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