Krylov-Quanten-Diagonalisierung von Gitter-Hamilton-Operatoren

from __future__ import annotations

import warnings

import numpy as np
import pandas as pd
import scipy.linalg as la
import matplotlib.pyplot as plt

from qiskit import QuantumCircuit, transpile
from qiskit.circuit import Parameter
from qiskit.circuit.library import PauliEvolutionGate
from qiskit.primitives import StatevectorEstimator
from qiskit.quantum_info import Operator, SparsePauliOp
from qiskit.synthesis import LieTrotter, SuzukiTrotter
from qiskit.transpiler import PassManager, Layout
from qiskit.transpiler.passes import CommutativeOptimization
from qiskit.transpiler.preset_passmanagers import generate_preset_pass_manager
from qiskit_ibm_runtime import QiskitRuntimeService, EstimatorV2, Batch
from qiskit_ibm_runtime.fake_provider import FakeMarrakesh

warnings.filterwarnings("ignore")


def make_heisenberg_hamiltonian(
    num_qubits: int,
    coupling: float = 1.0,
) -> SparsePauliOp:
    """Make a Heisenberg Hamiltonian for a 1D chain of qubits with nearest-neighbor interactions."""
    terms: list[tuple[str, complex]] = []

    def append_term(q0: int, q1: int, pauli: str):
        label = ["I"] * num_qubits
        label[num_qubits - 1 - q0] = pauli[0]
        label[num_qubits - 1 - q1] = pauli[1]
        terms.append(("".join(label), coupling))

    for pauli in ("XX", "YY", "ZZ"):
        for q in range(num_qubits - 1):
            append_term(q, q + 1, pauli)
    return SparsePauliOp.from_list(terms).simplify()


def _basis_state_transition_amplitude_sparse(
    hamiltonian: SparsePauliOp,
    bra_state: int,
    ket_state: int,
) -> complex:
    """Evaluate <bra_state|H|ket_state> for computational-basis states."""
    num_qubits = hamiltonian.num_qubits
    amplitude = 0.0 + 0.0j
    for pauli, coeff in zip(hamiltonian.paulis, hamiltonian.coeffs):
        new_state = ket_state
        phase = 1.0 + 0.0j
        for q in range(num_qubits):
            x = bool(pauli.x[q])
            z = bool(pauli.z[q])
            if not x and not z:
                continue
            bit = (new_state >> q) & 1
            if x and z:
                # Y|0> = i|1>, Y|1> = -i|0>
                phase *= 1j if bit == 0 else -1j
                new_state ^= 1 << q
            elif x:
                new_state ^= 1 << q
            else:
                # Z|0> = |0>, Z|1> = -|1>
                if bit:
                    phase *= -1
        if new_state == bra_state:
            amplitude += coeff * phase
    return amplitude


def basis_state_expectation_sparse(
    hamiltonian: SparsePauliOp,
    bitstring: str,
) -> complex:
    """Evaluate <bitstring|H|bitstring>."""
    state = int(bitstring, 2)
    return _basis_state_transition_amplitude_sparse(
        hamiltonian,
        bra_state=state,
        ket_state=state,
    )


def diagonalize_single_1_subspace(
    hamiltonian: SparsePauliOp,
) -> np.ndarray:
    """Diagonalize the Hamiltonian projected onto the single-excitation subspace."""
    num_qubits = hamiltonian.num_qubits

    # Integer basis states |...010...>, with the excitation at qubit k.
    basis = [1 << k for k in range(num_qubits)]

    h_single = np.empty((num_qubits, num_qubits), dtype=complex)

    for row, bra_state in enumerate(basis):
        for col, ket_state in enumerate(basis):
            h_single[row, col] = _basis_state_transition_amplitude_sparse(
                hamiltonian,
                bra_state=bra_state,
                ket_state=ket_state,
            )
    # Remove floating-point-level asymmetry.
    h_single = 0.5 * (h_single + h_single.conj().T)
    evals, _ = np.linalg.eigh(h_single)
    return np.real(evals)


def simple_transpilation(circuit: QuantumCircuit) -> QuantumCircuit:
    """Transpilation to simplify the circuit"""
    pm = PassManager(
        [
            CommutativeOptimization(),
        ]
    )
    circuit = transpile(circuit, optimization_level=3)
    circuit = pm.run(circuit)
    return circuit


