105f1dc09e
Implements ADR-0027 Phase 2 end-to-end. All 559 tests pass (was 523 + 1 xfail; ring_default_ws strict-xfail is now resolved). D0 — Worker-wait generalization (context.py): - _pending_worker_waits queue on RuntimeContext. - ctx.wait(h) in worker context defers to main via g.parent.switch(). Fast-path for already-completed handles. - Worker API is unchanged: tensor deploy, launch, etc. still look synchronous; they're transparently cooperatively scheduled. - Solves ADR-0024 Phase B kernel-greenlet orphan bug (env.run now only ever drives from main; kernel _parent is always main). D0.5 — Host-read barrier (tensor.py): - Explicit _HOST_READ_BARRIERS registry (T5.g closed-set via code review, not reflection-magic). - numpy/data/__getitem__/__repr__ drain pending worker-waits before host-observable read. - copy_: source-side barrier via source.numpy(). Target-side write barrier is intentionally NOT applied — global pending target barrier prematurely drains cross-rank collectives → deadlock. - Collective pending is excluded from barrier drain condition (collective is cross-rank; its own yield in all_reduce covers the invariant naturally). D1 — torch.multiprocessing.spawn (runtime_api/multiprocessing.py): - API signature parity with real PyTorch spawn; execution is cooperative greenlet scheduler (process isolation etc. are explicit non-goals per D1.0). - _drain_pending drains worker-waits then collectives in one barrier, loop-until-empty. - Round-based exception handling with SystemExit sibling abort + SpawnException(errors) wrapping root-cause ranks. - RuntimeContext attaches ctx.multiprocessing in __post_init__. - benches/ccl_allreduce.py hand-rolled loop collapses to one torch.multiprocessing.spawn call. D2–D6 — kernbench.tp package: - parallel_state: initialize_model_parallel, get_*_rank, get_*_world_size, with weak active-ctx registry in context.py. - layers: ColumnParallelLinear, RowParallelLinear (shape-only primitives — fp16 gemm via tl.load + tl.dot + tl.store). - kernels: _gemm_kernel used by TP layers (self-contained; no bench dependency). - primitives / mappings stubs per D6/D8. Data-path fixes (surfaced by TP gemm + all_reduce sequence): - sim_engine/op_log.py: dma_write snapshot is skipped for TCM sources (PE scratch is repopulated by Phase 2 math/gemm replay — capturing Phase-1-time snapshot picked up STALE data from prior kernel's output aliased at the same scratch addr, causing the later kernel's dma_write to overwrite Phase 2 result with stale value). - sim_engine/op_log.py + sim_engine/data_executor.py: per-operand space recorded on GemmCmd and composite gemm records so HBM-resident operands (tl.load output) don't default to TCM during replay. - runtime_api/context.py: ctx.zeros writes zero-init to MemoryStore at VA keys so kernels reading via VA see deterministic init even without explicit copy_(). Tests (Phase 1 + Phase 2): - test_worker_wait_drain (T3): orphan invariant + resume + multi-rank drain + idempotency + exception propagation. - test_mp_spawn (T4): spawn shape + bind + SpawnException scope. - test_host_read_barrier (T5): barrier contract per entry-point + closed-set registry check. - test_tp_parallel_state (T1): initialize + rank lookup. - test_tp_layers (T2): shape + deterministic numerical correctness (concat-matmul equality for RowParallel, not mean-only). - test_tp_mlp (T6): full 2-layer MLP with deterministic weight numerical match + rank-consistency post all-reduce. - test_ccl_allreduce_matrix: ring_default_ws xfail removed (T7). Regression: 523 pre + 35 new + 1 ex-xfail = 559 passed, 1 intentional skip (T3.e historical failure documentation). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
154 lines
4.6 KiB
Python
154 lines
4.6 KiB
Python
"""End-to-end matrix tests for the unified ``ccl_allreduce`` bench.
|
||
|
||
Each parametrized case writes a tmp ``ccl.yaml`` overlay that selects a
|
||
specific (algorithm, world_size, buffer_kind, n_elem) combination, then
|
||
runs the bench via the CLI and asserts the printed line reports all
|
||
ranks OK.
|
||
|
||
This single test file replaces the per-variant bench tests
|
||
(test_ccl_allreduce_e2e, test_ccl_mesh_allreduce, test_ccl_tree_allreduce,
|
||
test_ccl_multicube, test_ccl_multisip).
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import os
|
||
import textwrap
|
||
|
||
import pytest
|
||
|
||
import kernbench.cli.main as cli_main
|
||
|
||
|
||
CCL_YAML_TEMPLATE = textwrap.dedent("""\
|
||
defaults:
|
||
algorithm: {algorithm}
|
||
buffer_kind: {buffer_kind}
|
||
backpressure: sleep
|
||
n_slots: 4
|
||
slot_size: 4096
|
||
vc_chunk_size: 256
|
||
ipcq_credit_size_bytes: 16
|
||
|
||
algorithms:
|
||
{algorithm}:
|
||
module: {module}
|
||
topology: {topology}
|
||
buffer_kind: {buffer_kind}
|
||
{world_size_line}{n_elem_line}
|
||
""")
|
||
|
||
|
||
def _write_ccl_yaml(
|
||
tmp_path,
|
||
*,
|
||
algorithm: str,
|
||
module: str,
|
||
topology: str,
|
||
buffer_kind: str = "tcm",
|
||
world_size: int | None = None,
|
||
n_elem: int | None = None,
|
||
) -> str:
|
||
"""Write a tmp ccl.yaml in tmp_path and return its directory."""
