Parallel Communication Research Articles

An analog-AI chip for energy-efficient speech recognition and transcription

Models of artificial intelligence (AI) that have billions of parameters can achieve high accuracy across a range of tasks1,2, but they exacerbate the poor energy efficiency of conventional general-purpose processors, such as graphics processing units or central processing units. Analog in-memory computing (analog-AI)3–7 can provide better energy efficiency by performing matrix–vector multiplications in parallel on ‘memory tiles’. However, analog-AI has yet to demonstrate software-equivalent (SWeq) accuracy on models that require many such tiles and efficient communication of neural-network activations between the tiles. Here we present an analog-AI chip that combines 35 million phase-change memory devices across 34 tiles, massively parallel inter-tile communication and analog, low-power peripheral circuitry that can achieve up to 12.4 tera-operations per second per watt (TOPS/W) chip-sustained performance. We demonstrate fully end-to-end SWeq accuracy for a small keyword-spotting network and near-SWeq accuracy on the much larger MLPerf8 recurrent neural-network transducer (RNNT), with more than 45 million weights mapped onto more than 140 million phase-change memory devices across five chips.

Context-Aware Magnetic MIMO Wireless Charging with Parallel In-Band Communication

Wireless power transfer (e.g., based on RF or magnetic) enables convenient device charging, and triggers innovative applications that typically call for faster, smarter, economic, and even simultaneous adaptive charging for multiple smart devices. Designing such a wireless charging system meeting these multi-requirements faces critical challenges, mainly including the better understanding of real-time energy receivers’ status and the power-transferring channels, the limited capability and the smart coordination of the transmitters and receivers. In this work, we devise Camel , a context-aware MIMO MRC-WPT (magnetic resonant coupling based wireless power transfer) system, which enables adaptive charging of multiple devices simultaneously with a novel context sensing scheme. In Camel , we craft an innovative MIMO MRC-WPT channels’ state estimation and collision-aware parallel in-band communication among multiple transmitters and receivers. We design and implement the Camel prototype and conduct extensive experimental studies. The results validate our design and demonstrate that Camel can support simultaneous charging of as many as 10 devices, high-speed context sensing within 50 ms, and efficient parallel communication among transceivers within proximity of ∼0.5 m.

Performance analysis of a dual-hop parallel relayed mixed FSO-UWOC system

Abstract In this paper, we propose a dual-hop parallel relayed mixed free space optical-underwater optical communication (FSO-UWOC) system model to setup a high-speed communication link connecting a distant sender located at the lighthouse tower and the receiver inside the deep ocean to transmit and receive the data for the applications such as deep sea exploration, marine life study etc. The proposed model is the setup of multiple parallel cooperative dual hop communication link for the betterment of the overall system performance under the worst case scenarios. The receiver examines the end-to-end signal to noise ratio and a relay is selected which has the maximum SNR. The selected relay then decodes the incoming optical signal through FSO link into its corresponding visible light signal and further transmits it to the underwater exploration devices such as underwater drone via VLC link. The FSO link is modelled by the Gamma-Gamma fading distribution and the VLC link is modelled by Exponential Generalized Gamma distribution. The end-to-end SNR of the system is utilized to derived the outage probability of the FSO-UWOC system and the impact of the individual link parameters is studied and presented for the proposed system model.

Development of the application for determination of the optimal partitioning form of large-dimensional matrix’s elements for multiplication on three heterogeneous processors

The article presents the results of the development of a web application for finding the optimal form of splitting matrix elements between three abstract heterogeneous processors when performing the operation of their multiplication. The paper considers five classes of parallel matrix multiplication algorithms: serial communication with a barrier, parallel communication with a barrier, serial communication with overlapping, parallel communication with overlapping, parallel overlapping with alternation. The Hockney model is used to estimate the communication complexity of the algorithms. The work uses six non-rectangular candidate partitioning shapes identified by Ashley DeFlumere in her work [1] as a result of applying the «push» technology of redistribution of matrix elements between the processors: Square Corner, Rectangle Corner, Square Rectangle, Block Rectangle, L-Rectangle, Traditional 1D Rectangular. Determination of the optimality of the form is made on the basis of mathematical models presented in the works [2,3]. The programming languages Python and JavaScript, the Django framework, the pip package manager, and Ajax technology were used to develop a web application. Solving the problem of determining the optimal matrix shape will allow for efficient planning of computing power resources for various scientific fields using parallel matrix multiplication.

