campaigns: likelihood-lifecycle phase 2 row (2d-2g batch 0)

campaigns.yaml

@@ -145,6 +145,22 @@ campaigns:
     no project wiki/results/issue change since 2026-10-13 beyond autolens_profiling#420/#422/#424
     (interferometer only); releases 2026.10.16.1/.2 and 2026.10.17.1 supply no new measurement.'
   evidence: https://github.com/PyAutoLabs/autolens_profiling/blob/4db4d988e520a82219152743748c3188d485a4ba/wiki/campaigns/certified_positive_solver.md
+- id: likelihood-lifecycle
+  title: Likelihood lifecycle phase 2 (per-dataset-type runtime and breakdown cells on the pinned release)
+  status: active
+  updated: '2026-10-30'
+  next: 'Phase 2 sub-campaigns 2a-2g on pin 2026.10.25.1 (epic in Mind draft/research/autolens_profiling/likelihood_lifecycle_epic.md).
+    2a imaging, 2b interferometer and 2c point source rows committed (#461, #483, #480); 2b/2c quiet RAL
+    reruns in flight on their own branches. 2d multi_galaxy+group, 2e cluster, 2f multi_dataset+datacube and
+    2g weak: batch 0 ran 2026-10-29 (RAL 413272-413274/413292-413293, A100 413294-413297; all 56 legs exit 0,
+    every parity witness match, jax 0.11.2 with the eigen flag on every CPU leg). Walls commit
+    autolens_profiling#487 sets batch 1 at 0:30-1:30 (human /prm pending). 2g rows (the campaign''s rows
+    under D9) in autolens_profiling#488, stacked on #487. Human ruling 2026-10-30: loaded RAL nodes accepted
+    (batch-0 RAL rows had loadavg 95-109); batch 1 runs on shared ral nodes with no quiet gate. 2d driver
+    fixed to keep the eigen flag off GPU legs (#487, 830314e9). Batch 1 submitted 2026-10-30 (human go) from
+    autolens_profiling_p2dg at 830314e9 (#487 head, unmerged): RAL 413445-413452 (ral arrays), A100
+    413453-413459 (one job each). Next: verify batch 1, then PR B for 2d/2e/2f.'
+  evidence: https://github.com/PyAutoLabs/autolens_profiling/pull/487
 tasks:
 - id: setup_baseline_campaign
   campaign: setup-baseline

dashboard.md

@@ -1,6 +1,6 @@
 # PyAutoPulse — profiling dashboard
 
-<!-- pulse-campaigns:3283e557de1d110da97abe4c9ffeaed914e3a35fa18b55feff3e32ebb760654d -->
+<!-- pulse-campaigns:84cc47237d7c19f44558da7a0bc541c9efc3d1354cbb622031aa73aec5b7a23b -->
 ## Profiling Check In
 
 <details><summary>Full check-in prompt</summary>
@@ -182,6 +182,17 @@ Reviewed 2026-10-17. Parked unchanged. No new campaign evidence; existing C2/lib
 ### Active tasks
 
 
+</details>
+
+<details><summary>Likelihood lifecycle phase 2 (per-dataset-type runtime and breakdown cells on the pinned release) — active</summary>
+
+Reviewed 2026-10-30. Phase 2 sub-campaigns 2a-2g on pin 2026.10.25.1 (epic in Mind draft/research/autolens_profiling/likelihood_lifecycle_epic.md). 2a imaging, 2b interferometer and 2c point source rows committed (#461, #483, #480); 2b/2c quiet RAL reruns in flight on their own branches. 2d multi_galaxy+group, 2e cluster, 2f multi_dataset+datacube and 2g weak: batch 0 ran 2026-10-29 (RAL 413272-413274/413292-413293, A100 413294-413297; all 56 legs exit 0, every parity witness match, jax 0.11.2 with the eigen flag on every CPU leg). Walls commit autolens_profiling#487 sets batch 1 at 0:30-1:30 (human /prm pending). 2g rows (the campaign&#x27;s rows under D9) in autolens_profiling#488, stacked on #487. Human ruling 2026-10-30: loaded RAL nodes accepted (batch-0 RAL rows had loadavg 95-109); batch 1 runs on shared ral nodes with no quiet gate. 2d driver fixed to keep the eigen flag off GPU legs (#487, 830314e9). Batch 1 submitted 2026-10-30 (human go) from autolens_profiling_p2dg at 830314e9 (#487 head, unmerged): RAL 413445-413452 (ral arrays), A100 413453-413459 (one job each). Next: verify batch 1, then PR B for 2d/2e/2f.
+
+[Campaign evidence](https://github.com/PyAutoLabs/autolens_profiling/pull/487)
+
+### Active tasks
+
+
 </details>
 
 [Interactive board](https://pyautolabs.github.io/PyAutoPulse/)

knowledge/xla_cpu_deadlock_jaxlib_0_11_2.md

@@ -117,7 +117,13 @@ going forward". The record, its scope and its revisit conditions are in
 
 - **RAL.** The pin 2026.10.25.1 runs the same jaxlib 0.11.2 on RAL (its 2026.10.17.1
   `hpc_ral_cpu` rows record jaxlib 0.11.2). Whether the deadlock fires on a 236-core RAL node is
-  untested. The 2d legs apply the flag there regardless.
+  untested. The 2d legs apply the flag there regardless. Update 2026-10-30: the 2d-2g batch-0
+  arrays (RAL 413272-413274, 413292-413293; A100 413294-413297; jax/jaxlib 0.11.2 in the shared
+  venv) ran every JAX CPU leg with the flag and none hung (all 56 legs exit 0). Without the flag
+  on RAL is still untested.
+- **The flag on 2d GPU legs.** The 2d driver appends the flag whatever the platform, so all 14
+  2d A100 rows, GPU legs included, record it in `device.xla_flags`; the shared preamble keeps it
+  off the 2e-2g GPU legs (autolens_profiling#487).
 - **The 2a / 2b JAX CPU cells.** They were measured without the flag and completed. Nobody has
   tested whether those executables are susceptible on repeated calls, or whether a longer run
   (a fit) would hang.