|
||
ws_line = f" world_size: {world_size}\n" if world_size is not None else ""
|
||
nel_line = f" n_elem: {n_elem}\n" if n_elem is not None else ""
|
||
body = CCL_YAML_TEMPLATE.format(
|
||
algorithm=algorithm,
|
||
module=module,
|
||
topology=topology,
|
||
buffer_kind=buffer_kind,
|
||
world_size_line=ws_line,
|
||
n_elem_line=nel_line,
|
||
)
|
||
yaml_path = tmp_path / "ccl.yaml"
|
||
yaml_path.write_text(body)
|
||
return str(tmp_path)
|
||
|
||
|
||
CASES = [
|
||
# algorithm, module, topology, buffer_kind, world_size, n_elem, expected_ws
|
||
#
|
||
# Default fallback — no world_size override → ADR-0024 D1 derives
|
||
# from topology (SIP count = 2). Exercises the new SIP-level TP
|
||
# launcher + cross-SIP ring.
|
||
# ADR-0027 D0+D1 landed the architectural fix (worker-wait
|
||
# generalization + torch.multiprocessing.spawn scheduler drain), so
|
||
# this case now passes normally. Keeping it as the topology-default
|
||
# smoke.
|
||
pytest.param(
|
||
"ring_allreduce_tcm", "kernbench.ccl.algorithms.ring_allreduce",
|
||
"ring_1d", "tcm", None, 8, 2,
|
||
id="ring_default_ws",
|
||
),
|
||
# Buffer variants at 8-rank (fast — same kernel, different slot space).
|
||
pytest.param(
|
||
"ring_allreduce_tcm", "kernbench.ccl.algorithms.ring_allreduce",
|
||
"ring_1d", "tcm", 8, 32, 8,
|
||
id="ring_tcm_8",
|
||
),
|
||
pytest.param(
|
||
"ring_allreduce_hbm", "kernbench.ccl.algorithms.ring_allreduce",
|
||
"ring_1d", "hbm", 8, 32, 8,
|
||
id="ring_hbm_8",
|
||
),
|
||
pytest.param(
|
||
"ring_allreduce_sram", "kernbench.ccl.algorithms.ring_allreduce",
|
||
"ring_1d", "sram", 8, 32, 8,
|
||
id="ring_sram_8",
|
||
),
|
||
# Multi-cube (16-rank, cross-cube within 1 SIP).
|
||
pytest.param(
|
||
"ring_allreduce_16", "kernbench.ccl.algorithms.ring_allreduce",
|
||
"ring_1d", "tcm", 16, 16, 16,
|
||
id="ring_multi_cube",
|
||
),
|
||
# Mesh + tree algorithms.
|
||
pytest.param(
|
||
"mesh_allreduce_4", "kernbench.ccl.algorithms.mesh_allreduce",
|
||
"mesh_2d", "tcm", 4, 16, 4,
|
||
id="mesh_2x2",
|
||
),
|
||
pytest.param(
|
||
"tree_allreduce_7", "kernbench.ccl.algorithms.tree_allreduce",
|
||
"tree_binary", "tcm", 7, 16, 7,
|
||
id="tree_binary_7",
|
||
),
|
||
]
|
||
|
||
|
||
@pytest.mark.parametrize(
|
||
"algorithm,module,topology,buffer_kind,world_size,n_elem,expected_ws",
|
||
CASES,
|
||
)
|
||
def test_ccl_allreduce_matrix(
|
||
tmp_path, capsys, monkeypatch,
|
||
algorithm, module, topology, buffer_kind, world_size, n_elem, expected_ws,
|
||
):
|
||
"""Each (algorithm × buffer × world_size) combo passes through the
|
||
unified bench and yields all ranks OK."""
|
||
project_root = os.path.abspath(
|
||
os.path.join(os.path.dirname(__file__), "..")
|
||
)
|
||
yaml_dir = _write_ccl_yaml(
|
||
tmp_path,
|
||
algorithm=algorithm,
|
||
module=module,
|
||
topology=topology,
|
||
buffer_kind=buffer_kind,
|
||
world_size=world_size,
|
||
n_elem=n_elem,
|
||
)
|
||
monkeypatch.chdir(yaml_dir)
|
||
rc = cli_main.main([
|
||
"run",
|
||
"--topology", os.path.join(project_root, "topology.yaml"),
|
||
"--bench", "ccl_allreduce",
|
||
"--verify-data",
|
||
])
|
||
assert rc == 0
|
||
out = capsys.readouterr().out
|
||
assert "FAIL" not in out, f"unexpected FAIL in output:\n{out}"
|
||
assert f"{algorithm} (ws={expected_ws}): {expected_ws} OK" in out, (
|
||
f"expected '{algorithm} (ws={expected_ws}): {expected_ws} OK' "
|
||
f"in output:\n{out}"
|
||
)
|