def summarize_circuit(circuit: QuantumCircuit) -> dict[str, int | str]:
    """Summarize the circuit with depth, size, and 2-qubit gate information."""
    two_qubit_total = sum(
        inst.operation.num_qubits == 2 for inst in circuit.data
    )
    two_qubit_depth = circuit.depth(lambda x: x[0].num_qubits == 2)
    return {
        "depth": circuit.depth(),
        "size": circuit.size(),
        "2q gates": two_qubit_total,
        "2q depth": two_qubit_depth,
    }


def solve_thresholded_gevp(
    h_matrix: np.ndarray,
    s_matrix: np.ndarray,
    threshold: float = 1e-10,
) -> tuple[float, np.ndarray, int]:
    """Solve H c = E S c using canonical orthogonalization of S."""
    s_vals, s_vecs = la.eigh(s_matrix)

    valid = s_vals > threshold
    if not np.any(valid):
        raise ValueError(
            "All overlap eigenvalues were removed by thresholding."
        )

    keep = valid

    orthogonalizer = s_vecs[:, keep] @ np.diag(1.0 / np.sqrt(s_vals[keep]))
    h_orth = orthogonalizer.conj().T @ h_matrix @ orthogonalizer
    h_orth = 0.5 * (h_orth + h_orth.conj().T)

    eigvals, eigvecs = la.eigh(h_orth)

    coeffs = orthogonalizer @ eigvecs[:, 0]
    normalization = np.sqrt(np.real(coeffs.conj().T @ s_matrix @ coeffs))
    coeffs /= normalization

    return float(np.real(eigvals[0])), coeffs, int(np.sum(keep))

try:
    service = QiskitRuntimeService()
except Exception:
    QiskitRuntimeService.save_account(
        token="<api_token>", instance="<instance>", overwrite=True
    )
    service = QiskitRuntimeService()

backend = FakeMarrakesh()

# Problem definition for the simulator example
num_qubits = 12
hamiltonian = make_heisenberg_hamiltonian(num_qubits=num_qubits, coupling=1.0)
ref_bitstring = "000001000000"
ref_energy = basis_state_expectation_sparse(hamiltonian, ref_bitstring)

print("Hamiltonian:")
print(hamiltonian)
print(f"Reference state: |{ref_bitstring}>")
print("Reference energy: ", ref_energy)

dt = np.pi / (3 * (num_qubits - 1))
print("dt in Krylov basis:  ", dt)

krylov_dim = 10
num_trotter_steps = 5

qc_ref = QuantumCircuit(num_qubits)
for i, b in enumerate(reversed(ref_bitstring)):
    if b == "1":
        qc_ref.x(i)
display(qc_ref.draw("mpl", scale=0.5))

t = Parameter("t")

evol_gate = PauliEvolutionGate(
    hamiltonian,
    time=t,
    synthesis=LieTrotter(reps=num_trotter_steps),
    label="U(t)",
)

# Synthesize U(t) first and then control the synthesized circuit.
# This makes the controlled structure visible in the circuit drawer.
evolution_circuit = QuantumCircuit(num_qubits, name="U(t)")
evolution_circuit.append(evol_gate, range(num_qubits))
evolution_circuit = simple_transpilation(evolution_circuit)

# Make a controlled version of the evolution circuit.
controlled_evolution_gate = evolution_circuit.to_gate(label="U(t)").control(
    1, label="C-U(t)"
)
display(
    evolution_circuit.assign_parameters({t: 1.5}).draw(
        "mpl", scale=0.5, fold=-1
    )
)

ancilla = 0
system_qubits = list(range(1, num_qubits + 1))

extended_swap_test = QuantumCircuit(num_qubits + 1)

# Append state preparation part
extended_swap_test = extended_swap_test.compose(qc_ref, system_qubits)

# Prepare the coherent branch label, (|0> + |1>) / sqrt(2).
extended_swap_test.h(ancilla)

# Apply U(t) only to the |1> branch of the ancilla.
extended_swap_test.append(
    controlled_evolution_gate, [ancilla] + system_qubits
)

# Decompose once more for visualization so that control bullets are visible.
display(extended_swap_test.draw("mpl", fold=-1))

n_qubits = hamiltonian.num_qubits

observable_labels = [
    "Re S_0d",
    "Im S_0d",
    "Re H_0d",
    "Im H_0d",
]

