• Democratizing Hardware Design

    The OpenROAD project attacks the barriers of Cost, Expertise and Uncertainty (i.e., Risk) that block the feasibility of hardware design in advanced technologies.

    READ MORE

  • DARPA is reimagining U.S. Electronics

    OpenROAD is centered on digital SOC layout generation ("RTL-to-GDSII"), and is part of the broader DARPA IDEA program and Electronics Resurgence Initiative which seek to transform the design of hardware systems.

    READ MORE

  • 24 Hours, No Humans in the Loop

    OpenROAD aims to develop tools that adapt, self-tune, and never get stuck unexpectedly.

    READ MORE
OpenROAD_EDAOpenROAD@OpenROAD_EDA·
2 Dec

New: OpenROAD RTL-to-GDS v1.0 Expectations
We are pleased to provide a document with expectations regarding the OpenROAD RTL-to-GDS v1.0 flow for prospective users: https://buff.ly/2R9gurW

Have comments you want to share with us? Please, add them here: https://buff.ly/35QnON3

Reply on Twitter 1201433357529309185Retweet on Twitter 12014333575293091855Like on Twitter 12014333575293091856Twitter 1201433357529309185
Load More...

OpenROAD

The Problem

Our Goal

  • 24-hour, No-Human-In-The-Loop layout design for SOC, Package and PCB with no Power-Performance-Area (PPA) loss
  • Tapeout-capable tools in source code form, with permissive licensing → seed future “Linux of EDA”

Our Approach

  • No Humans: tools must adapt and self-tune, must never get stuck unexpectedly
  • 24 hours: extreme partitioning of problems
    • parallel search on cloud
    • machine learning for predictability
  • Mantra: Correctness and safety by construction
  • Mantra: Embrace freedom from choice
  • Mantra: Often, only one thread needs to succeed

Impact

  • Create new “Base Technologies” that enable 24-hour, autonomous design
    • Extreme partitioning (bite-sized problems)
    • Parallel search and optimization
    • Machine learning: models of tools, designs
  • New paradigm for design tools and methods: autonomy first
  • Bring down barriers to democratize HW design
  • Embedded vision chips (28nm/16nm) from Michigan Internal Design Advisors team
    • Layout @Michigan: 10+ weeks, significant resource
  • OpenROAD and IDEA goal: 1 day, no humans (!)

Team