Find IP Sell IP AI Assistant Chip Talk About Us
Log In

Quadric

Quadric is a forefront player in the development of processor architectures optimized for AI computing on devices. Their flagship product is the Chimera general-purpose neural processing unit (GPNPU), renowned for delivering exceptional machine learning inference performance. Unlike traditional processors, the Chimera GPNPU is designed to handle complex C++ code and machine learning models seamlessly, without the need to divide tasks among various processors. This design allows for efficient execution of classic machine learning models, vision transformers, and large language models, ultimately streamlining development processes for SoC designers and speeding up the integration of new ML models. The scalability of the Chimera GPNPU extends from 1 to 864 TOPs, catering to diverse application needs and incorporating a safety-enhanced version for automotive designs. This flexibility is invaluable, enabling developers to optimize performance and adapt to changing demands across different market segments. Quadric aims to simplify SoC design and boost productivity in algorithm development by providing a unified platform that merges matrix, vector, and scalar operations within a single execution pipeline. Quadric also offers a suite of tools including the Chimera SDK and DevStudio, facilitating the development, simulation, profiling, and deployment of applications on the Chimera GPNPU. With these tools, developers can leverage world-class compilers and visualization features to effectively manage SoC design choices. Additionally, Quadric provides insights and support to streamline the integration of new models and continue delivering cutting-edge solutions in various fields, particularly the automotive industry, where long product life cycles and evolving safety standards are key considerations. Read more

Is this your business? Claim it to manage your IP and profile

2
IPs available

Chimera GPNPU

The Chimera GPNPU by Quadric redefines AI computing on devices by combining processor flexibility with NPU efficiency. Tailored for on-device AI, it tackles significant machine learning inference challenges faced by SoC developers. This licensable processor scales massively offering performance from 1 to 864 TOPs. One of its standout features is the ability to execute matrix, vector, and scalar code in a single pipeline, essentially merging the functionalities of NPUs, DSPs, and CPUs into a single core. Developers can easily incorporate new ML networks such as vision transformers and large language models without the typical overhead of partitioning tasks across multiple processors. The Chimera GPNPU is entirely code-driven, empowering developers to optimize their models throughout a device's lifecycle. Its architecture allows for future-proof flexibility, handling newer AI workloads as they emerge without necessitating hardware changes. In terms of memory efficiency, the Chimera architecture is notable for its compiler-driven DMA management and support for multiple levels of data storage. Its rich instruction set optimizes both 8-bit integer operations and complex DSP tasks, providing full support for C++ coded projects. Furthermore, the Chimera GPNPU integrates AXI Interfaces for efficient memory handling and configurable L2 memory to minimize off-chip access, crucial for maintaining low power dissipation.

Quadric
All Foundries
All Process Nodes
AI Processor, AMBA AHB / APB/ AXI, CPU, DSP Core, GPU, Multiprocessor / DSP, Processor Core Dependent, Processor Core Independent, VGA, Vision Processor
View Details

Chimera SDK

The Chimera SDK by Quadric is a powerful toolkit designed to foster the development and deployment of applications on the Chimera GPNPU. This comprehensive platform enables developers to blend traditional C++ code with modern machine learning graphs, ensuring seamless implementation across diverse datasets. Available through both cloud and on-premise installation, the SDK provides the flexibility needed for extensive development environments. Key to the Chimera SDK is its Graph Compiler, which transforms machine learning models into efficient C++ code. The compiler optimizes graph structure, simplifies operators, and ensures compatibility with Chimera hardware by using the Chimera Compute Library. Such optimizations facilitate smooth integration of ML models with traditional signal processing routines, enhancing performance and functionality. Accompanying the SDK is the Chimera LLVM C++ Compiler, which utilizes the latest LLVM compiler infrastructure to generate Chimera-specific machine code. It is aided by the Chimera Instruction Set Simulator, allowing developers to profile and tune the application code within their own systems. This holistic development environment minimizes the typical complexity associated with multiple ecosystems, streamlining operations for hardware and software developers alike.

Quadric
AI Processor, Multiprocessor / DSP, Processor Core Independent, Vision Processor
View Details
Sign up to Silicon Hub to buy and sell semiconductor IP

Sign Up for Silicon Hub

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!

Switch to a Silicon Hub buyer account to buy semiconductor IP

Switch to a Buyer Account

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.

Add new company

Switch to a Silicon Hub buyer account to buy semiconductor IP

Create a Buyer Account

To evaluate IP you need to be logged into a buyer profile. It's free to create a buyer profile for your company.

Review added

Claim Your Business

Please enter your work email and we'll send you a link to claim your business.

Review added

Claim Email Sent

Please check your email for a link you can use to claim this business profile.

Chatting with Volt