{"id":575,"date":"2025-11-04T14:27:25","date_gmt":"2025-11-04T06:27:25","guid":{"rendered":"https:\/\/www.midytech.com\/?p=575"},"modified":"2025-11-04T14:27:25","modified_gmt":"2025-11-04T06:27:25","slug":"nvidia-sends-a-powerful-gpu-to-space","status":"publish","type":"post","link":"https:\/\/www.midytech.com\/index.php\/2025\/11\/04\/nvidia-sends-a-powerful-gpu-to-space\/","title":{"rendered":"Nvidia Sends a Powerful GPU to Space"},"content":{"rendered":"\n

On Sunday, 2 November,\u00a0Nvidia\u00a0sent\u00a0its powerful\u00a0H100 GPU\u00a0to space for the first time\u00a0to test how\u00a0data centers\u00a0could work in orbit.<\/p>\n\n\n\n

The GPU, featuring an 80-gigabyte RAM, is a hundred times as powerful as any computer ever flown in space. It will test a range of AI processing applications including analyzing\u00a0Earth observation\u00a0images and running a large language model by\u00a0Google. The test flight, onboard the Starcloud-1 satellite by Redmond, Va.\u2013based startup Starcloud, is the first step in an ambitious plan to move the world\u2019s power-hungry data-crunching infrastructure to space. Proponents think the idea makes sense: Far above the planet, in the emptiness of space, data centers wouldn\u2019t take up precious land or require as much energy and water for cooling. They wouldn\u2019t release warming\u00a0greenhouse gases\u00a0into the atmosphere either.<\/p>\n\n\n\n

Nvidia chips have been to space before. The Jetson machine-learning computing board has flown on several experimental and Earth-observing small\u00a0satellites. But H100 test flight opens an entirely new chapter for AI data-processing in space, paving the way for commercial services to start as early as next year.<\/p>\n\n\n\n

\u201cThe H-100 is about 100 times more powerful than any GPU computer that has been on orbit before,\u201d Philip Johnston, CEO and cofounder of Starcloud, told IEEE Spectrum<\/em>. \u201cIt will be the first time that a terrestrial-grade data-center GPU will be flown and operated in orbit.\u201d<\/p>\n\n\n\n

The three-year mission will be launched on SpaceX\u2019s Bandwagon 4\u00a0Falcon 9\u00a0flight. The 60-kilogram Starcloud-1 satellite will orbit Earth in a very low orbit at an altitude of about 350 kilometers. While there, it will be receiving data from a fleet of\u00a0synthetic aperture radar\u00a0(SAR) Earth-observing satellites operated by U.S. company Capella, process it in real time, and beam insights to Earth.<\/p>\n\n\n\n

\u201cDownlinking SAR data has historically been a huge problem because it\u2019s extremely voluminous,\u201d said Johnston. \u201cBut being able to process it in orbit will mean that we can only downlink the insight. The insight might be that there is a vessel at a certain location moving at a certain speed and in a certain direction. That will be just a 1-kilobyte packet versus the hundreds of gigabytes you would need to downlink the data.\u201d<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

The Case for Data Centers in Space<\/h2>\n\n\n\n

But orbital processing of data from Earth-orbiting satellites is only one part of Starcloud\u2019s vision. The company thinks that with advances in\u00a0rocket technology, especially with the cost reductions expected from SpaceX\u2019s Starship, future large-scale computing infrastructure could be placed in orbit rather than taking up precious space on Earth.<\/p>\n\n\n\n

\u201cAs the energy demands of AI development increase, orbital data centers represent a transformative environmental breakthrough\u2014cutting\u00a0greenhouse gas\u00a0emissions by orders of magnitude and eliminating the need for advanced cooling,\u201d Josh Parker, head of\u00a0sustainability\u00a0at Nvidia told\u00a0IEEE Spectrum<\/em>\u00a0in an email. \u201cBy harnessing low-cost, nonstop\u00a0solar energy\u00a0and avoiding land use and\u00a0fossil fuels, Starcloud\u2019s technology allows data centers to expand rapidly and sustainably, helping protect Earth\u2019s climate and critical natural resources as digital infrastructure grows.\u201d<\/p>\n\n\n\n

