Skip to content

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 interfacing.

xDSL: A Python-native compiler design toolkit providing SSA-based IRs and APIs to define, assemble, and optimise custom compilers and DSLs.

OML-vect: An open-source vectorisation and optimisation tool built on ONNX-MLIR that transforms machine-learning models into efficient, hardware-aware vectorised code for high-performance execution (GitHub and Docker).

HADES – Automated Hardware Design Exploration for Cryptographic Primitives: An open-source framework for automated security testing and analysis of hardware and embedded systems, supporting systematic evaluation of vulnerabilities and attack surfaces.

Myrtle: A Tiling Cost Model for the Snitch Cluster

CAIF: Fusion-aware Instruction scheduler