Add probe CLI improvements, D2H read, UCIe/HBM tuning, BW sweep

- Probe CLI: restructured output (tables first, routes below), per-hop
  timestamps, split cross-cube into best/worst cases, D2H read section
- UCIe overhead: 1ns -> 8ns per port (16ns per crossing) to fix
  cross-cube-best < cross-half latency inversion
- HBM efficiency: added efficiency=0.8 factor to hbm_ctrl, reducing
  effective BW from 256 to 204.8 GB/s
- Multi-size BW sweep: saturation tables (4KB-1MB) for all probe cases
- Probe default data size: 4KB -> 32KB for more realistic measurements
- IOChiplet NOC + D2H topology and tests
- NOC mesh, xbar, BW occupancy components and tests
- Cube mesh visualization diagram

278 tests pass.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

tests/test_routing.py

@@ -75,58 +75,60 @@ def test_resolve_nonexistent_node():
 
 
 def test_path_local_hbm_same_half():
-    """PE0 -> slice0 (local): pe_dma -> xbar.pe0 -> hbm_ctrl.slice0 (no chain hops)."""
+    """PE0 -> slice0 (local): pe_dma -> noc -> xbar_top -> hbm_ctrl.slice0."""
     g = _graph()
     router = PathRouter(g)
     path = router.find_path("sip0.cube0.pe0", "sip0.cube0.hbm_ctrl.slice0")
     assert path[0] == "sip0.cube0.pe0.pe_dma"
-    assert "sip0.cube0.xbar.pe0" in path
+    assert "sip0.cube0.noc" in path
+    assert "sip0.cube0.xbar_top" in path
     assert path[-1] == "sip0.cube0.hbm_ctrl.slice0"
-    # local access: no bridge and no chain traversal (shortest path = 3 nodes)
     assert not any("bridge" in n for n in path)
-    assert len(path) == 3  # pe_dma → xbar.pe0 → slice0
+    assert len(path) == 4  # pe_dma → noc → xbar_top → slice0
 
 
 # ── PathRouter: same-half remote HBM ────────────────────────────────
 
 
 def test_path_same_half_remote_hbm():
-    """PE0 -> slice1: same-half chain traversal pe0→pe1, no bridge."""
+    """PE0 -> slice1: same-half via noc → xbar_top, no bridge."""
     g = _graph()
     router = PathRouter(g)
     path = router.find_path("sip0.cube0.pe0", "sip0.cube0.hbm_ctrl.slice1")
     assert path[0] == "sip0.cube0.pe0.pe_dma"
-    assert "sip0.cube0.xbar.pe0" in path   # enter at pe0
-    assert "sip0.cube0.xbar.pe1" in path   # chain hop to pe1
+    assert "sip0.cube0.noc" in path
+    assert "sip0.cube0.xbar_top" in path
     assert path[-1] == "sip0.cube0.hbm_ctrl.slice1"
     assert not any("bridge" in n for n in path)
-    assert len(path) == 4  # pe_dma → xbar.pe0 → xbar.pe1 → slice1
+    assert len(path) == 4  # pe_dma → noc → xbar_top → slice1
 
 
 # ── PathRouter: cross-half HBM ──────────────────────────────────────
 
 
 def test_path_cross_half_hbm():
-    """PE0 -> slice4 (cross-half): pe_dma → xbar.pe0 → bridge.left → xbar.pe4 → slice4."""
+    """PE0 -> slice4 (cross-half): pe_dma → noc → xbar_top → bridge → xbar_bot → slice4."""
     g = _graph()
     router = PathRouter(g)
     path = router.find_path("sip0.cube0.pe0", "sip0.cube0.hbm_ctrl.slice4")
     assert path[0] == "sip0.cube0.pe0.pe_dma"
-    assert "sip0.cube0.xbar.pe0" in path
+    assert "sip0.cube0.xbar_top" in path
     assert any("bridge" in n for n in path), "cross-half HBM must traverse bridge"
-    assert "sip0.cube0.xbar.pe4" in path
+    assert "sip0.cube0.xbar_bot" in path
     assert path[-1] == "sip0.cube0.hbm_ctrl.slice4"
-    # Shortest cross-half path: pe_dma → xbar.pe0 → bridge.left → xbar.pe4 → slice4
-    assert len(path) == 5
+    assert len(path) == 6  # pe_dma → noc → xbar_top → bridge → xbar_bot → slice4
 
 
-def test_path_cross_half_requires_bridge():
-    """PE4 (bottom) -> slice2 (top) requires bridge traversal."""
+def test_path_cross_half_via_xbar_top():
+    """PE4 (bottom) -> slice2 (top) goes through xbar_top via NOC.
+
+    NOC connects directly to xbar_top (low routing weight), so
+    bottom PEs access top-half HBM through noc → xbar_top.
+    """
     g = _graph()
     router = PathRouter(g)
     path = router.find_path("sip0.cube0.pe4", "sip0.cube0.hbm_ctrl.slice2")
-    assert any("bridge" in n for n in path), "cross-half HBM must traverse bridge"
-    assert any("xbar.pe" in n for n in path)
+    assert "sip0.cube0.xbar_top" in path
     assert path[-1] == "sip0.cube0.hbm_ctrl.slice2"
 
 
@@ -141,16 +143,20 @@ def test_cross_half_distance_greater():
     assert dist_cross > dist_local
 
 
-def test_path_same_half_remote_longer():
-    """Same-half remote HBM (PE0->slice3) has greater distance than local (PE0->slice0)."""
+def test_path_same_half_same_distance():
+    """Same-half HBM slices (PE0->slice0 vs PE0->slice3) have same distance.
+
+    With xbar_top/bot, all top-half slices are equidistant via noc → xbar_top.
+    """
     g = _graph()
     router = PathRouter(g)
     _, dist_local = router.find_path_with_distance(
         "sip0.cube0.pe0", "sip0.cube0.hbm_ctrl.slice0")
     _, dist_remote = router.find_path_with_distance(
         "sip0.cube0.pe0", "sip0.cube0.hbm_ctrl.slice3")
-    assert dist_remote > dist_local, (
-        f"same-half remote ({dist_remote:.2f}mm) must > local ({dist_local:.2f}mm)"
+    assert dist_remote == dist_local, (
+        f"same-half slices should have equal distance: "
+        f"slice0={dist_local:.2f}mm, slice3={dist_remote:.2f}mm"
     )