CAMPBELL, Calif.--(BUSINESS WIRE)--Cornami’s break-through computing architecture is able to scale performance without penalties to deliver real-time computing for a number of critical and complex applications. The company’s proprietary technology reduces the use of power sources and lowers latency, while vastly increasing the compute performance for today’s massive datasets, whether at the edge or the cloud. This most notably includes accelerating Fully Homomorphic Encryption (FHE) for real-time computing on encrypted data sets, which is especially vital for cloud security.
FHE has long been described as transformative for data privacy and cloud security. This post von-Neumann algorithm was developed to enable computing on encrypted data sets while keeping the underlying data secure. In other words, assume that computing environments are compromised; so, secure the data.
Enabling FHE is a game-changer in cloud computing as it allows for extracting valuable data analytics without ever decrypting the data to expose the underlying plaintext data, whether it is sensitive intellectual property (IP), financial information, personally identifiable information (PII), intelligence insight, or beyond. FHE is a significant and critical technology for enterprise, industry, fintech, healthcare, academia and governments given the cost and damage associated with the growing number of cybercrimes and breaches at the trillions-of-dollars level. However, the challenge to date has been that FHE too computationally intensive to be commercially practical – until Cornami.
Paul Master, co-founder and CTO of Cornami, is speaking at the Linley Processor Event on October 22 and will be disclosing Cornami’s unique, scalable TruStream reconfigurable computational fabric that is a key ingredient of its innovative architecture. The company has achieved over 90 issued patents supporting its next-generation fully programable software-defined technology.
Data Is the New Oil - Next Generation Machine Learning (ML)
The value of analytics and data-driven insights are undeniable, and it has been coined by many that “Data is the New Oil.” So, what if a company could use your data without ever having direct access to it? FHE makes it possible to analyze or manipulate encrypted data without revealing the data to anyone. This facilitates secure information-sharing across authority boundaries without sacrificing the confidentiality and privacy of the data, delivering tremendous value to multiple markets including fintech, healthcare, mega-web, smart cities, governments and more, while supporting next-generation Machine Learning (ML) encrypted neural networks.
“In my role as CEO Emeritus at Mentor Graphics, I have been asked to speak at a number of events worldwide on AI and ML, as well as other semiconductor trends,” stated Dr. Walden ”Wally” Rhines, president and CEO of Cornami. “Of course, AI continues to drive a great deal of excitement and hype in technology and financial circles with analysts predicting it will drive trillions of dollars in spending and value creation during the coming decades. However, in order to achieve value from the data that drives these markets, the industry needs to address data security.
Massive security breaches bring regulatory pressure to restrict data collection and cloud-based information with the realization that regardless of effort, there are attack points at multiple levels, including risk from employees and/or consultants. FHE ushers in a new era, whereby encrypted data can be collected and built into encrypted machine learning models. Encrypted queries can be made to these models and the encrypted results returned to the user generating the query. The data is never revealed; it can be sold and/or otherwise shared again and again. Many have heralded this revolution as “Data Is the New Oil” because of the ability to protect and reuse the data with FHE.”
“In my research of this market for the government, it appeared that delivering FHE in real-time was at least a decade away,” added Rhines. Cornami’s unique architecture has achieved a milestone in its work with a market partner to validate the 106 performance required for real time performance, bringing FHE eight-to-ten years forward. It is a game-changer for cloud security and the reason I decided to join the company as its CEO and president.”
“Computing requirements have dramatically changed since the von Neumann era that still underlies current conventional processors,” stated Paul Master, co-founder and CTO of Cornami. “FHE and next-generation machine learning with encrypted neural nets require a different architecture design in order to meet requirements. This is why we built a ground- up new architecture, beginning with a unique software programming model. This software defines our TruStream computational fabric that can dynamically reconfigure the processing cores to best match the algorithm for the highest efficiency. Each core is independently programmable and can dynamically scale from thousands to millions of cores to deliver real-time computing without incurring penalties with regards to power consumption, latency and cost.”
Cornami is currently working with strategic partners for FHE and other ML driven markets, such as autonomous systems and vehicles, as well as robotics, sensors, and image detection. It is expanding its early customer access program. The company will release further details shortly.
About CORNAMI
Cornami is focused on the deployment of intelligent computing in real-time environments. The company has developed a scalable and massively parallel-processor architecture to address the shift in computing needs for the ever-increasing massive data sets of today, and into the future. This game-changing, software-defined technology delivers unprecedented scalability from thousands of cores on a single chip to millions across a system. All individually programmable. Cornami empowers developers, large enterprise, IoT, and edge-to-cloud computing to deliver high performance anywhere and on any device at the lowest power and latency. www.cornami.com