examples: fixed_patch_circle reports its blocked tiles (fix unbound fine_block)

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

examples/fixed_patch_circle.py

@@ -1,9 +1,9 @@
 """Public API demo: fixed 2:1 patch with a stationary, optionally actuated circle.
 
 From this checkout, after checking the selected physical GPU is idle:
-    PYTHONPATH="$PWD/src" CUDA_VISIBLE_DEVICES=0 python examples/fixed_patch_circle.py --fine-block 16 20
-    ... --speed -0.002 --fine-block 16 20 --mode slot_reservoir
-Omit --fine-block for the (equivalent) dense fine storage.
+    PYTHONPATH="$PWD/src" CUDA_VISIBLE_DEVICES=0 python examples/fixed_patch_circle.py
+    ... --speed -0.002 --mode slot_reservoir
+Both levels use blocked storage (--base-block, --fine-block tiles).
 
 A short smoke run (default 128 coarse steps): it shows setup, stepping and
 fluid-only diagnostics, not a developed flow, accuracy or long-time stability.
@@ -71,8 +71,10 @@ def main():
     parser.add_argument("--mode", choices=("periodic", "slot_reservoir"), default="periodic")
     parser.add_argument("--speed", type=float, default=.002,
                         help="normal surface velocity, coarse lattice units (+ blows, - sucks, 0 passive)")
-    parser.add_argument("--fine-block", type=int, nargs=2, metavar=("BY", "BX"),
-                        help="blocked fine storage; must divide the whole fine allocation (32 x 40 here)")
+    parser.add_argument("--base-block", type=int, nargs=2, metavar=("BY", "BX"), default=(12, 8),
+                        help="root tile; must divide the 24 x 32 root")
+    parser.add_argument("--fine-block", type=int, nargs=2, metavar=("BY", "BX"), default=(16, 20),
+                        help="fine tile; must divide the whole fine allocation (32 x 40 here)")
     parser.add_argument("--steps", type=int, default=128)
     args = parser.parse_args()
     if args.steps < 0:
@@ -86,20 +88,20 @@ def main():
     body = SimObject(0, geometry=CircleGeometry(*CENTER, RADIUS), center=CENTER, radius=RADIUS,
                      surface_actuation=spec)
     cfg = config(args.mode)
-    fine_block = tuple(args.fine_block) if args.fine_block else None
     # The caller owns the CUDA context; the stepper must be closed first (the
     # nested with-statement does that).
     with CudaContext(0) as context, FixedPatchStepper(
             cfg, context=context, coarse_boundary=args.mode, refinements=[BOUNDS],
-            level_blocks=[None, fine_block], level_objects=[(), (body,)]) as run:
+            level_blocks=[tuple(args.base_block), tuple(args.fine_block)],
+            level_objects=[(), (body,)]) as run:
         p = run.patch
         # Rest equilibrium is already postcollision G, so no initial collision is
         # needed. Non-leaf entries (covered, ghost, solid) are discarded by initialize.
         rest = np.asarray(compute_feq_d2q9(1.0, 0.0, 0.0), np.float32)[:, None, None]
         run.initialize(np.broadcast_to(rest, (9, *p.coarse_shape)),
                        np.broadcast_to(rest, (9, *p.fine_shape)))
-        storage = f"blocked {fine_block}" if fine_block else "dense"
-        print(f"mode={args.mode} fine storage={storage} speed={args.speed:+g} "
+        storage = f"blocked root {tuple(args.base_block)} fine {tuple(args.fine_block)}"
+        print(f"mode={args.mode} storage={storage} speed={args.speed:+g} "
               f"(fine allocation {p.fine_shape[0]}x{p.fine_shape[1]}, fine origin {p.fine_origin})")
         masks = leaf_masks(run, args.mode)
         start = leaf_diagnostics(*run.download(), masks)

examples/fixed_patch_jet.py

@@ -31,6 +31,7 @@ from CelerisLab.lbm.refinement import ACTIVE
 from CelerisLab.lbm.refinement_stepper import FixedPatchStepper
 
