From a3adeb2ac8d461fe7570bdbe9cde6637f2a0b236 Mon Sep 17 00:00:00 2001 From: igneum-labs <337424239+igneum-labs@users.noreply.github.com> Date: Tue, 6 Oct 2026 08:34:28 +0000 Subject: [PATCH] Counter ASIC 3.0 items 6 and 7: PC 2 family playbook posts both card key forms from settings.json, confirms the card quiet by the process list, restores cards and prover in a finally block --- tools/ca3-reserve/pc2-family-probe.ps1 | 52 +++++++++++++++++++++----- 1 file changed, 43 insertions(+), 9 deletions(-) diff --git a/tools/ca3-reserve/pc2-family-probe.ps1 b/tools/ca3-reserve/pc2-family-probe.ps1 index 1c2a78c8..21e18fb0 100644 --- a/tools/ca3-reserve/pc2-family-probe.ps1 +++ b/tools/ca3-reserve/pc2-family-probe.ps1 @@ -1,26 +1,56 @@ # Counter ASIC 3.0 item 6 (6 October 2026): the step cost of every reserve candidate family of spec 1.13.2 on PC 2's # RTX 5090 (docs/plans/counter-asic-3-reserve.md). A signed `run` job published with --stop-miners: the app stops its # miners before this script starts and restarts them when it ends (app/igneum-app/src/jobrun.rs, stop_miners_first); -# the script never quits, restarts or updates the app. It switches the prover off for the run and back on at the end -# (as tools/prover-floor/pc2-floor-measure.ps1 does), confirms the card is empty by nvidia-smi's compute-apps list -# (never api/state, which answers {} on this machine), writes proto-cuda/family-probe.cu (inlined below by +# the script also switches the NVIDIA card off through POST api/cards with the settings.json key in both forms (with and +# without the device index; 6 October 2026: the index-less form switched nothing on 5 October) and restores it, and +# switches the prover off for the run and back on, both in a finally block; it never quits, restarts or updates the +# app and never writes settings.json. The card is confirmed quiet by nvidia-smi's compute-apps list and the process +# list (never api/state, which answers {} on this machine), writes proto-cuda/family-probe.cu (inlined below by # make-pc2-playbook.sh, sha256 printed on both sides) into the job dir, compiles it with nvcc inside WSL2 # Ubuntu-24.04 (/usr/local/cuda-12.*) and runs it three times. Every number is a RESULT line; the probe's own # "RESULT FAMILY ..." lines carry kernel, best ms, G steps/s, ns per step, the ratio to the alu chain and ok=1 for # bit-exact against the CPU reference on two whole warps. Read back with `node tools/jobs.mjs `. $ErrorActionPreference = 'Continue' -$urlFile = if ($env:IGNEUM_APP_DIR) { Join-Path $env:IGNEUM_APP_DIR 'app.url' } else { Join-Path $env:LOCALAPPDATA 'igneum\app\app.url' } +$appDir = if ($env:IGNEUM_APP_DIR) { $env:IGNEUM_APP_DIR } else { Join-Path $env:LOCALAPPDATA 'igneum\app' } +$urlFile = Join-Path $appDir 'app.url' if (-not (Test-Path $urlFile)) { $urlFile = Join-Path $env:LOCALAPPDATA 'igneum\app\app.url' } $base = (Get-Content $urlFile -Raw).Trim().TrimEnd('/') function Stamp { (Get-Date).ToUniversalTime().ToString('yyyy-MM-ddTHH:mm:ssZ') } function Prove($on) { try { (Invoke-RestMethod -Method Post -Uri "$base/api/prove" -ContentType 'application/json' -Body (@{on=$on} | ConvertTo-Json -Compress) -TimeoutSec 10) | ConvertTo-Json -Compress } catch { "error: $_" } } function Smi($q) { try { (& nvidia-smi --query-gpu=$q --format=csv,noheader,nounits 2>$null) -join ' | ' } catch { 'nvidia-smi failed' } } function CudaApps { @(& nvidia-smi --query-compute-apps=pid,process_name,used_memory --format=csv,noheader 2>$null | ForEach-Object { "$_" } | Where-Object { $_ -match 'igneum|sp1|prove' }) } -"RESULT start $(Stamp) prover off for the run: $(Prove $false)" +function WorkerProcs { @(Get-Process -ErrorAction SilentlyContinue | Where-Object { $_.ProcessName -match 