Computer Architecture Research Articles

Design and implementation of a charge-sharing in-memory-computing macro with sparse feature for quantized neural network

With the rapid development of artificial intelligence technology, in-memory computing has become a research hotspot. In this article, we propose an in-memory computing (IMC) architecture that achieves high energy efficiency and performance. Our work is based on the working mechanism of charge sharing, enabling configurable multi-bit Multiply-Accumulate operations. This work employs a unique bit-cell structure to implement sparse strategies at the bit-level in IMC arrays and compensates for errors caused by non-ideal effects, thus achieving better energy efficiency and performance. A hardware-aware quantification method and a hardware simulation model based on Pytorch have been proposed to evaluate the hardware mapping and compare with other charge domain IMC works. The MNIST and CIFAR-10 datasets have been used to validate algorithm models and chip performance, achieving accuracy rates of 97.6% and 90.5%respectively. The IMC chip was fabricated with a 180 nm CMOS process. The measurement shows that the chip achieves an energy efficiency of 41.8 TOPS/W.

Distributed algorithm for parallel computation of the n queens solutions

The n-queen problem represents a classic challenge in artificial intelligence (AI) research. It involves the placement of n queens on an n x n chessboard, with the objective of ensuring that no queen threatens another. This problem has long been a source of fascination for mathematicians and computer scientists alike due to its inherent complexity. It is a well-known fact that as the value of ‘n’ increases, the problem becomes more challenging and falls into the NP problem class. Given the computational demands of the problem, parallel methods are of critical importance. It is noteworthy that scalable and parallel approaches for the n-queen problem remain to be developed. The majority of existing methods working on graphs attempt to parallelize a recursive sequential algorithm. However, the unpredictable nature of these algorithms makes it challenging to parallelize them on modern computer architectures. Consequently, we have selected an iterative algorithm from the literature in order to facilitate parallelization. This paper presents an innovative approach to parallelization that differs from traditional matrix-based strategies. The n-queen graph is distributed among a network of nodes, ensuring effective load balancing through dynamic partitioning and real-time computation. Our bespoke distributed algorithm, designed for the maximum clique problem on the n-queen graph, operates with true concurrency, thus obviating the necessity for resource or data sharing. The results of our assessment demonstrate that the parallel algorithm outperforms a cutting-edge sequential algorithm in terms of task completion time. The findings demonstrate that the speedups are almost perfect and that the workloads are distributed evenly across the network nodes. Furthermore, the results demonstrate high scalability, with task completion times decreasing as the number of nodes increases.

Cooling Trapped Ions with Phonon Rapid Adiabatic Passage

In recent demonstrations of the quantum charge-coupled device computer architecture, circuit times are dominated by cooling. Some motional modes of multi-ion crystals take orders of magnitude longer to cool than others because of low coolant ion participation. Here we demonstrate a new technique, that solves this issue by coherently exchanging the thermal populations of selected modes on timescales short compared to direct cooling. Using this method, which we call “phonon rapid adiabatic passage,” we can achieve subquanta temperatures from initial states with occupations as high as n¯∼200 quanta. Analogous to adiabatic rapid passage, we quasistatically couple these slow-cooling modes with fast-cooling modes using dc electric fields. When the crystal is then adiabatically ramped through the resultant avoided crossing, nearly complete phonon population exchange results. We demonstrate this on two-ion crystals, and show the indirect ground-state cooling of all radial modes—achieving an order of magnitude speedup compared to direct cooling. We also show the technique’s insensitivity to trap potential and control field fluctuations, and find that it still achieves subquanta temperatures starting as high as n¯∼200. Published by the American Physical Society 2024

An All-Optical General-Purpose CPU and Optical Computer Architecture

An All-Optical General-Purpose CPU and Optical Computer Architecture

Next-Generation Data Pipeline Designs for Modern Analytics : A Comprehensive Review

