CGRA-Flow is an integrated framework for CGRA compilation, exploration, synthesis, and development.
-
Updated
Jun 17, 2026 - Python
CGRA-Flow is an integrated framework for CGRA compilation, exploration, synthesis, and development.
A portable framework to map DFG (dataflow graph, representing an application) on spatial accelerators.
Dynamically Reconfigurable Architecture Template and Cycle-level Microarchitecture Simulator for Dataflow AcCelerators
Advanced PSP Media Engine library providing access to the ME's native core functions, and to the VME, facilitating integration and usage in homebrew projects.
DRA+RISC-V Exploration Framework
PSP Media Engine's Cracking the Unknown: The Virtual Mobile Engine (VME), the specialized move instructions, bitstream/context, and local DMACs, as well as the VLD unit and H.264 decoder
A low power platform based on X-HEEP and integrating the ESL-CGRA
Application Mapping Framework for spatially mapping CGRAs using Genetic Algorithm
A static dataflow CGRA with dynamic dataflow execution capability
Repository created for "Computação Gráfica" - CGRA
Code examples demonstrating how to use Sony's Virtual Mobile Engine 2 (VME2) and take advantage of this reconfigurable CGRA, plus a `me-custom-core` extension library to ease VME use in homebrew.
Add a description, image, and links to the cgra topic page so that developers can more easily learn about it.
To associate your repository with the cgra topic, visit your repo's landing page and select "manage topics."