Gahow Wang
547611e022
D2: run_benchmark.sh and run_experiments.sh still pass --time-scale and --max-inflight-sessions to the replayer, but those flags were removed when the project moved to trace-driven dispatch. The scripts cannot run as-is. D3: ~25 ad-hoc analyze_* / compare_* / profile_* / final_* scripts and a handful of single-experiment run_*.sh point at /home/admin/cpfs paths, deleted output directories, or a sampled trace file that no longer exists. Keep them in scripts/legacy/ for historical reference; the scripts that remain in scripts/ (analyze_trace, analyze_breakdown, analyze_cache_hit, analyze_eviction, compare_results, compute_roofline, sample_trace, analyze_agentic_patterns, simulate_cache_policies, plus launch_*.sh, gpu_monitor.sh, bench.sh) cover the current workflow. Adds scripts/legacy/README.md to document the archival policy.
scripts/legacy
One-shot scripts kept for historical reference. They were tied to specific
experiments (cluster paths, deleted output dirs, removed CLI flags such as
--time-scale / --max-inflight-sessions) and are no longer expected to
run as-is.
For new experiments use scripts/bench.sh. Pre-existing structured
analyses still live in scripts/ (e.g. analyze_trace.py,
analyze_breakdown.py, analyze_cache_hit.py, analyze_eviction.py,
compare_results.py, compute_roofline.py).
If you need to revive a legacy script, expect to:
- update hardcoded paths (cluster
/home/admin/cpfs/..., deleted trace files, missingoutputs/<exp>/...directories); - adapt to the current replayer CLI (
--time-scaleand--max-inflight-sessionswere removed when methodology moved to trace-driven dispatch); - re-verify the assumptions documented in
REPORT.md.