CCL allreduce: rename to lrab_hierarchical_allreduce + descriptive plots

Rename the intercube all-reduce identity to lrab_hierarchical_allreduce
(module, config key, distributed test) so the name reflects both levels
it implements: LRAB intra-SIP (local reduce to center root + broadcast)
and the hierarchical inter-SIP topology exchange (ring/torus/mesh).
ADR-0032 slug kept as the stable decision id; pure rename, no logic change.

Also in this batch:
- ADR-0032 (EN+KO): document the shipped center-root bidirectional reduce
  (doc was stale corner-root); annotate ccl.yaml root_cube as a placeholder.
- Rename allreduce + pe2pe latency plots to descriptive, title-matching
  filenames and retitle the in-plot headings; drop overview/overview_log.
- Point the PPTX image refs at the new plot names.

Doc + derived-artifact + rename only; no simulation behavior changed.

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

tests/test_allreduce_multidevice.py

@@ -189,15 +189,15 @@ TOPOLOGY_PATH = Path(__file__).parent.parent / "topology.yaml"
 
 CONFIGS = [
     pytest.param(
-        "intercube_allreduce", "ring_1d", 6, None, None,
+        "lrab_hierarchical_allreduce", "ring_1d", 6, None, None,
         id="ring_6sip",
     ),
     pytest.param(
-        "intercube_allreduce", "torus_2d", 6, 2, 3,
+        "lrab_hierarchical_allreduce", "torus_2d", 6, 2, 3,
         id="torus_6sip_2x3",
     ),
     pytest.param(
-        "intercube_allreduce", "mesh_2d_no_wrap", 6, 2, 3,
+        "lrab_hierarchical_allreduce", "mesh_2d_no_wrap", 6, 2, 3,
         id="mesh_6sip_2x3",
     ),
 ]
@@ -280,9 +280,9 @@ _SWEEP_N_ELEM = [
 _ELEM_BYTES_F16 = 2
 
 _SWEEP_TOPOLOGIES = [
-    ("intercube_allreduce", "ring_1d", 6, None, None),
-    ("intercube_allreduce", "torus_2d", 6, 2, 3),
-    ("intercube_allreduce", "mesh_2d_no_wrap", 6, 2, 3),
+    ("lrab_hierarchical_allreduce", "ring_1d", 6, None, None),
+    ("lrab_hierarchical_allreduce", "torus_2d", 6, 2, 3),
+    ("lrab_hierarchical_allreduce", "mesh_2d_no_wrap", 6, 2, 3),
 ]
 
 # Shared on-disk staging dir for parametrized sweep rows. Each
@@ -440,10 +440,22 @@ def _aggregate_sweep_plots() -> bool:
             continue
         xs = [r["bytes_per_pe"] for r in rs]
         ys = [r["latency_ns"] for r in rs]
-        title = (
-            f"Allreduce latency — {topo_name} "
-            f"(n_sips={rs[0]['n_sips']})"
+        _per_topo_titles = {
+            "ring_1d": "AllReduce_LRAB_Ring1D_6SiP(1x6)",
+            "torus_2d": "AllReduce_LRAB_2Dtorus_6SiP(2x3)",
+            "mesh_2d_no_wrap": "AllReduce_LRAB_2DMesh_6SiP(2x3)",
+        }
+        # Descriptive output filenames (parens → underscores for
+        # markdown/URL safety; topo key stays the summary.csv value).
+        _per_topo_files = {
+            "ring_1d": "AllReduce_LRAB_Ring1D_6SiP_1x6",
+            "torus_2d": "AllReduce_LRAB_2Dtorus_6SiP_2x3",
+            "mesh_2d_no_wrap": "AllReduce_LRAB_2DMesh_6SiP_2x3",
+        }
+        title = _per_topo_titles.get(
+            topo_name, f"Allreduce latency — {topo_name}"
         )
+        out_stem = _per_topo_files.get(topo_name, topo_name)
         fig, ax = plt.subplots(figsize=(8, 5))
         ax.plot(xs, ys, marker="o", color="tab:blue")
         ax.set_xscale("log", base=2)
@@ -453,75 +465,14 @@ def _aggregate_sweep_plots() -> bool:
         ax.grid(True, alpha=0.3)
         ax.xaxis.set_major_formatter(_bytes_fmt)
         fig.tight_layout()
-        fig.savefig(_SWEEP_OUT_DIR / f"{topo_name}.png", dpi=120)
+        fig.savefig(_SWEEP_OUT_DIR / f"{out_stem}.png", dpi=120)
         plt.close(fig)
 
