Josh Claman, CEO of Accelsius – Interview Series | By The Digital Insider

Josh Claman is the CEO of Accelsius, he is an expert global executive with over 30 years of experience in data center technology. He’s driven growth and innovation at NCR, AT&T, and, as a Dell Executive, he managed significant business units across Europe and the Americas, including as General Manager of Dell UK. Post-Dell, he has led ventures in 3D printing and digital health, championing transformative tech. He holds degrees with honors from the University of Illinois and advanced business qualifications from the University of South Carolina and Oxford University. 

Accelsius was formed in 2022 to develop and commercialize a cooling solution system based on years of scientific thermal research conducted by Bell Labs. Founded by Innventure — a technology commercialization company that specializes in identifying, funding, and scaling disruptive technologies — our experts have created a new liquid cooling system that is serviceable, scalable and resilient: NeuCool.

Can you tell us about how you became the CEO of Accelsius to commercialize its liquid cooling technology?

Over the past 18 months, the data center industry recognized that traditional, brute force air cooling techniques had reached their limits for data centers as new emerging AI, machine learning and other compute-intense applications started flooding data centers from Hyperscalers to enterprise and COLO operations.  To keep pace, chip and server performance and resulting wattages, and the associated thermals,  were growing at an unanticipated rate. Innventure, which funds innovative and sustainable technology companies, identified an IP from Nokia Bell Labs that delivered a two-phase, direct-to-chip solution that had the potential with further advanced engineering development and productization to revolutionize the industry.

Innventure bought the IP and asked me to come on board to build the company and commercialize the NeuCool technology into an enterprise-class solution. Soon after that, ChatGPT was launched just a few months later. This accelerated us into a tremendous growth phase with high-TDP, AI chips that demanded liquid cooling.

How does Accelsius' two-phase, direct-to-chip liquid cooling system differ from traditional air cooling methods?

Air cooling is a common but remarkably energy-inefficient solution used to cool data centers, particularly in dry, hot climates. As chips become more powerful and compute demands grow, air cooling becomes increasingly unsustainable and in-efficient. Air is not a good conductor of heat compared with liquid, which has up to 4,000 times greater amount of heat rejection compared with air.

With NeuCool, Accelsius direct-to-chip technology, the A1 safety-rated liquid coolant is pumped to Vaporators (or engineered cold plates) in place of the heatsinks on electronic components in an air-cooling configuration. While most of the heat (80%) is taken away by the NeuCool 2 phase Vaporators at the chip-level (CPU, GPU) and via the entire cooling loop, fans are still needed to help remove heat at the board level, but at a very low volume and velocity in most cases.

Direct to chip liquid cooling has an estimated 50% savings in energy costs and CO2 emissions in comparison to traditional air cooling.

Can you explain the environmental benefits of your cooling technology, particularly in terms of CO2 emissions and water usage? 

We use up to half as much electricity as an air-cooled data center – which means we reduce CO2 emissions by the same amount. We also consume zero water in our system, leading to greater environmental impacts.

How does Accelsius Ascent Model help data center operators transition from air to liquid cooling?

Many new data center and edge computing build-outs are being architected and constructed to facilitate liquid cooling from the start. For brownfield or existing data centers, NeuCool is uniquely able to be easily retrofitted with the familiar form factor of a direct-to-chip solution.

The Accelsius Ascent Model is a collaborative program that enables, empowers and actively guides data center operators through a progressive transition to liquid cooling. This unique program ensures that customers systematically receive maximum support, value and all key benefits of the NeuCool System.

We ensure a smooth transition into liquid cooling from air cooling potentially reaching its limits. The process involves modifications or retrofits to the server, rack and even facility. Our Kickstart program, part of the Ascent model, offers customers willing to try liquid cooling a chance to plan, test and gain experience in liquid cooling and forecast a hybrid IT environment for a smooth transition away from air cooling.

What challenges did you face while commercializing your technology, and how did you overcome them?

The historical supply chain crisis impacted our sector particularly hard, and this was something I was keenly aware of as I was working to scale Accelsius in 2022. We’ve prioritized a multi-layer AVL that will protect us in the future, and have also committed to having 85% of our top  vendors be NAM based to enable a more responsible supply chain.

