spb/localvm-research

Tue, Aug 11, 2026 4

1. expH: adaptive per-cell budget (~3s wall) + iostat ground-truth logger

   …

   Short cells (~10ms wall) produced impossible throughput readings;
   iostat log validates that measured bytes came from the disk controller.
   
   Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

   Simon-Pierre Boucher committed 1 mo ago · 1 file +50 −4
   b4a652d
2. expH fix: write test file with F_NOCACHE — first run measured page cache, not SSD

   …

   F_NOCACHE on a read fd does not bypass already-resident pages; writing
   the test file normally made every page resident, so 'cold' cells hit
   unified memory (42-115 GB/s, impossible for NVMe). Also recreate the
   file before the GPU-load phase since the warm phase repopulates cache.
   
   Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

   Simon-Pierre Boucher committed 1 mo ago · 1 file +21 −8
   da10e00
3. expH: SSD feasibility benchmark implementation + hypothesis

   …

   Measures internal NVMe read throughput: block sizes 4KB-4MB, random vs
   sequential, F_NOCACHE vs warm page cache, 1/4/8 threads, and key cells
   under concurrent MLX Metal matmul load. Embeds hardware manifest.
   
   Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

   Simon-Pierre Boucher committed 1 mo ago · 1 file +232 −7
   28f38d4
4. Bootstrap: charter-compliant skeleton, header enforcement, hardware manifest, experiment scaffolds

   …

   - Repository layout per CLAUDE.md §3
   - tools/check_headers.py enforcing §0.1 (58 files pass)
   - tools/new_experiment.py scaffolding with seven-field hypothesis block (§10)
   - benchmarks/hardware_manifest.py: macOS-native fingerprint (M5 Max / 48GB verified)
   - Eight micro-experiment scaffolds (§9, exp A–H)
   
   Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

   Simon-Pierre Boucher committed 1 mo ago · 1 file +33
   c709367