Commit graph

4 commits

Author SHA1 Message Date
igneum-labs
51dba1ce76 Counter ASIC 3.0 item 8: the latency-shadow knob (LoadClass +sh<S>x<R>), its packs and the PC 2 playbook
A shadow block of S ALU instructions run R times at the end of every iteration, drawn from the program stream after
the 64 base instructions, behind LoadClass::shadow: v2 and v3 draw nothing and emit nothing (the pinned packs are
byte-identical, cargo test 54 + 4 + 19 + 7 green). The interpreter, the three kernel dialects (both kernels each),
program.h and program.json carry it; the acceptance rule interprets the base program only. Packs for seed
igneum-genesis over class mx8 at 4,096 to 180,224 shadow instructions per hash (proto-cuda/packs-ca3-shadow), and
the PC 2 bench playbook tools/ca3-shadow/pc2-shadow-bench.ps1 (passes the publisher's three checks).

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-06 07:58:35 +00:00
igneum-labs
d85f4dec2b igneum-census: build against class v3 (Instr width/win/off, Program class/era_bytes, fetch layout, Scratch/Hot arms)
The ci run on 6f95751 (37387751432) failed in the census release build only; windows-ci was green.
The census generates the lottery hash's class, so every new field takes its v2 value and the two
experiment ops are unreachable.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-05 23:25:52 +00:00
igneum-labs
fdcab858e3 Lottery hash: generator version 2 (16 load slots, fresh sources, acceptance rule), every vector re-cut, packs regenerated, three workers re-checked, 20,000-program census
igneum-pow 0.2.0: generator v2 draws exactly 16 load slots from instructions 1..63, a
load's source from the registers written earlier and not read by a load since, the other
48 ops from the ten non-load weights; accept.rs is spec 01 section 1.4.6 (static: no
stale load source, every register injected; dynamic: 64 units on the seed-keyed
closed-form dataset, no constant bit, no lane-constant site, under 164 saturated, bias
within 136 of 1024, distinct addresses above 245,760); a rejected candidate is replaced
by the next attempt of the seed (seed || k_le32), 32 a consensus fault. Packs carry the
generator version, attempt and program id. Version 1 kept as generate_v1 for the census.

Packs: igneum-genesis, igneum-hourly, igneum-genesis-mh regenerated by igneum-pow export;
new igneum-devnet-v4-epoch0 (devnet genesis hash, day bytes 20730). Checks: Rust 39 of
39 tests; Metal natively via the Swift port (export cross-check 3 of 3 warps, identical
programs and vectors on five seeds incl. three with attempt 1, fuzz 2,000 of 2,000);
CUDA emu 4 of 4 packs; OpenCL emu 2 packs x 2 configurations; Apple OpenCL 4 of 4 packs
at 27.9 Mhash/s. Census 20,000: 5.225 percent rejected, accepted distinct mean 127.887.

Spec 01 0.2 (1.4.2, 1.4.3, 1.4.6, 1.11, 1.15, 1.16, 1.17), igneum-pow README, the CUDA,
OpenCL and Metal test notes, bench-log entry, ledger M5 and M6 Fixed.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-04 07:52:40 +00:00
igneum-labs
381061a077 Mac app: dial the public seed node first, the home node second
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-03 22:28:58 +00:00