This startup develops a parallel computing intellectual property that enhances CPU performance while maintaining full backward compatibility with existing processors and applications. By enabling processor manufacturers to streamline control and common components, the technology addresses inefficiencies in scaling parallelism in personal computing devices and smartphones.
Funding
$4.3M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.



BVFounders
Product
Problem
Modern CPUs face performance bottlenecks due to limitations in parallel processing, hindering advancements in computationally intensive applications such as AI, edge computing, and cloud technologies. Existing approaches to improve CPU performance offer incremental gains, failing to meet the increasing demand for processing power.
Solution
Flow Computing offers a Parallel Processing Unit (PPU) architecture that enhances CPU performance by enabling efficient parallel computing. The PPU is designed to integrate with existing CPU architectures, providing a performance boost without requiring significant changes to the underlying hardware. Flow Computing's technology includes a compiler ecosystem that balances performance gains with backward compatibility, allowing developers to leverage the PPU's capabilities while maintaining support for legacy code. The PPU architecture aims to improve performance in various applications, including AI, edge computing, data centers, and embedded systems.
Target Audience
Flow Computing's primary customers are CPU vendors and manufacturers looking to enhance the performance of their processors for applications requiring high computational power.
Features
- Parallel Processing Unit (PPU) architecture designed for integration with existing CPUs
- Compiler ecosystem to optimize code for parallel processing while maintaining backward compatibility
- Potential for up to 100x performance increase in CPU throughput
- Compatibility with various CPU architectures and process geometries
- Applications in AI, edge computing, data centers, and embedded systems