Parallel Communication Optimization Based on Graph Partition for Hexagonal Neutron Transport Simulation Using MOC Method

OpenMOC-HEX, a neutron transport calculation code with hexagonal modular ray tracing, has the capability of domain decomposition parallelism based on an MPI parallel programming model. In this paper, the optimization of inter-node communication was studied. Starting from the specific geometric arrangement of hexagonal reactors and the communication features of the Method of Characteristics, the computation and communication of all the hexagonal assemblies are mapped to a graph structure. Then, the METIS library is used for graph partitioning to minimize the inter-node communication under the premise of load balance on each node. Numerical results of an example hexagonal core with 1968 energy groups and 1027 assemblies demonstrate that the communication time is reduced by about 90%, and the MPI parallel efficiency is increased from 82.0% to 91.5%.

Large-Scale Simulation of Full Three-Dimensional Flow and Combustion of an Aero-Turbofan Engine on Sunway TaihuLight Supercomputer

Computational fluid dynamics- (CFD-) based component-level numerical simulation technology has been widely used in the design of aeroengines. However, due to the strong coupling effects between components, the numerical simulation of the whole engine considering the full three-dimensional flow and multi-component chemical reaction is still very difficult at present. Aimed at this problem, an efficient implicit solver, 'sprayDyMFoam' for an unstructured mesh, is developed in this paper based on the Sunway TaihuLight supercomputer. This sprayDyMFoam solver improves the PIMPLE algorithm in the solution of aerodynamic force and adjusts the existing droplet atomization model in the solution of the combustion process so as to meet the matching situation between components and the combustion chamber in the solution process. Meanwhile, the parallel communication mechanism of AMI boundary processing is optimized based on the hardware environment of the Sunway supercomputer. The sprayDyMFoam solver is used to simulate a typical double-rotor turbofan engine: the calculation capacity and efficiency meet the use requirements, and the obtained compressor performance can form a good match with the test. The research proposed in this paper has strong application value in high-confidence computing, complex phenomenon capturing, and time and cost reduction for aeroengine development.

Massively parallel modeling and inversion of electrical resistivity tomography data using PFLOTRAN

Abstract. Electrical resistivity tomography (ERT) is a broadly accepted geophysical method for subsurface investigations. Interpretation of field ERT data usually requires the application of computationally intensive forward modeling and inversion algorithms. For large-scale ERT data, the efficiency of these algorithms depends on the robustness, accuracy, and scalability on high-performance computing resources. In this regard, we present a robust and highly scalable implementation of forward modeling and inversion algorithms for ERT data. The implementation is publicly available and developed within the framework of PFLOTRAN, an open-source, state-of-the-art massively parallel subsurface flow and transport simulation code. The forward modeling is based on a finite-volume discretization of the governing differential equations, and the inversion uses a Gauss–Newton optimization scheme. To evaluate the accuracy of the forward modeling, two examples are first presented by considering layered (1D) and 3D earth conductivity models. The computed numerical results show good agreement with the analytical solutions for the layered earth model and results from a well-established code for the 3D model. Inversion of ERT data, simulated for a 3D model, is then performed to demonstrate the inversion capability by recovering the conductivity of the model. To demonstrate the parallel performance of PFLOTRAN's ERT process model and inversion capabilities, large-scale scalability tests are performed by using up to 131 072 processes on a leadership class supercomputer. These tests are performed for the two most computationally intensive steps of the ERT inversion: forward modeling and Jacobian computation. For the forward modeling, we consider models with up to 122 ×106 degrees of freedom (DOFs) in the resulting system of linear equations and demonstrate that the code exhibits almost linear scalability on up to 10 000 DOFs per process. On the other hand, the code shows superlinear scalability for the Jacobian computation, mainly because all computations are fairly evenly distributed over each process with no parallel communication.

