Auto-generated index of xdna-top experiment reports. Each entry is a self-contained, reproducible benchmark grounded in xdna-top evidence artifacts. Add a new docs/experiments/<slug>.md with front-matter and re-run tools/build_experiments_index.py — it appears here automatically.
| Experiment | Date | Platform | Headline |
|---|---|---|---|
| Structured-Output Reliability Across Sampling Configs (NPU LLM stack) | 2026-06-14 | AMD RYZEN AI MAX+ 395 (Strix Halo, gfx1151), kernel 6.17.0-35-generic, XRT 2.21.75 | Greedy decoding is the most reliable for structured (JSON) output across small models; aggressive repetition penalties (rep≈1.3) collapse valid output to near zero. Failures are structural, not creative. |
| NPU vs CPU Background-Job Contention on Strix Halo | 2026-06-13 | AMD RYZEN AI MAX+ 395 (Strix Halo, gfx1151), kernel 6.17.0-35-generic, XRT 2.21.75 | For a latency-tolerant background generation job next to an interactive iGPU model, the NPU does ~3x the throughput at ~3x better total-board perf/watt and contends slightly LESS with the main lane (~3.8% vs ~4.8% decode loss) than spare CPU cores. |
- NPU vs CPU Background-Job Contention on Strix Halo
artifacts/measurements/run1.m1_contention.jsonartifacts/measurements/run1.m2_cpu_arm.jsonartifacts/measurements/run2.m1_contention.jsonartifacts/measurements/run2.m2_cpu_arm.jsonartifacts/measurements/run3.m1_contention.jsonartifacts/measurements/run3.m2_cpu_arm.jsonartifacts/evidence/baseline.snapshot.jsonartifacts/evidence/npu.snapshot.jsonartifacts/evidence/cpu.snapshot.json