diff --git a/demo/fsic2026/FSiC2026_OpenROAD_MCP_Abstract.md b/demo/fsic2026/FSiC2026_OpenROAD_MCP_Abstract.md new file mode 100644 index 0000000..bf361cd --- /dev/null +++ b/demo/fsic2026/FSiC2026_OpenROAD_MCP_Abstract.md @@ -0,0 +1,19 @@ +# OpenROAD MCP: Let AI Close Your Timing + +## Abstract + +Timing closure remains one of the most time-consuming aspects of digital design, often requiring engineers to manually analyze critical paths, iterate on SDC constraints, and repeatedly run the implementation flow. This talk introduces OpenROAD MCP, a Model Context Protocol server that enables AI assistants to interact directly with OpenROAD through natural language. + +OpenROAD MCP bridges large language models with the OpenROAD RTL-to-GDS flow using Linux pseudo-terminals (PTY) for authentic terminal emulation. The server exposes tools for session management, Tcl command execution, and design visualization, allowing engineers to query timing reports, analyze violations, and iterate on constraints conversationally. + +A key design feature is the permission-ask security model: safe commands execute immediately while potentially destructive operations require explicit user approval. This approach balances AI-assisted productivity with user control. + +This presentation demonstrates OpenROAD MCP through a practical timing closure workflow and discusses its applicability for engineers learning EDA tools, senior designers debugging complex designs, and researchers exploring AI-assisted hardware design. + +--- + +**Format:** 10 minutes (including questions) + +**Presenter:** Jack Luar + +**Keywords:** OpenROAD, MCP, AI, EDA, chip design, open source diff --git a/demo/fsic2026/FSiC2026_OpenROAD_MCP_Script.txt b/demo/fsic2026/FSiC2026_OpenROAD_MCP_Script.txt new file mode 100644 index 0000000..15f52e1 --- /dev/null +++ b/demo/fsic2026/FSiC2026_OpenROAD_MCP_Script.txt @@ -0,0 +1,291 @@ +================================================================================ +OPENROAD MCP: AI-POWERED CHIP DESIGN THROUGH MODEL CONTEXT PROTOCOL +Free Silicon Conference 2026 - Presentation Script +================================================================================ + +PRESENTER: Jack Luar +DURATION: ~7-8 minutes presentation + 2-3 minutes Q&A +TOTAL: 10 minutes + +================================================================================ +TIMING GUIDE +================================================================================ + +[00:00 - 00:45] Introduction & Problem Statement (Slides 1-2) +[00:45 - 01:30] Solution Overview (Slides 3-4) +[01:30 - 02:30] Architecture & Features (Slides 5-6) +[02:30 - 04:00] Demo & Security (Slides 7-8) +[04:00 - 05:00] Innovations & Use Cases (Slides 9-10) +[05:00 - 06:00] Roadmap & Call to Action (Slides 11-12) +[06:00 - 06:30] Summary & Questions (Slides 13-14) +[06:30 - 10:00] Q&A Session + +================================================================================ +FULL SCRIPT +================================================================================ + +-------------------------------------------------------------------------------- +[SLIDE 1: TITLE] - 15 seconds +-------------------------------------------------------------------------------- + +Good morning everyone. Thank you for having me at FSiC 2026. + +My name is Jack Luar, and today I'm excited to present OpenROAD MCP — a project +that bridges AI assistants with open-source chip design tools. + +-------------------------------------------------------------------------------- +[SLIDE 2: THE PROBLEM] - 30 seconds +-------------------------------------------------------------------------------- + +Here's a situation every VLSI engineer knows. + +You're staring at debug logs. 23 setup violations. WNS is -0.05 ns. The clock +period is 0.46 ns and the design just won't close. + +You already know the answer is probably in the constraints. But confirming that +means reading critical paths, estimating what the design can achieve, adjusting +the SDC, re-running the flow, and checking again. An hour of mechanical work to +answer a question you could have answered in thirty seconds if someone handed +you the right report. + +That's the loop I wanted to break. + +-------------------------------------------------------------------------------- +[SLIDE 3: THE SOLUTION] - 20 seconds +-------------------------------------------------------------------------------- + +That's exactly what OpenROAD MCP enables. + +It's a Model Context Protocol server that sits between AI assistants like Claude +or Gemini and the OpenROAD chip design flow. It allows natural language +interaction with your design tools. + +The best part? It's open source and works with any MCP-compatible AI client. + +-------------------------------------------------------------------------------- +[SLIDE 4: WHAT IS MCP?] - 25 seconds +-------------------------------------------------------------------------------- + +For those unfamiliar, the Model Context Protocol is a standardized way for AI +assistants to interact with external tools. It's developed by Anthropic and is +rapidly gaining adoption in the industry. + +Think of it as a universal