Speedup constant factors in LookaheadSwap (#8068)

* Speedup constant factors in `LookaheadSwap`

This picks some of the low-hanging fruit in `LookaheadSwap`, avoiding
recalculating various properties and entities that are already known,
and making some access patterns more efficient.  It does not change the
complexity properties of the algorithm, which will still cause its
runtime to be excessive for large circuits.

* Put comment in correct location

Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

qiskit/transpiler/passes/routing/lookahead_swap.py

@@ -12,10 +12,11 @@
 
 """Map input circuit onto a backend topology via insertion of SWAPs."""
 
+import collections
+import copy
 import logging
-from copy import deepcopy
+import math
 
-from qiskit.circuit.quantumregister import QuantumRegister
 from qiskit.circuit.library.standard_gates import SwapGate
 from qiskit.transpiler.basepasses import TransformationPass
 from qiskit.transpiler.exceptions import TranspilerError
@@ -25,6 +26,25 @@
 logger = logging.getLogger(__name__)
 
 
+_Step = collections.namedtuple("_Step", ("state", "swaps_added", "gates_mapped", "gates_remaining"))
+"""Describes one possible step in the lookahead process.
+
+The fields are:
+
+    state (_SystemState): The current state of the system, including its virtual-to-physical layout.
+    swaps_added (list): List of qargs of swap gates introduced.
+    gates_mapped (list): Gates that were mapped, including added SWAPs.
+    gates_remaining (list): Gates that could not be mapped.
+"""
+
+_SystemState = collections.namedtuple(
+    "_SystemState",
+    ("layout", "coupling_map", "register", "swaps"),
+    # The None default applies to the right-most element, i.e. `swaps`.
+    defaults=(None,),
+)
+
+
 class LookaheadSwap(TransformationPass):
     """Map input circuit onto a backend topology via insertion of SWAPs.
 
@@ -100,21 +120,20 @@ def run(self, dag):
                 f"available device qubits ({number_of_available_qubits})."
             )
 
-        canonical_register = dag.qregs["q"]
-        trivial_layout = Layout.generate_trivial_layout(canonical_register)
-        current_layout = trivial_layout.copy()
+        register = dag.qregs["q"]
+        current_state = _SystemState(
+            Layout.generate_trivial_layout(register), self.coupling_map, register
+        )
 
         mapped_gates = []
-        ordered_virtual_gates = list(dag.serial_layers())
-        gates_remaining = ordered_virtual_gates.copy()
+        gates_remaining = list(dag.serial_layers())
 
         while gates_remaining:
             logger.debug("Top-level routing step: %d gates remaining.", len(gates_remaining))
 
             best_step = _search_forward_n_swaps(
-                current_layout,
+                current_state,
                 gates_remaining,
-                self.coupling_map,
                 self.search_depth,
                 self.search_width,
             )
@@ -126,108 +145,90 @@ def run(self, dag):
 
             logger.debug(
                 "Found best step: mapped %d gates. Added swaps: %s.",
-                len(best_step["gates_mapped"]),
-                best_step["swaps_added"],
+                len(best_step.gates_mapped),
+                best_step.swaps_added,
             )
 
-            current_layout = best_step["layout"]
-            gates_mapped = best_step["gates_mapped"]
-            gates_remaining = best_step["gates_remaining"]
+            current_state = best_step.state
+            gates_mapped = best_step.gates_mapped
+            gates_remaining = best_step.gates_remaining
 
             mapped_gates.extend(gates_mapped)
 
         if self.fake_run:
-            self.property_set["final_layout"] = current_layout
+            self.property_set["final_layout"] = current_state.layout
             return dag
 
         # Preserve input DAG's name, regs, wire_map, etc. but replace the graph.
         mapped_dag = dag.copy_empty_like()
-
         for node in mapped_gates:
             mapped_dag.apply_operation_back(op=node.op, qargs=node.qargs, cargs=node.cargs)
 
         return mapped_dag
 
 
-def _search_forward_n_swaps(layout, gates, coupling_map, depth, width):
+def _search_forward_n_swaps(state, gates, depth, width):
     """Search for SWAPs which allow for application of largest number of gates.
 
