Using Overclock's Akash Network, companies can turn their unused servers into Kubernetes-orchestrated Docker containers for rent. Credit: Thinkstock Putting unused CPUs to work is nothing new. In the modern era, it started in 1999 when the SETI Institute launched SETI@Home, a screensaver that also examined slices of radio signals gathered by a giant telescope for signs of intergalactic life. Nineteen years later, and ET still hasn’t phoned us. But the concept grew to dozens of science and math-related projects. I took part in the World Community Grid run by IBM for years, letting my idle PC look for potential cures for AIDS and Ebola. These are all client-side apps that people ran on their personal PC. Now a startup, misnamed Overclock (overclocking is a term for running your CPU faster than it is rated, something only system builders do), is doing something on the server side and for business. Overclock recently launched what it calls the Akash Network, an open marketplace that connects companies with unused compute capacity to users who need it. The company claims up to 85 percent of the world’s compute resources are sitting unused, a rather radical claim, which it doesn’t back up. How Overclock’s Akash Network works Once you set up the Akash agent, you are done. Workloads are sent to your servers, they’re executed, the results are sent back, and shut down. No intervention is needed on your part. That said, Overclock does provide the necessary tools to configure, deploy, monitor, and manage the workloads. A developer who needs the resources specifies their deployment criteria, such as resources needed, topology, and the price they are willing to pay, in a posting to the Akash blockchain. Providers with server cycles to offer automatically detect the new bid request and programmatically bid to host it. The lowest bid wins the auction, a lease is created, and the parties exchange keys. All of this is done with no human intervention. The Akash agent then begins picking up workloads in Docker containers, orchestrated by Kubernetes and distributed over Akash’s peer-to-peer file sharing protocol. Your applications can be run as is because they run in Docker containers. Payment via the Akash token is also done via the blockchain, allowing for a full audit of transactions by lessors and lessees. Since it’s all via blockchain, there is no point of failure — the loads can be balanced between different providers. And since there is no middle man and the lowest bidder always wins, no single entity can drive prices up. It all sounds like a nifty idea, and it might be great come Christmas, but I do wonder: If 85 percent of the world’s server compute capacity is unused, how many potential customers are there for a service that sells unused server capacity? We’ll see. The Akash (it means “sky” in Hindi) Network is now live, ready for rent or rental. Related content news AWS and Nvidia partner on Project Ceiba, a GPU-powered AI supercomputer The companies are extending their AI partnership, and one key initiative is a supercomputer that will be integrated with AWS services and used by Nvidia’s own R&D teams. By Andy Patrizio Nov 30, 2023 3 mins CPUs and Processors Generative AI Supercomputers news VMware stung by defections and layoffs after Broadcom close Layoffs and executive departures are expected after an acquisition, but there's also concern about VMware customer retention. By Andy Patrizio Nov 30, 2023 3 mins Virtualization Data Center Industry news AI partly to blame for spike in data center costs Low vacancies and the cost of AI have driven up colocation fees by 15%, DatacenterHawk reports. By Andy Patrizio Nov 27, 2023 4 mins Generative AI Data Center opinion Winners and losers in the Top500 supercomputer ranking Besides Nvidia, who had a great showing on the list of the world’s most powerful supercomputers? Almost everyone. By Andy Patrizio Nov 20, 2023 4 mins CPUs and Processors Data Center Podcasts Videos Resources Events NEWSLETTERS Newsletter Promo Module Test Description for newsletter promo module. Please enter a valid email address Subscribe