# X ⊗ I and Y ⊗ I.
# Qiskit's Pauli-label convention places qubit 0 on the rightmost character,
# so the ancilla Pauli is appended to the right.
obs_x_identity = SparsePauliOp("I" * n_qubits + "X")
obs_y_identity = SparsePauliOp("I" * n_qubits + "Y")

# X ⊗ H and Y ⊗ H.
obs_x_hamiltonian = SparsePauliOp.from_list(
    [
        (label + "X", coeff)
        for label, coeff in zip(
            hamiltonian.paulis.to_labels(),
            hamiltonian.coeffs,
        )
    ]
)

obs_y_hamiltonian = SparsePauliOp.from_list(
    [
        (label + "Y", coeff)
        for label, coeff in zip(
            hamiltonian.paulis.to_labels(),
            hamiltonian.coeffs,
        )
    ]
)

observables = [
    obs_x_identity,
    obs_y_identity,
    obs_x_hamiltonian,
    obs_y_hamiltonian,
]

for obs, label in zip(observables, observable_labels):
    print(f"Observable: {label}")
    print(obs)
    print()

def make_reduced_heisenberg_observables(
    ref_bitstring: str,
    coupling: float = 1.0,
) -> tuple[SparsePauliOp, SparsePauliOp, float]:
    """Build X⊗(H-T), Y⊗(H-T), and tau."""
    n_qubits = len(ref_bitstring)

    shifted_terms: list[tuple[str, complex]] = []
    tau = 0.0

    def bit(q: int) -> str:
        return ref_bitstring[n_qubits - 1 - q]

    def append_term(q0: int, q1: int, pauli: str):
        label = ["I"] * n_qubits
        label[n_qubits - 1 - q0] = pauli[0]
        label[n_qubits - 1 - q1] = pauli[1]
        shifted_terms.append(("".join(label), coupling))

    for q in range(n_qubits - 1):
        same_occupation = bit(q) == bit(q + 1)

        # ZZ contribution to tau
        tau += coupling * (1.0 if same_occupation else -1.0)

        # XX + YY survives only for opposite occupations.
        if not same_occupation:
            append_term(q, q + 1, "XX")
            append_term(q, q + 1, "YY")

    if shifted_terms:
        obs_x_shifted_hamiltonian = SparsePauliOp.from_list(
            [(label + "X", coeff) for label, coeff in shifted_terms]
        )
        obs_y_shifted_hamiltonian = SparsePauliOp.from_list(
            [(label + "Y", coeff) for label, coeff in shifted_terms]
        )
    else:
        obs_x_shifted_hamiltonian = SparsePauliOp(
            "I" * n_qubits + "X", coeffs=[0.0]
        )
        obs_y_shifted_hamiltonian = SparsePauliOp(
            "I" * n_qubits + "Y", coeffs=[0.0]
        )

    return obs_x_shifted_hamiltonian, obs_y_shifted_hamiltonian, tau


obs_x_shifted_hamiltonian, obs_y_shifted_hamiltonian, shift_tau = (
    make_reduced_heisenberg_observables(ref_bitstring)
)

print("Observable: Re shifted H_0d")
print(obs_x_shifted_hamiltonian)
print()

print("Observable: Im shifted H_0d")
print(obs_y_shifted_hamiltonian)
print()

print("tau =", shift_tau)

observables = [
    obs_x_identity,
    obs_y_identity,
    obs_x_shifted_hamiltonian,
    obs_y_shifted_hamiltonian,
]
observable_labels = [
    "Re S_0d",
    "Im S_0d",
    "Re shifted H_0d",
    "Im shifted H_0d",
]

# The comparison uses the largest time that appears in the first-row Krylov estimates.
# Circuit depth does not depend on this numeric value, but the Trotter error does.
comparison_time = (krylov_dim - 1) * dt


def make_heisenberg_hamiltonian_ordered(
    num_qubits: int,
    ordering: str,
    coupling: float = 1.0,
) -> SparsePauliOp:
    """Return the same Heisenberg Hamiltonian with a specified term ordering."""
    terms: list[tuple[str, complex]] = []
    even_edges = [(q, q + 1) for q in range(0, num_qubits - 1, 2)]
    odd_edges = [(q, q + 1) for q in range(1, num_qubits - 1, 2)]

