Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Technical digest - International Electron Devices Meeting/Technical digest

Experimental evaluation of simulated quantum annealing with MTJ-augmented p-bits

Andrea Grimaldi, Kemal Selçuk, Navid Anjum Aadit, K. Kobayashi, Qixuan Cao, Shuvro Chowdhury, Giovanni Finocchio, Shun Kanai, Hideo Ohno, Shunsuke Fukami, Kerem Yunus Camsari

Published Dec 3, 2022• 41 citations
Publisher

Abstract

The slowing down of Moore’s Law has created an exciting new era of electronics, leading to the emergence of various types of CMOS+X devices and architectures. Here, we present the first experimental demonstration of a probabilistic computer where a stochastic magnetic tunnel junction (sMTJ) drives a powerful CMOS-based field programmable gate array (FPGA) in a heterogeneous compute fabric. We use our machine to experimentally evaluate the simulated quantum annealing (SQA) algorithm, known to closely mimic the behavior of D-Wave’s quantum annealers which implement the transverse field Ising model (TFIM). Our machine matches the exact solution of the TFIM where p-bits in the FPGA are asynchronously driven by the stochastic dynamics of a magnetic tunnel junction. To compare the performance of SQA against classical annealing (CA) in hard combinatorial optimization at large scale, we also design a fully digital emulator of our asynchronous architecture in the FPGA. Our digital system uses 7,085 p-bits to factor up to 26-bit integers and is about 10X faster than optimized Tensor (TPU) and Graphics Processing Units (GPU) at lower power. Surprisingly, we find that the additional replica networks necessary for SQA do not lead to appreciably better performance over an optimized CA that is using the same computational resources. The systematic evaluation of the SQA algorithm we present will be relevant for other types of accelerators, such as photonic or electronic Ising machines and the integrated scaling of our CMOS + sMTJ architecture could lead to orders of magnitude further improvements over TPU and GPUs, according to experimentally-validated projections.

DOI
10.1109/iedm45625.2022.10019530

Related papers

A GPU-Based Quantum Annealing Simulator for Fully-Connected Ising Models Utilizing Spatial and Temporal Parallelism

Hasitha Muthumala Waidyasooriya, Masanori Hariyama

Simulated quantum annealing (SQA) is a probabilistic approximation method to find a solution for a combinatorial optimization problem using digital computers. The processing time of SQA increases exponentially with the number of variables. Therefore, acceleration of SQA is regarded as a very important topic. However, parallel implementation is difficult due to the serial nature of the quantum Monte Carlo algorithm used in SQA. In this paper, we propose a method to implement SQA in parallel on a GPU while preserving the data dependency. According to the experimental results, we have achieved over 97 times speed-up while maintaining the same accuracy-level compared to a single-core CPU implementation.

IEEE Access•Jan 1, 2020•23 citations

Stochastic Implementation of Simulated Quantum Annealing on PYNQ

Taiga Kubuta, Duckgyu Shin, Naoya Onizawa +1 more

It is well-known that quantum annealing (QA) is an excellent algorithm for solving combinatorial optimization problems (COPs). However, its hardware implementation poses challenges, requiring quantum devices. Therefore, a quantum Monte Carlo (QMC) method-based annealing approach called Simulated Quantum Annealing (SQA), which aims to emulate quantum annealing using classical computers, has been proposed. In the demo-night session, we will demonstrate a SQA based on stochastic computing (SC) on a standard FPGA board, called “PYNQ”. The use of SC-based data representation, along with the realization of SC-based spin-gate circuits, makes it possible to drastically reduce hardware costs compared to QA. This enhances the suitability for extending large-scale COPs.

International Conference on Field-Programmable Technology (FPT)•Dec 12, 2023•2 citations

A 1.87-TELOPS/W 3-D Ising Machine for Accelerated Quantum Monte Carlo With Reconfigurability Using CMOS p-Bits

