Silicon Valley startup Fabric Cryptography has raised $33 million in a Series A funding round to advance the development of a cryptography processing unit it calls the Verifiable Processing Unit (VPU). The funding round was co-led by Blockchain Capital and 1kx, with additional backing from Offchain Labs, Polygon, and Matter Labs. This follows a $6 million seed round led by Metaplanet, along with contributions from Inflection, Liquid2 Ventures, and others.
The fresh capital will be used to create specialized computing chips, software, and cryptographic algorithms for the VPU, a custom silicon chip designed specifically for cryptography. According to the company’s press release, the VPU is set to go into production later this year and promises to “drastically improve the speed and cost of running advanced cryptographic workloads” compared to traditional CPUs and GPUs.
Fabric Cryptography has already secured tens of millions of dollars in pre-orders for the VPU. The company is also building a software stack and cloud infrastructure to make its technology more accessible to developers and to meet growing market demand.
“There exists a whole world of advanced cryptographic algorithms that go beyond protecting our data, and can actually begin to guarantee trust, if we can run them efficiently,” said Fabric Cryptography co-founder and CEO Michael Gao. He noted that while billions have been invested in AI chips, the cryptography sector has been largely confined to using general-purpose CPUs and GPUs that are not optimized for the intensive mathematical operations required by advanced cryptography.
Dr. Wei Dai, a cryptographer and research partner at 1kx, highlighted that the VPU’s advantage lies in its “unique combination of programmability, flexibility, and performance.” Unlike fixed-function chips commonly used in cryptography, the VPU can adapt to emerging cryptographic algorithms, making it future-proof.
Fabric Cryptography was founded by MIT and Stanford dropouts with backgrounds in AI, and its team includes over 50 engineers and cryptographers from top companies like Nvidia, Google, Amazon, Groq, and Cerebras. The startup plans to leverage hardware-software co-design techniques typically used in AI hardware to bring a similar level of innovation to cryptography.
The development of the VPU could mark a significant leap forward in cryptographic processing, enabling new applications and boosting the efficiency of secure computing in a wide range of industries.