    def append_term(q0: int, q1: int, pauli: str):
        label = ["I"] * num_qubits
        label[num_qubits - 1 - q0] = pauli[0]
        label[num_qubits - 1 - q1] = pauli[1]
        terms.append(("".join(label), coupling))

    if ordering == "naive":
        for pauli in ("XX", "YY", "ZZ"):
            for q in range(num_qubits - 1):
                append_term(q, q + 1, pauli)
    elif ordering == "even-then-odd":
        for pauli in ("XX", "YY", "ZZ"):
            for q0, q1 in even_edges + odd_edges:
                append_term(q0, q1, pauli)
    elif ordering == "even-odd edge-grouped":
        for q0, q1 in even_edges + odd_edges:
            for pauli in ("XX", "YY", "ZZ"):
                append_term(q0, q1, pauli)
    else:
        raise ValueError(f"Unknown ordering: {ordering}")

    return SparsePauliOp.from_list(terms).simplify()


def build_numeric_evolution_circuit(
    hamiltonian: SparsePauliOp,
    synthesis,
    time_value: float,
    **synthesis_kwargs,
) -> QuantumCircuit:
    """Build a numeric circuit for exp(-i H t) with a chosen synthesis rule."""
    evolution_gate = PauliEvolutionGate(
        hamiltonian,
        time=time_value,
        synthesis=synthesis(**synthesis_kwargs),
    )
    circuit = QuantumCircuit(hamiltonian.num_qubits)
    circuit.append(evolution_gate, range(hamiltonian.num_qubits))
    return circuit


def process_infidelity(
    circuit: QuantumCircuit,
    exact_matrix: np.ndarray,
) -> float:
    """Return 1 - |Tr(U_circuit† U_exact) / d|²."""
    circuit_matrix = np.asarray(Operator(circuit).data)
    dim = circuit_matrix.shape[0]
    normalized_trace = np.vdot(circuit_matrix, exact_matrix) / dim
    fidelity = np.abs(normalized_trace) ** 2
    return float(np.clip(1.0 - fidelity, 0.0, 1.0))


hamiltonians_by_ordering = {
    ordering: make_heisenberg_hamiltonian_ordered(
        num_qubits, ordering, coupling=1.0
    )
    for ordering in ["naive", "even-then-odd", "even-odd edge-grouped"]
}

print(f"Comparison time: {comparison_time}\n")

for order_name, ham_ordered in hamiltonians_by_ordering.items():
    print(f"{order_name}:")
    print([op for op, _ in ham_ordered.to_list()])
    print()

print("Precomputing the exact evolution operator... ", end="")
exact_matrix = la.expm(-1j * comparison_time * hamiltonian.to_matrix())
print("Done")

ordering_comparison_rows = []
infidelity_reps = [1, 2, 4, 8]

for ordering, ham_ordered in hamiltonians_by_ordering.items():
    for reps in infidelity_reps:
        circuit = build_numeric_evolution_circuit(
            ham_ordered,
            LieTrotter,
            comparison_time,
            reps=reps,
        )
        decomposed_circuit = simple_transpilation(circuit)
        infidelity = process_infidelity(decomposed_circuit, exact_matrix)
        ordering_comparison_rows.append(
            {
                "ordering": ordering,
                "synthesis": f"LieTrotter(reps={reps})",
                "infidelity": infidelity,
                **summarize_circuit(decomposed_circuit),
            }
        )
        if reps == 1:
            print(f"Circuit for {ordering} ordering:")
            print([op for op, _ in ham_ordered.to_list()])
            display(decomposed_circuit.draw("mpl", fold=-1, scale=0.6))

ordering_comparison_df = pd.DataFrame(ordering_comparison_rows)
display(ordering_comparison_df)

hamiltonian_for_synthesis = hamiltonians_by_ordering["even-odd edge-grouped"]

synthesis_comparison_rows = []

