Counter ASIC 3.0 status: family run d (AMD compile answers; the loaded-card ratios unusable; run e with the card alone)

docs/plans/counter-asic-3-status.md

@@ -147,6 +147,7 @@ The live observer runs the shared checkout, which autosync fast-forwards from or
 |---|---|---|
 | item 3 (43c3ead) | spec 01 section 1.13.1's era table and `docs/plans/mixer-x4.md` section 2 still said `mixer_mult = 4`; the code (`LoadClass::MX8`, `V3_CLASS`) and spec 1.8.5 say 8 | both lines corrected on ca3-coord, 6 October 2026 |
 | PC 1 job 2 (family, run-ca3-pc1-amd-family-20261006, 16:56 to 16:59Z) | the probe ran on device 0, the integrated gfx1036, not the 9070 XT (device 1): every row `dev=0 name=` empty, alu 40.59 G steps/s (a one-CU figure); the rows are RDNA 2 iGPU ratios (shifts 1.15, bfe 1.15 native, andn 1.16, popc 1.55, clz 1.75, sel 1.81, shfla and shflx 1.89 through ds_bpermute, perm 2.43 and dot4 2.57 emulated, mm8 none: AMD's OpenCL C compiles no byte-permute, dot4 or WMMA builtin) and the 9070 XT column stays owed | the probe picks the device by name (gfx1201 on the newest AMD platform) and prints it in every row; re-run in the next PC 1 slot |
+| PC 1 family run d (run-ca3-pc1-amd-family-20261006-d, 17:17 to 17:20Z, exit 0; run b had failed because the script's probe parameter was named `$args`, PowerShell's automatic variable, so the splat was empty: renamed, with a rule added to `tools/ci/ps-drive-ref-check.sh` that fires on the old signature and stays quiet on the new) | the probe chose the 9070 XT by name (gfx1201, 32 CUs); every variant built on it: mm8 NATIVE through the WMMA builtin on gfx12 (exact unverified), dot4 native (sudot4), bfe native, the shuffles native (ds_bpermute, ds_swizzle), the byte permute EMULATED (no amd_perm path in AMD's OpenCL C). The step costs are unusable: the card was mining beside the probe, the alu chain read 226 then 195 G steps/s and the ratios swung from 5.9 to 11.8x (run 1) to 0.17 to 1.3x (run 2), the loaded card's scheduler | the 9070 XT column is taken with the card alone (run e, job 1's switch path), after the G2 job |
 | the identities job, first run (run-ca3-pc1-amd-identities-20261006, 17:02:10Z, failed in 0 s) | my own script: `"... under $appDir: nothing posted"` is a PowerShell 5.1 parse error (`$appDir:` reads as a drive-qualified variable), so the script never started; the script worker checks this shape by hand, CI did not | `${appDir}:`; the class guard `tools/ci/ps-drive-ref-check.sh` added to ci.yml (67 .ps1 files clean; a backtick-escaped `$` in a bash-generating here-string is ignored); the job republished as -b |
 | the identities job, run c (run-ca3-pc1-amd-identities-20261006-c, 17:05:53 to 17:07:53Z, done) | the 9070 XT's live entry amd:gfx1201 read identities 2 at 18.91 MH/s and 203 W before; the one POST (the app's cards-array shape) and a 120 s settle; after: identities 8, mining under a new worker pid, 18.9 MH/s (avg 18.77), 199 W. The identities count moves no rate (18.92 at 2 was the number to beat). Run b of the same job had failed on the flat body shape (400) | closed: PC 1's 9070 XT runs as it did before job 1 |
 | the reset job (16:55Z) | the 9070 XT's ADLX state read factory 0 after Ember run 6 (offsets zero, the flag cleared by the engine's set of 0); the app runs the card under amd:gfx1201 with identities 2 where it ran 8 before job 1's restore | the reset to factory 1 applied and read back; the one POST api/cards back to 8 identities running as its own job, the rate before and after recorded |