998cc85762
Major changes:
PE-level IPCQ infrastructure:
- New PE_IPCQ component: ring-buffer control plane with 4-direction
neighbor mapping, head/tail pointers, backpressure (poll/sleep).
- PE_DMA extended with vc_comm channel for IPCQ outbound/inbound DMA,
including in-flight data snapshot (D9) and op_log recording at
outbound time for Phase 2 replay correctness.
- IpcqDmaToken piggyback model: data + metadata travel together,
atomic visibility at receiver (invariant I6).
- Credit return fast path: bottleneck-BW latency, no fabric vc_comm.
Phase 2 data execution (ADR-0020 integration):
- op_log extended: DmaWriteCmd now captures src_space/src_addr for
Phase 2 dma_write copy; ipcq_copy ops recorded at outbound time.
- DataExecutor replays dma_write + ipcq_copy in t_start order.
- Engine._flush_data_phase: incremental cursor-based replay after
each engine.wait() so host reads see post-Phase-2 data.
- KernelRunner Phase 1 writes disabled when op_log is active to
prevent stale data from corrupting the MemoryStore snapshot.
TLContext / kernel API:
- tl.send(dir, src=TensorHandle), tl.recv(dir, shape, dtype),
tl.recv_async, tl.wait(RecvFuture), copy_to_dst mode.
- TensorHandle operator overloading (add/sub/mul/div) via thread-local
active TLContext → MathCmd dispatch through PE_MATH.
- PE-local scratch allocator for math output handles.
- tl.load returns space="hbm" handles for correct Phase 2 addressing.
- Additional math functions: maximum, minimum, fma, clamp, softmax, cdiv.
Unified ccl_allreduce bench (PyTorch-compat host code):
- Single benches/ccl_allreduce.py with run() + worker(rank, ws, torch)
split matching real PyTorch DDP worker pattern.
- torch.distributed facade: init_process_group, get_world_size,
get_rank, get_backend, all_reduce, barrier — only real PyTorch names.
- AhbmCCLBackend: eager install_ipcq at init, all_reduce dispatches
kernel via tensor shard metadata (n_elem from shards[0].nbytes).
- world_size derived from topology spec (sips × cubes × pes_per_cube)
with optional algorithm-level override in ccl.yaml.
Tensor API (PyTorch-compat surface):
- Tensor.numpy(): gather-aware (all shards via VA-based addressing).
- Tensor.copy_(source): scatter from host tensor into sharded target.
- RuntimeContext.from_numpy(arr): host-side staging tensor.
- Tensor.data property fixed to use numpy() (was shards[0]-only).
Algorithm modules moved to src/kernbench/ccl/algorithms/:
- ring_allreduce, mesh_allreduce, tree_allreduce, hello_send.
- Each module exports kernel_args(world_size, n_elem) helper.
- ccl.yaml module paths updated to kernbench.ccl.algorithms.*.
Dead code removed:
- 7 per-variant bench files (ccl_allreduce_{tcm,hbm,sram}, etc.).
- _run_ccl_bench greenlet-per-SIP scheduler.
- benches.loader.is_ccl_bench + run_rank detection.
- benches/ccl/ directory.
Tests:
- New test_ccl_allreduce_matrix.py: 7 parametrized cases
(ring×3 buffers, ring 8/16, mesh 4, tree 7).
- New test_runtime_api_tensor.py: copy_/numpy/from_numpy unit tests.
- Existing tests updated for new import paths + world_size_override.
Docs:
- Korean ccl-author-guide.md and ADR-0023 paths updated.
- New English versions: ccl-author-guide.en.md, ADR-0023.en.md.
502 tests pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
143 lines
4.1 KiB
Python
143 lines
4.1 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
|
||
pytest.param(
|
||
"ring_allreduce_tcm", "kernbench.ccl.algorithms.ring_allreduce",
|
||
"ring_1d", "tcm", None, 8, 256,
|
||
id="ring_full_system_tcm",
|
||
),
|
||
pytest.param(
|
||
"ring_allreduce_hbm", "kernbench.ccl.algorithms.ring_allreduce",
|
||
"ring_1d", "hbm", None, 8, 256,
|
||
id="ring_full_system_hbm",
|
||
),
|
||
pytest.param(
|
||
"ring_allreduce_sram", "kernbench.ccl.algorithms.ring_allreduce",
|
||
"ring_1d", "sram", None, 8, 256,
|
||
id="ring_full_system_sram",
|
||
),
|
||
pytest.param(
|
||
"ring_allreduce_8", "kernbench.ccl.algorithms.ring_allreduce",
|
||
"ring_1d", "tcm", 8, 32, 8,
|
||
id="ring_single_cube",
|
||
),
|
||
pytest.param(
|
||
"ring_allreduce_16", "kernbench.ccl.algorithms.ring_allreduce",
|
||
"ring_1d", "tcm", 16, 16, 16,
|
||
id="ring_multi_cube",
|
||
),
|
||
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}"
|
||
)
|