According to the\u00a0International Energy Agency, the world\u2019s data-crunching infrastructure is set to consume as much electricity by 2030 as the entire nation of\u00a0Japan. Data centers also require enormous amounts of water for cooling\u2014each day, a single 1-megawatt data center consumes as much water as about 1,000 people living in the developed world,\u00a0World Economic Forum\u00a0data suggests. The demand for computing continues to grow in step with advances in AI and so does data centers\u2019 hunger for consumables. The impacts are most intensely felt by\u00a0communities in the vicinity of these sites, which are increasingly concerned\u00a0about rising cost and disruptions to power and water supplies. Moving data centers to space could solve these problems, proponents of the technology think.<\/p>\n\n\n\n

\u201cMy expectation is that within 10 years, almost all new data centers will be built in space purely because of the constraint that we\u2019re facing on energy terrestrially,\u201d said Johnston.<\/p>\n\n\n\n

Making data centers on Earth run on fully\u00a0green energy\u00a0requires major investments into\u00a0solar power\u00a0generation and battery storage systems, he said. In space, no battery storage is needed as sunlight is available 24\/7. On top of that, each solar panel produces eight times as much electricity as its equivalent on Earth, which further decreases the cost, he added.<\/p>\n\n\n\n

\u201cThe only additional cost we have in space is the launch,\u201d Johnston said. \u201cWe see a breakeven with launch cost of around [US] $500 per kilo. With Starship, we\u2019re expecting launch costs much lower.\u201d<\/p>\n\n\n\n

Per kilogram,\u00a0launch prices for SpaceX\u2019s Starship, once the megarocket is fully operational, are estimated to range from $150 to as little as $10. The launcher has so far completed six successful flights and is expected to send the first batch of satellites to orbit next year.<\/p>\n\n\n\n

Starcloud is already planning its next mission, hoping to launch a ten-times more powerful data center than Starcloud-1 to space next year. The Starcloud-2 mission will be fitted with Nvidia\u2019s Blackwell GPU and several H100s. That mission, providing 7 kilowatts of computing power, is expected to provide commercial services to customers including Earth-observation satellite operators and the U.S.\u00a0Department of Defense, said Johnston.<\/p>\n\n\n\n

An even larger, 100-kilowatt satellite, should reach orbit in 2027. By the early 2030s, Starcloud thinks it can have a 40-megawatt data center in space crunching data at a cost equivalent to data centers on Earth. Starcloud is one of several companies with plans to outsource computing to space.\u00a0Axiom Space\u00a0unveiled similar plans earlier this year. Florida-based\u00a0Lonestar Holdings\u00a0sent a small data center to the\u00a0Moon\u00a0with the Intuitive Machines-2 mission earlier this year and envisions building up major data centers on Earth\u2019s companion in the coming years.<\/p>\n","protected":false},"excerpt":{"rendered":"

On Sunday, 2 November,\u00a0Nvidia\u00a0…<\/p>\n","protected":false},"author":2,"featured_media":577,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[9,8],"tags":[24,42,125,39,126],"class_list":["post-575","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-companies","category-deep-tech","tag-ai","tag-gpu","tag-h100","tag-nvidia","tag-space"],"_links":{"self":[{"href":"https:\/\/www.midytech.com\/index.php\/wp-json\/wp\/v2\/posts\/575","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.midytech.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.midytech.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.midytech.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.midytech.com\/index.php\/wp-json\/wp\/v2\/comments?post=575"}],"version-history":[{"count":1,"href":"https:\/\/www.midytech.com\/index.php\/wp-json\/wp\/v2\/posts\/575\/revisions"}],"predecessor-version":[{"id":578,"href":"https:\/\/www.midytech.com\/index.php\/wp-json\/wp\/v2\/posts\/575\/revisions\/578"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.midytech.com\/index.php\/wp-json\/wp\/v2\/media\/577"}],"wp:attachment":[{"href":"https:\/\/www.midytech.com\/index.php\/wp-json\/wp\/v2\/media?parent=575"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.midytech.com\/index.php\/wp-json\/wp\/v2\/categories?post=575"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.midytech.com\/index.php\/wp-json\/wp\/v2\/tags?post=575"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}