 BOUNDS, AMPLITUDE, WIDTH = (16, 4, 32, 28), .02, 12
+LEVEL_BLOCKS = [(12, 8), (8, 8)]  # blocked storage: 48x48 root, 56x40 fine window
 TIMES, MAX_MACH, MAX_SECONDS = (0, 300, 1200), .1, 120
 
 
@@ -132,7 +133,8 @@ def main():
                   lattice_model='D2Q9', collision='SRT', streaming='double_buffer',
                   store_precision='FP32', ddf_shifting=False, les_enabled=False)
     report = dict(config=dict(nx=48, ny=48, bounds=BOUNDS, W=WIDTH, A=AMPLITUDE, nu=.1,
-                              rho=1, tau_coarse=.8, tau_fine=1.1, coarse_boundary='slot_reservoir'),
+                              rho=1, tau_coarse=.8, tau_fine=1.1, coarse_boundary='slot_reservoir',
+                              level_blocks=LEVEL_BLOCKS),
                   guards=dict(check_every=50, positive_density=True, finite=True,
                               max_Mach=MAX_MACH, max_seconds=MAX_SECONDS,
                               timing='cooperative checks, not an exact interruption deadline'),
@@ -149,7 +151,8 @@ def main():
     start, run = time.monotonic(), None
     try:
         with CudaContext(0) as context, FixedPatchStepper(cfg, context=context,
-                coarse_boundary='slot_reservoir', refinements=[BOUNDS]) as run:
+                coarse_boundary='slot_reservoir', refinements=[BOUNDS],
+                level_blocks=LEVEL_BLOCKS) as run:
             p = run.patch
             masks = [np.ones(p.coarse_shape, bool), p.fine_kind == ACTIVE]
             masks[0][[0, -1]] = False

tests/unit/test_example_tiles.py

@@ -0,0 +1,65 @@
+"""The public examples run all-blocked: their level tiles must reach the device unchanged.
+
+Host only: a context whose activation raises proves construction (layouts, tables,
+boundary checks) succeeded up to the first CUDA call.
+"""
+import ast
+from dataclasses import replace
+from pathlib import Path
+import unittest
+from unittest.mock import Mock
+
+from CelerisLab.body.geometry.circle import CircleGeometry
+from CelerisLab.body.objects import SimObject
+from CelerisLab.config import LBMConfig
+from CelerisLab.lbm.refinement_stepper import FixedPatchStepper
+
+EXAMPLES = Path(__file__).resolve().parents[2] / "examples"
+
+
+def literal(name, constant):
+    """Module-level literal from an example, read without importing it (no pycuda)."""
+    tree = ast.parse((EXAMPLES / name).read_text())
+    for node in tree.body:
+        if isinstance(node, ast.Assign):
+            for target in node.targets:
+                names = target.elts if isinstance(target, ast.Tuple) else [target]
+                for i, t in enumerate(names):
+                    if isinstance(t, ast.Name) and t.id == constant:
+                        value = node.value.elts[i] if isinstance(target, ast.Tuple) else node.value
+                        return ast.literal_eval(value)
+    raise KeyError(constant)
+
+
+def forbidden():
+    return Mock(activate=Mock(side_effect=AssertionError("CUDA reached")), sm_arch="sm_70")
+
+
+class ExampleTiles(unittest.TestCase):
+    def test_fixed_patch_jet_tiles(self):
+        bounds, blocks = literal("fixed_patch_jet.py", "BOUNDS"), literal("fixed_patch_jet.py", "LEVEL_BLOCKS")
+        width, amplitude = literal("fixed_patch_jet.py", "WIDTH"), literal("fixed_patch_jet.py", "AMPLITUDE")
+        cfg = LBMConfig(nx=48, ny=48, viscosity=.1, velocity=0., wall_slot_width=width,
+                        wall_normal_velocity=amplitude, y_wall_bc="on_site_velocity",
+                        top_wall_bc="reservoir")
+        with self.assertRaisesRegex(AssertionError, "CUDA reached"):
+            FixedPatchStepper(cfg, context=forbidden(), coarse_boundary="slot_reservoir",
+                              refinements=[bounds], level_blocks=[tuple(b) for b in blocks])
+
+    def test_fixed_patch_circle_default_tiles(self):
+        bounds = literal("fixed_patch_circle.py", "BOUNDS")
+        nx, ny = literal("fixed_patch_circle.py", "NX"), literal("fixed_patch_circle.py", "NY")
+        center, radius = literal("fixed_patch_circle.py", "CENTER"), literal("fixed_patch_circle.py", "RADIUS")
+        body = SimObject(0, geometry=CircleGeometry(*center, radius), center=center, radius=radius)
+        periodic = LBMConfig(nx=nx, ny=ny, viscosity=.1)
+        slot = replace(periodic, velocity=0, wall_normal_velocity=.001, wall_slot_width=8,
+                       y_wall_bc="on_site_velocity", top_wall_bc="reservoir")
+        for mode, cfg in (("periodic", periodic), ("slot_reservoir", slot)):
+            with self.subTest(mode=mode), self.assertRaisesRegex(AssertionError, "CUDA reached"):
+                FixedPatchStepper(cfg, context=forbidden(), coarse_boundary=mode,
+                                  refinements=[bounds], level_blocks=[(12, 8), (16, 20)],
+                                  level_objects=[(), (body,)])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/validation/multigrid/test_refinement_blocked_base.py

@@ -2,6 +2,34 @@
 
 Run CPU and GPU classes in separate processes. GPU callers must first check
 resources/device availability; this file never selects or reserves a GPU.
+
+Dense/blocked route parity (DenseBlockedRouteParity): the same configuration,
+initial state, body/Jet schedule and tilings on three storage routes, only
+level_blocks varying: D/D [None, None], D/B [None, FINE_BLOCK] (dense root,
+the mixed pattern of current examples) and B/B [(12, 8), FINE_BLOCK]. Gate:
+every public and owner array identical in FP32 bits and NaN masks at steps
+0, 1, 2, 8 and after re-initialize; D/B and B/B raw-exchange ledgers equal.
+No tolerance. A mismatch is reported with route pair/level/step and diagnosed
+(boundary semantics vs arithmetic ordering), never widened.
+
+Route capabilities (rejections checked before CUDA by test_route_capability_matrix):
+
+  combination                                   D/D       D/B       B/B
+  periodic / slot_reservoir root, fine circle   yes       yes       yes   (parity gate)
+  actuated circle, velocity Jet + amplitude     yes       yes       yes   (parity gate)
+  raw/window exchange on a body level           rejected  yes       yes
+  shifted storage                               rejected  rejected  yes
+  projected explosion                           rejected  rejected  yes
+  channel root                                  rejected  rejected  yes
+  several L1 rectangles                         rejected  rejected  yes
+  depth >= 3 with a dense level                 rejected  rejected  yes
+Slot/reservoir walls are compile-time WALL_* macros on a dense root and the
+d_block_wall constant on a blocked root: BC-encoding parity, bit-identical by
+this gate. Dense fine bodies use CurvedLinkSoA + CurvedBoundaryKernel
+(n_objects > 0), blocked ones BlockCurvedBoundary; same links and physics,
+compared through the population rows. Parked here: MRT (covered by
+test_refinement_mrt_gpu::test_dense_versus_blocked_mrt_two_level), shifted and
+depth >= 3 (no dense route to compare), several bodies (later slice).
 """
 from contextlib import ExitStack, contextmanager, nullcontext
 from dataclasses import replace
@@ -20,6 +48,7 @@ from CelerisLab.lbm.descriptors import D2Q9_EX, D2Q9_EY
 from CelerisLab.lbm.refinement import ACTIVE, OUTER_GHOST, FixedPatch2D
 from CelerisLab.lbm.refinement_stepper import FixedPatchStepper, blocked_base_tables
 from test_refinement_blocked_fine import NX, NY, BOUNDS, config, state, circle, actuation
+from test_refinement_jets import SPEED, jet
 