for num_trotter_steps in [1, 2, 3, 4, 5]:
    synthesis_cases = [
        ("LieTrotter", LieTrotter, {"reps": num_trotter_steps}),
        (
            "SuzukiTrotter(order=2)",
            SuzukiTrotter,
            {"order": 2, "reps": num_trotter_steps},
        ),
        (
            "SuzukiTrotter(order=4)",
            SuzukiTrotter,
            {"order": 4, "reps": num_trotter_steps},
        ),
    ]
    for label, synthesis, kwargs in synthesis_cases:
        circuit = build_numeric_evolution_circuit(
            hamiltonian_for_synthesis,
            synthesis,
            comparison_time,
            **kwargs,
        )
        decomposed_circuit = simple_transpilation(circuit)
        synthesis_comparison_rows.append(
            {
                "synthesis": label,
                "reps": kwargs["reps"],
                "infidelity": process_infidelity(
                    decomposed_circuit, exact_matrix
                ),
                **summarize_circuit(decomposed_circuit),
            }
        )

synthesis_comparison_df = pd.DataFrame(synthesis_comparison_rows)
display(synthesis_comparison_df.sort_values(["2q gates", "2q depth"]))

# For memory free
exact_matrix = None

controlled_extended_swap_test = extended_swap_test

# Reuse the ordering and synthesis rule selected by the comparison above.
evol_gate_optimized = PauliEvolutionGate(
    hamiltonian_for_synthesis,
    time=t,
    synthesis=SuzukiTrotter(order=2, reps=num_trotter_steps),
)

uncontrolled_evolution = QuantumCircuit(num_qubits, name="U_ST2(t)")
uncontrolled_evolution.append(evol_gate_optimized, range(num_qubits))

controlled_state_prep = QuantumCircuit(num_qubits + 1, name="C-Prep")
for q, bit in enumerate(reversed(ref_bitstring)):
    if bit == "1":
        controlled_state_prep.cx(ancilla, system_qubits[q])

vacuum_bitstring = "0" * num_qubits
vacuum_energy = basis_state_expectation_sparse(hamiltonian, "0" * num_qubits)

optimized_extended_swap_test = QuantumCircuit(num_qubits + 1)
optimized_extended_swap_test.h(ancilla)

# Prepare |psi_ref> only on the |1> branch.
optimized_extended_swap_test.compose(controlled_state_prep, inplace=True)
optimized_extended_swap_test.barrier()

# Apply the Trotterized time evolution without control.
optimized_extended_swap_test.compose(
    uncontrolled_evolution,
    qubits=system_qubits,
    inplace=True,
)
optimized_extended_swap_test.barrier()

# Map |0>|0...0> to |0>|psi_ref>, leaving the |1> branch unchanged.
optimized_extended_swap_test.x(ancilla)
optimized_extended_swap_test.compose(controlled_state_prep, inplace=True)
optimized_extended_swap_test.x(ancilla)

# Cancel the known vacuum phase so that the same X/Y observables can be used.
optimized_extended_swap_test.p(-vacuum_energy * t, ancilla)
optimized_extended_swap_test = simple_transpilation(
    optimized_extended_swap_test
)

print(f"Vacuum energy E_vac = {vacuum_energy:.1f}")
display(
    optimized_extended_swap_test.assign_parameters({t: 1.0}).draw(
        "mpl", scale=0.5, fold=26
    )
)

pass_manager = generate_preset_pass_manager(
    backend=backend,
    optimization_level=3,
)

isa_controlled_extended_swap_test = pass_manager.run(
    controlled_extended_swap_test
)

pass_manager = generate_preset_pass_manager(
    backend=backend, optimization_level=3, routing_method="none"
)
isa_optimized_extended_swap_test = pass_manager.run(
    optimized_extended_swap_test
)

transpilation_result = [
    {
        "label": "abstract controlled U(t)",
        **summarize_circuit(isa_controlled_extended_swap_test),
    },
    {
        "label": "optimized non-controlled U(t)",
        **summarize_circuit(isa_optimized_extended_swap_test),
    },
]

display(pd.DataFrame(transpilation_result))


def filter_qubits_from_layout(layout):
    q_layout = Layout(
        {
            physical: virtual
            for physical, virtual in layout.get_physical_bits().items()
            if virtual._register.name == "q"
        }
    )
    return q_layout


print(
    filter_qubits_from_layout(
        isa_optimized_extended_swap_test.layout.initial_layout
    )
)

isa_observables = [
    op.apply_layout(isa_optimized_extended_swap_test.layout)
    for op in observables
]

pub_list = []
d_values = list(range(1, krylov_dim))

# Exact local statevector estimator.
estimator = StatevectorEstimator()

# We use the circuit before the transpilation for the local simulator,
# but we will use the transpiled circuit for the real backend.
for d in d_values:
    parameter_values = [d * dt]

    for ob in observables:
        pub_list.append(
            (
                optimized_extended_swap_test,
                ob,
                parameter_values,
            )
        )

job = estimator.run(pub_list)

