Quadric’s Chimera general-purpose neural processor executes complete AI/ML graphs—all layers, including pre- and post-processing functions traditionally run on separate DSP processors. To enable this, the Chimera Graph Compiler processes and optimizes a combination of NN graphs, Python code and C++ kernels into a single optimized executable. In this talk, we’ll present an overview of Quadric’s Chimera Graph Compiler, including compilation of ONNX graphs and Python code into C++ representations targeting Chimera. We’ll show examples of fully automated graph conversion and explain the custom operator creation flow. We’ll show how this advanced toolchain addresses the challenges faced by developers when implementing the full signal chain. Instead of piecemeal compilation of signal conditioning, NN graphs and post-processing via three separate SDKs—requiring the developer to integrate and tune the final code—the Chimera tools merge and optimize these closely related computations using multi-operation fusion, yielding greater programmer productivity and superior results.