Add reverse path response latency for PE DMA and PE_CPU→M_CPU

Model fabric response hop latency for PE-internal operations:
- HBM_CTRL sends PeDmaMsg response on reverse path instead of direct done signal
- PE_CPU sends ResponseMsg via NOC→M_CPU on kernel completion
- Add NOC→PE_DMA and PE_CPU→NOC edges in topology builder
- Make HBM BW test assertions dynamic based on topology efficiency

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

tests/test_probe.py

@@ -143,6 +143,14 @@ def _graph():
     return load_topology(TOPOLOGY_PATH)
 
 
+def _hbm_effective_bw() -> float:
+    """Compute HBM effective BW from topology spec: xbar_to_hbm_bw_gbs * efficiency."""
+    g = _graph()
+    raw_bw = g.spec["cube"]["links"]["xbar_to_hbm_bw_gbs"]
+    eff = g.spec["cube"]["components"]["hbm_ctrl"].get("attrs", {}).get("efficiency", 1.0)
+    return raw_bw * eff
+
+
 def _pe_dma_latency(src_cube: int, src_pe: int, dst_pe: int) -> float:
     engine = _engine()
     msg = PeDmaMsg(
@@ -190,15 +198,17 @@ def test_pe_dma_local_completes():
 
 
 def test_pe_dma_local_bottleneck_hbm():
-    """PE DMA pe0→slice0 (local): bottleneck = HBM effective BW (256 * 0.8 = 204.8)."""
+    """PE DMA pe0→slice0 (local): bottleneck = HBM effective BW."""
     bn = _pe_dma_bottleneck(src_cube=0, src_pe=0, dst_pe=0)
-    assert bn == 204.8, f"Local PE DMA bottleneck {bn}, expected 204.8"
+    expected = _hbm_effective_bw()
+    assert bn == expected, f"Local PE DMA bottleneck {bn}, expected {expected}"
 
 
 def test_pe_dma_same_half_bottleneck_hbm():
     """PE DMA pe0→slice1 (same half via xbar_top): bottleneck = HBM effective BW."""
     bn = _pe_dma_bottleneck(src_cube=0, src_pe=0, dst_pe=1)
-    assert bn == 204.8, f"Same-half PE DMA bottleneck {bn}, expected 204.8"
+    expected = _hbm_effective_bw()
+    assert bn == expected, f"Same-half PE DMA bottleneck {bn}, expected {expected}"
 
 
 def test_pe_dma_deterministic():
@@ -311,12 +321,13 @@ def test_d2h_latency_gte_h2d():
 
 
 def test_hbm_efficiency_applied():
-    """HBM edge BW should reflect efficiency factor (256 * 0.8 = 204.8)."""
+    """HBM edge BW should reflect efficiency factor from topology spec."""
     graph = _graph()
     edge_map = {(e.src, e.dst): e for e in graph.edges}
     e = edge_map.get(("sip0.cube0.xbar_top", "sip0.cube0.hbm_ctrl.slice0"))
     assert e is not None, "xbar_top -> hbm_ctrl.slice0 edge missing"
-    assert e.bw_gbs == 204.8, f"HBM edge BW {e.bw_gbs}, expected 204.8 (256*0.8)"
+    expected = _hbm_effective_bw()
+    assert e.bw_gbs == expected, f"HBM edge BW {e.bw_gbs}, expected {expected}"
 
 
 # ── 11. Sweep saturation ──────────────────────────────────────

tests/test_topology_compile.py

@@ -29,19 +29,19 @@ def test_full_graph_node_count():
 
 def test_full_graph_edge_count():
     g = _graph()
-    # Per cube: 168
+    # Per cube: 184
     #   PE-internal: 56
-    #   PE_DMA→noc: 8, noc→pe_cpu: 8
+    #   PE_DMA→noc: 8, noc→pe_dma: 8, noc→pe_cpu: 8, pe_cpu→noc: 8
     #   xbar_top→hbm{0..3}: 4+4=8, xbar_bot→hbm{4..7}: 4+4=8
     #   noc↔xbar_top: 2, noc↔xbar_bot: 2
     #   xbar_top↔bridge.left: 2, bridge.left↔xbar_bot: 2
     #   xbar_top↔bridge.right: 2, bridge.right↔xbar_bot: 2
     #   ucie: 64, m_cpu↔noc: 2, noc↔sram: 2
-    #   Total: 56+8+8+8+8+2+2+2+2+2+2+64+2+2 = 168
+    #   Total: 56+8+8+8+8+8+8+2+2+2+2+2+2+64+2+2 = 184
     # IO edges per SIP: 77
-    # Per SIP: 16*168 + 48 inter-cube + 77 IO = 2813
-    # Total: 2 * 2813 = 5626
-    assert len(g.edges) == 5626
+    # Per SIP: 16*184 + 48 inter-cube + 77 IO = 3069
+    # Total: 2 * 3069 = 6138
+    assert len(g.edges) == 6138
 
 
 # ── Full graph: specific nodes exist ─────────────────────────────────