# Local PrimitiveJob does not provide Runtime-style job inputs,
# so preserve the inputs directly.
inputs = pub_list
result = job.result()

print(f"Number of Krylov basis states: r = {len(d_values)}")
print(f"Number of PUBs: {len(pub_list)}")
print(f"Each d uses observables: {observable_labels}")

h_shifted_row_est = np.zeros(krylov_dim, dtype=complex)
s_row_est = np.zeros(krylov_dim, dtype=complex)

h_shifted_row_est[0] = ref_energy - shift_tau
s_row_est[0] = 1.0

for idx, (pub_input, pub_result) in enumerate(zip(inputs, result)):
    d_index, obs_index = divmod(idx, len(observables))
    ev = np.asarray(pub_result.data.evs).reshape(-1)[0]
    std = np.asarray(pub_result.data.stds).reshape(-1)[0]

    if obs_index == 0:
        s_row_est[d_index + 1] = ev
    elif obs_index == 1:
        s_row_est[d_index + 1] += 1j * ev
    elif obs_index == 2:
        h_shifted_row_est[d_index + 1] = ev
    elif obs_index == 3:
        h_shifted_row_est[d_index + 1] += 1j * ev

# H_0d = shifted_H_0d + tau * S_0d.
h_row_est = h_shifted_row_est + shift_tau * s_row_est

h_matrix_est = la.toeplitz(h_row_est.conj(), h_row_est)
s_matrix_est = la.toeplitz(s_row_est.conj(), s_row_est)

s_eigvals = la.eigvalsh(0.5 * (s_matrix_est + s_matrix_est.conj().T))
positive_s_eigvals = s_eigvals[s_eigvals > 1e-12]
s_condition_number = (
    positive_s_eigvals[-1] / positive_s_eigvals[0]
    if len(positive_s_eigvals) > 0
    else np.inf
)


with np.printoptions(precision=3, suppress=True):
    print("Estimated first row of S:")
    print(s_row_est)
    print()
    print("Estimated first row of H:")
    print(h_row_est)
    print()
    print("Eigenvalues of the estimated overlap matrix S:")
    print(s_eigvals)
    print(f"Condition number above 1e-12: {s_condition_number:.3e}")
    print()

exact_evals = diagonalize_single_1_subspace(hamiltonian)
exact_ground = min(exact_evals)
print("exact ground state energy:  ", exact_ground)

threshold = 1e-12
energy_convergence = []

for r in range(1, krylov_dim + 1):
    energy_est_kqd, coeffs_est, retained_est = solve_thresholded_gevp(
        h_matrix_est[:r, :r],
        s_matrix_est[:r, :r],
        threshold=threshold,
    )
    energy_convergence.append(energy_est_kqd)
    print(
        f"Krylov ground state energy (dim={r}, retained={retained_est}): ",
        energy_est_kqd,
    )

def plot_energy_convergence(energy_convergence, exact_ground, krylov_dim):
    fig, ax = plt.subplots(figsize=(7, 4.5))

    ax.plot(
        range(1, krylov_dim + 1),
        energy_convergence,
        marker="o",
        label="KQD estimate",
    )

    ax.axhline(
        exact_ground,
        linestyle="--",
        label=f"Exact ground energy = {exact_ground:.6f}",
    )

    ax.set_xlabel("Krylov dimension")
    ax.set_ylabel("Ground-state energy")
    ax.grid(True, alpha=0.3)
    ax.legend()
    plt.tight_layout()
    plt.show()


plot_energy_convergence(energy_convergence, exact_ground, krylov_dim)

# -------------------------Step 1-------------------------

# Map the classical problem to quantum circuits and observables.
# Problem and KQD parameters.
large_num_qubits = 30
large_krylov_dim = 7
large_num_trotter_steps = 3
large_dt = np.pi / (3 * (large_num_qubits - 1))
large_t = Parameter("t_large")

# Use a single excitation near the center of the chain.
large_excitation_qubit = large_num_qubits // 2
large_ref_label = ["0"] * large_num_qubits
large_ref_label[large_num_qubits - 1 - large_excitation_qubit] = "1"
large_ref_bitstring = "".join(large_ref_label)

