ClaudeandClaude Opus 5.5
2b10b01c49
Retired with the dense refinement route (results recorded at1573942and2469af7or named as accepted losses): - test_refinement_blocked_base: BlockedBaseGPU exact parity (3 tests), DenseBlockedRouteParity (6 tests incl. MRT and two bodies), DenseBlockedRouteCPU (capability matrix, ledger comparator); - test_refinement_blocked_fine: BlockedFineGPU dense-vs-blocked (3 tests); - test_refinement_mrt_gpu: test_dense_versus_blocked_mrt_two_level; - test_raw_exchange_gpu: test_dense_fine_storage_reference (private link_exchange cut-link oracle, accepted loss); - test_refinement_gpu: test_bounded_equivalence_and_ownership (dense CELERIS_REFINEMENT_AUDIT ownership counters, accepted loss); its physics stays in test_bounded_equivalence_blocked; eight_steps loses the audit branch and the misleading 'ownership/counts PASS' label; - test_fine_surface_gpu: test_fine_surface_four_hops (dense per-hop flux ledger, CurvedLinkSoA reflection oracle, audit counts: accepted losses; raw exchange covers the boundary part only, not full flux closure) and the dense SoA fault tests (missing surface buffer, close frees SoA); blocked equivalents remain in test_refinement_blocked_fine/_base; - test_raw_exchange.test_dense_observation_rejected_before_device_access. New TileContractCPU: level_blocks omitted/None/wrong length/None entry/ wrong arity/non-integer/bool/non-positive/non-tuple/not dividing all raise before CUDA; whole-level tiles reach CUDA. Rejection tests and fixtures pass tiles; launch-order and kernel-text tests follow the blocked root; examples/fixed_periodic_patch uses whole-level tiles (+ host tile test). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
163 lines
8.1 KiB
Python
163 lines
8.1 KiB
Python
"""CPU reduction and real host scheduling with CUDA doubles, not GPU physics."""
|
|
from contextlib import nullcontext
|
|
from dataclasses import replace
|
|
from unittest.mock import Mock
|
|
import numpy as np
|
|
import unittest
|
|
from CelerisLab.body.geometry.circle import CircleGeometry
|
|
from CelerisLab.body.objects import SimObject, SurfaceActuation
|
|
from CelerisLab.config import LBMConfig
|
|
from CelerisLab.lbm.blocks import BlockLayout2D
|
|
from CelerisLab.lbm.refinement import FixedPatch2D, prepare_fine_boundary
|
|
from CelerisLab.lbm.refinement_tables import _prepare_blocked_boundary
|
|
from CelerisLab.lbm.raw_exchange import summarize_exchange
|
|
from tests.unit.test_refinement_three_level_multipatch import host_module
|
|
|
|
|
|
def body(center=(16., 16.), radius=.5, speed=0.):
|
|
return SimObject(91, geometry=CircleGeometry(*center, radius), center=center, radius=radius,
|
|
surface_actuation=SurfaceActuation(.7, .85, speed))
|
|
|
|
|
|
def backend(observe=True, obj=None):
|
|
host = host_module()
|
|
calls = []
|
|
module = Mock()
|
|
module.get_global.return_value = (Mock(), 20)
|
|
module.get_function.side_effect = lambda name: Mock(side_effect=lambda *a, **k: calls.append((name, a, k)))
|
|
host.compiler.build_module.return_value = module
|
|
host.cuda.mem_alloc.side_effect = lambda n: Mock(size=n)
|
|
host.cuda.memcpy_dtoh.side_effect = lambda array, pointer: array.fill(0)
|
|
ctx = Mock(activate=nullcontext, sm_arch='sm_70')
|
|
run = host.FixedPatchStepper(LBMConfig(nx=48, ny=48, viscosity=.02), context=ctx,
|
|
refinements=[[(6, 6, 26, 26)], [(20, 20, 44, 44)], [(56, 56, 72, 72)]],
|
|
level_blocks=[(4, 4)]*4, level_objects=[(), (), (), (body() if obj is None else obj,)],
|
|
observe_raw_exchange=observe)
|
|
arrays = [np.full(l.shape, 1/9, np.float32) for l in run._levels]
|
|
run.initialize(*arrays)
|
|
return run, host, calls, arrays
|
|
|
|
|
|
class RawExchange(unittest.TestCase):
|
|
def _check_weights_split_and_window(self, level):
|
|
h = 2. ** -level
|
|
rows = np.array([[2, -3, 5, 7], [-1, 4, -2, -6], [99, 99, 99, 99]], np.float32)
|
|
kw = dict(body_id=0, level=level, h=h, time_end=3, reference_center=(7, 8))
|
|
last = summarize_exchange(rows, [0, 0, 1], [False, True, False], window='last_substep', **kw)
|
|
integral = rows.astype(float)*[h*h, h*h, h**3, h*h]/h
|
|
full = summarize_exchange(integral, [0, 0, 1], [False, True, False], window='last_base_step', **kw)
|
|
np.testing.assert_array_equal(last['total']['force'], np.array([1, 1])*h)
|
|
self.assertEqual(last['total']['torque'], 3 * h * h)
|
|
self.assertEqual(last['total']['mass_into_fluid'], h * h)
|
|
for name in ('force', 'torque', 'mass_rate'):
|
|
np.testing.assert_array_equal(last['total'][name], full['total'][name])
|
|
for name in ('force', 'impulse', 'torque', 'angular_impulse', 'mass_into_fluid'):
|
|
np.testing.assert_array_equal(last['total'][name],
|
|
np.asarray(last['wall'][name])+last['aperture'][name])
|
|
self.assertEqual(last['time_start'], 3 - h)
|
|
self.assertEqual(full['time_start'], 2)
|
|
self.assertEqual(last['sample_count'], 1)
|
|
self.assertEqual(full['sample_count'], 2 ** level)
|
|
self.assertEqual(full['reference_center'], (7, 8))
|
|
|
|
def test_final_substep_is_not_interval_mean(self):
|
|
kw = dict(body_id=0, level=1, h=.5, time_end=1, reference_center=(0, 0))
|
|
last = summarize_exchange([[4, 0, 0, 0]], [0], [False], window='last_substep', **kw)
|
|
full = summarize_exchange([[1.5, 0, 0, 0]], [0], [False], window='last_base_step', **kw)
|
|
self.assertEqual(last['total']['force'][0], 2)
|
|
self.assertEqual(full['total']['force'][0], 1.5)
|
|
|
|
def test_host_metadata_zero_jet_and_rows(self):
|
|
cfg = LBMConfig(nx=32, ny=32, viscosity=.1)
|
|
pair = FixedPatch2D.from_config(cfg, (4, 4, 28, 28))
|
|
boundary = prepare_fine_boundary(cfg, pair, [body(radius=2.15)])
|
|
local = replace(cfg, nx=pair.fine_shape[1], ny=pair.fine_shape[0], viscosity=.2)
|
|
local.validate()
|
|
layout = BlockLayout2D.build(*pair.fine_shape, 8, 8, periodic=(False, False))
|
|
b = _prepare_blocked_boundary(boundary, layout, local, ())
|
|
for key, idx in [('body_id', 3), ('rx', 4), ('ry', 5)]:
|
|
np.testing.assert_array_equal(b.tables[key], boundary.curved_host[idx])
|
|
self.assertTrue(b.tables['aperture'].any())
|
|
self.assertTrue((~b.tables['aperture']).any())
|
|
self.assertFalse(b.tables['surface_velocity'].any())