adapter — once you build an MCP server, any +MCP-compatible AI can use it. The communication is JSON-RPC based, making it +language-agnostic and easy to integrate. + +-------------------------------------------------------------------------------- +[SLIDE 5: ARCHITECTURE] - 30 seconds +-------------------------------------------------------------------------------- + +Here's how OpenROAD MCP works under the hood. + +OpenROAD expects an interactive terminal. Using a plain subprocess pipe gives +you buffering issues, broken prompts, and unreliable output. Instead, we create +a PTY — a pseudo-terminal — for each session. OpenROAD sees a real terminal +and behaves exactly as it would in an interactive shell. + +Sessions persist across commands. You load LEF, then Liberty, then Verilog, +then SDC — building up design state exactly as you would manually. And the +SessionManager can hold multiple concurrent sessions, which matters for design +space exploration: run the same design with three SDC variants in parallel, +collect the results, pick the winner. + +-------------------------------------------------------------------------------- +[SLIDE 6: CORE FEATURES] - 20 seconds +-------------------------------------------------------------------------------- + +Let me quickly walk through the core features: + +You can create interactive OpenROAD sessions that persist across commands, +execute Tcl commands with configurable timeouts, visualize design reports like +placement and routing images, and manage multiple sessions simultaneously. + +Everything you'd normally do in OpenROAD, but now accessible through an AI +assistant. + +-------------------------------------------------------------------------------- +[SLIDE 7: EXAMPLE WORKFLOW] - 30 seconds +-------------------------------------------------------------------------------- + +Here's what the workflow looks like in practice. + +First, you create an interactive session. Then load your design with read_verilog. +Run synthesis, check timing with report_timing, and view the results — including +placement and routing images. + +This is all accessible through natural language. You tell the AI what you want +to do, and it translates that into the appropriate OpenROAD commands. + +The key insight is that sessions persist — you build up design state across +multiple commands, just like you would in an interactive OpenROAD shell. + +-------------------------------------------------------------------------------- +[SLIDE 8: SECURITY MODEL] - 45 seconds +-------------------------------------------------------------------------------- + +Now, you might be thinking: "This sounds dangerous. An AI executing commands on +my chip design?" + +That's a valid concern, and we've designed security as a first-class feature. + +We use a deny-by-default whitelist approach. Safe commands like report_timing, +get_cells, set_property — these execute immediately. But potentially dangerous +commands like exec, source, or exit — the AI has to ask for your explicit +confirmation before running them. + +We call this the "permission-ask" model. Instead of blocking outright, the AI +returns a message saying "I need your permission to run this command." This +balances security with usability — you stay in control while still getting +AI assistance. + +-------------------------------------------------------------------------------- +[SLIDE 9: UNIQUE INNOVATIONS] - 30 seconds +-------------------------------------------------------------------------------- + +What makes OpenROAD MCP unique? + +First, it's the first MCP server specifically designed for EDA and chip design. + +Second, we use true pseudo-terminal emulation, not just pipe-based I/O. This +means interactive programs that require real terminal behavior work correctly. + +Third, our permission-ask security model is innovative for AI agents. + +Fourth, we have deep integration with OpenROAD-flow-scripts, automatically +discovering designs and platforms. + +And fifth, it's production-ready with over 80% test coverage. + +-------------------------------------------------------------------------------- +[SLIDE 10: USE CASES / DEMO] - 30 seconds +-------------------------------------------------------------------------------- + +Let me show you a real use case: the GCD timing closure demo. + +The nangate45/gcd design ships with a 0.46 ns clock constraint that fails timing +out of the box — 23 setup violations, WNS is -0.05 ns, status FAILED. + +Using OpenROAD MCP, the AI loads the design, runs report_clock_min_period, and +finds the minimum achievable period is 0.51 ns. It recommends relaxing the +constraint to 0.52 ns. + +After the change: WNS is ~0.00 ns, only 4 negligible violations remain, and +timing PASSES. + +The full demo is available in the demo/orfs-gcd-timing/ directory in the repo. + +-------------------------------------------------------------------------------- +[SLIDE 11: ROADMAP] - 20 seconds +-------------------------------------------------------------------------------- + +What's next for OpenROAD MCP? + +For version 0.2, we're working on complete RTL-to-GDS flow orchestration, +design space exploration, and