Skip to main content
S

SEMIBRAIN

SEMIBRAIN offers standard logic-based embedded Non-Volatile Memory (NVM) IP for simplified System-on-Chip (SoC) integration, reducing development time and fabrication costs. Their solutions also include processing-in-memory (PiM) technologies for energy-efficient AI acceleration.

Updated 2 months ago

Funding

Funding not disclosed

Funding rounds are not available yet.

Founders

Founder details are not available yet.

Product

Problem

Semiconductor companies face challenges in integrating non-volatile memory (NVM) into their System-on-Chip (SoC) designs, leading to increased development time and costs. The need for specialized memory IP that is both cost-effective and scalable for embedded applications is a significant hurdle in accelerating time-to-market for advanced semiconductor products.

Solution

SEMIBRAIN provides standard logic-based embedded NVM IP designed for seamless integration into SoCs. Our technology leverages a standard logic process, simplifying the manufacturing flow and reducing fabrication costs. This approach enables faster design cycles and accelerates the market entry of semiconductor devices requiring embedded flash memory. We also focus on processing-in-memory (PiM) technologies that integrate computation directly within memory macros, enhancing energy efficiency for AI acceleration.

Target Audience

Our primary customers are semiconductor companies and fabless design houses developing SoCs for various applications, including AI acceleration and embedded systems.

Features

  • Standard logic compatible embedded flash memory IP for simplified SoC integration.
  • Proprietary technology enabling low-power operation during idle states and extended memory lifetime.
  • Embedded flash memory IP integrated into compute-in-memory macros for energy-efficient AI acceleration.
  • Processing-in-memory (PiM) solutions leveraging charge-storage mechanisms for enhanced computational efficiency.
  • US Patent 11,862,227 granted for standard logic-compatible embedded flash memory IP.
  • Development of machine learning accelerator semiconductor chips based on RISC-V architecture.
This profile is AI-generated and may contain inaccuracies.