Skip to content

Design a Many-Accelerator SoC

Run many accelerators concurrently with the ESP software API

Open the guide

Many-accelerator demonstration with the ESP monitors and run-time reconfigurable cache coherence for accelerators:

What you will learn

  • Create a multi-accelerator instance of ESP
  • Use the ESP software API to configure a multi-accelerator application
    • run-time coherence reconfiguration
    • concurrent execution
    • point-to-point communication

Many-accelerator SoC workflow

What you will need

What you can read

ESP4ML: Platform-Based Design of Systems-on-Chip for Embedded Machine Learning

Davide Giri, Kuan-lin Chiu, Giuseppe Di Guglielmo, Paolo Mantovani, Luca P. Carloni

(Best Paper Nominee) Design, Automation and Test in Europe Conference (DATE), 2020

Paper Slides Video Tutorial

Runtime Reconfigurable Memory Hierarchy in Embedded Scalable Platforms

Davide Giri, Paolo Mantovani, Luca P. Carloni

(Invited) Asia and South Pacific Design Automation Conference (ASPDAC), 2019

Paper Slides

What you can contribute

The ESP team welcomes external contributions and collaborations, including:

  • An improved user-level API for accelerator configuration and scheduling
  • Novel algorithms for run-time selection of the cache-coherence model in multi-accelerator applications

See the contributing guidelines.