcano; it's simply no longer. To address these issues, there has been a shift toward liquid cooling solutions, which offer better heat dissipation by applying coolant directly to heat-generating components or immersing them in a conductive liquid.
[PDF Version]