'igneum-worker|igneum-miner' } | ForEach-Object { $_.ProcessName + ':' + $_.Id }) } +# the app's NVIDIA cards from its settings.json (READ ONLY; key = vendor:device:name), never api/state (it answers {} here). +# 6 October 2026 (coordinator): the 5 October scripts posted the key without the device index and switched nothing, so +# both forms are posted: the settings key as written and vendor:device. +$nvCards = @() +try { + $sj = Get-Content -LiteralPath (Join-Path $appDir 'settings.json') -Raw | ConvertFrom-Json + foreach ($prop in $sj.cards.PSObject.Properties) { + if ($prop.Name -like 'nvidia:*') { + $v = $prop.Value; $pp = [int] $v.power_pct; if ($pp -lt 50) { $pp = 80 } + $parts = $prop.Name -split ':' + $nvCards += @{ key = $prop.Name; short = ($parts[0] + ':' + $parts[1]); enabled = [bool] $v.enabled; identities = [int] $v.identities; power_pct = $pp } + } + } +} catch { "RESULT settings_read_failed $_" } +function SetCards([bool] $enabled) { + foreach ($c in $nvCards) { + foreach ($k in @($c.key, $c.short)) { + $body = @{ cards = @(@{ key = $k; enabled = $enabled; identities = $c.identities; power_pct = $c.power_pct }) } | ConvertTo-Json -Depth 5 + try { Invoke-RestMethod -Uri "$base/api/cards" -Method POST -Body $body -ContentType 'application/json' -TimeoutSec 10 | Out-Null; "RESULT cards key=$k enabled=$enabled posted" } catch { "RESULT cards key=$k enabled=$enabled error: $_" } + } + } +} +"RESULT start $(Stamp) nvidia cards in settings.json: $(($nvCards | ForEach-Object { $_.key + ' enabled=' + $_.enabled + ' identities=' + $_.identities + ' power_pct=' + $_.power_pct }) -join ' | ')" +"RESULT workers_before $(Stamp) $((WorkerProcs) -join ' ') cuda_apps=[$((CudaApps) -join '; ')]" +try { +"RESULT prover_off $(Stamp) $(Prove $false)" +SetCards $false Start-Sleep -Seconds 30 -$t = 0; $apps = @(CudaApps) -while ($t -lt 120 -and $apps.Count -gt 0) { Start-Sleep -Seconds 10; $t += 10; $apps = @(CudaApps) } -if ($apps.Count -eq 0) { "RESULT card $(Stamp) empty after $t s (no igneum, sp1 or prove compute app on the card)" } else { "RESULT card $(Stamp) UNCONFIRMED after $t s: the numbers below are beside " + ($apps -join '; ') } +$t = 30; $apps = @(CudaApps); $procs = @(WorkerProcs | Where-Object { $_ -match 'cuda' }) +while ($t -lt 150 -and ($apps.Count -gt 0 -or $procs.Count -gt 0)) { Start-Sleep -Seconds 10; $t += 10; $apps = @(CudaApps); $procs = @(WorkerProcs | Where-Object { $_ -match 'cuda' }) } +if ($apps.Count -eq 0 -and $procs.Count -eq 0) { "RESULT card $(Stamp) quiet after $t s (no igneum, sp1 or prove compute app; no igneum-worker-cuda process): the card to itself" } else { "RESULT card $(Stamp) UNCONFIRMED after $t s: the rows below are beside compute apps [" + ($apps -join '; ') + "] procs [" + ($procs -join ' ') + "]" } "RESULT gpus $(Stamp) $(Smi 'index,name,driver_version,memory.used,clocks.sm,clocks.mem,power.draw,temperature.gpu')" $job = $env:IGNEUM_JOB_DIR; if (-not $job) { $job = Join-Path $env:TEMP 'igneum-ca3-family' }; New-Item -ItemType Directory -Force -Path $job | Out-Null $cu = @' @@ -59,5 +89,9 @@ $bashFile = Join-Path $job 'measure.sh' [IO.File]::WriteAllText($bashFile, ($bash -replace "`r`n", "`n"), (New-Object System.Text.UTF8Encoding $false)) & wsl.exe -d Ubuntu-24.04 -u root -- bash (WslPath $bashFile) 2>&1 | ForEach-Object { ($_ -replace "`0", '') } "RESULT gpus_after $(Stamp) $(Smi 'clocks.sm,clocks.mem,power.draw,temperature.gpu')" -"RESULT end $(Stamp) prover back on: $(Prove $true)" +} finally { + # whatever happened above: the cards back to their settings.json state and the prover ON (the clear file's rule) + foreach ($c in $nvCards) { if ($c.enabled) { SetCards $true } } + "RESULT end $(Stamp) prover back on: $(Prove $true)" +} exit 0