d282144339
Land the new GQA fused-attention kernels (ADR-0060) for prefill/decode
across long and short context, the TL discipline primitives they depend
on (ADR-0062 lazy load, ADR-0063 scratch_scope + copy_to), and the
per-op-type CPU issue cost model (ADR-0064). Remove the pre-ADR-0060
mesh-attention baseline now that the unified kernels supersede it.
ADR-0060 (long context)
- _gqa_decode.py: M-fold + 2-level chain reduce-to-root (Level-2
intra-CUBE row-then-col + Level-1 inter-CUBE) — root-only output.
- _gqa_prefill.py: head-parallel + Ring KV rotation around C CUBEs,
online-softmax merge per ring step, per-CUBE distributed output.
- Each merge stage wraps in scratch_scope() and persists running
(m, l, O) via copy_to() to lift the 1 MiB scratch ceiling.
ADR-0060 §B.split.2 (short context, kv_per_cube in {1,2,4,8})
- _gqa_decode_short.py / _gqa_prefill_short.py: no cube-SP; each CUBE
owns whole KV heads; PE-parallel heads with intra-group chain
reduce. Prefill has no Ring KV (each head fully resident).
ADR-0062 (lazy tl.load): future-bearing TensorHandle, auto-wait at
first consuming op (dot/MATH/store/send/copy_to/composite).
ADR-0063 (tl.scratch_scope + tl.copy_to): scoped per-tile arena with
copy_to writeback primitive for persistent running state.
ADR-0064 (CPU issue cost model)
- common/cpu_issue_cost.py: per-op-type table (composite=40 ns,
primitives=5 ns); ratios are load-bearing per D1.
- TLContext: issue_cost_table param; _emit_dispatch_overhead(kind)
consults table with dispatch_cycles fallback (ADR-0046 §D6
back-compat).
- Live PE_CPU paths (greenlet + legacy) construct TLContext with
DEFAULT_CPU_ISSUE_COST so saturation lever (ADR-0060 §1) is
measurable end-to-end.
P7 headline bench: milestone-gqa-headline writes per-panel
op_log_summary to 1H_milestone_output/gqa_headline/sweep.json. No
figure renderers yet (deferred).
Removals (pre-ADR-0060 baseline now superseded):
- benches: _attention_mesh_kv.py, _attention_mesh_mlo.py,
_attention_mesh_mlo_2d.py, milestone_gqa_llama70b.py
- tests: test_attention_*, test_mesh_*, test_milestone_gqa_llama70b
- topology: llama70b_4sip.yaml (only consumer was the deleted diag)
- artifacts: 1H_milestone_output/gqa/ (sweep.json + 5 PNGs)
- tests/gqa/ plot helper + test (broken on Windows Tcl/Tkinter)
- ADR-0060/0061 references to deleted file paths cleaned up
(EN + KO kept in sync).
Tests: 124/124 focused regression green (attention + Phase E + TL
discipline + triton_emu + pe_components). Full regression: 764 pass,
2 pre-existing test_bench_registry failures (stale EXPECTED_NAMES
across multiple benches, not introduced here).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
168 lines
6.5 KiB
Python
168 lines
6.5 KiB
Python
"""Phase 1 spec test for lazy ``tl.load`` (ADR-0062).
|
|
|
|
ADR-0062 §D1/§D2: ``tl.load`` is non-blocking. It issues a ``DmaReadCmd``
|
|
and returns immediately with a ``TensorHandle`` carrying a pending
|
|
``LoadFuture``. The runtime auto-inserts a wait on that future at the
|
|
first consuming op (``tl.dot``, MATH ops, ``tl.store``, ``tl.send``,
|
|
``tl.copy_to``, ``tl.composite`` operands). Symmetric with the existing
|
|
``recv_async`` / ``RecvFuture`` pattern, generalised to HBM loads.
|
|
|
|
Phase 1 (this commit): tests only — production code lands in Phase 2.
|
|
All tests currently fail because:
|
|
- ``TensorHandle`` has no ``pending`` field
|
|
- ``LoadFuture`` class doesn't exist
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
from kernbench.common.pe_commands import DmaReadCmd
|
|
from kernbench.triton_emu.tl_context import TLContext
|
|
|
|
|
|
def _ctx() -> TLContext:
|
|
"""TLContext with a real scratch base so _make_compute_out allocates."""
|
|
return TLContext(
|
|
pe_id=0, num_programs=1, dispatch_cycles=0,
|
|
scratch_base=1 << 24, scratch_size=1 << 20,
|
|
)
|
|
|
|
|
|
# ── 1. tl.load handle carries a `pending` field ──────────────────────
|
|
|
|
|
|
def test_tl_load_handle_carries_pending_field():
|
|
"""ADR-0062 §D2: tl.load handle has a ``pending`` attribute that is
|
|
not None — it references the LoadFuture the consumer will await."""
|
|
ctx = _ctx()
|
|
handle = ctx.load(0x1000, shape=(8, 64), dtype="f16")
|
|
assert hasattr(handle, "pending"), (
|
|
"TensorHandle must have a `pending` field per ADR-0062 §D2"
|
|
)
|
|
assert handle.pending is not None, (
|
|
"tl.load handle must carry a non-None pending (LoadFuture)"
|
|
)
|
|
|
|
|
|
# ── 2. Constant / math-output handles have pending=None ──────────────
|
|
|
|
|
|
def test_constant_handle_pending_is_none():
|
|
"""Non-loaded handles (tl.zeros, tl.full, _make_compute_out, tl.arange)
|
|
have ``pending=None`` — there is no DMA to wait on. Consumer ops can
|
|
safely skip auto-wait for these inputs."""
