Inside the M4 Apple Neural Engine, Part 1: Reverse Engineering
maderix.substack.com · 1,909 words · saved by 1 readers
How we bypassed CoreML and talked directly to the hardware
Inside the M4 Apple Neural Engine, Part 1: Reverse Engineering How we bypassed CoreML and talked directly to the hardware manjeet singh Feb 28, 2026 147 11 20 Share A note on “we”: Throughout this series, “we” refers to maderix (human) and Claude Opus 4.6 (by Anthropic) working as a pair. The reverse engineering, benchmarking, and training code were developed collaboratively — human intuition driving the exploration, AI reasoning through the data and writing the analysis. We think this kind of human–AI collaboration is a new and natural way to do systems research: one partner as the architect
related reading
- Apple Neural Engine: Architecture, Programming, and Performancearxiv.org
- A friendly introduction to machine learning compilers and optimizershuyenchip.com
- Inside NVIDIA GPUs: Anatomy of high performance matmul kernels - Aleksa Gordićaleksagordic.com
- Jane Street Blog - Can you reverse engineer our neural network?blog.janestreet.com
- MatX: High-throughput chips for LLMsmatx.com
- Non_Interactive – Software & MLnonint.com
- PiTorch: ML on Baremetal Raspberry Pis | projectsmasonjwang.com
- The Short Case for Nvidia Stock | YouTube Transcript Optimizeryoutubetranscriptoptimizer.com
- Meta harness makes 10 times better Kimi K3 chipluoluo.ai
- Notes • Nick Arnernickarner.com
- Mixture-of-Kittens: our open-source MoE megakernel for NVL72scursor.com
- GitHub - JustVugg/colibri: Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦github.com