real-time monitoring during long runs. + +Looking further ahead, we plan machine learning integration for optimization +and multi-objective design exploration. + +-------------------------------------------------------------------------------- +[SLIDE 12: GET INVOLVED] - 15 seconds +-------------------------------------------------------------------------------- + +I encourage you to try it today. + +Installation is just a pip install. Use it with Claude Code or Gemini CLI. +The code is on GitHub, open source under Apache 2.0 license. + +Contributions and feedback are always welcome. + +-------------------------------------------------------------------------------- +[SLIDE 13: SUMMARY] - 15 seconds +-------------------------------------------------------------------------------- + +To summarize: + +OpenROAD MCP bridges AI assistants with chip design, provides a natural +language interface to OpenROAD, uses a security-first design, is production- +ready and open source. + +-------------------------------------------------------------------------------- +[SLIDE 14: QUESTIONS] - Transition to Q&A +-------------------------------------------------------------------------------- + +Thank you for your attention. I'm happy to take any questions. + +[PAUSE FOR Q&A] + +-------------------------------------------------------------------------------- +ANTICIPATED Q&A QUESTIONS & ANSWERS +-------------------------------------------------------------------------------- + +Q1: What OpenROAD versions are supported? +A1: We support OpenROAD 2.0 and later. The MCP server detects the version + automatically and adjusts behavior accordingly. + +Q2: Can this work with other EDA tools besides OpenROAD? +A2: The architecture is designed to be extensible. While we currently focus on + OpenROAD, the same pattern could be applied to other Tcl-based EDA tools + with minimal modifications. + +Q3: How does the PTY approach compare to simple pipe-based I/O? +A3: PTY emulation is essential for programs that check terminal properties, + like readline-based tools or programs that produce colored output. It also + handles interactive prompts correctly, which pipes cannot do. + +Q4: What's the performance overhead? +A4: Minimal. The async architecture and circular buffers keep overhead under + 5% for typical workloads. Session creation takes about 100-200ms. + +Q5: Is there support for remote OpenROAD instances? +A5: Currently, we support local OpenROAD instances. SSH tunneling or remote + execution is on the roadmap for v0.3. + +Q6: How do you handle long-running synthesis or routing jobs? +A6: Commands have configurable timeouts (default 30 seconds). For long jobs, + you can set longer timeouts or implement polling patterns using the + session inspection tools. + +Q7: What AI models work best with OpenROAD MCP? +A7: Claude 3.5+ and Gemini 2.0+ work excellently due to their strong + instruction following and code understanding. The MCP protocol is model- + agnostic, so any MCP-compatible client works. + +Q8: Can multiple users share the same MCP server? +A8: The current design is single-user per server instance. For multi-user + scenarios, we recommend running separate instances or implementing an + HTTP transport layer (planned for future releases). + +================================================================================ +PRESENTER NOTES +================================================================================ + +BEFORE THE TALK: +- Test laptop connection to projector +- Have backup PDF of slides +- Bring clicker/remote if available +- Test any live demo beforehand +- Have water nearby + +DURING THE TALK: +- Maintain eye contact +- Speak slowly and clearly +- Use hand gestures when explaining architecture +- Pause after key points +- Watch time — don't overrun + +IF THINGS GO WRONG: +- If live demo fails: Say "Let me show you the concept instead" and use the + code examples +- If projector fails: Offer to present from your laptop screen +- If running out of time: Skip detailed demo, go straight to summary + +AFTER THE TALK: +- Thank the organizers +- Offer to continue discussions during break +- Share contact information for follow-up + +================================================================================ +END OF SCRIPT +================================================================================ diff --git a/demo/fsic2026/openroad_logo.png b/demo/fsic2026/openroad_logo.png new file mode 100644 index 0000000..6bb28c4 Binary files /dev/null and b/demo/fsic2026/openroad_logo.png differ diff --git a/demo/fsic2026/precision_favicon.png b/demo/fsic2026/precision_favicon.png new file mode 100644 index 0000000..6ec8ea6 Binary files /dev/null and b/demo/fsic2026/precision_favicon.png differ diff --git a/demo/fsic2026/precision_logo.png b/demo/fsic2026/precision_logo.png new file mode 100644 index 0000000..b680234 Binary files /dev/null and b/demo/fsic2026/precision_logo.png differ diff --git a/demo/fsic2026/slides.html b/demo/fsic2026/slides.html new file mode 100644 index 0000000..2b3c2bc --- /dev/null +++ b/demo/fsic2026/slides.html @@ -0,0 +1,352 @@ + + + + + OpenROAD MCP - FSiC 2026 + + + + + +
+
+

