igneum-network/igneum
1
0
Fork 0
Code Issues Pull requests Releases Activity
966 commits 357 branches 1 tag 2 GiB
Commit graph

140 commits

Author SHA1 Message Date
igneum-labs
bb2bbe6404 Ember run 6: the helper registered on the scratch copy, so task_exe prefers the installed exe for every path that is not itself an install candidate, and the helper gains a reregister verb (no path argument; re-points the task at the install folder it finds itself, logs the action read back); the clock ladder and floor go to 45% with the 1% rate tolerance as the guard; a chosen point on the floor says floor, not optimum; the 5090 row (84 W saved for 0.15% of rate) on the fleet page; the re-point and no-prompt proof playbook; run 6 notes, threat note, bench log 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-06 16:35:03 +00:00
igneum-labs
1bd7b687c9 Run 5 (15:28 to 15:39Z): the 5090's five power rows in the bench log (the cap does not bind: 0.41 MH/W flat at 310 W); the playbook's watchdog killed the live three-card tune at the first clock step, so: idle = three consecutive status lines reading 0.00 MH/s and 300 s, never a missing match; the after snapshot and the engine-log dump on every exit; an elevated tune engine registers the Igneum Power Helper itself before its first step (the --sweep engine skipped the cap path where the registration lived); Ember 2 groundwork: the memory-clock knob in Point and Limits, the goal, the hill-climb plan (not yet wired to the engine) 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-06 15:44:06 +00:00
igneum-labs
c04ad2751c Merge master 532cdad into ember-tune (0.3.12's version files and the proving-v1 app merge; my own 2bd168b came back as 7c0dee1) 2026-10-06 15:03:37 +00:00
igneum-labs
0f8e5f70fc bench log: dry run 3 passed (the first measurement engine on PC 1 that mined: 5090 127.31 MH/s at 316.5 W, 4070 28.68 MH/s at 102.7 W), the folder-lock finding measured on PC 1 and its consequence 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-06 15:03:18 +00:00
igneum-labs
f6f2bdb013 release 0.3.12: merge proving-v1 app 20eb0dd (the segment-aligned prover, the held fresh record, the fresh-record rule harness) 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-06 08:37:18 +00:00
igneum-labs
20eb0dd045 bench-log: the fast-time harness on the fresh-record rule, both cases 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-06 08:35:13 +00:00
igneum-labs
869b0b63c5 bench-log and plan: the segment-aligned prover on PC 2 (9 whole segments in 30 min, 72 of 72 shards paid, 11.0% of the miner) and the chain rule's 8-DAA fresh window, its fix behind the switch 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-06 08:26:59 +00:00
igneum-labs
984727d828 Merge release-0.3.12 (095aa9e) into ember-tune: 0.3.11's six-section View and card order kept, Ember Tune's line and switches re-added on it; the tune fields move into hotplug::apply_pref; the power-cap plan keeps present(); both CI test lists; 132 app tests, 26 UI tests, every gate green 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-06 08:20:46 +00:00
igneum-labs
db6be27d5e release 0.3.12: merge proving-v1 app: paid_wei as a decimal string 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

# Conflicts:
#	docs/bench-log.md
 2026-10-06 08:16:26 +00:00
igneum-labs
764f01cf9e bench log: run 2 (07:21 to 07:56Z): the BOM in the copied settings, no miner started, nothing set, mining paused 36 min 13 s, the hold released by the runner itself 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-06 07:59:21 +00:00
igneum-labs
587a03b732 proving v1: the PC 2 segment-aligned prover job (tools/proving-v1/pc2-segments.ps1) and the CPU validation of --save-shards records and --prev 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-06 07:18:15 +00:00
igneum-labs
