Snowcap Compute Raises $23 Million for Revolutionary Superconducting AI Chips

Snowcap Compute raises $23 million for superconducting AI chips

SAN FRANCISCO, June 23 (Reuters) - Snowcap Compute, a startup working on building artificial intelligence computing chips using superconducting technology, on Monday raised $23 million and said that the former CEO of Intel will join its board. Snowcap aims to build computers that could one day beat today's best artificial intelligence systems, while using a fraction of the electricity. To do that, Snowcap plans to use a new kind of chip made with superconductors, which are materials that allow current to flow without electrical resistance. Scientists understand superconductors well and have theorized about making computer chips with them since at least the 1990s, but have faced a major challenge: To work, the chips need to be kept very cold in cryogenic coolers which themselves consume a lot of electricity. For decades that made superconductor chips a nonstarter, until AI chatbots ignited huge demand for computing power at the same time that conventional chips are hitting the limits of how much performance they can wring from every watt of power and are taxing electricity grids. Nvidia's forthcoming "Rubin Ultra" AI data center server due in 2027, for example, is expected to consume about 600 kilowatts of power. That means operating that single server at full capacity for one hour would consume about two thirds the average power that a U.S. house uses in a month. In that kind of changed world, dedicating a portion of a data center's power needs to cryogenic coolers makes sense if the performance gains are good enough, said Michael Lafferty, Snowcap's CEO, who formerly oversaw work on futuristic chips at Cadence Design Systems (CDNS.O), opens new tab. Snowcap believes that even after accounting for energy used in cooling, its chips will be about 25 times better than today's best chips in terms of performance per watt. "Power (efficiency) is nice, but performance sells," Lafferty said. "So we're pushing the performance level way up and pulling the power down at the same time." Snowcap's founding team includes two scientists - Anna Herr and Quentin Herr - who have done extensive work on superconducting chips at chip industry research firm Imed and defense firm Northrop Grumman (NOC.N), opens new tab, as well as former chip executives from Nvidia (NVDA.O), opens new tab and Alphabet's (GOOGL.O), opens new tab Google. While the chips can be made in a standard factory, they will require an exotic metal called niobium titanium nitride that Lafferty said depends on Brazil and Canada for key ingredients. Snowcap plans its first basic chip by the end of 2026, but full systems will not come until later. Despite the long development timeline, Pat Gelsinger, Intel's (INTC.O), opens new tab former CEO who led the investment for venture firm Playground Global and is joining Snowcap's board, said the computing industry needs a sharp break from its current trajectory of consuming ever more electricity. "A lot of data centers today are just being limited by power availability," Gelsinger said. Also joining the funding round were Cambium Capital and Vsquared Ventures. Reporting by Stephen Nellis in San Francisco; Editing by Christopher Cushing Our Standards: The Thomson Reuters Trust Principles., opens new tab Suggested Topics:Artificial Intelligence

Superconducting chip startup Snowcap Compute reels in $23M - SiliconANGLE

Snowcap Compute Inc., a startup that plans to make processors from semiconducting materials, has raised $23 million in funding. Playground Global led the seed investment with the participation of Joining Playground and Vsquared Ventures. In conjunction with its announcement of the raise today, Snowcap disclosed that former Intel Corp. Chief Executive Officer Pat Gelsinger has joined its board. Palo Alto, California-based Snowcap is led by CEO Michael Lafferty. He previously headed Cadence Design Systems Inc.'s More than Moore group, which focuses on emerging technologies such as quantum computers. Lafferty's two co-founders, Chief Science Officer Anna Herr and Chief Technology Officer Quentin Herr, were previously scientific directors at the IMEC research lab. "Superconducting logic lets us push beyond the limits of existing CMOS technology, achieving orders-of-magnitude gains in processing speed and efficiency," Lafferty said. "That performance is essential for the future of AI and quantum computing." When electrons pass through a processor's transistors, they produce heat. The same is not true for superconducting materials. Electrons don't generate any heat when they travel through a superconductor, a property that Snowcap hopes to harness to make data centers more efficient. The heat generated by the electricity inside processors has to be removed by cooling them. Today, the cooling equipment used to that end accounts for a significant percentage of data centers' power consumption. Because the flow of electricity through superconducting materials doesn't generate any heat, using such materials to make chips could significantly reduce data centers' cooling requirements. That, in turn, would lower data centers' power usage. According to Reuters, Snowcap estimates that processors made using its superconducting technology will be 25 times more power-efficient than today's "best chips." The company plans to make artificial intelligence accelerators optimized for both inference and training workloads. Furthermore, it believes that the technology could also be used to make other types of chips such as central processing units. Snowcap's chips will reportedly use a material called niobium titanium nitride. It's made by combining nitrogen with niobium-titanium, an alloy that is primarily used to make superconducting magnets. Such magnets can be found in systems such as particle accelerators and MRI machines. Superconducting magnets are made by shaping a piece of niobium-titanium into a wire and then winding the wire into a coil. When the metal is in the shape of a coil, it can produce significantly more powerful electromagnetic fields than otherwise. That's necessary for many of the use cases to which the technology is commonly applied. Superconductivity only emerges in materials such as niobium-titanium when they're cooled near absolute zero. According to Snowcap, its engineers will achieve that using standard hydrogen-powered cryogenic equipment. Hydrogen is the go-to choice for cooling superconductors because it becomes liquid near absolute zero, which is useful for removing heat. Hydrogen is also chemically inert, which means that it doesn't cause any chemical reactions in the devices it's meant to cool. Snowcap has also disclosed that its chips will use Josephson junctions. A Josephson junction is a nanostructure that some quantum computer companies use to make qubits. It comprises two superconducting devices separated by a thin layer of insulating, or non-conductive, material. Running a current through a Josephson junction allows electrons to jump through the insulating layer, a property that can be harnessed to carry out computations. Snowcap claims to have addressed several of the technical challenges involved in using superconductors to make chips. As a result, the company says that its processors can be made in existing fabs using standard 300-millimeter wafers. That removes the need to build new production lines, which should reduce manufacturing costs.

