agentleFS
vortexgpgpuvortexgpgpu/vortex/.agents/skills/simx-review/SKILL.md

simx-review

Skill2.4k starsChanged 7 days agoApache-2.0View on GitHub

Review checklist for Vortex SimX changes under sim/simx and sim/common. Use together with code-review whenever a diff touches the cycle model, the functional emulator, the SimObject framework or a model of an RTL unit.

Trending

More talk lately.thin dataabout the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 1 mentionApr 2026: 0 mentionsMay 2026: 1 mentionJun 2026: 0 mentionsJul 2026: 1 mentionAug 2026: 0 mentionsSep 2026: 1 mentionOct 2026: 1 mentionNov 2026: 1 mention
Dec 2025Jun 2026Nov 2026
Mentions a month of the vortexgpgpu/vortex repository that our weekly crawl found: only 13 in all, so this is a hint, not a trend. There is no adoption data for this file yet.

Who's talking about vortexgpgpu/vortex

The biggest 5 of 13 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 13

Talked about on GitHub and Hacker News (13 times).

On GitHub · 11

6 more on GitHub

On Hacker News · 2

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    No threading vocabulary in model code (atomics, mutexes, threads, deferred calls).

    line 27
  2. Distinctive:

    No comment that names an RTL signal or parameter, a task, a PR or a fix.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Reviewing SimX

Load docs/coding_guidelines_cpp.md, docs/designs/simobject.md, docs/designs/simx_simulator_architecture.md and AGENTS.md §4–§6 first.

The model's role

  • SimX is the RTL's timing model and the functional reference. A change to either side that moves cycles needs the other side, or a model_parity case showing the gap stays within tolerance (AGENTS.md §4).
  • A SimX-vs-RTL divergence is not fixed by editing SimX until it is shown which side is wrong (docs/bug_fixes.md §5). A SimX timing change must describe hardware the RTL builds or will build, not a convenience.
  • Instruction counts must match rtlsim exactly; any change to what retires (decode, traps, warp control, barriers) is functional, not timing.

Structure

  • Cardinal rule: modules talk only through their bound SimChannel/ SimEventLink ports. No reaching across the hierarchy (core_->processor()->..., a leaf unit grabbing global memory).
  • No threading vocabulary in model code (atomics, mutexes, threads, deferred calls); ci/check_simx_mt_boundary.sh enforces it, and the model must stay correct under serial and parallel execution.
  • Determinism: no reseeding of a global RNG, no iteration over unordered containers that decides timing, same-cycle events delivered in send order.
  • Configuration comes from the generated VX_config.h; never inject -DVX_CFG_* in a Makefile to work around a stale header (AGENTS.md §2).

Correctness

  • Queues: a bounded queue models the RTL depth and applies backpressure; an unbounded std::queue where the RTL has a FIFO hides a stall.
  • Lifetimes: a packet or request referenced after send or after its owner retires; iterator invalidation in a container that a callback can modify.
  • Width and sign: XLEN 64 addresses in 32-bit fields, int loop counters over uint64_t sizes, shifts by >= width.
  • Perf counters: a counter SimX reports must count the same event as the RTL's counter of the same name, or model_parity counter checks compare different things.

Style

  • Braces on every branch and loop; two-space indent.
  • DT/DP trace arguments comma-separated.
  • No comment that names an RTL signal or parameter, a task, a PR or a fix.

Evidence

  • A timing change names the parity case before and after, and the perf baseline diff if perf_gate moves (re-recorded by a human with --update-baselines, never by an agent or CI).
  • A functional change names the regression or ISA test that covers it.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.