Is this your business? Claim it to manage your IP and profile
The Quadric Chimera General Purpose Neural Processing Unit (GPNPU) delivers unparalleled performance for AI workloads, characterized by its ability to handle diverse and complex tasks without requiring separate processors for different operations. Designed to unify AI inference and traditional computing processes, the GPNPU supports matrix, vector, and scalar tasks within a single, cohesive execution pipeline. This design not only simplifies the integration of AI capabilities into system-on-chip (SoC) architectures but also significantly boosts developer productivity by allowing them to focus on optimizing rather than partitioning code. The Chimera GPNPU is highly scalable, supporting a wide range of operations across all market segments, including automotive applications with its ASIL-ready versions. With a performance range from 1 to 864 TOPS, it excels in running the latest AI models, such as vision transformers and large language models, alongside classic network backbones. This flexibility ensures that devices powered by Chimera GPNPU can adapt to advancing AI trends, making them suitable for applications that require both immediate performance and long-term capability. A key feature of the Chimera GPNPU is its fully programmable nature, making it a future-proof solution for deploying cutting-edge AI models. Unlike traditional NPUs that rely on hardwired operations, the Chimera GPNPU uses a software-driven approach with its source RTL form, making it a versatile option for inference in mobile, automotive, and edge computing applications. This programmability allows for easy updating and adaptation to new AI model operators, maximizing the lifespan and relevance of chips that utilize this technology.
The Chimera Software Development Kit (SDK) from Quadric offers a comprehensive environment for the development of complex applications targeting the Chimera GPNPU. Designed to ease the process of leveraging the full potentials of Quadric's cutting-edge processor architecture, the Chimera SDK combines traditional C++ code with AI models to streamline the deployment of machine learning workloads. The SDK supports preparing AI and ML models for execution without necessitating any proprietary modifications, thereby preserving the natural flow of data and operations. One of the standout features of the Chimera SDK is its facility to enable seamless integration of ONNX-based AI graphs with C++ code, making it an ideal tool for developers looking to optimize AI solutions across different data processing needs. This integration ensures that a wide spectrum of machine learning and traditional algorithms can be executed efficiently on a single processor core, eliminating the need for multi-core or multi-processor dependencies. This SDK empowers users with tools to compile, simulate, profile, and deploy AI models in a flexible yet robust environment. The Chimera SDK includes the advanced Chimera Graph Compiler (CGC) and the LLVM C++ Compiler, both crucial for optimizing AI and traditional workloads. With capabilities such as graph simplification, memory optimization, and code generation tailored specifically for Chimera's architecture, developers can achieve higher levels of performance optimization for their applications. This SDK not only enhances productivity but also extends the flexibility to adapt model changes long after initial SoC deployment, ensuring the sustainability and longevity of integrated AI solutions.
Kyocera Document Solutions licenses Quadric's semiconductor IP, enabling advanced system-on-a-chip designs for next-generation printing devices. Read more
Exploring the challenges and solutions in connecting AI accelerators across diverse domains using discussions from industry experts. Read more
Delve into the challenges and solutions for ensuring semiconductor IP remains adaptable in the face of rapidly evolving AI models and software. Read more
Kyocera partners with Quadric to power AI in next-gen processors with Chimera GPNPU, enhancing edge devices for smart cities and factories with efficient AI processing. Read more
Join the world's most advanced semiconductor IP marketplace!
It's free, and you'll get all the tools you need to discover IP, meet vendors and manage your IP workflow!
No credit card or payment details required.
Join the world's most advanced AI-powered semiconductor IP marketplace!
It's free, and you'll get all the tools you need to advertise and discover semiconductor IP, keep up-to-date with the latest semiconductor news and more!
Plus we'll send you our free weekly report on the semiconductor industry and the latest IP launches!
To evaluate IP you need to be logged into a buyer profile. Select a profile below, or create a new buyer profile for your company.