Snowcap Compute raises $23 million for superconducting AI chips

Snowcap Compute, a startup working on building artificial intelligence computing chips using superconducting technology, on Monday raised $23 million and said that the former CEO of Intel will join its board. Snowcap aims to build computers that could one day beat today's best artificial intelligence systems, while using a fraction of the electricity. To do that, Snowcap plans to use a new kind of chip made with superconductors, which are materials that allow current to flow without electrical resistance. Scientists understand superconductors well and have theorized about making computer chips with them since at least the 1990s, but have faced a major challenge: To work, the chips need to be kept very cold in cryogenic coolers which themselves consume a lot of electricity. For decades that made superconductor chips a nonstarter, until AI chatbots ignited huge demand for computing power at the same time that conventional chips are hitting the limits of how much performance they can wring from every watt of power and are taxing electricity grids. Nvidia's forthcoming "Rubin Ultra" AI data center server due in 2027, for example, is expected to consume about 600 kilowatts of power. That means operating that single server at full capacity for one hour would consume about two thirds the average power that a US house uses in a month. In that kind of changed world, dedicating a portion of a data center's power needs to cryogenic coolers makes sense if the performance gains are good enough, said Michael Lafferty, Snowcap's CEO, who formerly oversaw work on futuristic chips at Cadence Design Systems. Snowcap believes that even after accounting for energy used in cooling, its chips will be about 25 times better than today's best chips in terms of performance per watt. "Power (efficiency) is nice, but performance sells," Lafferty said. "So we're pushing the performance level way up and pulling the power down at the same time." Snowcap's founding team includes two scientists - Anna Herr and Quentin Herr - who have done extensive work on superconducting chips at chip industry research firm Imed and defense firm Northrop Grumman, as well as former chip executives from Nvidia and Alphabet's Google. While the chips can be made in a standard factory, they will require an exotic metal called niobium titanium nitride that Lafferty said depends on Brazil and Canada for key ingredients. Snowcap plans its first basic chip by the end of 2026, but full systems will not come until later. Despite the long development timeline, Pat Gelsinger, Intel's former CEO who led the investment for venture firm Playground Global and is joining Snowcap's board, said the computing industry needs a sharp break from its current trajectory of consuming ever more electricity. "A lot of data centers today are just being limited by power availability," Gelsinger said. Also joining the funding round were Cambium Capital and Vsquared Ventures.

From Power-Hungry AI to Energy Saver: Snowcap's $23M Move to Revolutionize Computing - Alphabet (NASDAQ:GOOG), Cadence Design Systems (NASDAQ:CDNS)

