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

Towards scalability improvements of HybriD-GM quantum simulator

João Vítor Venceslau Coelho, Anderson Ávila, Samuel Xavier‐de‐Souza, Renata Reiser

Published Oct 9, 2023• 0 citations
Publisher

Abstract

Currently quantum computers require specialized hardware to be used, until they become more feasibly the testing of quantum algorithms is done by simulation, which is a task of high temporal and spacial complexity. To address this issue, the HybriD-GM simulator, and many others around the world, are under research and improvement, this paper is an ongoing work on improvements for the multi-core support of the HybriD-GM simulator, the experiments are done with the Shor and Grover algorithms, while varying the number of cores and qubits for each, to improve the scalability the removal of critical regions by the usage of tasks and other OpenMP resources is exploited, and the study about the impact of others variables on the simulator is already planned, as well improvements for future works on the GPU, and GPU-CPU approaches and expansion to distributed computing for horizontal scalability of the system.

DOI
10.5753/weit.2023.26608

Related papers

HybriD-GM: A Framework for Quantum Computing Simulation Targeted to Hybrid Parallel Architectures

Anderson Ávila, Hélida Santos, Anderson Paiva Cruz +5 more

This paper presents the HybriD-GM model conception, from modeling to consolidation. The D-GM environment is also extended, providing efficient parallel executions for quantum computing simulations, targeted to hybrid architectures considering the CPU and GPU integration. By managing projection operators over quantum structures, and exploring coalescing memory access patterns, the HybriD-GM model enables granularity control, optimizing hardware resources in distributed computations organized as tree data structures. In the HybriD-GM evaluation, simulations of Shor's and Grover's algorithms achieve significant performance improvements in comparison to the previous D-GM version, and also with other related works, for example, LIQUi|⟩ and ProjectQ simulators.

Entropy•Mar 14, 2023•5 citations

Improving in situ GPU simulation of quantum computing in the D-GM environment

Anderson Ávila, Renata Reiser, Mauricio Lima Pilla +1 more

Exponential increase and global access to read/write memory states in quantum computing (QC) simulation limit both the number of qubits and quantum transformations which can be currently simulated. Although QC simulation is parallel by nature, spatial and temporal complexity are major performance hazards, making this a nontrivial application for high performance computing. A new methodology employing reduction and decomposition optimizations has shown relevant results, but its GPU implementation could be further improved. In this work, we develop a new kernel for in situ GPU simulation that better explores its resources without requiring further hardware. Shor’s and Grover’s algorithms are simulated up to 25 and 21 qubits respectively and compared to our previous version, to [Formula: see text] simulator and to ProjectQ framework, showing better results with relative speedups up to 4.38×, 3357.76× and 333× respectively.

The International Journal of High Performance Computing Applications•Jan 16, 2019•4 citations

HybriD-GM: Um Modelo Paralelo para Computação Quântica direcionado às Arquiteturas Híbridas

Anderson Ávila, Bruno Moura, Rafael Bastos +6 more

This paper has as its primary objective to introduce the the HybriD-GM model conception, as well as extend the D-GM environment, providing efficient parallel executions for quantum computing simulations, targeted to hybrid architectures considering both CPU and GPU. By managing projection operators over quantum structures, and exploring coalescing memory access patterns, the HybriD-GM model enables the granularity control, optimizing hardware resources in distributed computations organized as tree data-structures. In the HybriD-GM evaluation, simulations of Shor’s and Grover’s algorithms achieve significant performance improvements in comparison to the D-GM previous version and to the LIQUi|⟩ and ProjectQ simulators.

Simpósio em Sistemas Computacionais de Alto Desempenho (SSCAD)•Oct 23, 2024•2 citations

Optimizing Quantum Simulation for Heterogeneous Computing: a Hadamard Transformation Study

Anderson Ávila, Murilo Schumalfuss, Renata Reiser +2 more

The D-GM execution environment improves distributed simulation of quantum algorithms in heterogeneous computing environments comprising both multi-core CPUs and GPUs. The main contribution of this work consists in the optimization of the environment VirD-GM, conceived in three steps: ( i ) the theoretical studies and implementation of the abstractions of the Mixed Partial Process defined in the qGM model, focusing on the reduction of the memory consumption regarding multidimensional QTs; ( ii ) the distributed/parallel implementation of such abstractions allowing its execution on clusters of GPUs; ( iii ) and optimizations that predict multiplications by zero-value of the quantum states/transformations, implying reduction in the number of computations. The results obtained in this work embrace the distribute/parallel simulation of Hadamard gates up to 21 qubits, showing scalability with the increase in the number of computing nodes.

Journal of Physics Conference Series•Oct 19, 2015•7 citations

GPU-aware distributed quantum simulation

Anderson Ávila, Adriano Maron, Renata Reiser +2 more

The simulation of algorithms from quantum computing is currently the most affordable solution for development of new applications. Due to the high computational cost of such simulation, solutions towards novel features that increase the performance are always desired. This work proposes an extension for the D-GM's simulation framework, establishing the support for GPU-aware distributed quantum simulation. The project explores the concepts of heterogeneous computing, merging distributed and GPU computing in a single programming environment. Our results comprehend the distributed simulation of systems comprised by Hadamard transformations up to 21 qubits. Detailed analysis and a performance comparison between PyCUDA and JCUDA frameworks for our application are discussed. This work is a significant step towards the ultimate goal of our project, which is the hybrid simulation of quantum algorithms, i.e., exploring multi-core CPUs and GPUs distributed along a cluster, achieving scalability when larger systems are simulated.

