From d5d7dc56622aafcdfa814c62afc91ade1ccecaa1 Mon Sep 17 00:00:00 2001 From: igneum-labs <337424239+igneum-labs@users.noreply.github.com> Date: Wed, 7 Oct 2026 18:03:59 +0000 Subject: [PATCH] Counter ASIC 3.0 (hash): the PC 1 queue of 7 October 2026, prepared, nothing published: the class v4 efficiency pass (clock locks, v4 against v3, the card alone, elevated), G1 + the AMD ladder on the sub-version 3 kit, item 6's family run e with its re-kit, Ember Tune per card (5080, 9070 XT), the publish lines tools/ca3-v4-amend: pc1-v4-efficiency.ps1 (the job id names the card; -lgc grid 2,850 to 1,400 with the four Ember caps on it, so the owed 5090 clock rows fall out; the fingerprint checked on every step; nvidia-smi sampler by pid; -rgc in finally; voltage: no nvidia-smi lever, the V/F curve follows the lock), pc1-v4-sub3-amd-g1.ps1 (tools/ca3-pc1-amd's G1 + ladder shape on fetch-ca3-v4-sub3-pc1-20261007, the 13 packs' Mac fingerprints as the table), pc1-amd-family-20261007.ps1 (run e, the new kit id only), pc1-ember-card.ps1 (the installed app tunes the one card named by the job id), pc1-publish-20261007.sh (the exact lines, the order, the kit sha256s). Kits built on build-1 with mingw from this tree. CI checks run locally: playbook-quit, copied-sources, bash-body green. The dr736 derive job is not in the queue (its packs are not in this tree). Co-Authored-By: Claude Fable 5.1 --- .../ca3-v4-amend/pc1-amd-family-20261007.ps1 | 149 ++++++++++ tools/ca3-v4-amend/pc1-ember-card.ps1 | 74 +++++ tools/ca3-v4-amend/pc1-publish-20261007.sh | 33 +++ tools/ca3-v4-amend/pc1-v4-efficiency.ps1 | 204 ++++++++++++++ tools/ca3-v4-amend/pc1-v4-sub3-amd-g1.ps1 | 260 ++++++++++++++++++ 5 files changed, 720 insertions(+) create mode 100644 tools/ca3-v4-amend/pc1-amd-family-20261007.ps1 create mode 100644 tools/ca3-v4-amend/pc1-ember-card.ps1 create mode 100755 tools/ca3-v4-amend/pc1-publish-20261007.sh create mode 100644 tools/ca3-v4-amend/pc1-v4-efficiency.ps1 create mode 100644 tools/ca3-v4-amend/pc1-v4-sub3-amd-g1.ps1 diff --git a/tools/ca3-v4-amend/pc1-amd-family-20261007.ps1 b/tools/ca3-v4-amend/pc1-amd-family-20261007.ps1 new file mode 100644 index 00000000..45dfed52 --- /dev/null +++ b/tools/ca3-v4-amend/pc1-amd-family-20261007.ps1 @@ -0,0 +1,149 @@ +# 7 October 2026 copy for the PC 1 queue: tools/ca3-pc1-amd/pc1-amd-family.ps1 (run e) unchanged except the kit id, since a machine +# runs a fetch id once and the 0.3.21 host build wipes the jobs folder: fetch-ca3-pc1-amd-family-20261007 (the probe rebuilt on +# build-1 from this tree's proto-opencl/family-probe.c). +# Counter ASIC 3.0, PC 1 AMD job 2 (6 October 2026, run e: the 9070 XT ALONE): item 6's step cost of every reserve candidate family of spec +# 1.13.2 on PC 1's RX 9070 XT (machine ae432dc7, gfx1201), docs/plans/counter-asic-3-reserve.md, status file section +# 3 "Item 6" (the OWED AMD column). Run a (run-ca3-pc1-amd-family-20261006, 150 s, exit 0) measured ordinal 0, PC 1's +# integrated gfx1036 (one CU: alu 40.59 G steps/s against the 9070 XT's expected 1,000 to 2,000): the device list parse +# ran a second -match after the capturing one, which overwrote $Matches, so every device read idx 0 and an empty name, +# and the probe took a bare ordinal. Run b: the probe picks the card BY NAME (`--device-name gfx1201`, the match on the +# newest AMD platform by driver version, the kit worker's dedup rule; `RESULT device_choice name= index= platform= driver= +# cus=`), prints the device's name, CUs and platform on every RESULT line, and refuses with `RESULT error` when no +# gfx1201 is listed; the older-platform duplicate and the gfx1036 run after it by explicit ordinal, as their own labelled +# columns. Run d (17:17Z, the card by name, every variant built) showed a dependent-chain ratio does NOT survive the +# card's own miner: the alu chain read 226 then 195 G steps/s and the ratios swung from 5.9 to 11.8x to 0.17 to 1.3x +# between runs (the loaded card's scheduler, not the ops), while the Mac and 5090 columns were taken with the card alone. +# Run e: the 9070 XT is switched OFF by the RUNNER (`--cards-off amd:gfx1201` at publish, the app's own card path, put +# back on ANY exit with its own enabled flag, identities and cap: rule of 6 October 2026, a script never posts to +# /api/cards) for its three runs; this script only confirms by the process list that the card's opencl worker is gone; +# the 5090 and the 4070 keep mining (NOT --stop-miners). The gfx1036 and the old-platform columns run +# AFTER the restore, beside the miners, as they are not the card under test. mm8 stays exact=unverified: the gfx12 WMMA +# iu8 16x16x16 fragment layout is in no source at hand, and a guessed CPU layout would turn a wrong guess into exact=no. The probe is the family kit's +# family-probe-cl.exe (proto-opencl/family-probe.c of branch ca3-pc1-amd, cross-compiled with mingw, OpenCL.dll at run +# time; the Mac ran the same source bit-exact on Apple OpenCL), three runs per device, each best of 3 with a fresh seed +# per repetition, device event time, bit-exact against the CPU reference on two whole 32-lane groups. Every family is +# tried through every form AMD's OpenCL C offers; a form that does not compile prints build=failed with the first line +# of the build log and the run goes on (run a's finding: AMD's OpenCL C compiles no amd_perm, no sudot4, no WMMA +# builtin; ds_bpermute does compile). Never quits, pauses, resumes or updates the installed app; never writes +# settings.json. Lines: the probe's own `RESULT FAMILY name= ms= gsteps= ratio= exact= path= variant= ... device= cus= +# platform=` and `RESULT FAMILYBEST ...`, each prefixed `RESULT run= dev=