FracTLcore® Compute Fabric

Next-Generation Intelligent Computing

Cornami’s break-through FracTLcore® computing architecture can scale performance without penalties to deliver real-time computing for several critical and complex applications. The company’s proprietary technology reduces the use of power sources and lowers latency, while vastly increasing the computing performance for today’s massive datasets, whether at the edge or in the cloud. This includes, most notably, accelerating Fully Homomorphic Encryption (FHE) for real-time computing on encrypted data sets, which is vital for data privacy and cloud security.

“Cornami has developed a new architecture that breaks the bottleneck of traditional CPU and GPU designs to enable tremendous scalability and flexibility. This architecture can be applied to many end applications but is particularly effective for applications that require enormous compute power and handle copious data sets.”

Linley Gwennap

Principal analyst at The Linley Group and editor-in-chief of Microprocessor Report

Encrypted Computing at Scale

Solving today’s critical data privacy and security problems requires advanced solutions. Fully Homomorphic Encryption (FHE) and Artificial Intelligence (AI) are being deployed to support ever-increasing data sets. Keeping data encrypted “in use” presents new opportunities to extract valuable insights while protecting data privacy in highly regulated markets.

Cornami’s breakthrough FracTLcore Computing Fabric seamlessly scales from thousands of cores on a single chip to millions of cores across systems, transparent to the software. This delivers a “reboot” to the computing industry to scale performance without penalties.

Cornami’s unique technology can scale to deliver real-time computing with low power consumption, latency, and cost; delivering the highest silicon efficiency.

How Fast Do You Want to Go?

Scale to deliver real-time Fully Homomorphic Encryption (FHE) for quantum-secure privacy-preserving computing on encrypted data sets vital for cloud security.

Process privacy-preserving machine learning (PPML) models using data from multiple owners without ever exposing the underlying plaintext data.

  • Data owners maintain control of their decryption key.
  • Data privacy, confidentiality, and control are all preserved.

Dial the size of the FracTLcore Computing Fabric up or down to meet performance vs. cost requirements.

  • Add additional systems for penalty-free linear scaling up to 64 million cores.

Unique FracTLcore Computing Fabric Technology

  • Share-nothing Architecture – avoids bottlenecks inherent in legacy computing architectures.
  • Massively Parallel – supports all forms of parallelism without restriction (SIMD, MIMD, Data Flow, Pipelining, Systolic, MapReduce, etc.)
  • Streaming processing – Streaming data architecture fully exploits all the parallelism and pipelining available within the application domain.

Mother Nature

The human brain is the most amazing information-processing system in the world. Mother Nature has been perfecting it for about a billion years. After much trial and error, She has settled on streams, pipelining, parallelism and asynchrony.

The FracTLcore Architecture

  • Stream-centric rather than thread-centric
  • Pipelining is automatic and pervasive
  • Can express all forms of parallelism
  • Operates asynchronously

Separation of Concerns

In computer science, separation of concerns (SoC) is a design principle for separating a computer program into distinct sections, such that each section addresses a separate concern .

In the TruStream Programming Model, that means separating a program into two domains:

  • Thread Domain
  • Stream Domain
Scroll to Top