Share this article

Fabric, Startup Building 'VPU' Chips for Cryptography, Raises $33M

The fundraising, co-led by Blockchain Capital and 1kx, will be used to "build computing chips, software and cryptographic algorithms," the company said.

Fabric Cryptography team (Fabric Cryptography)
Fabric Cryptography team (Fabric Cryptography)

Fabric Cryptography, a startup focused on hardware, has raised $33 million in a Series A fundraising round co-led by Blockchain Capital and 1kx.

Other participating investors included Offchain Labs, Polygon and Matter Labs. The project previously had raised $6 million in a seed round led by Metaplanet. Fabric was founded by MIT and Stanford dropouts Michael Gao and Tina Ju, along with hardware veterans such as Sagar Reddy, according to a press release.

STORY CONTINUES BELOW
Don't miss another story.Subscribe to the The Protocol Newsletter today. See all newsletters

The fresh funds will be used to "build computing chips, software and cryptographic algorithms," the company said.

At the heart of Fabric's roadmap is a new processing unit known as the "verifiable processing unit," or VPU, which will be tailored to handle cryptography, according to the project.

Companies are developing new computing chips to handle rising use from AI – with its heavy demand for fast computation from graphics processing units, or GPUs – as well as cryptography-intensive blockchain applications.

Fabric said in the press release that the VPU is "the first custom silicon chip that uses an instruction set architecture specific to cryptography," which means that "any cryptographic algorithm can be broken down into its mathematical building blocks that are natively accelerated and supported by the chip."

The new chips are slated to go into production later this year, Fabric said.

The VPUs are "poised to drastically improve the speed and cost of running advanced cryptographic workloads, compared to CPUs, GPUs and fixed-function cryptography," according to the press release. They "will do for cryptography what Nvidia’s GPUs and many other startups’ chips are doing for AI."

Bradley Keoun

Bradley Keoun is CoinDesk's managing editor of tech & protocols, where he oversees a team of reporters covering blockchain technology, and previously ran the global crypto markets team. A two-time Loeb Awards finalist, he previously was chief global finance and economic correspondent for TheStreet and before that worked as an editor and reporter for Bloomberg News in New York and Mexico City, reporting on Wall Street, emerging markets and the energy industry. He started out as a police-beat reporter for the Gainesville Sun in Florida and later worked as a general-assignment reporter for the Chicago Tribune. Originally from Fort Wayne, Indiana, he double-majored in electrical engineering and classical studies as an undergraduate at Duke University and later obtained a master's in journalism from the University of Florida. He is currently based in Austin, Texas, and in his spare time plays guitar, sings in a choir and hikes in the Texas Hill Country. He owns less than $1,000 each of several cryptocurrencies.

Bradley Keoun