Snowcap Compute, a semiconductor startup developing superconducting AI chips, announced a $23 million seed round on Monday. According to Reuters, the company is backed by Playground Global and led by former Intel CEO Pat Gelsinger, who will also serve as board chair. The funding round also included Cambium Capital and Vsquared Ventures. The startup aims to create high-performance computing platforms that require significantly less power than current-generation chips. Snowcap said its superconducting architecture will deliver 25 times better performance per watt compared to existing AI systems. Don't Miss: Peter Thiel turned $1,700 into $5 billion -- now accredited investors are eyeing this software company with similar breakout potential. Learn how you can invest with $1,000 at just $0.30/share. Invest early in CancerVax's breakthrough tech aiming to disrupt a $231B market. Back a bold new approach to cancer treatment with high-growth potential. Pre-IPO Offer: Get A Piece Of A Nearly $5T Global Opportunity By Joining BOXABL As An Early Shareholder At Just $0.80/Share Massive Demand & Disruptive Potential - Boxabl has received interest for over 190,000 homes, positioning itself as a major disruptor in the housing market. Revolutionary Manufacturing Approach - Inspired by Henry Ford's assembly line, Boxabl's foldable tiny homes are designed for high-efficiency production, making homeownership more accessible. Affordable Investment Opportunity - With homes priced at $60,000, Boxabl is raising $1 billion to scale production, offering investors a chance to own a stake in its growth. Share Price: $0.80 Min. Investment: $1,000 Valuation: $3.5B Click Here To Invest For Just $0.80/Share ($1000 Min)Aiming for Radical Gains in AI and Quantum Computing Snowcap Compute's superconducting chips are designed to operate with zero electrical resistance and require cryogenic cooling to function, according to Reuters. The company said the chips are being developed to reduce electricity consumption in artificial intelligence computing, a sector facing increasing energy demands. Nvidia's NVDA upcoming Rubin Ultra server, expected in 2027, is projected to consume around 600 kilowatts of power -- about two-thirds of the monthly electricity use of a typical U.S. household, Reuters reported. Snowcap CEO Michael Lafferty, formerly with Cadence Design Systems CDNS, told Reuters that the performance-to-power ratio of Snowcap's architecture justifies the energy spent on cooling. "We're pushing the performance level way up and pulling the power down at the same time," he said. Snowcap plans to release a basic chip by the end of 2026. Full system deployments will follow at a later stage. The chips will be manufactured in a conventional factory using niobium titanium nitride sourced from Brazil and Canada, Reuters reported. Trending: GoSun's Breakthrough Rooftop EV Charger Already Has 2,000+ Units Reserved -- Become an Investor in This $41.3M Clean Energy Brand Today Gelsinger: Compute Needs a 'Sharp Break' From Today's Power Demands Gelsinger, who stepped down as Intel CEO in December, said the industry must rethink its reliance on increasingly power-hungry chips. "A lot of data centers today are just being limited by power availability," he told Reuters. In a LinkedIn post, Gelsinger described Snowcap as "the first commercially viable superconducting compute platform," and said it delivers performance and efficiency gains across classical, AI, and quantum workloads. He called it his first public investment as general partner at Playground Global and said the company's technology could address compute bottlenecks and "push the boundaries of what is possible with silicon." See Also: Maximize saving for your retirement and cut down on taxes: Schedule your free call with a financial advisor to start your financial journey - no cost, no obligation. Team Includes Veterans From Nvidia, Northrop Grumman, and Google Snowcap's founding team includes superconducting researchers Anna Herr and Quentin Herr, who previously worked at chip research firm Imed and defense contractor Northrop Grumman Corp. NOC. The team also includes former executives from Nvidia and Alphabet Inc.'s GOOG GOOGL)) Google unit. According to Snowcap, its architecture is engineered for high-performance AI inference and training, quantum-classical hybrid workloads, and low-latency systems. Snowcap Joins Broader Push to Rethink Post-CMOS Era Founded in 2024, Snowcap enters a growing field of startups pursuing alternatives to conventional complementary metal-oxide-semiconductor-based processors. The company said its superconducting logic offers "orders-of-magnitude gains in processing speed and efficiency" and aims to support emerging compute workloads spanning AI, high-performance computing, and quantum workflows. Read Next: Are you rich? Here's what Americans think you need to be considered wealthy. CDNSCadence Design Systems Inc$305.110.47%Stock Score Locked: Edge Members Only Benzinga Rankings give you vital metrics on any stock - anytime. Unlock RankingsEdge RankingsMomentum40.83Growth79.39Quality58.11Value7.47Price TrendShortMediumLongOverviewGOOGAlphabet Inc$178.222.17%NOCNorthrop Grumman Corp$494.000.07%NVDANVIDIA Corp$157.591.66%Market News and Data brought to you by Benzinga APIs

