llvm
Skill305 starsChanged 9 days agoLicence not identifiedView on GitHub
Tune and analyse a FlyDSL kernel at the LLVM level: pick a compile hint, function attribute, or AMDGPU backend flag, then PROVE it reached codegen. Covers the `compile_hints` keys, the `llvm_options` cl::opt escape hatch, `rocdl.*` / raw LLVM function attributes, per-arch options for gfx950 and gfx1250, dumping and reading `NN_llvm_ir.ll`, replaying the LLVM half with `llc`, and the knobs in this repo that silently do nothing. Use when asked to reduce spills, raise occupancy, change the instruction schedule, set waves_per_eu or flat_work_group_size, pass an `-mllvm` or `-amdgpu-*` flag, sweep scheduler strategies, read LLVM IR or ISA the compiler produced, or explain why a tuning knob had no measurable effect. For before/after register and spill deltas use `/isa-resource-diff`; for why-is-it-slow with a profiler use `/kernel-trace-analysis`; for building LLVM use `/build-flydsl`. Usage: /llvm <question, kernel, or knob>
In this repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- add-target-atom-opSkill
- api-stabilitySkill
- bisect-perf-regressionSkill
- build-flydslSkill
- build-rocm-imageSkill
- capture-kernel-traceSkill
- debug-flydsl-kernelSkill
- flydsl-kernel-authoringSkill
- flydsl-tile-programmingSkill
- format-codeSkill
- gemm-optimizationSkill
- isa-resource-diffSkill
- kernel-code-cleanupSkill
- kernel-trace-analysisSkill
- lds-optimizationSkill
- oob-detectionSkill
- prefetch-data-loadSkill
- release-api-checkSkill
- review-prSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
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
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.