This comprehensive article examines the transformative evolution of data pipeline architectures in modern analytics, focusing on the integration of real-time and batch-processing methodologies to meet contemporary data processing demands. The article investigates how advanced frameworks like Apache Spark and Databricks, coupled with innovative technologies such as Delta Lake, are reshaping traditional data processing paradigms to accommodate increasing data volumes and complexity. Through a detailed article of hybrid pipeline architectures, data quality mechanisms, and observability practices, this paper demonstrates the critical role of next-generation pipeline designs in enabling organizations to build scalable, reliable, and maintainable data infrastructures. The article explores the implementation of ACID-compliant data lake technologies, automated monitoring systems, and sophisticated quality assurance methods that collectively ensure data integrity and processing efficiency. Key findings highlight the significance of emerging technologies, including edge computing and serverless architectures, in shaping future data pipeline designs. The article provides valuable insights into architectural patterns, best practices, and future trends that organizations can leverage to optimize their data processing capabilities and maintain competitive advantage in an increasingly data-driven business landscape.

Real-time multicompartment Hodgkin-Huxley neuron emulation on SoC FPGA

Advanced computational models and simulations to unravel the complexities of brain function have known a growing interest in recent years in the field of neurosciences, driven by significant technological progress in computing platforms. Multicompartment models, which capture the detailed morphological and functional properties of neural circuits, represent a significant advancement in this area providing more biological coherence than single compartment modeling. These models serve as a cornerstone for exploring the neural basis of sensory processing, learning paradigms, adaptive behaviors, and neurological disorders. Yet, the high complexity of these models presents a challenge for their real-time implementation, which is essential for exploring alternative therapies for neurological disorders such as electroceutics that rely on biohybrid interaction. Here, we present an accessible, user-friendly, and real-time emulator for multicompartment Hodgkin-Huxley neurons on SoC FPGA. Our system enables real-time emulation of multicompartment neurons while emphasizing cost-efficiency, flexibility, and ease of use. We showcase an implementation utilizing a technology that remains underrepresented in the current literature for this specific application. We anticipate that our system will contribute to the enhancement of computation platforms by presenting an alternative architecture for multicompartment computation. Additionally, it constitutes a step toward developing neuromorphic-based neuroprostheses for bioelectrical therapeutics through an embedded real-time platform running at a similar timescale to biological networks.

GPU Parallel Computing Architectures : Unlocking the Power of Parallelism for High-Performance Applications

Graphics Processing Units (GPUs) have evolved from specialized graphics rendering hardware to become powerful parallel computing architectures, revolutionizing high-performance computing across diverse domains. This comprehensive article explores the fundamental principles of GPU parallel computing architectures, their design, and their impact on modern computational challenges. We begin by examining the multi-core structure, memory hierarchy, and data processing capabilities of GPUs, including the SIMD execution model and thread organization. The article then delves into prominent programming models like CUDA and OpenCL, discussing their features and comparative advantages. We explore how GPUs are leveraged for general-purpose computing in scientific simulations, machine learning, and big data analytics, while also addressing the challenges inherent in GPU parallel computing, such as data transfer bottlenecks and load balancing. Recent technological advancements, including tensor cores, unified memory architecture, and ray tracing acceleration, are analyzed for their transformative potential. The article concludes by examining future directions in GPU technology, including integration with emerging technologies like quantum computing, advancements in energy efficiency, and the potential impact on solving complex global challenges. Through this comprehensive analysis, we illustrate the pivotal role of GPU parallel computing architectures in shaping the future of high-performance computing and their potential to address some of the world's most pressing computational problems.

Characterizing structural features of two-dimensional particle systems through Voronoi topology

Abstract This paper introduces a new approach toward characterizing local structural features of two-dimensional particle systems. The approach can accurately identify and characterize defects in high-temperature crystals, distinguish a wide range of nominally disordered systems, and robustly describe complex structures such as grain boundaries. This paper also introduces two-dimensional functionality into the open-source software program VoroTop which automates this analysis. This software package is built on a recently-introduced multithreaded version of Voro++, enabling the analysis of systems with billions of particles on high-performance computer architectures.

Research on motion target detection based on infrared biomimetic compound eye camera.

