Building an Open-Source Verilog Simulator with AI: 580K Lines in 43 Days - Normal Computing

Let's talk<br>Menu

About

Research

Writing

Solutions - EDA

Solutions - ASICS

Careers

LET’S TALKLET’S TALK<br>LET’S TALK

© 2026 Normal Computing Corp.<br>Privacy Policy | Terms & Conditions

Sign up for the latest news & Insights<br>Submit

Thank you! Your submission has been received.

Oops! Something went wrong while submitting the form.

LET’S TALKLET’S TALK<br>LET’S TALK

3.2.2026<br>Building an Open-Source Verilog Simulator with AI: 580K Lines in 43 Days

Thomas Ahle

How one Normal engineer used AI agents to build a practical verification stack on top of CIRCT: simulation, formal verification, mutation testing, and more.

Commercial EDA toolchains cost teams millions of dollars a year across simulation, formal, synthesis, and physical design. The individual tools are well-understood, the specifications are public (IEEE 1800-2017), and open-source compiler infrastructure like CIRCT already exists.<br>We wanted to understand how far agentic AI could go on a well-specified but labor-intensive engineering problem.<br>Over 43 days in January and February 2026, we used AI Agents to land 2,968 commits on a CIRCT fork — adding a full event-driven simulator, VPI/cocotb integration, UVM runtime support, bounded model checking, logic equivalence checking, and mutation testing. The result is a practical, open-source verification stack that can simulate real-world protocol testbenches end-to-end.<br>This post is a technical account of what happened, what the numbers look like, and what we think it means.<br>What is CIRCT, and What Was Missing?<br>CIRCT (Circuit IR Compilers and Tools) is an LLVM-based infrastructure for hardware design and verification. It provides a rich set of intermediate representations: (HW, Comb, Seq, LLHD, Moore) and tools for parsing Verilog (circt-verilog, powered by slang), optimizing IR (circt-opt), and basic formal checking (circt-bmc, circt-lec).<br>What it did not have was a practical simulation runtime. You could parse Verilog into LLVM’s Intermediate Representation (MLIR)  and lower it through various dialects, but you couldn’t actually run a testbench. The gap between “we can compile Verilog” and “we can simulate a design” was enormous.<br>Bridging that gap is exactly the kind of task where agentic AI shines: the specification is known (IEEE 1800), the interfaces are well-defined, and the work is largely volume — thousands of op handlers, system calls, edge cases — rather than fundamental research.<br>By the Numbers<br>The fork adds 580,430 lines across 3,846 files, with only 10,985 lines removed from upstream. The chart below shows the full story: cumulative lines of code (blue), test file count (purple), and weekly commit velocity (orange numbers along the bottom), with color-coded development phases and milestone annotations.

Development timeline: LOC growth, test file count, weekly commit velocity, and feature milestones. Phase bands show the progression from foundation through hardening.The pace started at ~25 commits/day in week 1 and peaked at 124 commits/day in week 7 (Feb 10–16). This isn’t because the AI got faster — it’s because the later work was more mechanical (regression infrastructure, test harnesses, quality gates) while the earlier work required more design iteration. Test files grew from 987 (upstream baseline) to 4,229 — a 4.3x increase, with a sharp inflection around Feb 6 when formal and mutation suites came online.<br>One of the main external drivers of progress was sv-tests, a test suite designed to check compliance with the SystemVerilog standard by the CHIPS Alliance. As of writing, the CIRCT project is at 73%, while the two main free simulators, Verilator and Icarus, are at 94% and 80%, respectively. The chart above shows our progress of taking CIRCT to 100% IEEE support in a month and a half.<br>Where the Work Went<br>Every one of the 2,968 commits is accounted for in a named category:

Full commit breakdown. Formal verification leads at 652 commits, followed by docs/iteration logs (521), Verilog frontend (461), mutation testing (372), and simulation engine (367).Formal verification (BMC + LEC) and mutation testing together account for over 1,000 commits — 34% of the total. The “Docs & iteration logs” category (521) reflects the project’s 1,554-iteration engineering log, which tracked every AI interaction cycle. The Verilog frontend (461 commits) covers ImportVerilog and MooreToCore, the two major lowering passes that convert parsed Verilog into simulatable IR.<br>How We Worked with Agents

AI attribution: 40% Claude Opus 4.5, 14% Claude Opus 4.6, 46% Codex models<br>We used a variety of models in the AI agent software. Claude handled 54% of commits. Early work used Opus 4.5 with a custom StopHook to maintain continuity across long sessions. Opus 4.6 with team mode removed the need for that, letting the agent run autonomously through multi-step tasks.<br>Codex handled the remaining 46%. Version 5.2 had coordination...