Artificial Intelligence (AI) is transforming HPC by enabling users to gain key insights from massive amounts of data that were previously unmanageable. Given the critical research these systems are tasked to perform, these high-density clusters are expected to run at 100% utilization for sustained periods, making cooling performance even more critical.
Cutting edge AI and HPC requires the highest performance versions of the latest CPUs and GPUs – such as NVIDIA’s V100 GPUs and Intel’s Xeon Scalable Processors. These chip wattages translate into substantially higher wattage densities at both the node-level and rack-level because of the component wattages and the requirement for the shortest possible signal distance between processors, GPUs, switches both in and between cluster racks.
D2C Ingredient Coolers
Drop-in replacements for air heat sinks that transfer heat out of the server with liquid
Rack level Liquid Assisted Air Cooled (LAAC) solution for air cooled data centers
Rack level direct to chip (D2C) solution for liquid cooled data centers