Direct liquid cooling emerges as key to exascale computing efficiency
Exascale computing is no longer a distant concept, but a reality reshaping how massive computational tasks are approached.
However, this rise has brought new challenges, particularly in thermal management. There now exists a growing adoption of direct liquid cooling to manage the intense heat generated by powerful CPUs and GPUs, according to Armando Acosta (pictured), director of HPC product management at Dell Technologies Inc.
"If you look at the rise of exascale, what you're starting to see now is with the rise of exascale and these large machines and HPC supercomputers, guess what? New challenges arise when you try to go to that scale," Acosta said. "When you look at exascale, what it's driving is more direct liquid cooling technologies. If you want the highest performance, you want the best CPU, or the highest performing GPU ... you have to do direct liquid cooling."
Acosta spoke with theCUBE Research's Dave Vellante and Savannah Peterson at SC24, during an exclusive broadcast on theCUBE, SiliconANGLE Media's livestreaming studio. They discussed the emergence, enterprise value and potential challenges of exascale computing. (* Disclosure below.)
As HPC evolves, standards and modularity are becoming essential. Dell's innovative OCP OVR3 rack, featuring external power shelves, demonstrates how modular design simplifies maintenance and ensures uninterrupted performance. This approach aligns with the company's dedication to agile innovation, enabling faster time-to-market solutions for diverse workloads.
"We've got a rack in our booth," Acosta said. "It's an OCP OVR3 rack, 21-inch design. But what we're now looking at is if you want the ultimate performance, it's not going to fit in a 19-inch form factor anymore. But when you look at that 21-inch, when you try to pack in direct liquid cool manifolds, quick disconnects and power distribution units, it starts to get packed in and the serviceability goes to the wayside. What we did with our new design is we took serviceability to the heart of that, because that's what customers told us what they wanted."
By adopting modular specifications, such as the Data Center Modular Hardware System, Dell supports silicon diversity, allowing customers to integrate Intel Corp., Advanced Micro Devices Inc. and Nvidia Corp. components seamlessly. This standardization reduces costs and accelerates deployment, ensuring systems can adapt to ever-changing demands, Acosta noted.
Here's the complete video interview, part of SiliconANGLE's and theCUBE Research's coverage of SC24: