lbm: delete PeriodicBlockStepper; a single blocked level is FixedPatchStepper(refinements=[]) (S2)
The second owner of one blocked level goes. Its capability is the zero-refinement FixedPatchStepper added in f764d68/985db14 (periodic SRT level, stationary passive circles, shifted storage, NaN spare, single wait), which matched it array for array on GPU at1318fc2(3 splits x +-circle x shifted/unshifted) and passes the host lifecycle and fault contracts. API change for callers: PeriodicBlockStepper(cfg, BlockLayout2D.build(ny, nx, by, bx), context=c, objects=o) -> FixedPatchStepper(cfg, context=c, refinements=[], level_blocks=[(by, bx)], level_objects=[tuple(o)]) download() returns a 1-tuple; static-circle tables are _level_boundaries[0].tables (was .boundary); no free-memory preflight. - lbm/block_stepper.py deleted; MAX_GRID_DIM lives in refinement_stepper. - tests/validation/multigrid/test_block_stepper.py: same frozen GPU gates (split identity, FP64 oracle, circle across seams) and pre-CUDA rejection cases on the single level; the old-vs-new bitwise test is retired with the old class (its result is the1318fc2record). - tests/unit/test_block_step_sync.py folded into test_single_level.py (step(n) vs n x step(1) roles and one wait, step(0), mid-batch launch failure), which also gains bad-state rejection before upload, download failure and activation-failure retry on close. - test_shifted_storage and test_raw_exchange_gpu use the single level; the raw-exchange reference feeds the AMR Jet column and raw ledger through the root level boundary instead of patching a private kernel field. - Pinned historical runners (taylor_green/run_case.py, run_jet_circle_cv.py) are unchanged: they only run on trees that still ship PeriodicBlockStepper. No alias. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
d58f06f0fa
commit
8e1feffcad
12 files changed
+153
-536
No files matched your search
@@ -2,10 +2,11 @@
|
||||
|
||||
Per step: halo refresh -> static BFL (circles only) -> BlockStep with a null
|
||||
kind, one stream wait per step(n) call, NaN spare after initialize. An upload,
|
||||
launch or wait failure fails the instance and keeps its step count.
|
||||
launch, wait or download failure fails the instance and keeps its step count;
|
||||
close retains resources for retry when context activation fails.
|
||||
"""
|
||||
from contextlib import nullcontext
|
||||
from unittest.mock import Mock
|
||||
from unittest.mock import MagicMock, Mock
|
||||
import unittest
|
||||
|
||||
import numpy as np
|
||||
@@ -108,6 +109,87 @@ class SingleLevel(unittest.TestCase):
|
||||
with self.assertRaisesRegex(RuntimeError, "failed"):
|
||||
run.step(1)
|
||||
|
||||
def test_step_n_waits_once_and_matches_n_single_steps(self):
|
||||
many, log_many, _ = backend()
|
||||
many.step(3)
|
||||
single, log_single, _ = backend()
|
||||
for _ in range(3):
|
||||
single.step(1)
|
||||
names = [name for name, _ in log_many]
|
||||
self.assertEqual(names.count("sync"), 1)
|
||||
self.assertEqual(names[-1], "sync")
|
||||
self.assertEqual(names.count("BlockStep"), 3)
|
||||
|
||||
def roles(run, log): # same launch order and buffer roles as three step(1) calls
|
||||
level = run._levels[0]
|
||||
tags = {id(level.current): "c", id(level.spare): "s"}
|
||||
return [(n, tuple(tags.get(id(x), "-") for x in a)) for n, a in log if n != "sync"]
|
||||
self.assertEqual(roles(many, log_many), roles(single, log_single))
|
||||
self.assertIsNot(many._levels[0].current, many._levels[0].spare)
|
||||
self.assertEqual((many.step_count, single.step_count), (3, 3))
|
||||
|
||||
def test_step_zero_launches_and_waits_for_nothing(self):
|
||||
run, log, _ = backend()
|
||||
log.clear()
|
||||
run.step(0)
|
||||
self.assertEqual((log, run.step_count), ([], 0))
|
||||
|
||||
def test_launch_failure_mid_batch_fails_without_waiting(self):
|
||||
run, log, host = backend()
|
||||
step = run._levels[0].kernel
|
||||
calls = []
|
||||
|
||||
def failing(*args, **kwargs):
|
||||
calls.append(1)
|
||||
if len(calls) == 2:
|
||||
raise RuntimeError("launch failure")
|
||||
return step(*args, **kwargs)
|
||||
|
||||
run._levels[0].kernel = failing
|
||||
log.clear()
|
||||
with self.assertRaises(RuntimeError):
|
||||
run.step(3)
|
||||
self.assertNotIn("sync", [name for name, _ in log])
|
||||
self.assertEqual((run.step_count, run._status), (0, "failed"))
|
||||
with self.assertRaises(RuntimeError):
|
||||
run.download()
|
||||
|
||||
def test_initialize_rejects_bad_state_before_upload(self):
|
||||
run, log, _ = backend(initialize=False)
|
||||
good = state()
|
||||
for bad in (good[:, :-1], np.where(np.arange(32) == 3, np.nan, good), -good):
|
||||
with self.assertRaises(ValueError):
|
||||
run.initialize(bad)
|
||||
self.assertNotIn("upload", [name for name, _ in log])
|
||||
run.initialize(good)
|
||||
self.assertEqual([name for name, _ in log].count("upload"), 2)
|
||||
|
||||
def test_download_failure_fails_instance(self):
|
||||
run, _, host = backend()
|
||||
host.cuda.memcpy_dtoh.side_effect = RuntimeError("read failed")
|
||||
with self.assertRaisesRegex(RuntimeError, "read failed"):
|
||||
run.download()
|
||||
for operation in (run.download, run.step):
|
||||
with self.assertRaisesRegex(RuntimeError, "failed"):
|
||||
operation()
|
||||
|
||||
def test_activation_failure_retains_resources_for_retry(self):
|
||||
run, _, _ = backend()
|
||||
allocations, stream = run._allocations[:], run._stream
|
||||
unavailable = MagicMock()
|
||||
unavailable.__enter__.side_effect = RuntimeError("activation failed")
|
||||
run.ctx.activate = Mock(side_effect=[unavailable, nullcontext()])
|
||||
with self.assertRaisesRegex(RuntimeError, "activation failed"):
|
||||
run.close()
|
||||
self.assertEqual(run._status, "failed")
|
||||
self.assertEqual(run._allocations, allocations)
|
||||
self.assertIs(run._stream, stream)
|
||||
run.close()
|
||||
self.assertEqual(run._status, "closed")
|
||||
self.assertEqual(run._levels, [])
|
||||
for allocation in allocations:
|
||||
allocation.free.assert_called_once()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in new issue
Block a user