da2178b113 Aggregation cost on the 5090 (5 October, night): the chained aggregation is 2.1 s alone and 9.7 s beside the miner, the batch-log2 curve (2^16 buys 1.6x for a fifth of the hash rate), batch and tree folds estimated, two streams and SP1 knobs closed; the host times the stdin build and names the knobs, --save-shards; the PC 2 job scripts and the readers 
The statement and the pinned guests are unchanged; every fixture proof verifies as before. The defaults stay (batch-log2 22, SP1 defaults): the one knob that moves a mining card's prover costs a fifth of the hash rate; the plan carries the trade for the project lead and the batch fold for the next pin. Measured: docs/bench-log.md "aggregation cost on the RTX 5090"; the plan line: docs/plans/proving-v1.md "Aggregation cost (5 October, night)". Also: make-package's gate skips the exporter's .node-plan.json side files and takes the run lock for its execute step; the state-reply class (/api/state answering {} once paid_wei passes u64::MAX) found on the way and fixed on the app branch at 8e07279.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
(cherry picked from commit ea38ece9eaa5949dd657cbfea5308c4948177ff8)
 2026-10-06 07:04:50 +00:00
igneum-labs
25d86c3e11 bench log: the 22:31 UTC installer run was a second install of 0.3.10 over 0.3.10 (PC 1 took 0.3.10 at 21:40:41Z through update-now), not how PC 1 got 0.3.10 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-06 07:03:26 +00:00
igneum-labs
2804508b30 C35 named: PC 1's 22:31 UTC quit was the per-user installer launched by the second engine's own updater (0.3.9 under min_supported_version = urgent, beating auto_update = false); a second engine never runs the updater (IGNEUM_APP_NO_OTA=1, implied by --sweep; the playbooks set it; the CI check demands it); bench log and plan carry the named source 
Source: the scratch engine's own log in collect ember-c35-collect-1 (06:59Z): 22:31:02Z '0.3.10 is available: downloading',
22:31:05Z 'update: starting the installer first ... ota-apply.ps1', and the installed app's 'quit:' at 22:31:06Z.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-06 07:01:57 +00:00
igneum-labs
8e07279454 app: /api/state never answers {} again (paid_wei over u64::MAX broke to_value; the field is a decimal string, the error is logged once) 
serde_json's to_value refuses a u128 over u64::MAX (18.45 IGN) and state_json turned the error into json!({}). A paid shard is 1.23 IGN on average, so a proving machine's dashboard went blank about 15 paid shards after every app start. Unit test over the boundary; 114 app tests pass.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-06 00:27:35 +00:00
igneum-labs
cc906785b2 Merge ca2-coord (8aefe0a) into release-0.3.11: the Counter ASIC 2.0 docs commits (N4 rows, gate cells, digests, rules, status; the five cited documents already in the tree) 
# Conflicts:
#	docs/bench-log.md
 2026-10-05 23:06:38 +00:00
igneum-labs
c7c38046aa Merge branch 'ca2-epoch' into ca2-coord 
# Conflicts:
#	docs/bench-log.md
 2026-10-05 23:04:46 +00:00
igneum-labs
377b21fd0f Merge branch 'ca2-soundness' into ca2-coord 
# Conflicts:
#	docs/bench-log.md
#	proto-metal/packbench.swift
 2026-10-05 23:04:45 +00:00
igneum-labs
937563d9dd Merge branch 'ca2-analysis' into ca2-coord 
# Conflicts:
#	docs/bench-log.md
 2026-10-05 23:04:14 +00:00
igneum-labs
bda44dca15 Merge ca2-epoch (0db67de) into release-0.3.11: docs and standalone probe sources the evidence rows cite (C38); nothing a built artefact reads 
# Conflicts:
#	docs/bench-log.md
 2026-10-05 23:03:46 +00:00
igneum-labs
c9d93c8b7e Merge ca2-analysis (4d0f7ec) into release-0.3.11: docs and standalone probe sources the evidence rows cite (C38); nothing a built artefact reads 
# Conflicts:
#	docs/bench-log.md
 2026-10-05 23:03:45 +00:00
igneum-labs
dba36378ae bench log + plan: C35 corrected (the quit was not the 0.3.11 update; what is established, the hang, the orphans, the prompt, the fixes) 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 23:00:52 +00:00
igneum-labs
f3c6b18300 bench log + plan: PC 1 run 1 aborted by the 0.3.11 update 47 s in, the before snapshots of both cards, the AMD offset-range finding and its consequence per tier 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 22:44:46 +00:00
igneum-labs
42d157f505 Merge commit 'e16984b' into release-0.3.11 
# Conflicts:
#	docs/bench-log.md
#	docs/evidence.md
#	site/litepaper.html
 2026-10-05 22:39:34 +00:00
igneum-labs
40f1317b45 Merge branch 'ca2-coord' into release-0.3.11 
# Conflicts:
#	docs/bench-log.md
 2026-10-05 22:39:12 +00:00
igneum-labs
4d70bccab3 Merge remote-tracking branch 'origin/master' into ca2-v3 
# Conflicts:
#	docs/bench-log.md
#	proto-opencl/host.c
 2026-10-05 22:34:07 +00:00
igneum-labs
65c7f6a380 C29 and D11: the verifier line on the fixed crate, the bounty struck until escrowed, the final-class rates in the public tables; status 22:25 2026-10-05 22:25:02 +00:00
igneum-labs
85105f8270 Bench log: Counter ASIC 2.0, the numbers (the level 3 page section); litepaper anchor 2026-10-05 22:20:05 +00:00
igneum-labs
848871bcd5 verifier regression of ebafbf4 fixed (derive_items out of line, one instance per cache size with the line mask a constant: v2 0.609 ms per unit against readwidth's 0.607, was 1.33); x8 into class v3 under the delegated rule (V3_CLASS = MX8; mx8-genesis and mx8-devnet-epoch0 re-exported through the seam, the devnet one with the era inside; the mx4 packs kept as the x4 record, generator 2); tests/packs.rs and tests/mixer.rs on the x8 class; mixer-x4.md 6.2a, 6.4a, 6.5 decision, 6.6 the regression; chip-model-v3.md headline x8 (0.92x with the factor); bench-log addendum with the PC 1 build rows 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 22:10:55 +00:00
igneum-labs
091bfbff89 bench-log: the root-socket recurrence of 21:25Z and the fix job of 22:01Z (the prover proved again at 22:02Z) 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 22:03:06 +00:00
igneum-labs
9c4439670d mixer x4: the measure session (v2 / x4 / x8 verifier 1.33 / 1.94 / 2.79 ms per unit on a loaded core, 1.45x and 2.1x; the 256 MiB fill 172 to 175 ms; the Metal 1 GiB build flat at 21 ms, latency-bound), the verification-throughput consequences (C19), what is unverified and what is owed; the bench-log entry; the PC 1 two-card playbook; the measured verifier row in the chip model 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 22:02:28 +00:00
igneum-labs
cb3bc0efe7 hot table (Counter ASIC 2.0 layer 5), measured and not adopted, on the ca2-v3 composed class (squash of tag ca2-cache-history-2026-10-05) 
LoadClass::hot (Option<HotClass { mb, k, added }>) beside mix, slots, scratch, mixer_mult, growth and era; V3_CLASS = { era: None, hot: None, ..LoadClass::MX4 } (hot stays None: the hot code is behind the flag, measured and not adopted). Op::Hot, the hot slots drawn after the scratch slots, no width roll (v2_loads allows the added form's extra slots), the id suffix hot/<S><k>[added], the hot parsing inside parse_loads, the era branch first in name(). HotTable under seed_words("igneum-hot/" || epoch seed) with the cache chain and tag umHT, read at H[mulhi(src, HOT_WORDS)]; DatasetSource::hot attached by new_class_day and from_seed_bytes_class; the acceptance stand-in dataset_elem(idx, S[2], S[3]); the three emitters (hot argument after the init words, ht_segment and igneum_hot_fill beside the layout-aware cores); packfile.h hot fields beside class, era, attempt and mixerMult; OpenCL host, Metal packbench and NVRTC worker fill H on the device and self-test it. Eight packs under proto-cuda/packs-ca2-hot (replaced hot32k4 hot64k4 hot96k4 hot64k2 hot64k8, added hot32k4a hot64k4a hot96k4a) re-exported on the merged crate: vectors unchanged, program.h and program.json carry the mixer fields. docs/plans/hot-table.md (design, spec text, per-tier budget, chip model, Mac and PC measurements, the decision: layer 5 out of v3, the 3.0 note); bench-log entry and addenda with job ids and worker sha256s; the two PC playbooks.

Checks on this commit: cargo test --release 53 + 19 pass (the pinned v2, mx4, era, readwidth and hot packs); the pinned packs under proto-cuda/packs, packs-ca2-mixer, packs-ca2-era and packs-readwidth untouched; Metal packbench and Apple OpenCL --bench-pack on all eight hot packs (run lock, 2^20 at base 0): 96/96 lanes, hot table head, last line and FNV PASS, one fingerprint per pack on both harnesses, equal to the fingerprints before the rebase (hot32k4 679e5e83378d3790, hot64k4 d4c9e456b039fdef, hot96k4 7c98eceffee9fd73, hot64k2 f43b10a95879b8e5, hot64k8 c11309d743be9392, hot32k4a afb700b2d997c847, hot64k4a ba214baa9c1a9e85, hot96k4a 29e1916aed6deff5). No era or mixer behaviour changed: every resolution kept the ca2-v3 side and appended the hot branch.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 21:57:39 +00:00
igneum-labs
39714700d9 era layout (Counter ASIC 2.0 layers 4 and 8) behind the class flag, on the ca2-v3 seam: the 7-draw era stream from E_n (stride, interleave, width pinned at 4 B), per-site window draws (dataset, half, quarter at a 256 MiB floor), the strided windowed load address in the interpreter, the acceptance mirror and the three emitters, the interleaved dataset layout riding with the program (memhard::Layout, mh_t/mh_j/mh_addr, Epoch::dataset_word), V3_CLASS with the era drawn inside by generate_from_seed_bytes_program_class, --era / --era-widths on the CLI, six class v3 era packs (packs-ca2-era), tests, the design doc, host.cu/host.c deriving host words through the pack's mh_word, emu/test-layout.sh, the PC 1 playbook 
Squashed from six commits (tag ca2-era-pre-squash) for one merge.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 21:41:33 +00:00
igneum-labs
6ff6701378 bench log: Ember Tune, what PC 1 could measure tonight (elevated=False, the cancelled prompt at 20:09 UTC, the 9070 XT off the bus), the pipeline verified without a card, the tier consequences 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 21:26:31 +00:00
igneum-labs
0db67deeb3 ca2-epoch: the Mac compile-ahead measurement (10 fresh programs 15.9 / 17.7 / 20.4 ms min / median / max, the devnet pack 79 ms then 1 ms from the shader cache) in docs/bench-log.md and epoch-length.md section 6; the per-card table and the 600-s floor filled 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 21:19:33 +00:00
igneum-labs
2da9902ff2 Merge branch 'amd-prove' into ca2-coord 
# Conflicts:
#	docs/bench-log.md
 2026-10-05 21:03:58 +00:00
igneum-labs
ffd6727d0d docs/analysis/amd-proving.md: no zkVM proves on AMD (SP1, RISC Zero, Jolt, OpenVM, ICICLE cited), the SP1 CPU prover measured on PC 1 beside the miners (282 s a shard at any size, 30 GB RSS: no CPU tier), the tier consequences and the public line; PC 1 job scripts with the bash -n gate; bench-log entry 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 21:02:59 +00:00
igneum-labs
82f4d6058f Proving v1: the harness passes on the final fork tree (N = 8, 21 checks in 244 s) 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 20:57:33 +00:00
igneum-labs
8d43c4f909 Proving v1: the miner-on curve's 2^25 rows (the prototype shard 24.7 GB and 38.8 s beside the miner) 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 20:56:32 +00:00
igneum-labs
0623e7e8f5 Proving v1: the miner-on curve (the adopted shard 22.2 GB and 13.2 s beside the miner; the prototype 30.1 GB): the 24 GB tier measured, the public lines updated 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 20:55:54 +00:00
igneum-labs
d355b4c952 Proving v1: the S_p curve's re-plan points (28.4 GB at 20 M cycles: the peak is flat from 20 M to 60 M) 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 20:49:26 +00:00
igneum-labs
983f85618d Proving v1: the S_p curve, card alone (13.9 GB floor, 20.4 GB at the v1 shard, 28.3 GB at the prototype shard): the 12 and 16 GB tiers cannot prove on SP1 6.8.1's GPU server, 24 GB proves v1 shards, 32 GB the prototype 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 20:43:22 +00:00
igneum-labs
dc98578dec AMD telemetry: igneum-gpu-telemetry (ADLX on Windows, amdgpu sysfs on Linux, PDH utilisation fallback) feeds the card row's draw, temperature, fan, memory clock and MH/W; measured on PC 1: 9070 XT 198.9 W, 64 C, 657 rpm, 17.73 MH/s = 0.089 MH/W beside the 5090 at 307.6 W, 122.30 MH/s = 0.398 MH/W 
the project lead watched the 9070 XT at 90% usage with its fans barely turning and the app could not say what it drew: the
draw, temperature and MH per watt line came from nvidia-smi only, and the earlier per-watt figure used the board
rating. proto-opencl/gpu-telemetry.c prints one line per AMD card per sample (bus from SetupAPI by the display
device's name, kind, name, watts, temp_c, fan_rpm, fan_pct, mclk_mhz, gclk_mhz, util_pct, source), built by
build-windows.sh against vendor/adlx (the SDK clone), shipped by make-payload.sh and push-inputs.sh. The engine
runs it with -l 5 beside nvidia-smi (Source::AmdTelemetry, tick_amd_telemetry), parse_amd_telemetry fills
power_w, temp_gpu, fan_pct, fan_rpm, mclk_mhz, util_pct and telemetry_at on the AMD card matched by kind and
ordinal, so eff_mhw and the dashboard's existing line show it; app.js shows fan and memory clock when present.
