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>
141 lines
4.4 KiB
Python
141 lines
4.4 KiB
Python
"""Tests for IPCQ strict shape/dtype validation (ADR-0023 D14 F2)."""
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass, field
|
|
from typing import Any
|
|
|
|
import pytest
|
|
import simpy
|
|
|
|
from kernbench.common.ipcq_types import (
|
|
IpcqDmaToken,
|
|
IpcqEndpoint,
|
|
IpcqInitEntry,
|
|
IpcqInvalidDirection,
|
|
IpcqMetaArrival,
|
|
IpcqRecvCmd,
|
|
IpcqRequest,
|
|
IpcqSendCmd,
|
|
)
|
|
from kernbench.components.builtin.pe_ipcq import PeIpcqComponent
|
|
from kernbench.runtime_api.kernel import IpcqInitMsg
|
|
from kernbench.topology.types import Node
|
|
|
|
|
|
# ── helpers (smaller copy of test_pe_ipcq fixtures) ────────────────
|
|
|
|
|
|
@dataclass
|
|
class _FakeTxn:
|
|
request: Any
|
|
done: simpy.Event
|
|
result_data: dict[str, Any] = field(default_factory=dict)
|
|
|
|
|
|
def _make(env, strict: bool = True):
|
|
node = Node(
|
|
id="sip0.cube0.pe0.pe_ipcq", kind="pe_ipcq",
|
|
impl="builtin.pe_ipcq",
|
|
attrs={"strict_validation": strict},
|
|
pos_mm=None,
|
|
)
|
|
comp = PeIpcqComponent(node, ctx=None)
|
|
comp.in_ports["host"] = simpy.Store(env)
|
|
comp.out_ports["sip0.cube0.pe0.pe_dma"] = simpy.Store(env)
|
|
comp.start(env)
|
|
|
|
peer_credit = simpy.Store(env)
|
|
ep = IpcqEndpoint(
|
|
sip=0, cube=0, pe=1, buffer_kind="tcm",
|
|
rx_base_pa=0x10_000, rx_base_va=0,
|
|
n_slots=4, slot_size=4096,
|
|
)
|
|
init_msg = IpcqInitMsg(
|
|
correlation_id="t", request_id="t",
|
|
target_sips=(0,), target_cubes=(0,), target_pe=0,
|
|
entries=(IpcqInitEntry(
|
|
direction="W", peer=ep,
|
|
my_rx_base_pa=0x40_000, my_rx_base_va=0,
|
|
n_slots=4, slot_size=4096,
|
|
peer_credit_store=peer_credit,
|
|
),),
|
|
backpressure_mode="sleep",
|
|
buffer_kind="tcm",
|
|
credit_size_bytes=16,
|
|
)
|
|
done = env.event()
|
|
comp.in_ports["host"].put(_FakeTxn(request=init_msg, done=done))
|
|
env.run(until=done)
|
|
return comp
|
|
|
|
|
|
# ── F2 tests ─────────────────────────────────────────────────────────
|
|
|
|
|
|
def test_strict_mode_dtype_mismatch_raises():
|
|
env = simpy.Environment()
|
|
comp = _make(env, strict=True)
|
|
|
|
# Pre-arrive metadata with f32 dtype
|
|
fake_token = IpcqDmaToken(
|
|
src_addr=0, src_space="tcm",
|
|
dst_addr=0x40_000, dst_endpoint=comp._queue_pairs["W"]["peer"],
|
|
nbytes=64, handle_id="x",
|
|
shape=(8,), dtype="f32", # mismatched
|
|
sender_seq=0,
|
|
src_sip=0, src_cube=0, src_pe=1, src_direction="E",
|
|
)
|
|
comp.in_ports["host"].put(IpcqMetaArrival(token=fake_token))
|
|
env.run(until=5)
|
|
|
|
# recv expecting f16 → should raise on strict
|
|
recv_cmd = IpcqRecvCmd(direction="W", shape=(8,), dtype="f16", handle_id="r")
|
|
req = IpcqRequest(command=recv_cmd, done=env.event())
|
|
comp.in_ports["host"].put(req)
|
|
with pytest.raises(ValueError, match="dtype"):
|
|
env.run(until=req.done)
|
|
|
|
|
|
def test_strict_mode_shape_mismatch_raises():
|
|
env = simpy.Environment()
|
|
comp = _make(env, strict=True)
|
|
|
|
fake_token = IpcqDmaToken(
|
|
src_addr=0, src_space="tcm",
|
|
dst_addr=0x40_000, dst_endpoint=comp._queue_pairs["W"]["peer"],
|
|
nbytes=64, handle_id="x",
|
|
shape=(16,), dtype="f16", # wrong shape
|
|
sender_seq=0,
|
|
src_sip=0, src_cube=0, src_pe=1, src_direction="E",
|
|
)
|
|
comp.in_ports["host"].put(IpcqMetaArrival(token=fake_token))
|
|
env.run(until=5)
|
|
|
|
recv_cmd = IpcqRecvCmd(direction="W", shape=(8,), dtype="f16", handle_id="r")
|
|
req = IpcqRequest(command=recv_cmd, done=env.event())
|
|
comp.in_ports["host"].put(req)
|
|
with pytest.raises(ValueError, match="shape"):
|
|
env.run(until=req.done)
|
|
|
|
|
|
def test_non_strict_mode_silently_accepts():
|
|
env = simpy.Environment()
|
|
comp = _make(env, strict=False)
|
|
|
|
fake_token = IpcqDmaToken(
|
|
src_addr=0, src_space="tcm",
|
|
dst_addr=0x40_000, dst_endpoint=comp._queue_pairs["W"]["peer"],
|
|
nbytes=64, handle_id="x",
|
|
shape=(16,), dtype="f32", # both wrong
|
|
sender_seq=0,
|
|
src_sip=0, src_cube=0, src_pe=1, src_direction="E",
|
|
)
|
|
comp.in_ports["host"].put(IpcqMetaArrival(token=fake_token))
|
|
env.run(until=5)
|
|
|
|
recv_cmd = IpcqRecvCmd(direction="W", shape=(8,), dtype="f16", handle_id="r")
|
|
req = IpcqRequest(command=recv_cmd, done=env.event())
|
|
comp.in_ports["host"].put(req)
|
|
env.run(until=req.done)
|
|
assert req.done.triggered # no exception
|