# Use the ordering and product formula selected in the preceding section.
large_hamiltonian = make_heisenberg_hamiltonian_ordered(
    large_num_qubits,
    ordering="even-odd edge-grouped",
    coupling=1.0,
)
large_ref_energy = float(
    np.real(
        basis_state_expectation_sparse(large_hamiltonian, large_ref_bitstring)
    )
)
large_vacuum_energy = float(
    np.real(
        basis_state_expectation_sparse(
            large_hamiltonian, "0" * large_num_qubits
        )
    )
)

large_evolution_gate = PauliEvolutionGate(
    large_hamiltonian,
    time=large_t,
    synthesis=SuzukiTrotter(order=2, reps=large_num_trotter_steps),
)
large_uncontrolled_evolution = QuantumCircuit(
    large_num_qubits,
    name="U_ST2_large(t)",
)
large_uncontrolled_evolution.append(
    large_evolution_gate,
    range(large_num_qubits),
)

# Build the control-free extended-swap-test circuit.
large_ancilla = 0
large_system_qubits = list(range(1, large_num_qubits + 1))

large_controlled_state_prep = QuantumCircuit(
    large_num_qubits + 1,
    name="C-Prep-large",
)
large_controlled_state_prep.cx(
    large_ancilla,
    large_system_qubits[large_excitation_qubit],
)

large_extended_swap_test = QuantumCircuit(large_num_qubits + 1)
large_extended_swap_test.h(large_ancilla)
large_extended_swap_test.compose(large_controlled_state_prep, inplace=True)
large_extended_swap_test.compose(
    large_uncontrolled_evolution,
    qubits=large_system_qubits,
    inplace=True,
)
large_extended_swap_test.x(large_ancilla)
large_extended_swap_test.compose(
    large_controlled_state_prep.inverse(),
    inplace=True,
)
large_extended_swap_test.x(large_ancilla)
large_extended_swap_test.p(
    -large_vacuum_energy * large_t,
    large_ancilla,
)

# Reuse the Hamiltonian-shifting construction from the preceding section.
(
    large_obs_x_shifted_hamiltonian,
    large_obs_y_shifted_hamiltonian,
    large_shift_tau,
) = make_reduced_heisenberg_observables(large_ref_bitstring)

large_observables = [
    SparsePauliOp("I" * large_num_qubits + "X"),
    SparsePauliOp("I" * large_num_qubits + "Y"),
    large_obs_x_shifted_hamiltonian,
    large_obs_y_shifted_hamiltonian,
]
large_observable_labels = [
    "Re S_0d",
    "Im S_0d",
    "Re shifted H_0d",
    "Im shifted H_0d",
]

# -------------------------Step 2-------------------------

# Optimize the problem for quantum execution.
# Select a real backend and transpile the parameterized circuit to ISA form.
large_backend = service.backend("ibm_boston")
large_pass_manager = generate_preset_pass_manager(
    backend=large_backend, optimization_level=3, routing_method="none"
)
large_isa_circuit = large_pass_manager.run(large_extended_swap_test)
large_isa_observables = [
    observable.apply_layout(large_isa_circuit.layout)
    for observable in large_observables
]

large_two_qubit_gate_count = sum(
    instruction.operation.num_qubits == 2
    for instruction in large_isa_circuit.data
)

print(f"Backend: {large_backend.name}")
print(f"System qubits: {large_num_qubits}")
print(f"Total circuit qubits: {large_isa_circuit.num_qubits}")
print(f"Krylov dimension: {large_krylov_dim}")
print(f"Time step: {large_dt:.6f}")
print(f"Shift tau: {large_shift_tau}")
print(f"ISA circuit depth: {large_isa_circuit.depth()}")
print(f"ISA two-qubit gates: {large_two_qubit_gate_count}")
print(
    f"ISA two-qubit depth: {large_isa_circuit.depth(lambda x: x[0].num_qubits == 2)}"
)