Outage performance analysis for relay-assisted UWOC systems over GGD weak turbulence with nonzero boresight pointing errors

In this paper, we mainly investigate the outage performance of serial and parallel relay-assisted underwater wireless optical communication (UWOC) systems based on a newly proposed aggregated underwater fading model. In order to overcome the deficiency of the traditional underwater weak turbulence models, that is, they could not accurately fit the measured data in the laboratory, the generalized gamma distribution (GGD) which has been verified by a series of experiments is chosen for the first time to characterize the weak oceanic turbulence. Then, we establish a new receiving signal model which has integrated the implicit path loss plus multipath propagation effect shown by fading free impulse response (FFIR), GGD weak oceanic turbulence, and nonzero boresight pointing errors. Next, we deduce the closed-form expression of the probability density function (PDF) of the hybrid fading considering GGD weak turbulence and nonzero boresight errors based on the new receiving signal model above through double-exponential Taylor expansion and higher transcendental Whittaker function. Finally, the analytical expressions of the outage probabilities for point-to-point (P2P) link, serial and parallel relay-assisted UWOC systems are further derived respectively under the proposed aggregated channel. Numerical simulations are also provided to validate the accuracy of the theoretical formulae derived above, and to show the effects of the key system parameters on the outage performance of relaying UWOC systems.

Design of the Polarization-Independent Wavelength Multiplexing Holographic Metasurface

Metasurface regulates the polarization, phase, amplitude, frequency, and other characteristics of electromagnetic waves through the subwavelength microstructure. By using its polarization characteristics, it can realize the functions of optical rotation and vector beam generation. It is the most widely used method of regulation. However, parallel optical manipulation, imaging, and communication usually require polarization-insensitive focused (or vortex) arrays of beams, so polarization-independent wavelength multiplexing optical systems need to be considered. In this paper, the genetic algorithm combined with the computer-generated hologram (CGH) is used to control the transmission phase of the structure itself, and on the basis of wavelength multiplexing, the corresponding array of focused or vortex beams without the polarization selection property is realized. The simulation software results show that the method has a huge application prospect in optical communication and optical manipulation.

Scalable computational kernels for mortar finite element methods

Targeting simulations on parallel hardware architectures, this paper presents computational kernels for efficient computations in mortar finite element methods. Mortar methods enable a variationally consistent imposition of coupling conditions at high accuracy, but come with considerable numerical effort and cost for the evaluation of the mortar integrals to compute the coupling operators. In this paper, we identify bottlenecks in parallel data layout and domain decomposition that hinder an efficient evaluation of the mortar integrals. We then propose a set of computational strategies to restore optimal parallel communication and scalability for the core kernels devoted to the evaluation of mortar terms. We exemplarily study the proposed algorithmic components in the context of three-dimensional large-deformation contact mechanics, both for cases with fixed and dynamically varying interface topology, yet these concepts can naturally and easily be transferred to other mortar applications, e.g. classical meshtying problems. To restore parallel scalability, we employ overlapping domain decompositions of the interface discretization independent from the underlying volumes and then tackle parallel communication for the mortar evaluation by a geometrically motivated reduction of ghosting data. Using three-dimensional contact examples, we demonstrate strong and weak scalability of the proposed algorithms up to 480 parallel processes as well as study and discuss improvements in parallel communication related to mortar finite element methods. For the first time, dynamic load balancing is applied to mortar contact problems with evolving contact zones, such that the computational work is well balanced among all parallel processors independent of the current state of the simulation.

CP3d: A comprehensive Euler-Lagrange solver for direct numerical simulation of particle-laden flows