|
|
# Classification does not disappear when prescribed velocity is zero.
|
|
self.assertEqual(len(b.tables['cell']), len(boundary.curved_host[0]))
|
|
|
|
def test_four_level_schedule_publication_and_fixed_storage(self):
|
|
run, host, calls, arrays = backend()
|
|
b = run._level_boundaries[3]
|
|
rows = len(b.tables['cell'])
|
|
self.assertEqual(b.last_raw.size, rows * 16)
|
|
self.assertEqual(b.interval_integral.size, rows * 32)
|
|
with self.assertRaisesRegex(RuntimeError, 'completed'):
|
|
run.read_raw_exchange(0, level=3)
|
|
run.step()
|
|
names = [name for name, _, _ in calls]
|
|
self.assertEqual(names.count('BlockAccumulateExchange'), 8)
|
|
for i, (name, args, kw) in enumerate(calls):
|
|
if name == 'BlockAccumulateExchange':
|
|
self.assertEqual(names[i - 1], 'BlockCurvedBoundary')
|
|
self.assertEqual(names[i + 1], 'BlockStep')
|
|
self.assertIs(args[0], b.last_raw)
|
|
self.assertIs(args[1], b.interval_integral)
|
|
self.assertEqual(args[3:], (0.125, 0.125))
|
|
self.assertIs(kw['stream'], run._stream)
|
|
self.assertEqual(host.cuda.memset_d8_async.call_count, 1)
|
|
value = run.read_raw_exchange(0, level=3)
|
|
self.assertEqual(value['sample_count'], 8)
|
|
self.assertEqual(value['time_start'], 0)
|
|
run.step(0)
|
|
self.assertEqual(run.read_raw_exchange(0, level=3)['time_end'], 1)
|
|
self.assertEqual(run.read_raw_exchange(0, level=3, window='last_substep')['time_start'], 0.875)
|
|
run.step(2)
|
|
self.assertEqual(run.read_raw_exchange(0, level=3)['time_start'], 2)
|
|
run.initialize(*arrays)
|
|
with self.assertRaisesRegex(RuntimeError, 'completed'):
|
|
run.read_raw_exchange(0, level=3)
|
|
run.close()
|
|
|
|
def test_torque_reference_uses_geometry_center_not_optional_object_center(self):
|
|
for center in (None, (3., 4.)):
|
|
obj = SimObject(91, geometry=CircleGeometry(16., 16., .5), center=center, radius=.5)
|
|
run, _, _, _ = backend(obj=obj)
|
|
run.step()
|
|
result = run.read_raw_exchange(0, level=3)
|
|
self.assertEqual(result['reference_center'], (16.0, 16.0))
|
|
self.assertNotEqual(result['reference_center'], tuple(obj.center))
|
|
run.close()
|
|
|
|
def test_disabled_has_nulls_and_no_observation_allocation_or_launch(self):
|
|
run, host, calls, _ = backend(False)
|
|
b = run._level_boundaries[3]
|
|
self.assertIs(b.last_raw, b.interval_integral)
|
|
self.assertIs(b.interval_integral, None)
|
|
run.step()
|
|
for name, args, _ in calls:
|
|
if name == 'BlockCurvedBoundary':
|
|
self.assertEqual(tuple(args[8:]), (0, 0, 0))
|
|
self.assertTrue(all((n != 'BlockAccumulateExchange' for n, _, _ in calls)))
|
|
host.cuda.memset_d8_async.assert_not_called()
|
|
with self.assertRaisesRegex(RuntimeError, 'disabled'):
|
|
run.read_raw_exchange(0, level=3)
|
|
run.close()
|
|
|
|
def test_failed_sync_never_publishes_partial_interval(self):
|
|
run, host, calls, _ = backend()
|
|
run.step()
|
|
run._stream.synchronize.side_effect = RuntimeError('device failure')
|
|
with self.assertRaisesRegex(RuntimeError, 'device failure'):
|
|
run.step()
|
|
self.assertFalse(run._exchange_valid)
|
|
with self.assertRaisesRegex(RuntimeError, 'failed'):
|
|
run.read_raw_exchange(0, level=3)
|
|
run._stream.synchronize.side_effect = None
|
|
run.close()
|
|
|
|
def test_all_depth_weights(self):
|
|
for level in (1, 2, 3, 7):
|
|
self._check_weights_split_and_window(level)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|