Snowcap Compute raises $23 million for superconducting AI chips

Snowcap Compute, a startup working on building artificial intelligence computing chips using superconducting technology, on Monday raised $23 million and said that the former CEO of Intel will join its board. Snowcap aims to build computers that could one day beat today's best artificial intelligence systems, while using a fraction of the electricity. To do that, Snowcap plans to use a new kind of chip made with superconductors, which are materials that allow current to flow without electrical resistance. Scientists understand superconductors well and have theorized about making computer chips with them since at least the 1990s, but have faced a major challenge: To work, the chips need to be kept very cold in cryogenic coolers which themselves consume a lot of electricity. For decades that made superconductor chips a nonstarter, until AI chatbots ignited huge demand for computing power at the same time that conventional chips are hitting the limits of how much performance they can wring from every watt of power and are taxing electricity grids. Nvidia's forthcoming "Rubin Ultra" AI data center server due in 2027, for example, is expected to consume about 600 kilowatts of power. That means operating that single server at full capacity for one hour would consume about two thirds the average power that a U.S. house uses in a month. In that kind of changed world, dedicating a portion of a data center's power needs to cryogenic coolers makes sense if the performance gains are good enough, said Michael Lafferty, Snowcap's CEO, who formerly oversaw work on futuristic chips at Cadence Design Systems CDNS.O. Snowcap believes that even after accounting for energy used in cooling, its chips will be about 25 times better than today's best chips in terms of performance per watt. "Power (efficiency) is nice, but performance sells," Lafferty said. "So, we're pushing the performance level way up and pulling the power down at the same time." Snowcap's founding team includes two scientists, Anna and Quentin Herr, who have done extensive work on superconducting chips at chip industry research firm Imed and defense firm Northrop Grumman as well as former chip executives from Nvidia and Alphabet's Google. While the chips can be made in a standard factory, they will require an exotic metal called niobium titanium nitride that Lafferty said depends on Brazil and Canada for key ingredients. Snowcap plans its first basic chip by the end of 2026, but full systems will not come until later. Despite the long development timeline, Pat Gelsinger, Intel's former CEO who led the investment for venture firm Playground Global and is joining Snowcap's board, said the computing industry needs a sharp break from its current trajectory of consuming ever more electricity. "A lot of data centers today are just being limited by power availability," Gelsinger said. Also joining the funding round were Cambium Capital and Vsquared Ventures.

Snowcap Compute raises $23 million for superconducting AI chips

SAN FRANCISCO (Reuters) -Snowcap Compute, a startup working on building artificial intelligence computing chips using superconducting technology, on Monday raised $23 million and said that the former CEO of Intel will join its board. Snowcap aims to build computers that could one day beat today's best artificial intelligence systems, while using a fraction of the electricity. To do that, Snowcap plans to use a new kind of chip made with superconductors, which are materials that allow current to flow without electrical resistance. Scientists understand superconductors well and have theorized about making computer chips with them since at least the 1990s, but have faced a major challenge: To work, the chips need to be kept very cold in cryogenic coolers which themselves consume a lot of electricity. For decades that made superconductor chips a nonstarter, until AI chatbots ignited huge demand for computing power at the same time that conventional chips are hitting the limits of how much performance they can wring from every watt of power and are taxing electricity grids. Nvidia's forthcoming "Rubin Ultra" AI data center server due in 2027, for example, is expected to consume about 600 kilowatts of power. That means operating that single server at full capacity for one hour would consume about two thirds the average power that a U.S. house uses in a month. In that kind of changed world, dedicating a portion of a data center's power needs to cryogenic coolers makes sense if the performance gains are good enough, said Michael Lafferty, Snowcap's CEO, who formerly oversaw work on futuristic chips at Cadence Design Systems. Snowcap believes that even after accounting for energy used in cooling, its chips will be about 25 times better than today's best chips in terms of performance per watt. "Power (efficiency) is nice, but performance sells," Lafferty said. "So we're pushing the performance level way up and pulling the power down at the same time." Snowcap's founding team includes two scientists - Anna Herr and Quentin Herr - who have done extensive work on superconducting chips at chip industry research firm Imec and defense firm Northrop Grumman, as well as former chip executives from Nvidia and Alphabet's Google. While the chips can be made in a standard factory, they will require an exotic metal called niobium titanium nitride that Lafferty said depends on Brazil and Canada for key ingredients. Snowcap plans its first basic chip by the end of 2026, but full systems will not come until later. Despite the long development timeline, Pat Gelsinger, Intel's former CEO who led the investment for venture firm Playground Global and is joining Snowcap's board, said the computing industry needs a sharp break from its current trajectory of consuming ever more electricity. "A lot of data centers today are just being limited by power availability," Gelsinger said. Also joining the funding round were Cambium Capital and Vsquared Ventures. (Reporting by Stephen Nellis in San Francisco; Editing by Christopher Cushing)