Generated by All in One SEO v4.9.10, this is an llms.txt file, used by LLMs to index the site.

# CONVOLVE

Seamless design of Smart Edge Processors

## Sitemaps

- [XML Sitemap](https://convolve.eu/sitemap.xml): Contains all public & indexable URLs for this website.

## Pages

- [Home](https://convolve.eu/) - CONVOLVE enforces Europe's position in the design and development of smart edge processors and ensure it becomes a dominant player in the global market.
- [DELIVERABLES](https://convolve.eu/deliverables/) - CONVOLVE DELIVERABLES This list corresponds to the list of public CONVOLVE deliverables, over the 3 year project. Dates and titles will be updated as needed.
- [SCIENTIFIC PUBLICATIONS](https://convolve.eu/scientific-publications/) - CONVOLVE SCIENTIFIC PUBLICATIONS 1. Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge Rutishauser, G., Conti, F. and Benini, L., 2023, June. Free bits: Latency optimization of mixed-precision quantized neural networks on the edge. In 2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS) (pp. 1-5). IEEE. Abstract: Mixed-precision quantization, where a
- [DEMOS](https://convolve.eu/demos/) - CONVOLVE Demos 1. Denoising with Early Exit Denoising with Early Exit This repository contains the point demo for the GNA use-case of speech enhancement using early-exiting neural networks. Try the demo Additional information This work was carried out collaboratively by two partners UIR and GNA.The demo was produced by Alaa Zniber (UIR). 2. Efficient Hyperspectral Imaging
- [TOOLS & DESIGNS](https://convolve.eu/tools/) - CONVOLVE TOOLS & DESIGNS 1. ZigZag: An open source performance estimation and optimization framework for single core AI accelerators. 2. Stream: An open source performance estimation, scheduling and optimization framework for multi-core AI accelerators. 3. SNAX: An open source template for Accelerator integration into a multi-core AI fabric, with efficient yet flexible memory interfacing. 4. xDSL:
- [WHO WE ARE](https://convolve.eu/who-we-are/) - CONVOLVE WHO WE ARE CONVOLVE consortium consists of 18 partners from academia and industry with strong complementary competencies in different levels of design hierarchy. Technische Universiteit Eindhoven (Project Coordinator) The main role of TU/e is the project coordination (WP9), but also has major contributions in WP3, developing research and design composable real-time platforms and associated modelling,
- [EVENTS](https://convolve.eu/events/) - CONVOLVE EVENTS External CONVOLVE at DATE 202622 April 2026, Verona, Italy The CONVOLVE project was presented at the Design, Automation and Test in Europe Conference (DATE) 2026. In the session “From Physical Tamper Detection to AI-Assisted Trust Verification”, Adrian Marotzke (NXP Semiconductors) presented the paper “The PMP Snapshot Engine: Fast and Fault-Resilient PMP Reconfiguration for RISC-V”,
- [OUTPUTS](https://convolve.eu/outputs/) - CONVOLVE OUTPUTS Materials CONVOLVE Brochure 2024 CONVOLVE Flyer 2024 Tools ZigZag: An open source performance estimation and optimization framework for single core AI accelerators Stream: An open source performance estimation, scheduling and optimization framework for multi-core AI accelerators SNAX: An open source template for Accelerator integration into a multi-core AI fabric, with efficient yet flexible memory
- [COMUNICATION MATERIALS](https://convolve.eu/comunication-materials/) - CONVOLVE COMUNICATION MATERIALS CONVOLVE Brochure 2024 CONVOLVE Flyer 2024
- [WHO WE ARE #3](https://convolve.eu/who-we-are-2/) - CONVOLVE WHO WE ARE CONVOLVE consortium consists of 18 partners from academia and industry with strong complementary competencies in different levels of design hierarchy. Technische Universiteit Eindhoven (Project Coordinator) The main role of TU/e is the project coordination (WP9), but also has major contributions in WP3, developing research and design composable real-time platforms and associated modelling,
- [WHAT WE DO](https://convolve.eu/what-we-do/) - CONVOLVE WHAT WE DO CONVOLVE enforces the EU’s position in the design and development of smart edge-processors, such that it can become a dominant player in the global edge processing market. With the rise of deep learning (DL), our world braces for Artificial Intelligence (AI) in every edge device, creating an urgent need for edge-AI processing
- [WORK PACKAGES](https://convolve.eu/work-packages/) - CONVOLVE WORK PACKAGES To achieve the CONVOLVE objectives, a 36-month work plan has been carefully designed based on seven strongly interrelated technical (WP 1-7) and two non-technical work packages (WPs 8 and 9). WP1: Use case and application requirements, metrics, and baseline establishes the edge application use cases. They set the requirements needed for smart edge
- [CONTACT](https://convolve.eu/contact/) - CONVOLVE CONTACT Get in contact with us for any questions regarding the CONVOLVE project!
- [Terms and conditions](https://convolve.eu/terms-and-conditions/) - CONVOLVE Terms and Conditions All rights reserved. All logos are fully subject to the copyright of the holders/sources and are not to be employed for personal purposes, of any kind, by users of this information service. Any use for personal purposes requires the express consent of the holder. Attribution is also required to the authors and
- [Privacy Policy](https://convolve.eu/privacy-policy/) - CONVOLVE Privacy Policy Introduction This Privacy Notice will inform you as to how the CONVOLVE Consortium (hereinafter referred to as the “Consortium”, “we”, “us” and “our”) collects and processes information about you and in particular your personal data. We hereby assure you that this Privacy and Personal Data Protection Policy (“Policy”) fully respects and complies with
- [Cookies Policy](https://convolve.eu/cookie-policy/) - CONVOLVE Cookies Policy In order to make your visits to our project Site as pleasant as possible, the Convolve Consortium uses cookies. These cookies automatically track and collect certain technical information that your browser sends to us. This information might include Internet protocol (IP) addresses, the browser type, browser language, Internet service providers (ISP), referring/exit pages,