P9 cloud task: install gcc (linker for the Rust build); guide: kernel installation

docs/user_guide.md

@@ -19,6 +19,15 @@ uv venv && uv pip install -e .          # add ".[dev]" for tests and linters
 .venv/bin/simurg --version
 ```
 
+**Optional compiled kernels** (≈ 3–4× faster genotyping, 4× faster manifest loading; results are byte-identical):
+
+```bash
+curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --profile minimal   # Rust (needs a C linker, e.g. gcc)
+uv pip install ./rust/simurg-core
+.venv/bin/python -c "from simurg._core import backend; print(backend())"                   # rust 1.0.0
+```
+
+Without them the same code runs in pure Python/NumPy; `SIMURG_PURE_PYTHON=1` forces that path.
 Only pure-Python dependencies are needed (numpy, pyarrow, typer, rich, pyyaml, openpyxl). VCF/BCF, tabix/CSI
 indexes and PLINK files are written by SimurgArray itself; bcftools/plink2 are not required (they are used only
 as test oracles).
@@ -148,8 +157,9 @@ A nightly differential run (`scripts/nightly.py`) re-checks these against the or
   diplotyping are not in v1.0.
 * The largest cohort tested is 2141 samples (plan goal ≥ 10 000). Memory grows with samples × loci in the cohort
   QC steps; on an 8 GB machine keep `--threads` low (≈ 2–3 GB per worker for GSA/Omni-size arrays).
-* Speed is that of NumPy: genotyping a GSA sample takes ~3 CPU-seconds on a server core (360 samples in 2 min on
-  16 cores) and ~25 s on a Raspberry Pi 5 core; a compiled core is planned (P9).
+* Speed: with the compiled kernels a GSA sample takes ~1.1 s on a Raspberry Pi 5 core (pure Python ~3.4 s); see
+  `docs/validation/P9.md` for server numbers and thread scaling. Loading a manifest/cluster file is a fixed cost
+  per run (GSA ~5 s, Omni2.5 ~15 s on the Pi).
 * Methylation arrays: control-probe QC only.
 
 ## Troubleshooting