OpenROAD MCP

+

Bridging AI Assistants with Open-Source Chip Design

+

Jack Luar

+

Free Silicon Conference 2026

+
+
+ Precision Innovations + +
+
1 / 14
+
+ + +
+

The Problem: Chip Design is Hard

+ +
"Why is my chip failing timing?" — A question every designer asks
+
+ Precision Innovations + +
+
2 / 14
+
+ + +
+

The Solution: OpenROAD MCP

+

An AI-Friendly Bridge to OpenROAD

+ +
+ Precision Innovations + +
+
3 / 14
+
+ + +
+

What is MCP?

+

Model Context Protocol

+ + 
AI Assistant ←→ MCP Server ←→ Your Tools
+
+ Precision Innovations + +
+
4 / 14
+
+ + +
+

Architecture Overview

+
┌─────────────────┐ MCP Protocol ┌───────────────┐ +│ Claude/Gemini │ ←─────────────────→ │ FastMCP Server│ +└─────────────────┘ (STDIO) └───────┬───────┘ + │ + ▼ + ┌───────────────┐ + │ OpenROAD │ + │ (via PTY) │ + └───────────────┘
+

Key Technologies:

+ +
+ Precision Innovations + +
+
5 / 14
+
+ + +
+

Core Features

+ + + + + + + +
FeatureDescription
Interactive SessionsCreate persistent OpenROAD sessions
Command ExecutionRun Tcl commands with timeout support
Report VisualizationView placement, routing, CTS images
Session ManagementMultiple concurrent sessions
Command HistorySearch and review past commands
+
+ Precision Innovations + +
+
6 / 14
+
+ + +
+

Example Workflow

+ 
# 1. Create a session
+create_interactive_session()
+
+# 2. Load a design
+interactive_openroad("read_verilog my_design.v")
+
+# 3. Run synthesis
+interactive_openroad("synth_design")
+
+# 4. Check timing
+interactive_openroad("report_timing")
+
+# 5. View results
+list_report_images(platform="sky130", design="my_design")
+
+ Precision Innovations + +
+
7 / 14
+
+ + +
+

Security Model: Permission-Ask Approach

+

Deny-by-Default Whitelist

+ + + + + +
CategoryExamplesBehavior
Allowedreport_*, get_*, set_*Execute immediately
Blockedexec, source, exitAsk for confirmation
Dangerousfile, socketAlways blocked
+

Why this matters: AI agents can be helpful but cautious

+
+ Precision Innovations + +
+
8 / 14
+
+ + +
+

Unique Innovations

+

What Makes OpenROAD MCP Special?