Tests: three on the parser with lines captured on PC 1 and the Mac fixture; the sysfs path ran on a fixture tree.

Measured over 20:27:45 to 20:29:41 UTC with both cards mining (docs/bench-log.md, under the 9070 XT ceiling table):
9070 XT 198.9 W (193 to 212), 64 C, 657 rpm, 2,505 MHz memory, 3,290 MHz shader, 100% busy, 17.73 MH/s =
0.089 MH/W; RTX 5090 307.6 W, 69 C, 44% fan, 122.30 MH/s = 0.398 MH/W.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 20:43:21 +00:00
igneum-labs
81d1193f10 Proving v1: the memory sweep and the miner-on peaks, the root-socket class fix (cleanup lines, tools/ci/prover-socket-check.sh in CI), the host's --budget re-plan and the S_p curve job, the RAM and aggregation-card gates, N = 8 in the fast-time file and spec 7.4 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 20:35:13 +00:00
igneum-labs
4d0f7ecf9a Counter ASIC 2.0 layer 7: RTX 5090 and RX 9070 XT dot4 numbers from PC 1 (job run-dot4-20261005): dp4a 7.45 T/s on the 5090 via inline PTX, v_dot4_i32_iu8 0.66 T/s on the 9070 XT via the clang builtin in Adrenalin OpenCL C, signed emulation 7.1x / 1.46x / 4.7x the ALU step on NVIDIA / AMD / Apple; no PC platform lists cl_khr_integer_dot_product 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 20:31:33 +00:00
igneum-labs
ce296adeb5 Proving v1: the 12 GB memory sweep on the 5090 (13.9 GB floor on an empty shard, 28.3 GB on a full one, no knob moves the floor) 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 20:27:45 +00:00
igneum-labs
b1532bb3d6 read-width: bench-log entry and docs/plans/read-width.md (three cards, probes, widths, the per-load mix, the scratch at 32 and 128 KiB, chip model, recommendation: keep v2; w16 the only width that passes the rules and closes nothing); test multiply made wrapping (dev-profile overflow check) 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 20:24:40 +00:00
igneum-labs
78a11dba28 scratch-soundness.md: the five findings, the recompute-versus-store arithmetic at 64, 256 and 2,048 slots, the named on-die-cache chip row per variant (2.4x at every share under the cap) beside the M16 mixer lever, the host tag contract, the vector requirements, the Metal results (228 of 228 pass, 3 of 3 built-in failures caught); bench-log entry with the commands and counts 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 20:21:49 +00:00
igneum-labs
7f2087a266 Proving v1: the chain of 8 on the 5090 measured (N = 2, 4, 8: 32.6, 66.8, 135.6 s; chained aggregation 9.7 s a block on a mining card), the fleet table re-cut on the measured rows 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 20:21:14 +00:00
igneum-labs
0aac3a2e68 Proving v1: the chain of 2 on the 5090 (31.8 s, the chained aggregation 9.5 s), the job aborted by the 0.3.10 restart at block 3 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-05 20:21:14 +00:00