The cooled mid-wave infrared biomimetic compound eye camera has wide range of applications, such as industrial inspection, military project, and security. Due to the low resolution of individual eyes and the large field view of the imaging system, existing motion target enhancement and detection algorithms cannot effectively detect all potential targets. To address this issue, we propose an improved elementary motion detector model that combines a double-layer ON_OFF channel and a cross-type computational architecture, which is able to suppress a stationary background and enhance moving targets. In order to further reduce the missed detection, we designed the spatial and temporal consistency detection methods of the compound eye structure, which further improved the accuracy and stability of the detection results. The experimental results show that our method can fully utilize the features of the image and can be applied to the enhancement and detection of moving objects in complex scenes, and the detection efficiency is significantly improved.

Interpreting Federated Learning (FL) Models on Edge Devices by Enhancing Model Explainability with Computational Geometry and Advanced Database Architectures

Federated learning (FL) on edge devices has emerged as a promising approach for decentralized model training, enabling data privacy and efficiency in distributed networks. However, the complexity of these models presents significant challenges in terms of transparency and interpretability, which are critical for trust and accountability in real-world applications. This paper explores the integration of explainable AI techniques to enhance model interpretability within federated learning systems. By incorporating computational geometry, we aim to optimize model structure and decision-making processes, providing clearer insights into how models generate predictions. Additionally, we examine the role of advanced database architectures in managing the complexity of federated learning models on edge devices, ensuring efficient data handling and storage. Together, these approaches contribute to a more transparent, efficient, and scalable framework for federated learning on edge networks, addressing key challenges in both model explainability and performance optimization. This review highlights recent advancements and suggests future directions for research at the intersection of federated learning (FL), edge computing, explainability, and computational techniques.

Practical hardware demonstration of a multi-sensor goal-oriented semantic signal processing and communications network

Recent advancements in machine learning, particularly real-time extraction of rich semantic information, reshape signal processing techniques and related hardware architectures. To address the highly challenging requirements of next-generation signal processing applications in networked platforms, we investigate low-power hardware implementation alternatives for a multi-sensor, goal-oriented semantic communications network. Specifically, we focus on cost-effective Raspberry Pis in a multi-sensor semantic video communication application, showcasing adaptability from traditional CPU/GPU configurations. Additionally, we provide a preliminary investigation on implementing semantic extraction tasks through in-memory computation using memristor arrays to further emphasize the potential future of low-power low-cost semantic signal processing. Hardware demonstrations using Raspberry Pi 4Bs and simulations with in-memory computation architectures offer promising hardware architectures with cost-effective and low-power sensor alternatives to the next-generation semantic signal processing applications and semantic communication systems.

Integrating Generative AI in Cloud Computing Architectures: Transformative Impacts on Efficiency and Innovation

Integrating Generative AI in Cloud Computing Architectures: Transformative Impacts on Efficiency and Innovation

“Design of a Trustworthy Cloud-Native National Digital Health Information Infrastructure for Secure Data Management and Use”

Abstract Since 2022, Malawi Ministry of Health (MoH) designated the development of a National Digital Health Information System (NDHIS) as one of the most important pillars of its national health strategy. This system is built upon a distributed computing infrastructure employing the following state-of-art technologies: (1) digital healthcare devices to capture medical data; (2) Kubernetes-based Cloud-Native Computing architecture to simplify system management and service deployment; (3) Zero-Trust Secure Communication to protect confidentiality, integrity and access rights of medical data transported over the Internet; (4) Trusted Computing to allow medical data to be processed by certified software without compromising data privacy and sovereignty. Trustworthiness, including reliability, security, privacy and business integrity, of this system was ensured by a peer-to-peer network of trusted medical information guards deployed as the gatekeepers of every computing node on this system. This NDHIS shall facilitate Malawi to attain universal health coverage by 2030 through its scalability and operation efficiency. It shall improve medical data quality and security by adopting a paperless approach. It will also enable MoH to offer data rental services to healthcare researchers and AI model developers around the world. This project is spearheaded by the Digital Health Division (DHD) under MoH. The trustworthy computing infrastructure was designed by a taskforce assembled by the DHD in collaboration with Luke International in Norway, and a consortium of hardware and software solution providers in Taiwan. A prototype that can connect community clinics with a district hospital has been tested at the Taiwan Pingtung Christian Hospital.