     Args:
-        layout (Layout): Map from virtual qubit index to physical qubit index.
+        state (_SystemState): The ``namedtuple`` collection containing the state of the physical
+            system.  This includes the current layout, the coupling map, the canonical register and
+            the possible swaps available.
         gates (list): Gates to be mapped.
-        coupling_map (CouplingMap): CouplingMap of the target backend.
         depth (int): Number of SWAP layers to search before choosing a result.
         width (int): Number of SWAPs to consider at each layer.
     Returns:
-        optional(dict): Describes solution step found. If None, no swaps leading
-            to an improvement were found. Keys:
-            layout (Layout): Virtual to physical qubit map after SWAPs.
-            swaps_added (list): List of qargs of swap gates introduced.
-            gates_remaining (list): Gates that could not be mapped.
-            gates_mapped (list): Gates that were mapped, including added SWAPs.
-
+        Optional(_Step): Describes the solution step found.  If ``None``, no swaps leading to an
+        improvement were found.
     """
-    gates_mapped, gates_remaining = _map_free_gates(layout, gates, coupling_map)
-
-    base_step = {
-        "layout": layout,
-        "swaps_added": [],
-        "gates_mapped": gates_mapped,
-        "gates_remaining": gates_remaining,
-    }
+    if state.swaps is None:
+        # Include symmetric couplings (e.g [0,1] and [1,0]) as one swap.
+        state = state._replace(
+            swaps={((a, b) if a < b else (b, a)) for a, b in state.coupling_map.get_edges()}
+        )
+    gates_mapped, gates_remaining = _map_free_gates(state, gates)
+    base_step = _Step(state, [], gates_mapped, gates_remaining)
 
     if not gates_remaining or depth == 0:
         return base_step
 
-    # Include symmetric 2q gates (e.g coupling maps with both [0,1] and [1,0])
-    # as one available swap.
-    possible_swaps = {tuple(sorted(edge)) for edge in coupling_map.get_edges()}
-
-    def _score_swap(swap):
-        """Calculate the relative score for a given SWAP."""
-        trial_layout = layout.copy()
-        trial_layout.swap(*swap)
-        return _calc_layout_distance(gates, coupling_map, trial_layout)
-
-    ranked_swaps = sorted(possible_swaps, key=_score_swap)
+    ranked_swaps = sorted(
+        (_score_state_with_swap(swap, state, gates) for swap in state.swaps),
+        key=lambda x: x[0],
+    )
     logger.debug(
         "At depth %d, ranked candidate swaps: %s...",
         depth,
-        [(swap, _score_swap(swap)) for swap in ranked_swaps[: width * 2]],
+        [(swap, score) for score, swap, _ in ranked_swaps[: width * 2]],
     )
 
-    best_swap, best_step = None, None
-    for rank, swap in enumerate(ranked_swaps):
-        trial_layout = layout.copy()
-        trial_layout.swap(*swap)
-        next_step = _search_forward_n_swaps(
-            trial_layout, gates_remaining, coupling_map, depth - 1, width
-        )
+    best_swap, best_step, best_score = None, None, -math.inf
+    for rank, (_, swap, new_state) in enumerate(ranked_swaps):
+        next_step = _search_forward_n_swaps(new_state, gates_remaining, depth - 1, width)
 
         if next_step is None:
             continue
 
+        next_score = _score_step(next_step)
         # ranked_swaps already sorted by distance, so distance is the tie-breaker.
-        if best_swap is None or _score_step(next_step) > _score_step(best_step):
+        if next_score > best_score:
             logger.debug(
                 "At depth %d, updating best step: %s (score: %f).",
                 depth,
-                [swap] + next_step["swaps_added"],
-                _score_step(next_step),
+                [swap] + next_step.swaps_added,
+                next_score,
             )
-            best_swap, best_step = swap, next_step
+            best_swap, best_step, best_score = swap, next_step, next_score
 
