SliQSim Qiskit Interface - Execute SliQSim on Qiskit

Introduction

This is a Qiskit provider for SliQSim where you can execute SliQSim from Qiskit framework as a backend option.

SliQSim is a BDD-based quantum circuit simulator implemented in C/C++ on top of CUDD package. In SliQSim, a bit-slicing technique based on BDDs is used to represent quantum state vectors. For more details of the simulator, please refer to the paper.

Installation

To use this provider, one should first install IBM's Qiskit (<=0.36.2), and then install the provider with pip.

pip install qiskit==0.36.2
pip install qiskit-sliqsim-provider

Execution

The gate set supported in SliQSim now contains Pauli-X (x), Pauli-Y (y), Pauli-Z (z), Hadamard (h), Phase and its inverse (s and sdg), π/8 and its inverse (t and tdg), Rotation-X with phase π/2 (rx(pi/2)), Rotation-Y with phase π/2 (ry(pi/2)), Controlled-NOT (cx), Controlled-Z (cz), Toffoli (ccx and mcx), SWAP (swap), and Fredkin (cswap).

For simulation types, we provide both sampling(default) and statevector simulation options, where the sampling simulation samples outcomes from the output distribution obtained after the circuit is applied, and the statevector simulation calculates the resulting state vector of the quantum circuit. Please turn off the optimization (optimization_level=0) to avoid using gates out of supported gate set. The following examples demostrate the usage of the provider.

# Import tools
from qiskit import QuantumCircuit, QuantumRegister, ClassicalRegister, execute
from qiskit_sliqsim_provider import SliQSimProvider

# Initiate SliQSim Provider
provider = SliQSimProvider()

# Construct a 2-qubit bell-state circuit
qr = QuantumRegister(2)
cr = ClassicalRegister(2)
qc = QuantumCircuit(qr, cr)

qc.h(qr[0])
qc.cx(qr[0], qr[1])
qc.measure(qr, cr)

# Get the backend of sampling simulation
backend = provider.get_backend('sampling')

# Execute simulation
job = execute(qc, backend=backend, shots=1024, optimization_level=0)

# Obtain and print the results
result = job.result()
print(result.get_counts(qc))

In the above Python code, we construct a 2-qubit bell-state circuit with measurement gates at the end, and execute the simulator with sampling simulation backend option sampling. The sampled result is then printed:

{'00': 523, '11': 501}

Circuits can also be read from files in OpenQASM format, which is used by Qiskit. Here we read a circuit, which is also a 2-qubit bell-state circuit but with no measurements gates, to showcase the statevector simulation:

qc = QuantumCircuit.from_qasm_file("../SliQSim/examples/bell_state.qasm")

To execute the statevector simulation, the backend option sampling is replaced with all_amplitude:

backend = provider.get_backend('all_amplitude')
job = execute(qc, backend=backend, optimization_level=0)

and after obtaining the results, we acquire the state vector instead of the counts of sampled outcomes:

result = job.result()
print(result.get_statevector(qc))

The state vector is then printed:

[0.707107+0.j 0.      +0.j 0.      +0.j 0.707107+0.j]

One may also use our simulator by executing a compiled binary file. Check this repo.

Citation

Please cite the following paper if you use our simulator for your research:

Y. Tsai, J. R. Jiang, and C. Jhang, "Bit-Slicing the Hilbert Space: Scaling Up Accurate Quantum Circuit Simulation to a New Level," 2020, arXiv: 2007.09304

@misc{tsai2020bitslicing,
      title={Bit-Slicing the Hilbert Space: Scaling Up Accurate Quantum Circuit Simulation to a New Level},
      author={Yuan{-}Hung Tsai and Jie{-}Hong R. Jiang and Chiao{-}Shan Jhang},
      year={2020},
      note={arXiv: 2007.09304}
}

Contact

If you have any questions or suggestions, feel free to create an issue, or contact us through matthewyhtsai@gmail.com.