+
    +
  1. MCP server for OpenROAD with natural language interface
    2. +
  2. True PTY terminal emulation (not just pipe-based)
    3. +
  3. Permission-ask security model for AI agents
    4. +
  4. ORFS integration with automatic design discovery
    5. +
  5. Production-ready: 80%+ test coverage, async architecture
    6. +
+
+ Precision Innovations + +
+
9 / 14
+
+ + +
+

Use Cases

+

Demo: GCD Timing Closure

+ + + + + +
MetricBeforeAfter
WNS-0.05 ns~0.00 ns
Setup Violations234 (negligible)
StatusFAILEDPASSED
+

Workflow:

+ +
+ Precision Innovations + +
+
10 / 14
+
+ + +
+

Roadmap

+

What's Next?

+
+
+

v0.2 Goals:

+
    +
  • Complete RTL-to-GDS flow orchestration
    • +
  • Design space exploration
    • +
  • Real-time monitoring during long runs
    • +
+
+
+

Future Vision:

+
    +
  • Machine learning integration
    • +
  • Multi-objective optimization
    • +
  • Cloud deployment support
    • +
+
+
+
+ Precision Innovations + +
+
11 / 14
+
+ + +
+

Get Involved

+

Try It Today!

+ 
# Add to Claude Code
+claude mcp add --transport stdio openroad-mcp -- \
+  uvx --from git+https://github.com/luarss/openroad-mcp openroad-mcp
+
+# GitHub
+github.com/luarss/openroad-mcp
+

Community:

+ +
+ Precision Innovations + +
+
12 / 14
+
+ + +
+

Summary

+

Key Takeaways

+
    +
  1. OpenROAD MCP bridges AI assistants with chip design
    2. +
  2. Natural language interface to OpenROAD
    3. +
  3. Security-first design with permission-ask model
    4. +
  4. Production-ready and open source
    5. +
  5. Community-driven development
    6. +
+
+ Precision Innovations + +
+
13 / 14
+
+ + +
+
+

Questions?

+

Thank You!

+

+ Contact: Jack Luar

+ GitHub: github.com/luarss/openroad-mcp +

+
+
+ Precision Innovations + +
+
14 / 14
+
+ + + diff --git a/demo/orfs-gcd-timing/README.md b/demo/orfs-gcd-timing/README.md index 4e92649..6da9ac7 100644 --- a/demo/orfs-gcd-timing/README.md +++ b/demo/orfs-gcd-timing/README.md @@ -6,8 +6,8 @@ This demo shows how to fix timing violations in the nangate45/gcd design by rela ## Problem Statement The default nangate45/gcd configuration has timing violations: - **WNS (Worst Negative Slack)**: -0.05 ns -- **TNS (Total Negative Slack)**: -0.53 ns -- **Setup violations**: 23 paths +- **TNS (Total Negative Slack)**: -0.57 ns +- **Setup violations**: 33 paths - **Target clock period**: 0.46 ns (too aggressive) - **Achievable clock period**: ~0.51 ns @@ -106,7 +106,7 @@ set_output_delay [expr $clk_period * $clk_io_pct] -clock $clk_name [all_outputs] 2. **Copy improved constraint to ORFS**: ```bash - cp /home/luars/openroad-mcp/demo/orfs-gcd-timing/configs/improved_timing.sdc \ + cp /home/luars/fsf-conference/demo/orfs-gcd-timing/configs/improved_timing.sdc \ /home/luars/OpenROAD-flow-scripts/flow/designs/nangate45/gcd/constraint_relaxed.sdc ``` @@ -133,7 +133,7 @@ set_output_delay [expr $clk_period * $clk_io_pct] -clock $clk_name [all_outputs] Use the provided `run_demo.sh` script: ```bash -cd /home/luars/openroad-mcp/demo/orfs-gcd-timing +cd /home/luars/fsf-conference/demo/orfs-gcd-timing ./run_demo.sh ``` @@ -274,8 +274,8 @@ When helping users with timing closure in OpenROAD: Clock Period: 0.46 ns Target Frequency: 2174 MHz WNS: -0.05 ns ❌ -TNS: -0.53 ns ❌ -Setup Violations: 23 ❌ +TNS: -0.57 ns ❌ +Setup Violations: 33 ❌ Status: FAILED ```