         if (
             rank >= min(width, len(ranked_swaps) - 1)
             and best_step is not None
             and (
-                len(best_step["gates_mapped"]) > depth
-                or len(best_step["gates_remaining"]) < len(gates_remaining)
+                len(best_step.gates_mapped) > depth
+                or len(best_step.gates_remaining) < len(gates_remaining)
                 or (
-                    _calc_layout_distance(
-                        best_step["gates_remaining"], coupling_map, best_step["layout"]
-                    )
-                    < _calc_layout_distance(gates_remaining, coupling_map, layout)
+                    _calc_layout_distance(best_step.gates_remaining, best_step.state)
+                    < _calc_layout_distance(gates_remaining, new_state)
                 )
             )
         ):
@@ -239,24 +240,24 @@ def _score_swap(swap):
     else:
         return None
 
-    logger.debug("At depth %d, best_swap set: %s.", depth, [best_swap] + best_step["swaps_added"])
-
-    best_swap_gate = _swap_ops_from_edge(best_swap, layout)
-    return {
-        "layout": best_step["layout"],
-        "swaps_added": [best_swap] + best_step["swaps_added"],
-        "gates_remaining": best_step["gates_remaining"],
-        "gates_mapped": gates_mapped + best_swap_gate + best_step["gates_mapped"],
-    }
+    best_swap_gate = _swap_ops_from_edge(best_swap, state)
+    out = _Step(
+        best_step.state,
+        [best_swap] + best_step.swaps_added,
+        gates_mapped + best_swap_gate + best_step.gates_mapped,
+        best_step.gates_remaining,
+    )
+    logger.debug("At depth %d, best_swap set: %s.", depth, out.swaps_added)
+    return out
 
 
-def _map_free_gates(layout, gates, coupling_map):
+def _map_free_gates(state, gates):
     """Map all gates that can be executed with the current layout.
 
     Args:
-        layout (Layout): Map from virtual qubit index to physical qubit index.
+        state (_SystemState): The physical characteristics of the system, including its current
+            layout and the coupling map.
         gates (list): Gates to be mapped.
-        coupling_map (CouplingMap): CouplingMap for target device topology.
 
     Returns:
         tuple:
@@ -267,12 +268,13 @@ def _map_free_gates(layout, gates, coupling_map):
 
     mapped_gates = []
     remaining_gates = []
+    layout_map = state.layout._v2p
 
     for gate in gates:
         # Gates without a partition (barrier, snapshot, save, load, noise) may
         # still have associated qubits. Look for them in the qargs.
         if not gate["partition"]:
-            qubits = [n for n in gate["graph"].nodes() if isinstance(n, DAGOpNode)][0].qargs
+            qubits = _first_op_node(gate["graph"]).qargs
 
             if not qubits:
                 continue
@@ -281,7 +283,7 @@ def _map_free_gates(layout, gates, coupling_map):
                 blocked_qubits.update(qubits)
                 remaining_gates.append(gate)
             else:
-                mapped_gate = _transform_gate_for_layout(gate, layout)
+                mapped_gate = _transform_gate_for_system(gate, state)
                 mapped_gates.append(mapped_gate)
             continue
 
@@ -291,10 +293,10 @@ def _map_free_gates(layout, gates, coupling_map):
             blocked_qubits.update(qubits)
             remaining_gates.append(gate)
         elif len(qubits) == 1:
-            mapped_gate = _transform_gate_for_layout(gate, layout)
+            mapped_gate = _transform_gate_for_system(gate, state)
             mapped_gates.append(mapped_gate)
-        elif coupling_map.distance(*(layout[q] for q in qubits)) == 1:
-            mapped_gate = _transform_gate_for_layout(gate, layout)
+        elif state.coupling_map.distance(layout_map[qubits[0]], layout_map[qubits[1]]) == 1:
+            mapped_gate = _transform_gate_for_system(gate, state)
             mapped_gates.append(mapped_gate)
         else:
             blocked_qubits.update(qubits)
@@ -303,43 +305,67 @@ def _map_free_gates(layout, gates, coupling_map):
     return mapped_gates, remaining_gates
 
