by Mira Steinmetz | Jul 20, 2026 | 2026, News
Release: emmtrix Studio Version 2026.07 July 20, 2026 emmtrix Studio 2026.07 is now available. Highlights include: The new emmtrix Edge AI Compiler, designed to bring AI models to embedded edge devices. It automatically applies target-specific code transformations and...
by Mira Steinmetz | Jul 16, 2026 | 2026, News
Inference Runtime or Generated C Code? July 16, 2026 Your ONNX model passes validation.Now you need to make it part of the embedded application. Do you add an inference runtime or generate C code that you can build, inspect, debug, and maintain with the rest of your...
by Mira Steinmetz | Jun 30, 2026 | 2026, News
ONNX Community Meetup 2026: Lessons Learned Building an ONNX-to-C Compiler June 30, 2026 The recording of Dr. Timo Stripf’s presentation at the ONNX Community Meetup 2026 is now available on YouTube. The talk shares lessons learned from building an ahead-of-time...
by Mira Steinmetz | Jun 3, 2026 | 2026, News
New One-Page Overview: emmtrix Edge AI Compiler June 03, 2026 What happens between ONNX and target-aware C code? We have summarized the emmtrix Edge AI Compiler workflow in a compact one-page overview. It shows how AI models are transformed for embedded deployment...
by Mira Steinmetz | May 21, 2026 | 2026
Generic Code Rarely Uses Target Hardware Well emmtrix Tech PostsCategory: emmtrix Edge AI Compiler The same AI logic can behave very differently across embedded architectures. AURIX TC4x PPU, ARM Neon/SVE, RISC-V RVV, and x86 AVX expose different ways to use vector...