We present a comprehensive Euler-Lagrange solver, CP3d, for the direct numerical simulation of particle-laden flows. The solver can handle one-way, two-way, interface-unresolved four-way and interface-resolved coupling regime. To make the solver versatile, different numerical approaches are available for fluid, particle as well as the coupling sub-solver. For the sake of computational accuracy and efficiency, a third-order exponential approximation method is proposed for Basset history force in interface-unresolved regime, and a new simplified lubrication force model based on the averaged integration is utilized in interface-resolved simulation to account for the short-range hydrodynamic force. The volume integration approach is also modified to adapt the staggered mesh configuration. The present solver is intensively validated against several benchmarks. A 2D pencil-like domain decomposition is implemented for parallel communication. The resulting solver is able to simulate large scale cases with billions of grid points and millions of moving particles in interface-resolved four-way regime, using only hundreds of computational cores. In addition, a nearly perfect linear strong scaling performance is achieved. In our test, CP3d is more than ten times faster than other similar solver reported in the literature. Program summaryProgram Title: Channel-Particle 3D, CP3d.CPC Library link to program files:https://doi.org/10.17632/7j6kcf8629.1.Developer's repository link:https://github.com/gongzheng-justin/CP3d.Code Ocean capsule:https://codeocean.com/capsule/0609843.Licensing provisions: MIT License.Programming language: Fortran 95, parallelized using MPI.External libraries: FFTW.Nature of problem:CP3d provides a comprehensive tool to perform the direct numerical simulation for particle-laden flows. One-way, two-way, interface-unresolved four-way and interface-resolved coupling regimes can be conducted.Solution method: the code employs second-/fourth-order finite-difference discretization for the fluid Navier-Stokes equation, and numerically solves the Maxey-Riley equation for the particle phase. In four-way regime, particle collisions are considered by discrete-element method. Immersed boundary method is utilized in the interface-resolved coupling regime.

A Parallel Compact Gannet Optimization Algorithm for Solving Engineering Optimization Problems

The Gannet Optimization Algorithm (GOA) has good performance, but there is still room for improvement in memory consumption and convergence. In this paper, an improved Gannet Optimization Algorithm is proposed to solve five engineering optimization problems. The compact strategy enables the GOA to save a large amount of memory, and the parallel communication strategy allows the algorithm to avoid falling into local optimal solutions. We improve the GOA through the combination of parallel strategy and compact strategy, and we name the improved algorithm Parallel Compact Gannet Optimization Algorithm (PCGOA). The performance study of the PCGOA on the CEC2013 benchmark demonstrates the advantages of our new method in various aspects. Finally, the results of the PCGOA on solving five engineering optimization problems show that the improved algorithm can find the global optimal solution more accurately.

Avoided mode-crossing assisted single soliton formation

Single soliton micro-comb (SMC) provides a tool for nonlinear optics investigation, and has become a novel integrated coherent source for portable optical clock, precise measurement and massive parallel optical communication systems, etc. Here, we demonstrate a new approach for deterministic single soliton generation in a microresonator. The microresonator is pumped at a mode with a frequency shift of −160 MHz due to the avoided mode-crossing (AMX), which enhances the local dispersion to form native mode spaced (NMS) Turing pattern directly. The Turing pattern provides a potential field to capture and sustain single soliton. Moreover, the high power chaotic microcomb is absent, which enables stable accessing of single SMC state. Our experiment presents a different dynamics of single soliton generation, which paves a new way for stable and deterministic single soliton micro-comb formation for practical applications.

Reliability Study for Communication System: A Case Study of an Underground Mine

After summarizing and evaluating works on system reliability, various models and results for predicting and evaluating system reliability have been introduced. However, we have not seen a study conducted to assess the reliability of communication systems in an underground mine. Underground mining operations are normally dependent on communication system reliability. The main purpose of this work is to study the failure of a theoretical underground mine communication system, propose a method to improve its reliability, and predict the results of the suggested method using system dynamic modeling. This study contributes to improving the reliability of communication systems in underground mines. In the case of a single nonredundant system, three options were implemented: doubling corrective maintenance, increasing preventative maintenance by 50%, and combining both measures. These three options were modeled by combining Markov modelling with system dynamic modelling methodology and were confirmed by experiments and simulation results. This combination of modelling constitutes the novelty of this study. In this paper, actual system component failure data was used for simulation for the single nonredundant system, after doubling corrective maintenance, increasing preventative maintenance by 50%, and combining in the case of implementing simultaneously both maintenance changes, but not for developing single and dual standby system models. Therefore, these models should be suitable for practical use, as they are based on actual working systems. Modelling confirmed that placing a communication system in each shaft of the theoretical underground mine increases the reliability of the communication system. The degree of availability of the communication system with single standby device shows the result of 62.38% while the communication system with two standby devices and three parallel communication systems’ availability rating shows a result of 85.18%.