Fog Computing Technology Research: A Retrospective Overview and Bibliometric Analysis

Researchers’ interest in Fog Computing and its application in different sectors has been increasing since the last decade. To discover the emerging trends inherent to this architecture, we analyzed the scientific literature indexed in Scopus through a bibliometric study. Exposing trends in areas of development will allow researchers to understand the changes and evolution over time. For analysis purposes, we used three approaches: performance analysis, science mapping, and literature clustering. Analysis results revealed promising investigation areas in the Fog Computing architecture from 2012 to 2021, which emphasizes that Fog Computing will continue to be an interesting field of research in the future.

Memristor-Based Approximate Query Architecture for In-Memory Hyperdimensional Computing

Memristor-Based Approximate Query Architecture for In-Memory Hyperdimensional Computing

Prediction of chaotic dynamics and extreme events: A recurrence-free quantum reservoir computing approach

In chaotic dynamical systems, extreme events manifest in time series as unpredictable large-amplitude peaks. Although deterministic, extreme events appear seemingly randomly, which makes their forecasting difficult. By learning the dynamics from observables (data), reservoir computers can time accurately predict extreme events and chaotic dynamics, but they may require many degrees of freedom (large reservoirs). In this paper, by exploiting quantum-computer ansätze and entanglement, we design reservoir computers with compact reservoirs and accurate prediction capabilities. First, we propose the recurrence-free quantum reservoir computer (RF-QRC) architecture. By developing quantum feature maps and removing recurrent connections, the RF-QRC has quantum circuits with smaller depths. This allows the RF-QRC to scale well with higher-dimensional chaotic systems, which makes it suitable for hardware implementation. Second, we forecast the temporal chaotic dynamics and their long-term statistics of low- and higher-dimensional dynamical systems. We find that RF-QRC requires smaller reservoirs than classical reservoir computers for higher-dimensional systems and the same predictability. Third, we apply the RF-QRC to the time prediction of extreme events in a model of a turbulent shear flow with turbulent bursts. We find that the RF-QRC has longer predictability than the classical reservoir computer for extreme events forecasting. The results and analyses indicate that quantum-computer ansätze offers nonlinear expressivity and computational scalability, which are useful for forecasting chaotic dynamics and extreme events. This work opens new opportunities for using quantum machine learning on near-term quantum computers. Published by the American Physical Society 2024

TOLEDO: enhancing Maestro GUI for non-expert users to perform massive MD simulations

Classical Molecular Dynamics (MD) simulates the dynamical evolution of biological systems at the atomic level. Using MD in conjunction with high-performance computing (HPC) architectures, we can evaluate the possible interactions between a ligand library against one protein target to find a drug that can influence a protein target to cure a disease. Simultaneously, we can also obtain information about their dynamic evolution. One of the primary software packages for MD simulations is Desmond, which employs Maestro for the setup, execution, and analysis of MD through a graphical user interface (GUI), which is suitable even for non-expert users. However, using the GUI, users can typically run only one short (less than 1000 ns) MD each time. Our work aims to create a method/protocol to run several MD simulations simultaneously on a remote HPC cluster within Maestro-Desmond. In this work, we provide TOLEDO (Throughput Optimization of Ligand-Protein Systems Exploration through Dynamics simulation in Optimized HPC systems) to overcome such limitations and run several MD simulations simultaneously. The best feature of TOLEDO is its independence from the usual time constraints of many clusters, with storage space being the only limitation. To run TOLEDO, we prepare/set up the protein-ligand complex before running MD via Maestro GUI. Next, we run the main TOLEDO script for several MD simulations on a supercomputer. When TOLEDO finishes, users obtain reports and graphics. The obtained results are easily interpretable. In essence, TOLEDO significantly enhances MD throughput beyond the capabilities of the Maestro GUI.