# -------------------------Step 3-------------------------

# Execute on quantum hardware with Qiskit Runtime primitives.
# Submit one job per d, with all four observables in that job.
large_d_values = list(range(1, large_krylov_dim))
retrieve_batch_id = None
large_jobs = []

if retrieve_batch_id is None:
    large_estimator_options = {
        "default_shots": 8192,
        "dynamical_decoupling": {
            "enable": True,
            "sequence_type": "XpXm",
        },
        "resilience": {
            "measure_mitigation": True,
            "measure_noise_learning": {
                "num_randomizations": 32,
                "shots_per_randomization": 256,
            },
            "layer_noise_learning": {
                "max_layers_to_learn": 4,
                "layer_pair_depths": [0, 1, 2, 4, 16, 32],
                "num_randomizations": 32,
                "shots_per_randomization": 128,
            },
            "zne_mitigation": True,
            "zne": {
                "amplifier": "pea",
                "noise_factors": [1.0, 1.5, 2.0],
                "extrapolator": ("exponential", "linear"),
            },
        },
        "twirling": {
            "enable_gates": True,
            "enable_measure": True,
            "num_randomizations": 32,
            "shots_per_randomization": 256,
            "strategy": "active-accum",
        },
    }

    with Batch(backend=large_backend) as large_batch:
        large_batch_id = large_batch.session_id
        large_estimator = EstimatorV2(
            mode=large_batch,
            options=large_estimator_options,
        )
        # Krylov quantum diagonalization of lattice Hamiltonians -> TUT_KQDOLH.
        large_estimator.options.environment.job_tags = ["TUT_KQDOLH"]

        for d in large_d_values:
            parameter_values = [d * large_dt]
            pubs_for_d = [
                (large_isa_circuit, observable, parameter_values)
                for observable in large_isa_observables
            ]
            job = large_estimator.run(pubs_for_d)
            large_jobs.append(job)
            print(
                f"Submitted d={d}: job_id={job.job_id()}, "
                f"PUBs={len(pubs_for_d)}"
            )

    print(f"Batch ID: {large_batch_id}")
else:
    large_batch_id = retrieve_batch_id
    large_jobs = service.jobs(
        session_id=large_batch_id,
        limit=None,
        descending=False,
    )

large_job_ids_by_d = {
    d: job.job_id() for d, job in zip(large_d_values, large_jobs)
}
print(f"Job IDs by d: {large_job_ids_by_d}")

# -------------------------Step 4-------------------------

# Post-process the quantum results and solve the classical GEVP.
# Reconstruct the first rows of S and the shifted Hamiltonian matrix.
large_s_row_est = np.zeros(large_krylov_dim, dtype=complex)
large_h_shifted_row_est = np.zeros(large_krylov_dim, dtype=complex)
large_s_row_est[0] = 1.0
large_h_shifted_row_est[0] = large_ref_energy - large_shift_tau

for d, job in zip(large_d_values, large_jobs):
    job_result = job.result()

    if len(job_result) != len(large_observables):
        raise RuntimeError(
            f"Expected {len(large_observables)} PUB results for d={d}, "
            f"but received {len(job_result)}."
        )

    expectation_values = [
        np.asarray(pub_result.data.evs).reshape(-1)[0]
        for pub_result in job_result
    ]

    large_s_row_est[d] = expectation_values[0] + 1j * expectation_values[1]
    large_h_shifted_row_est[d] = (
        expectation_values[2] + 1j * expectation_values[3]
    )

# H_0d = shifted_H_0d + tau * S_0d.
large_h_row_est = large_h_shifted_row_est + large_shift_tau * large_s_row_est

large_s_matrix_est = la.toeplitz(
    large_s_row_est.conj(),
    large_s_row_est,
)
large_h_matrix_est = la.toeplitz(
    large_h_row_est.conj(),
    large_h_row_est,
)

large_exact_gnd = min(diagonalize_single_1_subspace(large_hamiltonian))

large_energy_convergence = []

with np.printoptions(precision=5, suppress=True):
    print("Estimated first row of S:")
    print(large_s_row_est)
    print("Estimated first row of H:")
    print(large_h_row_est)
    print("exact ground state energy:  ", large_exact_gnd)

    for r in range(1, large_krylov_dim + 1):
        energy_est_kqd, coeffs_est, retained_est = solve_thresholded_gevp(
            large_h_matrix_est[:r, :r],
            large_s_matrix_est[:r, :r],
            threshold=5e-2,
        )
        large_energy_convergence.append(energy_est_kqd)
        print(
            f"Krylov ground state energy (dim={r}, retained={retained_est}): ",
            energy_est_kqd,
        )

plot_energy_convergence(
    large_energy_convergence, large_exact_gnd, large_krylov_dim
)