rtx-cfd/rtx-fsi PERF-2 P3-iii: the MarchPlane — lane-table V-cycle kernels (ml_*), the batched apply over K lanes' own operators, the plane rendezvous inside the CG's preconditioner (lane thread-local, CG guard), set_plane_lane/plane_counters; the fsi2_overset_plane driver (K lane threads, one process); G-P0 unit tests: K distinct operators batched = solo apply bit for bit, uneven lanes served exactly

Co-Authored-By: Claude Fable 5.1 <[email protected]>

crates/specialized/rtx-cfd/tests/gpu_kernel_comprehensive_tests.rs

@@ -420,7 +420,10 @@ mod gpu_kernel_tests {
 
         // Check that center has highest value
         let center_val = phi_result[center];
-        assert!(center_val < 0.0, "Center value should be negative (∇²φ = f, a positive source)");
+        assert!(
+            center_val < 0.0,
+            "Center value should be negative (∇²φ = f, a positive source)"
+        );
 
         Ok(())
     }