About

Quadric simplifies the design and programming of System on Chips (SoCs) specifically for machine learning applications. Their main product, the Chimera General-Purpose Neural Processing Unit (GPNPU), combines matrix and vector operations with scalar control code in one execution pipeline. This integration allows developers to avoid splitting application code across different processors, making the development process more efficient. Quadric primarily targets clients in the semiconductor industry, including SoC developers and manufacturers, who need to improve their machine learning capabilities. Unlike competitors, Quadric offers a complete solution that includes both hardware and software tools, such as the Chimera LLVM C Compiler and Instruction Set Simulator, enabling developers to design, simulate, and deploy their applications seamlessly. The goal of Quadric is to enhance the performance and ease of development for machine learning applications on SoCs.

Simplify's Take

What believers are saying

• Quadric's recent Series B funding round, raising an additional $10M, provides significant financial resources to expand their commercial and engineering teams.
• Strategic partnerships with companies like Ams Osram enhance Quadric's capabilities in edge-based smart sensing solutions, opening new market opportunities.
• The introduction of the Quadric Developer Studio offers a collaborative development environment, further simplifying the design and programming of SoCs for ML applications.

What critics are saying

• The highly competitive semiconductor industry requires Quadric to continuously innovate to maintain its edge.
• Dependence on strategic partnerships, such as with Ams Osram, could pose risks if these collaborations face challenges or dissolve.

What makes Quadric unique

• Quadric's Chimera GPNPU uniquely integrates matrix, vector, and scalar operations in a single execution pipeline, eliminating the need for partitioning application code between different processors.
• The ability to run any code written in C makes Chimera highly versatile and powerful for implementing new neural network operations, unlike many specialized processors.
• Quadric's comprehensive solution, including the Chimera LLVM C Compiler and Instruction Set Simulator, streamlines the entire ML application development process.

Help us improve and share your feedback! Did you find this helpful?

YesNo