kernels: name compilation entries by storage route (uniform.cu, blocked.cu)

kernel_v2.cu -> uniform.cu (whole-domain NX/NY, Simulation) and
blocks.cu -> blocked.cu (one block window, every blocked level), with
InitTubeFlow_v2 -> InitTubeFlow. All live callers, include comments,
CONFIG.md, lifecycle doc and current-tree tests move together; no alias.
refinement.cu keeps its name until the dense-route decision.
Historical-revision tooling that names the old files (LES source pins,
timing/J campaign runners, TG run_case, supported_settings citations at
888c8038, development notes) is unchanged on purpose.
No arithmetic change; the PTX symbol InitTubeFlow_v2 is renamed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/unit/test_build_contracts.py

@@ -168,7 +168,7 @@ class BuildContracts(unittest.TestCase):
                 with self.assertRaises(subprocess.CalledProcessError):
                     compiler.compile_kernel(build_dir=build)
             self.assertEqual(Path(previous).read_bytes(), old_bytes)
-            self.assertEqual(sorted(Path(build).glob("kernel_v2-*.ptx")), [])  # no partial output
+            self.assertEqual(sorted(Path(build).glob("uniform-*.ptx")), [])  # no partial output
             compiler.cleanup_build_dir(build)
 
 

tests/unit/test_numerical_operators.py

@@ -135,6 +135,6 @@ def test_d2_entrypoint_compiles_in_isolation(tmp_path, model, shift, storage):
             source=re.sub(r"(#define\s+"+key+r"\s+)\S+",lambda match: match[1]+str(value),source)
         path.write_text(source)
     result=subprocess.run([nvcc,"-ptx","-arch=sm_70","-std=c++17",
-                           str(copy/"kernel_v2.cu"),"-o",str(tmp_path/"kernel.ptx")],
+                           str(copy/"uniform.cu"),"-o",str(tmp_path/"kernel.ptx")],
                           capture_output=True,text=True)
     assert result.returncode == 0, result.stderr

tests/unit/test_planar_velocity.py

@@ -18,7 +18,7 @@ from .test_state_regressions import device, make_field, manager
 def test_planar_helper_moments_and_known_populations(tmp_path):
     root = Path(__file__).resolve().parents[2]
     assert Path(CelerisLab.__file__).resolve() == root/'src/CelerisLab/__init__.py'
-    assert Path(compiler.kernel_path('kernel_v2.cu')).resolve() == root/'src/CelerisLab/lbm/kernels/kernel_v2.cu'
+    assert Path(compiler.kernel_path('uniform.cu')).resolve() == root/'src/CelerisLab/lbm/kernels/uniform.cu'
     lines = compile_run(tmp_path, 'planar_velocity.cpp', dict(WALL_NORMAL_VELOCITY='0.0f'))
     cx = np.array([0,1,-1,0,0,1,-1,1,-1])
     cy = np.array([0,0,0,1,-1,1,-1,-1,1])

tests/unit/test_refinement_mrt.py

@@ -22,7 +22,7 @@ class RefinementMRTHost(unittest.TestCase):
 
     def test_srt_statements_and_guards_preserved(self):
         """MRT is an additive compile-time branch; SRT statements and other guards remain."""
-        blocks = (KERNELS / "blocks.cu").read_text() + (KERNELS / "step/block_step.cu").read_text()
+        blocks = (KERNELS / "blocked.cu").read_text() + (KERNELS / "step/block_step.cu").read_text()
         channel = (KERNELS / "step/block_channel.cu").read_text()
         block_collision = (KERNELS / "operators/block_collision.cuh").read_text()
         self.assertIn('#include "operators/block_collision.cuh"', blocks)