hpca-experiments
Use when auditing an HPCA evaluation: declaring the fidelity contract (simulator, configuration, workloads, sampled regions, validation), matching each claim to its instrument, capturing real-silicon machine state, tuning baselines honestly, and reporting per-workload distributions rather than a single mean.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill hpca-experiments --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# HPCA Experiments Use this to stress-test an HPCA evaluation before the July gate. Architecture reviews are won and lost on methodology: a mechanism can be sound and still be rejected if the numbers cannot be trusted against their instrument. ## Declare the fidelity contract Every HPCA evaluation rests on a contract the paper must state explicitly: - **Tool and version.** Which simulator (and commit), or which real machine. - **Fidelity scope.** What the model captures and what it abstracts — an in-order functional model and a cycle-level OoO model make different claims believable. - **Configuration.** Core width, cache hierarchy, memory/DRAM timing model, interconnect — the parameters a reviewer needs to reproduce the setup. - **Workloads and regions.** The suite, the inputs, and how regions were sampled (e.g., SimPoint-style sampling) rather than run to completion. - **Validation.** What the timing models were validated against, with the error. A number outside its contract is unreviewable; a contract stated up front pre-empts half the methodology objections. ## Match each claim to its instrument | Claim type | Credible instrument | Not credible from | |---|---|---| | Cycle-leve
- Declare the fidelity contract
- Match each claim to its instrument
- Capture machine state for silicon
- Tune baselines honestly
- Report the distribution
- Pre-submission audit
- Output format
What does the hpca-experiments skill do?
Use when auditing an HPCA evaluation: declaring the fidelity contract (simulator, configuration, workloads, sampled regions, validation), matching each claim to its instrument, capturing real-silicon machine state, tuning baselines honestly, and reporting per-workload distributions rather than a single mean.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill hpca-experiments --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Awesome-Journal-Skills, a repository with 984 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.