dse-loop

Iteratively run programs and extract numeric metrics to optimize design parameters.

1|1|Updated May 19, 2026
One-click install
npx skills add https://github.com/zhuyingqin/ARIS-WEB --skill dse-loop-zhuyingqin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dse-loop
Source: https://github.com/zhuyingqin/ARIS-WEB/tree/main/crates/runtime/assets/skills/dse-loop
Command: npx skills add https://github.com/zhuyingqin/ARIS-WEB --skill dse-loop-zhuyingqin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

It solves the problem of finding near-optimal configurations in a large design or parameter space by repeatedly running a program, extracting a metric, and iteratively tuning inputs until the objective is met or time runs out.

Core Features & Use Cases

  • Autonomous run → analyze → iterate loop: Executes the target workload, parses results into an objective value, selects the next parameters, and repeats.
  • Parameter range inference: If ranges are missing, it reads the codebase to infer valid parameter types and sensible sweep values, then logs the inferred space for review.
  • Robust bookkeeping & stopping rules: Creates a full run directory with CSV logs, outputs, state recovery JSON, and a final markdown report with convergence and recommendations.
  • Use Case: When you need to tune gem5, Yosys/DC scripts, RTL simulations, OpenROAD/Innovus flows, or formal verification parameters to optimize a measurable metric under constraints.

Quick Start

Use the dse-loop skill to run your simulator or build command, tune the specified parameters toward your objective metric, and stop automatically when the target is reached or the timeout expires.

Frequently Asked Questions about dse-loop

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate parameter tuning for computer architecture simulation sweeps?

Automate parameter tuning for computer architecture simulation sweeps by iteratively running the target workload, parsing the output for a numeric objective metric, and guiding subsequent parameter choices. This applies to simulation scripts, synthesis tuning, and formal verification settings.

Can I use this to optimize EDA synthesis and routing flows without manually specifying parameter ranges?

Yes, you can optimize EDA synthesis and routing flows without manual ranges because the system reads the source code to infer valid parameter types and sensible sweep values when missing. It logs the inferred design space for your review before proceeding.

How does the design space exploration loop decide when to stop running iterations?

The design space exploration loop stops running iterations based on predefined timeout limits, maximum iteration counts, patience thresholds, and success criteria. It records run outputs and recovery state in JSON to ensure deterministic logging throughout the process.

What is the best way to tune RTL verification parameters to beat a specific target metric?

The best way to tune RTL verification parameters is to set a target metric and let the autonomous run-analyze-iterate loop execute. It extracts the metric from each run, adjusts inputs accordingly, and stops automatically when the target is reached or time expires.

Do I need to manually log outputs when running gem5 or Yosys parameter optimization?

No, you do not need to manually log outputs when running gem5 or Yosys parameter optimization. The system creates a full run directory with CSV logs, output files, state recovery JSON, and a final markdown report with convergence details and recommendations.

Are there limitations when inferring valid parameter types from source code for EDA optimization?

When inferring valid parameter types from source code for EDA optimization, the limitation is that the inferred design space must be reviewed to ensure the sensible sweep values match your constraints before the autonomous iteration begins.