gqa(decode-4cases): Case 2 — Cube-Repl × PE-TP (no comm; 8× memory) (5C.B)

Second case in the GQA decode 4-cases comparative study per
GQA_full_deck.pptx slide 11. Case 2 replicates K, V across all 8
cubes × 8 PEs (the slide-11 8 KB/tok/PE memory waste) and has zero
inter-rank comm. For B=1 (single-user decode default), only PE 0
of CUBE 0 has work — the inherent PE-TP waste slide 11 calls out.

Changes:
- New kernel: src/kernbench/benches/_gqa_attention_decode_cube_repl_pe_tp.py
  Simplest of the 4 cases. Active rank loads full Q/K/V from HBM,
  computes attention via S_kv tile sweep with online-softmax merge,
  writes O. All non-(0,0) ranks early-return. No tl.send/recv.
- src/kernbench/benches/milestone_gqa_decode_4cases.py:
    - Add panel single_kv_group_decode_gqa_cube_repl_pe_tp (Case 2)
      to _PANELS and _PANEL_DISPATCH.
    - Add _run_decode_panel_cube_repl_pe_tp helper: DPPolicy K/V/Q/O
      = cube=replicate, pe=replicate (models 8× memory waste).
    - Extend _make_bench_fn to dispatch kind="decode_cube_repl_pe_tp"
      to the new runner.
- tests/attention/test_milestone_gqa_decode_4cases.py:
    4 new tests assert Case 2 contract: panel registered, smoke
    completion, zero ipcq_copy (no comm), single dma_write from cube 0.

Verification: 8/8 tests pass (4 Case 4 anchor + 4 new Case 2).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

tests/attention/test_milestone_gqa_decode_4cases.py

@@ -39,6 +39,7 @@ from kernbench.topology.builder import resolve_topology
 TOPOLOGY_DEFAULT = Path(__file__).resolve().parents[2] / "topology.yaml"
 
 _CASE4_PANEL = "single_kv_group_decode_gqa_cube_sp_pe_sp"
+_CASE2_PANEL = "single_kv_group_decode_gqa_cube_repl_pe_tp"
 _CUBE_RE = re.compile(r"\bcube(\d+)\b")
 
 
@@ -161,6 +162,112 @@ def test_case4_root_at_center_cube_6():
 # ── T4: 2-phase AR ipcq pattern matches the predicted Case-4 traffic ─
 
 
+def _run_case2_smoke(*, S_kv: int):
+    """Drive the Case 2 decode panel via the case-specific runner.
+
+    Case 2 = Cube-Repl × PE-TP. K, V are replicated everywhere (the
+    slide-11 memory waste); for B=1 only one rank does the work; no
+    inter-rank comm.
+    """
+    from kernbench.benches.milestone_gqa_decode_4cases import (
+        _run_decode_panel_cube_repl_pe_tp,
+    )
+    topo = resolve_topology(str(TOPOLOGY_DEFAULT))
+
+    def _bench_fn(ctx):
+        _run_decode_panel_cube_repl_pe_tp(
+            ctx, panel=_CASE2_PANEL,
+            C=8, P=8,
+            T_q=1, S_kv=S_kv,
+            d_head=128, h_q=8, h_kv=1,
+        )
+
+    return run_bench(
+        topology=topo, bench_fn=_bench_fn,
+        device=resolve_device(None),
+        engine_factory=_engine_factory,
+    )
+
+
+# ── Case 2 — T1: panel registered ───────────────────────────────────
+
+
+def test_case2_panel_registered():
+    """The Case 2 panel must be in the bench's ``_PANELS`` +
+    ``_PANEL_DISPATCH`` with the expected single-KV-group dims.
+
+    Case 2: Cube-Repl × PE-TP. K, V replicated everywhere
+    (8 KB/tok/PE — slide-11 memory waste); no inter-rank comm.
+    For B=1 only one rank works (PEs 1-7 idle — slide-11 calls
+    out this PE-TP waste).
+    """
+    from kernbench.benches.milestone_gqa_decode_4cases import (
+        _PANEL_DISPATCH,
+        _PANELS,
+    )
+    assert _CASE2_PANEL in _PANELS, (
+        f"{_CASE2_PANEL!r} not in _PANELS; got {_PANELS}"
+    )
+    assert _CASE2_PANEL in _PANEL_DISPATCH
+    kind, params = _PANEL_DISPATCH[_CASE2_PANEL]
+    assert kind == "decode_cube_repl_pe_tp"
+    assert params.get("C") == 8
+    assert params.get("P") == 8
+    assert params.get("T_q") == 1
+    assert params.get("S_kv") == 131_072
+    assert params.get("d_head") == 128
+    assert params.get("h_q") == 8
+    assert params.get("h_kv") == 1
+
+
+# ── Case 2 — T2: smoke runner completes ─────────────────────────────
+
+
+def test_case2_runner_smoke():
+    """Case 2 runner drives the new kernel to completion at smoke S_kv."""
+    result = _run_case2_smoke(S_kv=8192)
+    assert result.completion.ok, (
+        f"Case 2 decode smoke at C=8 P=8 must complete; "
+        f"got {result.completion}"
+    )
+
+
+# ── Case 2 — T3: zero inter-rank comm by design ─────────────────────
+
+
+def test_case2_zero_ipcq_copy_no_comm():
+    """Case 2's defining property: full KV per rank ⇒ NO inter-rank
+    communication. Slide 11 lists comm cost as 'none'.
+    """
+    result = _run_case2_smoke(S_kv=8192)
+    assert result.completion.ok
+    n_copy = _count(result.engine.op_log, "ipcq_copy")
+    assert n_copy == 0, (
+        f"Case 2 must have zero inter-rank comm; got ipcq_copy={n_copy}"
+    )
+
+
+# ── Case 2 — T4: single dma_write from cube 0 (B=1 single-rank work) ─
+
+
+def test_case2_single_dma_write_at_cube_0():
+    """For B=1, only PE 0 of CUBE 0 does the work (the inherent PE-TP
+    waste at B=1). Exactly 1 dma_write, from cube 0.
+    """
+    result = _run_case2_smoke(S_kv=8192)
+    assert result.completion.ok
+    cubes = _dma_write_cubes(result.engine.op_log)
+    assert cubes, "expected at least one dma_write for the final O store"
+    distinct = set(cubes)
+    assert distinct == {0}, (
+        f"Case 2 B=1 single writer must be cube 0; "
+        f"got cubes={sorted(distinct)}"
+    )
+
+
+# ── Case 4 — T4 (existing, kept) ────────────────────────────────────
+
+
 def test_case4_two_level_ar_ipcq_pattern():
     """Total ipcq_copy for the Case 4 reduce at (C, P, sub_w) =
     (8, 8, 4):