Ming-Che Li, Archisman Ghosh, Risi Jaiswal +2 more

Qubit-based quantum annealing processors operate at ultra-low temperatures (15 mK) requiring enormous cooling energy. Consequently, there is a lot of interest in quantum Monte Carlo (QMC) algorithms that can be used to emulate quantum computing on classical machines. However, prior classical emulators implemented on CPUs, GPUs, or field-programmable gate arrays (FPGAs) are orders of magnitude slower than quantum annealers highlighting the need for dedicated application-specific integrated circuits (ASICs). Over the past decade, many ASICs have been developed, including general Ising solvers, typically implemented as digital system on chip (SoCs) targeting highly complex graphs, and specific Ising solvers, which address relatively simple Ising graphs using analog computing paradigms. General solvers often suffer from high power consumption, while specific solvers lack reconfigurability. This work presents, for the first time, a QMC algorithm implemented on a 3-D Ising computer fabricated in commercial 65-nm CMOS technology. Specifically, it solves a quantum problem in which a transverse field Ising (TFI) Hamiltonian is applied to an unconventional octagonal lattice. The reconfigurable integrated circuit (IC) also supports traditional 2-D Ising models for solving combinatorial optimization problems (COPs), offering better reconfigurability than prior specific Ising solvers. This IC achieved an energy-to-solution of$41.9~\mu $J at 1 MHz and$16.65~\mu $J at 10 MHz at 0.5 V for the QMC problem. Compared to previous FPGA implementations, this is a three-order-of-magnitude improvement and a six-order-of-magnitude improvement over CPU-based solutions. This article also proposes a new energy efficiency metric,$E_{\text {ELOP}}$(Energy per ELementary OPeration), to better benchmark p-bit-based Ising solvers. Our IC achieves an$E_{\text {ELOP}}$of 1350 fJ at 1 MHz and 535 fJ at 10 MHz (measured at 0.5 V) for solving the QMC problem, which are also equivalent to the energy efficiency of 0.74 and 1.87 TELOPS/W (ELementary OPeration per Second per Watt).

IEEE Journal of Solid-State Circuits•Jun 17, 2026•0 citations

Data-Transfer-Bottleneck-Less Architecture for FPGA-Based Quantum Annealing Simulation

Chia-Yin Liu, Hasitha Muthumala Waidyasooriya, Masanori Hariyama

Quantum Annealing (QA) is a classical probabilistic algorithm that provides a heuristic to find the globally optimal solution for a combinatorial optimization problem by using quantum tunneling processes. Quantum annealing simulation can be implemented on Field Programmable Gate Arrays (FPGAs) using Quantum Monte Carlo (QMC) simulation in the transverse Ising model. Since input data of the QMC simulation increases exponentially with the problem size, we have to use the DRAM of an FPGA board to store these data. However, storing data in DRAM causes two problems. One is the limited data access bandwidth, and the other is the limitation of DRAM capacity. We propose a data-transfer-bottleneck-less FPGA-based accelerator for quantum annealing simulation and apply it to implement number partitioning problem, which is one of the combinatorial optimization problems. The critical idea of our architecture is not storing but computing the large data in FPGA kernels and eliminating the burden on data transfer. We implement the proposed architecture on Stratix 10 FPGA and achieve up to 39.6 times speed-up compared to CPU-based quantum annealing simulation. We also achieve up to 2.8 times speed-up and implement 262,144 spins, which is 64 times increase compared to the most recent FPGA implementation.

International Symposium on Computing and Networking•Nov 1, 2019•10 citations

Accelerated quantum Monte Carlo with probabilistic computers

Shuvro Chowdhury, Kerem Yunus Camsari, Supriyo Datta

Abstract Quantum Monte Carlo (QMC) techniques are widely used in a variety of scientific problems and much work has been dedicated to developing optimized algorithms that can accelerate QMC on standard processors (CPU). With the advent of various special purpose devices and domain specific hardware, it has become increasingly important to establish clear benchmarks of what improvements these technologies offer compared to existing technologies. In this paper, we demonstrate 2 to 3 orders of magnitude acceleration of a standard QMC algorithm using a specially designed digital processor, and a further 2 to 3 orders of magnitude by mapping it to a clockless analog processor. Our demonstration provides a roadmap for 5 to 6 orders of magnitude acceleration for a transverse field Ising model (TFIM) and could possibly be extended to other QMC models as well. The clockless analog hardware can be viewed as the classical counterpart of the quantum annealer and provides performance within a factor of < 10 of the latter. The convergence time for the clockless analog hardware scales with the number of qubits as ∼ N, improving the ∼ N2 scaling for CPU implementations, but appears worse than that reported for quantum annealers by D-Wave.

arXiv:2210.17526•Communications Physics•Apr 27, 2023•35 citations

Benchmark study of simulated quantum annealing and asynchronous parallel simulated annealing for quadratic unconstrained binary optimization-based semiprime factorization

Gianbiagio Curato, Manuel Ponzi, Edoardo Chiatello +1 more

Simulated quantum annealing (SQA) has been widely studied as a heuristic for solving hard optimization problems, including integer factorization formulated as a quadratic unconstrained binary optimization (QUBO) problem. In this work, we present a replication-oriented benchmark of annealing-based solvers applied to biprime factorization using the direct QUBO mapping. We perform a controlled comparison of SQA, implemented via path-integral Monte Carlo, simulated annealing (SA), and asynchronous parallel simulated annealing (A-PSA), evaluating their performance in terms of probability of success and time to solution. Here, A-PSA denotes a multistart strategy consisting of multiple independent SA trajectories with no inter-replica interactions. Solver and encoding parameters are systematically optimized using Bayesian optimization to ensure a fair and reproducible comparison. Our results reproduce previously reported performance trends: SQA outperforms conventional SA on the considered QUBO landscapes, while SQA and A-PSA can exhibit closely comparable performance in specific regimes, highlighting the importance of multistart baselines in annealing-based benchmarking. All simulations are performed on commodity multithreaded CPU hardware using open-source software, enabling straightforward reproducibility without reliance on specialized experimental platforms. As a reference benchmark, the largest semiprime successfully factorized in our study is 8 219 999 = 32 749 × 251 , matching results previously obtained using quantum annealing hardware.