We also have a dynamic manufacturing and assembly model which blends lower volume, early stage in-house production with an integrated tier 1 global manufacturing partner, which gives us more control and flexibility.

How do you see the role of liquid cooling evolving as AI and machine learning technologies continue to advance?

As AI and ML advancements increase, direct to chip liquid cooling will eventually become the de-facto cooling technology in data centers. Leaders at NVIDIA and Intel have already declared this in recent announcements,  supported by this blog here.

What advice would you give to other entrepreneurs looking to tackle complex technical challenges in the hardware technology space?

Don’t get too far ahead of yourself and run out of runway: this is one of the main reasons hard tech businesses fail.

While the phrase “Move slow, don’t break things” works well for companies that emphasize speed and experimentation, the exact opposite is true for those pursuing operational innovation.

It is important to remember that just because a technology or new way of doing business is novel doesn’t mean it’s always appropriate for the buyer or the market. Operational innovation results from a cautious approach built with iterative steps rather than transformational ones.

Can you share any success stories or case studies where Accelsius' technology has made a significant impact on data center operations?

One noteworthy partner is Texas Advanced Computing Center (TACC). We now support Vista, which is a new leading-edge, high-performance supercomputer, that manages TACC’s AI workloads. Vista uses NVIDIA GH100 Grace Hopper Superchips with TDPs up to 1000 watts per socket.

As per confidentiality standards, we plan to release additional customer profiles soon.

What do you think are the biggest misconceptions about liquid cooling technology in the industry today?

There are a few misconceptions about liquid cooling in the industry that I am happy to address.

First, we have seen some hesitation in combining liquids and servers within data center racks. Our direct-to-chip architecture is heavily engineered to prevent leakage, subsiding this popular fear. In the rare event that there is a leak, the dielectric fluid we use will not destroy or damage servers.

Another common misconception is that liquid cooling technologies are difficult to implement into current brownfield data centers. If done correctly, direct-to-chip cooling technology should fit into traditional racks  without the need for special mounting or difficult retrofitting.

How does Accelsius plan to scale its operations to meet the growing demand for advanced cooling solutions?

We have a robust product portfolio, enabling modular building of liquid cooling solutions from one rack to many – with increasing heat removal capability as rack densities continue to grow. We also have an expansive partner eco-system that enables us to assemble, deploy, integrate and service at volume and across a wide geographic coverage area. Lastly, in 2024 we've launched our presence in Europe, and will continue to expand our services there.

Thank you for the great interview, readers who wish to learn more should visit Accelsius


#000, #2022, #2024, #3D, #3DPrinting, #Accelsius, #Advice, #Ai, #AIChips, #Air, #Americas, #Amp, #Announcements, #Applications, #Approach, #Architecture, #Blog, #Board, #Building, #Business, #CEO, #ChatGPT, #Chip, #Chips, #CO2, #Collaborative, #Companies, #Comparison, #Computing, #Cooling, #Cpu, #Data, #DataCenter, #DataCenters, #Dell, #Development, #DigitalHealth, #Edge, #EdgeComputing, #Electricity, #Electronic, #Emissions, #Energy, #Engineering, #Enterprise, #Environment, #Environmental, #Europe, #Factor, #Fear, #Flooding, #Forecast, #Form, #Funding, #Future, #Geographic, #Global, #Gpu, #Growth, #Guides, #Hardware, #Health, #Heat, #How, #Hybrid, #Impact, #Impacts, #Industry, #Innovation, #Intel, #INterview, #Interviews, #It, #Learn, #Learning, #LED, #Liquid, #Liquids, #Loop, #MachineLearning, #Manufacturing, #Ml, #Model, #Modular, #Nokia, #Nvidia, #One, #Opposite, #Other, #Performance, #Plan, #Prevent, #Printing, #Process, #Production, #Research, #Safety, #Savings, #Scale, #Scaling, #Scientific, #Server, #Servers, #Space, #Speed, #Standards, #Stories, #Studies, #Success, #Supercomputer, #SupplyChain, #Sustainable, #SustainableTechnology, #Tech, #Technology, #Texas, #Transition, #UK, #Units, #University, #Vendors, #Water
Published on The Digital Insider at https://is.gd/tgtemH.

Comments