igneum/docs/benchmarks
igneum-labs eca4111c34 Reproducible benchmark package: one command per platform (bench/repro.sh, repro.ps1), run on the Mac and PC 2; PC 1 owed
bench/: repro.sh (Linux, macOS) and repro.ps1 (Windows) print the machine, check the genesis pack's lottery hash vectors on
the CPU and every GPU, hash for 120 s per card at 1 GiB, probe random reads at 4, 64, 256 and 1024 MiB, sweep the same
sizes, prove and verify one fixture shard when a 12 GB NVIDIA card and a prover host exist, and write one JSON result (the
bench table's row shape, every command, every binary's sha256, the tolerances) plus a table. make-package.sh builds
igneum-repro-<tag>.tar.gz and .zip from the existing cross-build scripts; ingest.mjs checks a result against
bench/reference.json and adds "reproduced externally" rows to site/miner-bench.json only when every number agrees;
publish-public.sh --repro publishes next to the downloads (not deployed). The workers gained --list, --bench --pack
--seconds --dataset-mib and --memprobe (CUDA from the readwidth branch, OpenCL memprobe from opencl-rdna4, Metal new) with
RESULT and DEVICE lines; igneum-pow gained check-pack; the pack reader accepts a string-seed pack.

Runs (docs/benchmarks/repro.md, the bench-log entry, evidence rows 4, 5, 15): the Mac under the measure lock (Metal
27.674 MH/s, Apple OpenCL 26.875, 96/96 on CPU, Metal and OpenCL, 2^24 fingerprint 25f96e7dce90bd4e, 3.40 G random
reads/s, CPU verify 0.611 ms per warp); PC 2 (96/96 through NVRTC, NVIDIA OpenCL and AMD OpenCL with the same
fingerprint; gfx1036 3.312 MH/s; the 5090 rows beside the app's live miner, 62.4 MH/s, not the card's; the live host
proved and verified the shard through step 6, compressed 33.9 s). PC 1 went down before its slot; owed.

Classes closed: the PC job parses the package script before touching a card and bench/ is in the Windows 5.1 parse job;
the card-off is confirmed by nvidia-smi's compute-apps list and the prover's state read from settings.json, never
api/state; PowerShell case-only variable pairs fail CI (bench/jobs/ps-case-check.sh); the package builder keeps the Mac
workers outside the stage and checks every binary with file -b.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-06 01:16:24 +00:00
..
finality-v3-2026-10-04 Finality rule v3 (ledger F21, F22): simulator scenario M, spec 03 Q4/Q5, cloud vote-timing analysis, v3 harness runner, fast-time profile, bench-log entry, devnet rollout plan 2026-10-04 20:04:12 +00:00
memory-floods-2026-10-04 benchmarks: the vmmap captures carry no local timezone stamp (identity check) 2026-10-05 10:31:44 +00:00
repro-2026-10-06 Reproducible benchmark package: one command per platform (bench/repro.sh, repro.ps1), run on the Mac and PC 2; PC 1 owed 2026-10-06 01:16:24 +00:00
round4-consensus-2026-10-04 Round-4 consensus items: final runs on 977db931 (reorg-final2, the red team's f23 / f24b / f24c), the M31 and un-determination entries, result files 2026-10-05 02:17:49 +00:00
proving-e2e.md Docs: ledger P12 fixed in the proving code and P20 fixed in the host; spec 7.6 shard statement definitions and the provisional S_p; benchmark standard rows 2026-10-04 10:10:17 +00:00
repro.md Reproducible benchmark package: one command per platform (bench/repro.sh, repro.ps1), run on the Mac and PC 2; PC 1 owed 2026-10-06 01:16:24 +00:00