Files
kernbench2/tests/test_ccl_allreduce_matrix.py
T
ywkang bcf941dcee Speed up regression: 25min → 6min (test matrix + DataExecutor cleanup)
Test matrix restructure:
- 256-rank full-system ring runs only ONCE (marked pytest.mark.slow)
  instead of 7× across matrix + perf tests. Cross-SIP routing is
  verified by the single run; buffer variants (tcm/hbm/sram) are
  tested at 8-rank where they finish in <0.5s.
- Performance tests use 8-rank instead of 256-rank.
- `pytest -m "not slow"` completes in ~2.5min (local dev).
- Full suite including slow: ~6min (CI).

DataExecutor optimization:
- Remove ThreadPoolExecutor from DataExecutor.run(). Same-t_start
  groups are almost always size 1, so the thread pool creation and
  dispatch overhead dominated. Simple sequential loop is faster.
- Skip dma_read ops at the loop level (they are always no-ops in
  Phase 2 but were dispatched through _execute_op → _execute_memory).
- Remove redundant CLI Phase 2 re-execution: engine._flush_data_phase
  already replays during engine.wait(); the CLI now only prints the
  diagnostic summary without re-running DataExecutor.

502 tests pass. Wall time: 25m30s → 5m43s (full), 2m28s (no slow).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-12 20:52:07 -07:00

151 lines
4.5 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""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
#
# Full-system (256-rank, cross-SIP) — run only ONCE (tcm). Buffer
# variant differences are purely IPCQ slot placement; the compute path
# is identical. Cross-SIP routing is the real thing being verified here.
pytest.param(
"ring_allreduce_tcm", "kernbench.ccl.algorithms.ring_allreduce",
"ring_1d", "tcm", None, 8, 256,
id="ring_full_system",
marks=pytest.mark.slow,
),
# 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}"
)