Chimera Compute Library (CCL) API

The Chimera Compute Library (CCL) application programming interface (API) makes it possible to write high-performance, data-parallel algorithms targeting Quadric's Chimera General-Purpose Neural Processing Unit (GPNPU) cores.

Quadric recognizes that introducing a new architecture with a new programming model can initially be a daunting task for a developer. One of the key goals behind the design of the Chimera GPNPU architecture is to make it possible to write performant code with ease.

1. Overview of GPNPU Architecture
2. GPNPU Programming Model
3. Tutorial: Creating a Simple Kernel
4. Tutorial: Writing a Kernel in C++ API