It is widely believed that quantum computers (if realized) will be more powerful than today’s computers from the viewpoint of computational complexity . However, it is not obvious how to utilize quantum computers in practical situations. For practical purposes, a Grover search may be one of the most promising quantum algorithms known so far. Thus, in this paper, we propose an efficient framework where we can use Grover search for general programming. Our framework has the following steps. (1) A programmer writes a program by using standard C++ programming language. (2) Some if expressions within for loops in the C++ source code are chosen as candidates to be performed as a Grover search on a quantum computer. (3) The framework automatically generates a corresponding quantum circuit for each Grover search chosen in (2). Unlike the existing quantum circuit design methods, we can treat large problems in our quantum circuit design. (4) By evaluating the number of primitive quantum gates in the quantum circuit generated in (3), the framework determines whether the processing time of the quantum circuit is faster than the processing time of the corresponding if expression on a classical computer. If the framework determines that the quantum circuit is faster, it generates some interface source codes for a classical computer. Thus, in our framework, a programmer can use a Grover search with almost no effort.
Abstract Grover’s search algorithms, including various partial Grover searches (PGS), experience scaling problems when multiple solutions are sought, as the number of iterations increases with the number of solutions or marked states, making implementation more computationally expensive. Inspired by recent PGS algorithms for multi-solution searchers, this article proposes a scalable Grover quantum search algorithm, referred to as Bi-directional Multi-solution scalable Grover Search (BMGS), to efficiently search for an arbitrary number of solutions from an unstructured database. We introduced a novel multi-segment bidirectional search tactic with PGS across multiple equal segments of each state, starting from an initial state and multiple marked states in parallel, obviating the need for merge operations. We have shown in this work that for each solution our novel approach requires at most N(1−b⌊dkr⌋1) N 1 - 1 b ⌊ r dk ⌋ iterations (here, N=2r N = 2 r elements, k=log2b k = log 2 b , d is the number of equal segments on r qubits, and b is the branching factor). Our proposed BMGS algorithm is benchmarked against state-of-the-art Depth-First Grover Search (DFGS) and PGS implementations for an arbitrary number of solutions, ranging from 2 to 20 qubits, as a proof of concept. We also show that our BMGS requires fewer iterations for shallow quantum circuits and achieves an optimal O O ( sN s N ) average complexity for s solutions, when dk<r d k < r . The Qiskit Python implementation of the proposed BMGS algorithm is available on GitHub ( https://github.com/hafeezzwiz21/Multi-Solution-DFGS-BMGS ).
This paper proposes a practical framework for quantum programming. In our framework, the parts of a program to be performed on a quantum computer are almost automatically determined, and the other parts are performed on a classical computer. We only consider Grover Search to be performed on a quantum computer in the framework because the other quantum algorithms known so far cannot be applied to general cases. By considering only Grover Search, we have several advantages that show our framework is really practical.