ACM Symposium on Applied Computing•Mar 24, 2014•35 citations

High-Performance Quantum Computing Simulation for the Quantum Geometric Machine Model

A. Maron, Renata Reiser, Mauricio Lima Pilla

Due to the unavailability of quantum computers, simulation of quantum algorithms using classical computers is still the most affordable option for research of algorithms and models for quantum computing. As such simulation requires high computing power and memory resources, and computations are regular and data-intensive, GPUs become a suitable solution for accelerating the simulation of quantum algorithms. This work introduces an extension of the execution library for the VPE-qGM environment to support GPU acceleration. Hadamard gates with up to 20 quantum bits were simulated, and speedups of up to approximately 540× over a sequential simulation and of approximately 85× over a 8-core distributed simulation in the VirD-GM environment were achieved.

IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid)•May 1, 2013•14 citations
Currently quantum computers require specialized hardware to be used, until they become more feasibly the testing of quantum algorithms is done by simulation, which is a task of high temporal and spacial complexity. To address this issue, the HybriD-GM simulator, and many others around the world, are under research and improvement, this paper is an ongoing work on improvements for the multi-core support of the HybriD-GM simulator, the experiments are done with the Shor and Grover algorithms, while varying the number of cores and qubits for each, to improve the scalability the removal of critical regions by the usage of tasks and other OpenMP resources is exploited, and the study about the impact of others variables on the simulator is already planned, as well improvements for future works on the GPU, and GPU-CPU approaches and expansion to distributed computing for horizontal scalability of the system.
This paper presents the HybriD-GM model conception, from modeling to consolidation. The D-GM environment is also extended, providing efficient parallel executions for quantum computing simulations, targeted to hybrid architectures considering the CPU and GPU integration. By managing projection operators over quantum structures, and exploring coalescing memory access patterns, the HybriD-GM model enables granularity control, optimizing hardware resources in distributed computations organized as tree data structures. In the HybriD-GM evaluation, simulations of Shor's and Grover's algorithms achieve significant performance improvements in comparison to the previous D-GM version, and also with other related works, for example, LIQUi|⟩ and ProjectQ simulators.
Exponential increase and global access to read/write memory states in quantum computing (QC) simulation limit both the number of qubits and quantum transformations which can be currently simulated. Although QC simulation is parallel by nature, spatial and temporal complexity are major performance hazards, making this a nontrivial application for high performance computing. A new methodology employing reduction and decomposition optimizations has shown relevant results, but its GPU implementation could be further improved. In this work, we develop a new kernel for in situ GPU simulation that better explores its resources without requiring further hardware. Shor’s and Grover’s algorithms are simulated up to 25 and 21 qubits respectively and compared to our previous version, to [Formula: see text] simulator and to ProjectQ framework, showing better results with relative speedups up to 4.38×, 3357.76× and 333× respectively.
This paper has as its primary objective to introduce the the HybriD-GM model conception, as well as extend the D-GM environment, providing efficient parallel executions for quantum computing simulations, targeted to hybrid architectures considering both CPU and GPU. By managing projection operators over quantum structures, and exploring coalescing memory access patterns, the HybriD-GM model enables the granularity control, optimizing hardware resources in distributed computations organized as tree data-structures. In the HybriD-GM evaluation, simulations of Shor’s and Grover’s algorithms achieve significant performance improvements in comparison to the D-GM previous version and to the LIQUi|⟩ and ProjectQ simulators.
The D-GM execution environment improves distributed simulation of quantum algorithms in heterogeneous computing environments comprising both multi-core CPUs and GPUs. The main contribution of this work consists in the optimization of the environment VirD-GM, conceived in three steps: ( i ) the theoretical studies and implementation of the abstractions of the Mixed Partial Process defined in the qGM model, focusing on the reduction of the memory consumption regarding multidimensional QTs; ( ii ) the distributed/parallel implementation of such abstractions allowing its execution on clusters of GPUs; ( iii ) and optimizations that predict multiplications by zero-value of the quantum states/transformations, implying reduction in the number of computations. The results obtained in this work embrace the distribute/parallel simulation of Hadamard gates up to 21 qubits, showing scalability with the increase in the number of computing nodes.
The simulation of algorithms from quantum computing is currently the most affordable solution for development of new applications. Due to the high computational cost of such simulation, solutions towards novel features that increase the performance are always desired. This work proposes an extension for the D-GM's simulation framework, establishing the support for GPU-aware distributed quantum simulation. The project explores the concepts of heterogeneous computing, merging distributed and GPU computing in a single programming environment. Our results comprehend the distributed simulation of systems comprised by Hadamard transformations up to 21 qubits. Detailed analysis and a performance comparison between PyCUDA and JCUDA frameworks for our application are discussed. This work is a significant step towards the ultimate goal of our project, which is the hybrid simulation of quantum algorithms, i.e., exploring multi-core CPUs and GPUs distributed along a cluster, achieving scalability when larger systems are simulated.
Due to the unavailability of quantum computers, simulation of quantum algorithms using classical computers is still the most affordable option for research of algorithms and models for quantum computing. As such simulation requires high computing power and memory resources, and computations are regular and data-intensive, GPUs become a suitable solution for accelerating the simulation of quantum algorithms. This work introduces an extension of the execution library for the VPE-qGM environment to support GPU acceleration. Hadamard gates with up to 20 quantum bits were simulated, and speedups of up to approximately 540× over a sequential simulation and of approximately 85× over a 8-core distributed simulation in the VirD-GM environment were achieved.