ccl: add missing configure_sfr_intracube_pe_ring (fix milestone-gqa import)

The single_user_prefill/single_user_decode panels of milestone-gqa-llama70b
(landed in e748a62) import configure_sfr_intracube_pe_ring from
kernbench.ccl.sfr_config, but the function definition was left in the
local working tree and never made it into that commit. Because the
bench registry eager-imports every bench module at CLI startup, the
missing symbol breaks `kernbench` entirely and cascades into 7 test
failures + 18 collection errors for anyone on a fresh checkout.

Installs an 8-PE logical ring inside every cube on every SIP (E/W
direction labels, no intercube or inter-SIP edges). Mutually exclusive
with configure_sfr_intercube_multisip on the same engine — the bench
picks one per panel-run (ADR-0058 D2).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/kernbench/ccl/sfr_config.py

@@ -161,3 +161,79 @@ def configure_sfr_intercube_multisip(
         algo_module=mock_module,
         rank_to_pe=pe_idx_to_pe,
     )
+
+
+# ── Intra-cube PE ring (ADR-0058 Proposed) ─────────────────────────────
+
+
+def configure_sfr_intracube_pe_ring(
+    engine: Any,
+    spec: dict,
+    cfg: dict,
+) -> dict[str, Any]:
+    """Install an 8-PE logical ring inside every cube on every SIP.
+
+    Per cube ``c`` on every SIP, every PE ``i`` ∈ [0, pes_per_cube) gets:
+
+        nbrs[i]["E"] = pe ((i + 1) % pes_per_cube)  on the same cube and sip
+        nbrs[i]["W"] = pe ((i - 1) % pes_per_cube)  on the same cube and sip
+
+    No intercube or inter-SIP edges are installed by this function — the
+    single_user_* attention panels (ADR-0057) operate inside one cube,
+    so cross-cube traffic is architecturally not part of their kernel.
+
+    The ``E``/``W`` direction namespace is shared with
+    ``configure_sfr_intercube_multisip`` (which writes cube-mesh
+    same-lane edges to the same names). The two installs are
+    **mutually exclusive on the same engine** — the bench is responsible
+    for picking one per panel-run (ADR-0058 D2). v1 does not add a
+    runtime guard.
+
+    Args:
+        engine: GraphEngine with ``_components``.
+        spec:   topology spec dict (from topology.yaml).
+        cfg:    merged algorithm config (from ``resolve_algorithm_config``).
+
+    Returns:
+        The install plan dict from ``install_ipcq`` (same shape as
+        ``configure_sfr_intercube_multisip``).
+    """
+    cm = spec["sip"]["cube_mesh"]
+    n_cubes = int(cm["w"]) * int(cm["h"])
+    n_sips = int(spec.get("system", {}).get("sips", {}).get("count", 1))
+    pl = spec["cube"]["pe_layout"]
+    pes_per_cube = int(pl["pe_per_corner"]) * len(pl["corners"])
+
+    world_size = n_sips * n_cubes * pes_per_cube
+    pe_idx_to_pe: list[tuple[int, int, int]] = [
+        (sip, cube, pe)
+        for sip in range(n_sips)
+        for cube in range(n_cubes)
+        for pe in range(pes_per_cube)
+    ]
+
+    def _pe_idx(sip: int, cube: int, pe: int) -> int:
+        return (sip * n_cubes + cube) * pes_per_cube + pe
+
+    def _neighbors(pe_idx: int, ws: int, _base: dict) -> dict[str, int]:
+        tmp = pe_idx
+        pe = tmp % pes_per_cube
+        tmp //= pes_per_cube
+        cube = tmp % n_cubes
+        sip = tmp // n_cubes
+        return {
+            "E": _pe_idx(sip, cube, (pe + 1) % pes_per_cube),
+            "W": _pe_idx(sip, cube, (pe - 1) % pes_per_cube),
+        }
+
+    mock_module = types.SimpleNamespace(neighbors=_neighbors)
+
+    cfg_copy = dict(cfg)
+    cfg_copy["world_size"] = world_size
+    cfg_copy["topology"] = "none"
+
+    return install_ipcq(
+        engine, spec, cfg_copy,
+        algo_module=mock_module,
+        rank_to_pe=pe_idx_to_pe,
+    )