 BASE_BLOCKS = ((24, 32), (12, 8), (3, 4), (1, 1))
 FINE_BLOCK = (16, 20)
@@ -324,5 +353,128 @@ class BlockedBaseGPU(unittest.TestCase):
                             print(f"PASS {label}: full finite bits/NaN masks at 0,1,2,8 + reset", flush=True)
 
 
+ROUTES = (("D/D", [None, None]), ("D/B", [None, FINE_BLOCK]), ("B/B", [(12, 8), FINE_BLOCK]))
+
+
+def same_summary(a, b):
+    """Exact equality of nested exchange summaries (dicts, sequences, arrays, numbers)."""
+    if isinstance(a, dict):
+        return a.keys() == b.keys() and all(same_summary(a[k], b[k]) for k in a)
+    if isinstance(a, (list, tuple)):
+        return len(a) == len(b) and all(same_summary(x, y) for x, y in zip(a, b))
+    a, b = np.asarray(a), np.asarray(b)
+    if a.dtype.kind in "biufc" and b.dtype.kind in "biufc":
+        return a.shape == b.shape and np.array_equal(a, b, equal_nan=True)
+    return a.dtype == b.dtype and np.array_equal(a, b)  # labels such as the window name
+
+
+class DenseBlockedRouteCPU(unittest.TestCase):
+    def test_same_summary_compares_labels_and_every_number(self):
+        ledger = {"window": "last_base_step", "time_start": 3, "total": {"force": [1.0, -2.0],
+                  "torque": 0.5}, "aperture": {"force": np.array([np.nan, 1.0])}}
+        self.assertTrue(same_summary(ledger, replace_value(ledger, ())))
+        for path, value in ((("window",), "last_substep"), (("time_start",), 4),
+                            (("total", "force"), [1.0, -2.000001]), (("total", "torque"), 0.25),
+                            (("aperture", "force"), np.array([0.0, 1.0]))):
+            with self.subTest(path=path):
+                self.assertFalse(same_summary(ledger, replace_value(ledger, path, value)))
+                self.assertFalse(same_summary(replace_value(ledger, path, value), ledger))
+
+    def test_route_capability_matrix(self):
+        context = Mock(activate=Mock(side_effect=AssertionError("CUDA reached")))
+        periodic = config("periodic")
+        inner = (BOUNDS[0] + 2, BOUNDS[1] + 2, BOUNDS[2] - 2, BOUNDS[3] - 2)
+        second = (BOUNDS[0], BOUNDS[1], BOUNDS[0] + 2, BOUNDS[1] + 2)
+        cases = (
+            ("raw exchange on dense body level", periodic, dict(
+                level_blocks=[None, None], level_objects=[(), (circle(),)], observe_raw_exchange=True)),
+            ("shifted D/D", replace(periodic, ddf_shifting=True), dict(level_blocks=[None, None])),
+            ("shifted D/B", replace(periodic, ddf_shifting=True), dict(level_blocks=[None, FINE_BLOCK])),
+            ("projected D/D", periodic, dict(level_blocks=[None, None], explosion="projected_linear")),
+            ("projected D/B", periodic, dict(level_blocks=[None, FINE_BLOCK], explosion="projected_linear")),
+            ("channel D/B", periodic, dict(level_blocks=[None, FINE_BLOCK], coarse_boundary="channel")),
+            ("several L1 rectangles", periodic, dict(refinements=[[BOUNDS, second]], level_blocks=[None, None])),
+            ("depth 3 dense", periodic, dict(refinements=[BOUNDS, inner], level_blocks=[None, None, None])),
+        )
+        for label, cfg, kw in cases:
+            kw.setdefault("refinements", [BOUNDS])
+            with self.subTest(label), self.assertRaises(ValueError):
+                FixedPatchStepper(cfg, context=context, **kw)
+        context.activate.assert_not_called()
+
+
+def replace_value(tree, path, value=None):
+    """Deep copy of a nested dict with the item at ``path`` replaced (no change for ())."""
+    if isinstance(tree, dict):
+        return {k: (value if path == (k,) else replace_value(v, path[1:], value) if path[:1] == (k,)
+                    else replace_value(v, (), None)) for k, v in tree.items()}