|
|
ctx = _ctx()
|
|
z = ctx.zeros((8, 64), dtype="f16")
|
|
assert getattr(z, "pending", "MISSING") is None, (
|
|
"tl.zeros handle must have pending=None"
|
|
)
|
|
f = ctx.full((8, 64), value=0.0, dtype="f16")
|
|
assert getattr(f, "pending", "MISSING") is None, (
|
|
"tl.full handle must have pending=None"
|
|
)
|
|
a = ctx.arange(0, 8, dtype="i32")
|
|
assert getattr(a, "pending", "MISSING") is None, (
|
|
"tl.arange handle must have pending=None"
|
|
)
|
|
|
|
|
|
def test_compute_out_pending_is_none():
|
|
"""Scratch-allocated output handles (via _make_compute_out) have
|
|
pending=None. Math ops produce them; no DMA → no auto-wait needed
|
|
when they're consumed downstream."""
|
|
ctx = _ctx()
|
|
out = ctx._make_compute_out(shape=(8, 64), dtype="f16")
|
|
assert getattr(out, "pending", "MISSING") is None, (
|
|
"compute-out handle must have pending=None"
|
|
)
|
|
|
|
|
|
# ── 3. LoadFuture class exists ───────────────────────────────────────
|
|
|
|
|
|
def test_loadfuture_class_exists():
|
|
"""ADR-0062 §D2: LoadFuture class wraps the DMA done event and a
|
|
resolved-flag, analogous to RecvFuture for IPCQ. Lives in
|
|
tl_context.py to keep all greenlet bridge types in one module."""
|
|
from kernbench.triton_emu.tl_context import LoadFuture # added Phase 2
|
|
assert LoadFuture is not None
|
|
|
|
|
|
# ── 4. Distinct loads produce distinct LoadFutures ───────────────────
|
|
|
|
|
|
def test_distinct_loads_have_distinct_pending():
|
|
"""ADR-0062 §D2: two tl.load calls (different addresses) produce two
|
|
independent LoadFuture objects. Each consumer must wait on the
|
|
right one — sharing the same future would over-serialise."""
|
|
ctx = _ctx()
|
|
h1 = ctx.load(0x1000, shape=(8,), dtype="f16")
|
|
h2 = ctx.load(0x2000, shape=(8,), dtype="f16")
|
|
assert h1.pending is not None and h2.pending is not None
|
|
assert h1.pending is not h2.pending, (
|
|
"distinct loads must have distinct LoadFuture objects"
|
|
)
|
|
|
|
|
|
# ── 5. LoadFuture starts unresolved ──────────────────────────────────
|
|
|
|
|
|
def test_loadfuture_starts_unresolved():
|
|
"""ADR-0062 §D2: a fresh LoadFuture has resolved=False — the consumer
|
|
op must await it before reading. Once awaited (in greenlet mode by
|
|
auto-wait at first use), the SimPy event triggers and a subsequent
|
|
consumer can skip the yield."""
|
|
ctx = _ctx()
|
|
h = ctx.load(0x1000, shape=(8,), dtype="f16")
|
|
assert h.pending.resolved is False, (
|
|
"LoadFuture must start unresolved; got resolved=True at issue time"
|
|
)
|
|
|
|
|
|
# ── 6. op_log: dma_read_count unchanged from blocking version ────────
|
|
|
|
|
|
def test_op_log_dma_read_count_unchanged():
|
|
"""ADR-0062 §D2 (last paragraph) / Test Req 4: each tl.load still
|
|
emits exactly one DmaReadCmd. The asynchrony is a scheduling
|
|
property, not a new op kind — dma_read_count and existing op_log
|
|
consumers see no change."""
|
|
ctx = _ctx()
|
|
ctx.load(0x1000, shape=(8, 64), dtype="f16")
|
|
ctx.load(0x2000, shape=(8, 64), dtype="f16")
|
|
ctx.load(0x3000, shape=(8, 64), dtype="f16")
|
|
dma_cmds = [c for c in ctx.commands if isinstance(c, DmaReadCmd)]
|
|
assert len(dma_cmds) == 3, (
|
|
f"lazy tl.load must still emit one DmaReadCmd per call; "
|
|
f"got {len(dma_cmds)}"
|
|
)
|
|
|
|
|
|
# ── 7. Handle metadata fields preserved across the lazy change ───────
|
|
|
|
|
|
def test_tl_load_handle_metadata_unchanged():
|
|
"""ADR-0062 §D1: the tl surface is unchanged. The handle's addr,
|
|
shape, dtype, nbytes, space, pinned fields are identical to the
|
|
blocking version — only `pending` is new."""
|
|
ctx = _ctx()
|
|
h = ctx.load(0x1000, shape=(8, 64), dtype="f16")
|
|
assert h.addr == 0x1000
|
|
assert h.shape == (8, 64)
|
|
assert h.dtype == "f16"
|
|
assert h.nbytes == 8 * 64 * 2
|
|
assert h.space == "hbm"
|
|
assert h.pinned is True
|
|
|
|
|
|
# ── 8. LoadFuture carries the DmaReadCmd it wraps ────────────────────
|
|
|
|
|
|
def test_loadfuture_carries_cmd():
|
|
"""ADR-0062 §D2: LoadFuture references the DmaReadCmd it wraps so
|
|
the runtime can resolve handle → command → completion event at
|
|
auto-wait time. Mirrors RecvFuture.cmd."""
|
|
ctx = _ctx()
|
|
h = ctx.load(0x1000, shape=(8, 64), dtype="f16")
|
|
assert hasattr(h.pending, "cmd"), "LoadFuture.cmd must exist"
|
|
assert isinstance(h.pending.cmd, DmaReadCmd)
|
|
assert h.pending.cmd.handle is h
|