Hardware
Release host
Best evidence for actual latency and throughput on that named machine.
Reproducibility instrument / v0.1
Pin the fixture. Repeat the workload. Record query plans and CPU features. Catch a 15% regression before your users catch a SIGILL.
One record, not a timing screenshot
A release claim becomes a record
A fast query and a portable binary are different claims. The lab keeps the workload identical while making the execution environment impossible to miss.
Pin SQLite, fixture bytes, PRAGMAs, repetitions, queries, and at least three CPU profiles in one TOML file.
Run the same binary on hardware, in a container, or under QEMU. Every report keeps its evidence label.
Compare matching contexts. Changed results stop the comparison; median regressions above your threshold stop CI.
Recorded walkthrough
This static walkthrough mirrors fields emitted by the real CLI. No workload or report is uploaded.
$ sqlite-workload-lab run lab.toml \
--profile x86-64-v2 --out reports/candidate
✓ Fixture sha256 7c50…6a2e
✓ SQLite 3.50.4 / pinned
✓ Repetitions 12 measured + 2 warmups
! Evidence emulator / x86_64
"profile": "x86-64-v2",
"evidence_kind": "emulator",
"profile_match": true,
"required": ["sse4_2", "popcnt"],
"forbidden": ["avx", "avx2"],
"plan": "SCAN docs VIRTUAL TABLE INDEX 0:M2"
Descriptive medians only. The lab does not claim statistical significance.
Compatibility without ambiguity
Hardware
Best evidence for actual latency and throughput on that named machine.
Container
Reproduces libraries and build context; it does not change the host CPU.
Emulator
Exercises an older CPU model and exposes leaked AVX flags before release.
Local by construction
One Rust binary. A checked-in TOML manifest. No account, token, collector, hosted runner, or automatic tuning.
Read the full workload schema# Install from a clone
$ cargo install --path .
# Create and validate a pinned workload
$ sqlite-workload-lab init lab.toml
$ sqlite-workload-lab check lab.toml
Valid: 1 query across 3 CPU profiles.
The CLI has no networking or telemetry. The documentation site stores no personal data and uses no analytics, cookies, third-party scripts, or remote fonts.