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>

src/kernbench/benches/milestone_gqa_decode_4cases.py

@@ -32,12 +32,17 @@ import json
 import os
 from pathlib import Path
 
+from kernbench.benches._gqa_attention_decode_cube_repl_pe_tp import (
+    gqa_attention_decode_cube_repl_pe_tp_kernel,
+)
 from kernbench.benches.milestone_gqa_headline import (
     _ccl_cfg,
     _run_decode_panel,
     _summarize_op_log,
 )
 from kernbench.benches.registry import bench
+from kernbench.ccl.sfr_config import configure_sfr_intercube_multisip
+from kernbench.policy.placement.dp import DPPolicy
 
 _OUTPUT_DIR = (
     Path(__file__).resolve().parent
@@ -51,11 +56,12 @@ _SWEEP_JSON = _OUTPUT_DIR / "sweep.json"
 
 
 _PANELS = (
-    "single_kv_group_decode_gqa_cube_sp_pe_sp",  # Case 4
-    # Cases 1-3 to be added by 5C.A/B/C
+    "single_kv_group_decode_gqa_cube_sp_pe_sp",      # Case 4 ★ optimal
+    "single_kv_group_decode_gqa_cube_repl_pe_tp",    # Case 2 (no comm; 8× memory)
+    # Cases 1, 3 to be added by 5C.A/C
 )
 
-# Each entry: (kind, panel-specific params for _run_decode_panel).
+# Each entry: (kind, panel-specific params).
 # LLaMA-3.1-70B single-KV-head group target:
 #   1 KV head, h_q = 8 (G = 8 group), d_head = 128
 #   8 cubes (head-parallel group), 8 PEs/cube
@@ -68,22 +74,63 @@ _PANEL_DISPATCH: dict[str, tuple[str, dict]] = {
         "T_q": 1, "S_kv": 131_072,
         "d_head": 128, "h_q": 8, "h_kv": 1,
     }),
+    "single_kv_group_decode_gqa_cube_repl_pe_tp": ("decode_cube_repl_pe_tp", {
+        # Case 2: K, V replicated everywhere (8× memory waste); PEs TP
+        # on batch. For B=1 only one rank works (slide-11 PE-TP waste).
+        # No inter-rank communication.
+        "C": 8, "P": 8,
+        "T_q": 1, "S_kv": 131_072,
+        "d_head": 128, "h_q": 8, "h_kv": 1,
+    }),
 }
 
 
 # ── Per-panel runner ─────────────────────────────────────────────────
 
 
+def _run_decode_panel_cube_repl_pe_tp(
+    ctx, *, panel: str, C: int, P: int,
+    T_q: int, S_kv: int,
+    d_head: int, h_q: int, h_kv: int,
+) -> None:
+    """Case 2 runner: K, V replicated everywhere; B=1 single-rank work.
+
+    DPPolicy models the cluster-wide memory waste — every rank holds
+    full K, V in its HBM region. Only PE 0 of CUBE 0 computes (the
+    kernel early-returns on every other rank), so only one rank reads
+    from its HBM copy and writes the output.
+    """
+    configure_sfr_intercube_multisip(ctx.engine, ctx.spec, _ccl_cfg())
+    dp_repl = DPPolicy(cube="replicate", pe="replicate",
+                       num_cubes=C, num_pes=P)
+    q = ctx.zeros((T_q, h_q * d_head),
+                  dtype="f16", dp=dp_repl, name=f"{panel}_q")
+    k = ctx.zeros((S_kv, h_kv * d_head),
+                  dtype="f16", dp=dp_repl, name=f"{panel}_k")
+    v = ctx.zeros((S_kv, h_kv * d_head),
+                  dtype="f16", dp=dp_repl, name=f"{panel}_v")
+    o = ctx.empty((T_q, h_q * d_head),
+                  dtype="f16", dp=dp_repl, name=f"{panel}_o")
+    ctx.launch(
+        panel, gqa_attention_decode_cube_repl_pe_tp_kernel,
+        q, k, v, o,
+        T_q, S_kv, h_q, h_kv, d_head, C, P,
+        _auto_dim_remap=False,
+    )
+
+
 def _make_bench_fn(panel: str):
     kind, params = _PANEL_DISPATCH[panel]
 
     def _bench_fn(ctx):
         if kind == "decode":
             _run_decode_panel(ctx, panel=panel, **params)
+        elif kind == "decode_cube_repl_pe_tp":
+            _run_decode_panel_cube_repl_pe_tp(ctx, panel=panel, **params)
         else:
             raise RuntimeError(
                 f"milestone-gqa-decode-4cases panel {panel!r} has "
-                f"unsupported kind={kind!r}; only 'decode' is allowed."
+                f"unsupported kind={kind!r}."
             )
     return _bench_fn