+    return np.array(tree, copy=True) if isinstance(tree, np.ndarray) else tree
+
+
+class DenseBlockedRouteParity(unittest.TestCase):
+    """D/D vs D/B vs B/B, unshifted SRT, one circle or one velocity Jet; see module docstring."""
+
+    def run_routes(self, mode, objects=(), jets=(), switch=None):
+        from CelerisLab.cuda.context import CudaContext
+        cfg = config(mode)
+        p = FixedPatch2D.from_config(cfg, BOUNDS)
+        arrays = state(NY, NX, 1), state(*p.fine_shape, 2)
+        results = {}
+        with CudaContext(0) as context:
+            for name, blocks in ROUTES:
+                observe = bool(objects) and blocks[1] is not None
+                snapshots, ledgers = [], []
+                with FixedPatchStepper(cfg, context=context, coarse_boundary=mode, refinements=[BOUNDS],
+                                       level_blocks=blocks, level_objects=[(), tuple(objects)],
+                                       level_jets=[(), tuple(jets)],
+                                       observe_raw_exchange=observe) as backend:
+                    backend.initialize(*arrays)
+                    for step in (0, 1, 2, 8):
+                        if step == 8 and switch is not None:
+                            backend.set_jet_amplitude(0, switch)
+                        backend.step(step - backend.step_count)
+                        snapshots.append(backend.download() + raw(backend))
+                        if observe and step:
+                            ledgers.append(tuple(backend.read_raw_exchange(0, window=window)
+                                                 for window in ("last_base_step", "last_substep")))
+                    backend.initialize(*arrays)
+                    snapshots.append(backend.download() + raw(backend))
+                results[name] = snapshots, ledgers
+        return results
+
+    def check(self, label, results):
+        reference, _ = results["D/D"]
+        for name in ("D/B", "B/B"):
+            for step, actual, expected in zip((0, 1, 2, 8, "reset"), results[name][0], reference):
+                for index, (a, b) in enumerate(zip(actual, expected)):
+                    exact(self, a, b, f"{label} {name} vs D/D step={step} array={index}")
+        if results["D/B"][1]:
+            for step, a, b in zip((1, 2, 8), results["D/B"][1], results["B/B"][1]):
+                self.assertTrue(same_summary(a, b), f"{label} raw exchange D/B vs B/B step={step}")
+        for name, (snapshots, _) in results.items():
+            masses = [float(np.nansum(level.astype(np.float64))) for level in snapshots[3][:2]]
+            print(f"{label} {name}: step 8 mass by level {masses}", flush=True)
+        print(f"PASS {label}: D/D = D/B = B/B bits/NaN masks at 0,1,2,8 + reset", flush=True)
+
+    def test_body_free(self):
+        for mode in ("periodic", "slot_reservoir"):
+            self.check(f"{mode} body-free", self.run_routes(mode))
+
+    def test_passive_circle(self):
+        for mode in ("periodic", "slot_reservoir"):
+            self.check(f"{mode} circle", self.run_routes(mode, objects=[circle()]))
+
+    def test_actuated_circle(self):
+        for mode in ("periodic", "slot_reservoir"):
+            for speed in (SPEED, -SPEED):
+                self.check(f"{mode} actuated {speed}",
+                           self.run_routes(mode, objects=[circle(actuation(speed))]))
+
+    def test_velocity_jet_with_amplitude_switch(self):
+        for mode in ("periodic", "slot_reservoir"):
+            self.check(f"{mode} jet switch",
+                       self.run_routes(mode, objects=[circle()], jets=[jet()], switch=-SPEED))
+
+
 if __name__ == "__main__":
     unittest.main()