 
-def _calc_layout_distance(gates, coupling_map, layout, max_gates=None):
+def _calc_layout_distance(gates, state, max_gates=None):
     """Return the sum of the distances of two-qubit pairs in each CNOT in gates
     according to the layout and the coupling.
     """
     if max_gates is None:
-        max_gates = 50 + 10 * len(coupling_map.physical_qubits)
+        max_gates = 50 + 10 * len(state.coupling_map.physical_qubits)
+
+    layout_map = state.layout._v2p
+    out = 0
+    for gate in gates[:max_gates]:
+        if not gate["partition"]:
+            continue
+        qubits = gate["partition"][0]
+        if len(qubits) == 2:
+            out += state.coupling_map.distance(layout_map[qubits[0]], layout_map[qubits[1]])
+    return out
 
-    return sum(
-        coupling_map.distance(*(layout[q] for q in gate["partition"][0]))
-        for gate in gates[:max_gates]
-        if gate["partition"] and len(gate["partition"][0]) == 2
-    )
+
+def _score_state_with_swap(swap, state, gates):
+    """Calculate the relative score for a given SWAP.
+
+    Returns:
+        float: the score of the given swap.
+        Tuple[int, int]: the input swap that should be performed.
+        _SystemState: an updated system state with the new layout contained.
+    """
+    trial_layout = state.layout.copy()
+    trial_layout.swap(*swap)
+    new_state = state._replace(layout=trial_layout)
+    return _calc_layout_distance(gates, new_state), swap, new_state
 
 
 def _score_step(step):
     """Count the mapped two-qubit gates, less the number of added SWAPs."""
     # Each added swap will add 3 ops to gates_mapped, so subtract 3.
-    return len([g for g in step["gates_mapped"] if len(g.qargs) == 2]) - 3 * len(
-        step["swaps_added"]
-    )
+    return len([g for g in step.gates_mapped if len(g.qargs) == 2]) - 3 * len(step.swaps_added)
 
 
-def _transform_gate_for_layout(gate, layout):
+def _transform_gate_for_system(gate, state):
     """Return op implementing a virtual gate on given layout."""
-    mapped_op_node = deepcopy([n for n in gate["graph"].nodes() if isinstance(n, DAGOpNode)][0])
+    mapped_op_node = copy.copy(_first_op_node(gate["graph"]))
 
-    device_qreg = QuantumRegister(len(layout.get_physical_bits()), "q")
-    mapped_qargs = [device_qreg[layout[a]] for a in mapped_op_node.qargs]
+    device_qreg = state.register
+    layout_map = state.layout._v2p
+    mapped_qargs = [device_qreg[layout_map[a]] for a in mapped_op_node.qargs]
     mapped_op_node.qargs = mapped_qargs
 
     return mapped_op_node
 
 
-def _swap_ops_from_edge(edge, layout):
+def _swap_ops_from_edge(edge, state):
     """Generate list of ops to implement a SWAP gate along a coupling edge."""
-    device_qreg = QuantumRegister(len(layout.get_physical_bits()), "q")
+    device_qreg = state.register
     qreg_edge = [device_qreg[i] for i in edge]
 
     # TODO shouldn't be making other nodes not by the DAG!!
     return [DAGOpNode(op=SwapGate(), qargs=qreg_edge, cargs=[])]
+
+
+def _first_op_node(dag):
+    """Get the first op node from a DAG."""
+    # This doesn't use `DAGCircuit.op_nodes` because that function always consumes the entire
+    # iterator to create a list, whereas we only need the first element.
+    return next(node for node in dag.nodes() if isinstance(node, DAGOpNode))

releasenotes/notes/speedup-lookahead-swap-4dd162fee2d25d10.yaml

@@ -0,0 +1,10 @@
+---
+features:
+  - |
+    The transpiler pass :class:`.LookaheadSwap` (used by :func:`.transpile` when
+    ``routing_method="lookahead"``) has seen some performance improvements and
+    will now be approximately three times as fast.  This is purely being more
+    efficient in its calculations, and does not change the complexity of the
+    algorithm.  In most cases, a more modern routing algorithm like
+    :class:`.SabreSwap` (``routing_method="sabre"``) will be vastly more
+    performant.