APS Open Science•Jun 3, 2026•0 citations
The slowing down of Moore’s Law has created an exciting new era of electronics, leading to the emergence of various types of CMOS+X devices and architectures. Here, we present the first experimental demonstration of a probabilistic computer where a stochastic magnetic tunnel junction (sMTJ) drives a powerful CMOS-based field programmable gate array (FPGA) in a heterogeneous compute fabric. We use our machine to experimentally evaluate the simulated quantum annealing (SQA) algorithm, known to closely mimic the behavior of D-Wave’s quantum annealers which implement the transverse field Ising model (TFIM). Our machine matches the exact solution of the TFIM where p-bits in the FPGA are asynchronously driven by the stochastic dynamics of a magnetic tunnel junction. To compare the performance of SQA against classical annealing (CA) in hard combinatorial optimization at large scale, we also design a fully digital emulator of our asynchronous architecture in the FPGA. Our digital system uses 7,085 p-bits to factor up to 26-bit integers and is about 10X faster than optimized Tensor (TPU) and Graphics Processing Units (GPU) at lower power. Surprisingly, we find that the additional replica networks necessary for SQA do not lead to appreciably better performance over an optimized CA that is using the same computational resources. The systematic evaluation of the SQA algorithm we present will be relevant for other types of accelerators, such as photonic or electronic Ising machines and the integrated scaling of our CMOS + sMTJ architecture could lead to orders of magnitude further improvements over TPU and GPUs, according to experimentally-validated projections.
Simulated quantum annealing (SQA) is a probabilistic approximation method to find a solution for a combinatorial optimization problem using digital computers. The processing time of SQA increases exponentially with the number of variables. Therefore, acceleration of SQA is regarded as a very important topic. However, parallel implementation is difficult due to the serial nature of the quantum Monte Carlo algorithm used in SQA. In this paper, we propose a method to implement SQA in parallel on a GPU while preserving the data dependency. According to the experimental results, we have achieved over 97 times speed-up while maintaining the same accuracy-level compared to a single-core CPU implementation.
It is well-known that quantum annealing (QA) is an excellent algorithm for solving combinatorial optimization problems (COPs). However, its hardware implementation poses challenges, requiring quantum devices. Therefore, a quantum Monte Carlo (QMC) method-based annealing approach called Simulated Quantum Annealing (SQA), which aims to emulate quantum annealing using classical computers, has been proposed. In the demo-night session, we will demonstrate a SQA based on stochastic computing (SC) on a standard FPGA board, called “PYNQ”. The use of SC-based data representation, along with the realization of SC-based spin-gate circuits, makes it possible to drastically reduce hardware costs compared to QA. This enhances the suitability for extending large-scale COPs.
Qubit-based quantum annealing processors operate at ultra-low temperatures (15 mK) requiring enormous cooling energy. Consequently, there is a lot of interest in quantum Monte Carlo (QMC) algorithms that can be used to emulate quantum computing on classical machines. However, prior classical emulators implemented on CPUs, GPUs, or field-programmable gate arrays (FPGAs) are orders of magnitude slower than quantum annealers highlighting the need for dedicated application-specific integrated circuits (ASICs). Over the past decade, many ASICs have been developed, including general Ising solvers, typically implemented as digital system on chip (SoCs) targeting highly complex graphs, and specific Ising solvers, which address relatively simple Ising graphs using analog computing paradigms. General solvers often suffer from high power consumption, while specific solvers lack reconfigurability. This work presents, for the first time, a QMC algorithm implemented on a 3-D Ising computer fabricated in commercial 65-nm CMOS technology. Specifically, it solves a quantum problem in which a transverse field Ising (TFI) Hamiltonian is applied to an unconventional octagonal lattice. The reconfigurable integrated circuit (IC) also supports traditional 2-D Ising models for solving combinatorial optimization problems (COPs), offering better reconfigurability than prior specific Ising solvers. This IC achieved an energy-to-solution of$41.9~\mu $J at 1 MHz and$16.65~\mu Jat10MHzat0.5VfortheQMCproblem.ComparedtopreviousFPGAimplementations,thisisathree−order−of−magnitudeimprovementandasix−order−of−magnitudeimprovementoverCPU−basedsolutions.Thisarticlealsoproposesanewenergyefficiencymetric,J at 10 MHz at 0.5 V for the QMC problem. Compared to previous FPGA implementations, this is a three-order-of-magnitude