-    colors = {"ring_1d": "tab:blue", "torus_2d": "tab:orange",
-              "mesh_2d_no_wrap": "tab:green"}
-
-    # ── Hand-derived theoretical model for torus_2d (6 SIPs) ──
-    # Critical-path analysis (per packet, packet = 128 B at NoC):
-    #   local intra-SIP reduce + broadcast = 8 hops × 57 ns = 456 ns
-    #   global X-direction reduce          = 5 UCIe + 1 UAL = 445 ns
-    #   global Y-direction reduce          = 5 UCIe + 1 UAL = 445 ns
-    #   per-packet startup latency         = 456 + 445 + 445 = 1346 ns
-    # Packet count is PER CUBE (8 PEs/cube cooperate on the cube tile).
-    # At 6144 packets/cube the pipelined total is 8741 ns, so the
-    # bottleneck-stage interval τ = (8741 − 1346) / (6144 − 1) ≈ 1.204 ns.
-    # T_theoretical(N) = 1346 + (N − 1) × τ
-    #   where N = ceil((bytes_per_pe × 8) / 128) = ceil(bytes_per_pe / 16)
-    NOC_PACKET_BYTES = 128
-    PES_PER_CUBE = 8
-    T_STARTUP_NS = 1346.0
-    TAU_NS = (8741.0 - 1346.0) / (6144 - 1)  # ≈ 1.2038 ns/packet
-
-    def _theoretical_torus_2d_ns(bytes_per_pe: int) -> float:
-        bytes_per_cube = int(bytes_per_pe) * PES_PER_CUBE
-        n_packets = max(1, -(-bytes_per_cube // NOC_PACKET_BYTES))  # ceil
-        return T_STARTUP_NS + (n_packets - 1) * TAU_NS
-
-    fig, ax = plt.subplots(figsize=(9, 6))
-    for topo_name in topologies:
-        rs = sorted(
-            [r for r in records if r["sip_topology"] == topo_name],
-            key=lambda r: r["bytes_per_pe"],
-        )
-        if not rs:
-            continue
-        ax.plot(
-            [r["bytes_per_pe"] for r in rs],
-            [r["latency_ns"] for r in rs],
-            marker="o",
-            label=f"{topo_name} (n_sips={rs[0]['n_sips']})",
-            color=colors.get(topo_name),
-        )
-
-    # Theoretical torus_2d curve across all payload sizes.
-    torus_rs = sorted(
-        [r for r in records if r["sip_topology"] == "torus_2d"],
-        key=lambda r: r["bytes_per_pe"],
-    )
-    if torus_rs:
-        xs_th = [r["bytes_per_pe"] for r in torus_rs]
-        ys_th = [_theoretical_torus_2d_ns(r["bytes_per_pe"]) for r in torus_rs]
-        ax.plot(
-            xs_th, ys_th,
-            color="tab:red", linestyle="--", linewidth=1.6, marker="x",
-            label="theoretical torus_2d (6 SIPs)",
-        )
-
-    ax.set_xscale("log", base=2)
-    ax.set_xlabel("Bytes per PE (log scale)")
-    ax.set_ylabel("Time (ns)")
-    ax.set_title("Multi-device allreduce latency by topology")
-    ax.grid(True, alpha=0.3)
-    ax.set_xlim(left=min(r["bytes_per_pe"] for r in records) / 2,
-                right=max(r["bytes_per_pe"] for r in records) * 1.5)
-    ax.legend()
-    ax.xaxis.set_major_formatter(_bytes_fmt)
-    fig.tight_layout()
-    fig.savefig(_SWEEP_OUT_DIR / "overview.png", dpi=120)
-    plt.close(fig)
+    # Combined overview.png is no longer emitted — the broken-y-axis
+    # comparison (scripts/emit_overview_with_external_ref.py →
+    # comparison_mesh_vs_ring_vs_2DTorus_vs_theoretical_vs_fsim.png)
+    # supersedes it. Per-topology plots above and summary.csv are still
+    # produced.
 
     # Cleanup row staging dir so a partial future run doesn't pick up
     # stale rows.
@@ -535,7 +486,7 @@ def _aggregate_sweep_plots() -> bool:
     except OSError:
         pass
 
-    print(f"\nWrote {_SWEEP_OUT_DIR / 'overview.png'} "
+    print(f"\nWrote per-topology plots + summary.csv to {_SWEEP_OUT_DIR} "
           f"from {len(records)} rows")
     return True