On a Simplified Approach to Achieve Parallel Performance and Portability Across CPU and GPU Architectures

This paper presents software advances to easily exploit computer architectures consisting of a multi-core CPU and CPU+GPU to accelerate diverse types of high-performance computing (HPC) applications using a single code implementation. The paper describes and demonstrates the performance of the open-source C++ matrix and array (MATAR) library that uniquely offers: (1) a straightforward syntax for programming productivity, (2) usable data structures for data-oriented programming (DOP) for performance, and (3) a simple interface to the open-source C++ Kokkos library for portability and memory management across CPUs and GPUs. The portability across architectures with a single code implementation is achieved by automatically switching between diverse fine-grained parallelism backends (e.g., CUDA, HIP, OpenMP, pthreads, etc.) at compile time. The MATAR library solves many longstanding challenges associated with easily writing software that can run in parallel on any computer architecture. This work benefits projects seeking to write new C++ codes while also addressing the challenges of quickly making existing Fortran codes performant and portable over modern computer architectures with minimal syntactical changes from Fortran to C++. We demonstrate the feasibility of readily writing new C++ codes and modernizing existing codes with MATAR to be performant, parallel, and portable across diverse computer architectures.

Implementation of Parallel Applications on Linear Systolic and Star Topologies by Using Multistage Omega Network

Contemporary computer architecture comprises multicomputer settings. Multiple computers provide the facility of high performance to implement multiple threads that are faster and concurrently with different processors that can execute tasks simultaneously. The challenges are as follows: cost and high performance. Certain firms have to provide funding to establish data centers that need locations, hardware, and technicians. After the passage of a period of time, such equipment requires maintenance (updating and upgrading) to take place on it. This paper tackles these challenges by passing the drawbacks of data centers. It provides an algorithm that simulates a virtual machine, as one client is to be connected with eight servers to implement two applications namely convolution and mathematical operations. To represent different topologies, the algorithm simulates supercomputer systems by applying multistage omega network topology and parallel processing. Two types of topologies execute linear systolic and star, and is implemented on transmission control protocol (TCP) and user datagram protocol (UDP) protocols. The goal of this paper is to provide a kernel that draws near a cloud computing system by exploiting the JAVA programming language with its techniques (threading, socket, socket server, Datagram socket, and datagram packet). The results offer the connection between the client and servers to be successfully simulated by using multistage omega network. The linear systolic and star topologies are simulated in virtual parallel processing.

Exploring nanoparticle dynamics in binary chemical reactions within magnetized porous media: a computational analysis

Artificial Neural Networks are incredibly efficient at handling complicated and nonlinear mathematical problems, making them very useful for tackling these challenges. Artificial neural networks offer a special computational architecture that is extremely valuable in disciplines like biotechnology, biological computing, and computational fluid dynamics. The present work investigates the applicability of back-propagation artificial neural networks in conjunction with the Levenberg-Marquardt algorithm for evaluating heat transmission in hybrid nanofluids. This work focuses on the computational analysis of a MgO + GO/EG hybrid nanofluid’s steady mixed convection flow over an exponentially stretched sheet, considering multiple slip boundary conditions, thermal conductivity, heat generation, and thermal radiation. A nonlinear system of ordinary differential equations is produced from the basic associated partial differential system by performing the proper exponential similarities modifications. For generating benchmark datasets, the resulting ordinary differential equations are processed employing the bvp4c method. Considering benchmark datasets set aside for training (70%), testing (15%), and validation (15%), the Levenberg-Marquardt algorithm, which employs back-propagation in artificial neural networks, is implemented. The accuracy of the suggested strategy for handling nonlinear problems is verified utilizing mean squared error, error histograms, and regression analysis, which are all used to evaluate the methodology. Outstanding agreement is seen when ANN outputs are compared to numerical results. The flow properties, including temperature, velocity, and concentration profiles, are shown graphically and numerically. For practical purposes, it is therefore essential to analyze the flow and heat transfer in hybrid nanofluids over exponentially extending and shrinking surfaces under mixed convection and heat source scenarios. Hybrid nanofluid problems have a wide range of practical and industrial applications, such as medication delivery, manufacturing, microelectronics, nuclear plant cooling, and marine engineering.