improvement and a six-order-of-magnitude improvement over CPU-based solutions. This article also proposes a new energy efficiency metric,Jat10MHzat0.5VfortheQMCproblem.ComparedtopreviousFPGAimplementations,thisisathree−order−of−magnitudeimprovementandasix−order−of−magnitudeimprovementoverCPU−basedsolutions.Thisarticlealsoproposesanewenergyefficiencymetric,E_{\text {ELOP}}(EnergyperELementaryOPeration),tobetterbenchmarkp−bit−basedIsingsolvers.OurICachievesan(Energy per ELementary OPeration), to better benchmark p-bit-based Ising solvers. Our IC achieves an(EnergyperELementaryOPeration),tobetterbenchmarkp−bit−basedIsingsolvers.OurICachievesanE_{\text {ELOP}}$of 1350 fJ at 1 MHz and 535 fJ at 10 MHz (measured at 0.5 V) for solving the QMC problem, which are also equivalent to the energy efficiency of 0.74 and 1.87 TELOPS/W (ELementary OPeration per Second per Watt).
Quantum Annealing (QA) is a classical probabilistic algorithm that provides a heuristic to find the globally optimal solution for a combinatorial optimization problem by using quantum tunneling processes. Quantum annealing simulation can be implemented on Field Programmable Gate Arrays (FPGAs) using Quantum Monte Carlo (QMC) simulation in the transverse Ising model. Since input data of the QMC simulation increases exponentially with the problem size, we have to use the DRAM of an FPGA board to store these data. However, storing data in DRAM causes two problems. One is the limited data access bandwidth, and the other is the limitation of DRAM capacity. We propose a data-transfer-bottleneck-less FPGA-based accelerator for quantum annealing simulation and apply it to implement number partitioning problem, which is one of the combinatorial optimization problems. The critical idea of our architecture is not storing but computing the large data in FPGA kernels and eliminating the burden on data transfer. We implement the proposed architecture on Stratix 10 FPGA and achieve up to 39.6 times speed-up compared to CPU-based quantum annealing simulation. We also achieve up to 2.8 times speed-up and implement 262,144 spins, which is 64 times increase compared to the most recent FPGA implementation.
Abstract Quantum Monte Carlo (QMC) techniques are widely used in a variety of scientific problems and much work has been dedicated to developing optimized algorithms that can accelerate QMC on standard processors (CPU). With the advent of various special purpose devices and domain specific hardware, it has become increasingly important to establish clear benchmarks of what improvements these technologies offer compared to existing technologies. In this paper, we demonstrate 2 to 3 orders of magnitude acceleration of a standard QMC algorithm using a specially designed digital processor, and a further 2 to 3 orders of magnitude by mapping it to a clockless analog processor. Our demonstration provides a roadmap for 5 to 6 orders of magnitude acceleration for a transverse field Ising model (TFIM) and could possibly be extended to other QMC models as well. The clockless analog hardware can be viewed as the classical counterpart of the quantum annealer and provides performance within a factor of < 10 of the latter. The convergence time for the clockless analog hardware scales with the number of qubits as ∼ N, improving the ∼ N2 scaling for CPU implementations, but appears worse than that reported for quantum annealers by D-Wave.
Simulated quantum annealing (SQA) has been widely studied as a heuristic for solving hard optimization problems, including integer factorization formulated as a quadratic unconstrained binary optimization (QUBO) problem. In this work, we present a replication-oriented benchmark of annealing-based solvers applied to biprime factorization using the direct QUBO mapping. We perform a controlled comparison of SQA, implemented via path-integral Monte Carlo, simulated annealing (SA), and asynchronous parallel simulated annealing (A-PSA), evaluating their performance in terms of probability of success and time to solution. Here, A-PSA denotes a multistart strategy consisting of multiple independent SA trajectories with no inter-replica interactions. Solver and encoding parameters are systematically optimized using Bayesian optimization to ensure a fair and reproducible comparison. Our results reproduce previously reported performance trends: SQA outperforms conventional SA on the considered QUBO landscapes, while SQA and A-PSA can exhibit closely comparable performance in specific regimes, highlighting the importance of multistart baselines in annealing-based benchmarking. All simulations are performed on commodity multithreaded CPU hardware using open-source software, enabling straightforward reproducibility without reliance on specialized experimental platforms. As a reference benchmark, the largest semiprime successfully factorized in our study is 8 219 999 = 32 749 × 251 , matching results previously obtained using quantum annealing hardware.