Application of a Parallel Adaptive Cuckoo Search Algorithm in the Rectangle Layout Problem

The meta-heuristic algorithm is a global probabilistic search algorithm for the iterative solution. It has good performance in global optimization fields such as maximization. In this paper, a new adaptive parameter strategy and a parallel communication strategy are proposed to further improve the Cuckoo Search (CS) algorithm. This strategy greatly improves the convergence speed and accuracy of the algorithm and strengthens the algorithm’s ability to jump out of the local optimal. This paper compares the optimization performance of Parallel Adaptive Cuckoo Search (PACS) with CS, Parallel Cuckoo Search (PCS), Particle Swarm Optimization (PSO), Sine Cosine Algorithm (SCA), Grey Wolf Optimizer (GWO), Whale Optimization Algorithm (WOA), Differential Evolution (DE) and Artificial Bee Colony (ABC) algorithms by using the CEC-2013 test function. The results show that PACS algorithm outperforms other algorithms in 20 of 28 test functions. Due to the superior performance of PACS algorithm, this paper uses it to solve the problem of the rectangular layout. Experimental results show that this scheme has a significant effect, and the material utilization rate is improved from 89.5% to 97.8% after optimization.

Assessment of Multivariate Information Transmission in Space-Time-Frequency Domain: A Case Study for EEG Signals.

Multivariate signal (MS) analysis, especially the assessment of its information transmission (for example, from the perspective of network science), is the key to our understanding of various phenomena in biology, physics and economics. Although there is a large amount of literature demonstrating that MS can be decomposed into space-time-frequency domain information, there seems to be no research confirming that multivariate information transmission (MIT) in these three domains can be quantified. Therefore, in this study, we attempted to combine dynamic mode decomposition (DMD) and parallel communication model (PCM) together to realize it. We first regarded MS as a large-scale system and then used DMD to decompose it into specific subsystems with their own intrinsic oscillatory frequencies. At the same time, the transition probability matrix (TPM) of information transmission within and between MS at two consecutive moments in each subsystem can also be calculated. Then, communication parameters (CPs) derived from each TPM were calculated in order to quantify the MIT in the space-time-frequency domain. In this study, multidimensional electroencephalogram (EEG) signals were used to illustrate our method. Compared with traditional EEG brain networks, this method shows greater potential in EEG analysis to distinguish between patients and healthy controls. This study demonstrates the feasibility of measuring MIT in the space-time-frequency domain simultaneously. This study shows that MIT analysis in the space-time-frequency domain is not only completely different from the MS decomposition in these three domains, but also can reveal many new phenomena behind MS that have not yet been discovered.

Configuring Reconfigurable Intelligent Surface for Parallel MIMO Visible Light Communications with Asymptotic Capacity Maximization

As an emerging technology, reconfigurable intelligent surface (RIS) has attracted increasing attention due to the ability to configure the wireless propagation environment. Parallel multiple-input multiple-output (MIMO) visible light communication (VLC) is suitable for some scenarios, e.g., multi-user time-division multiple access for indoor VLCs. The application of RIS in VLC is a promising trend in the future, and this paper investigates the employment of RIS in a parallel MIMO VLC system with asymptotic capacity maximization. To this end, the RIS-aided parallel MIMO VLC channel model is derived in this paper under the point source assumption, and then, as for the non-convex optimization problem, instead of searching exhaustively for the optimal solution, we propose a low-complexity near-optimal relaxing particle swarm optimization (RPSO) algorithm to optimize the RIS parameters. Meanwhile, we discover that the convex relaxation is an effective method for the optimization problems. Finally, numerical results indicate the effectiveness of the proposed design of RIS, and meanwhile, the asymptotic capacity can be improved to a great degree by adopting RIS in the parallel MIMO VLC system.

An efficient communication strategy for massively parallel computation in CFD

With the development of high-performance computers, it is necessary to develop efficient parallel algorithms in the field of computational fluid dynamics (CFD). In this study, a novel parallel communication strategy based on asynchronous and packaged communication is proposed. The strategy implements an aggregated communication process, which requires only one communication in each iteration step, significantly reducing the number of communications. The correctness and convergence of the novel strategy are demonstrated from both theoretical and experimental perspectives. And based on the real vehicle CHN-T model with 140 million meshes, a detailed performance comparison and analysis is performed for the novel strategy and the traditional strategy, showing that the novel strategy has significant advantages in terms of scalability. Finally, the strong scalability and weak scalability tests are carried out separately for the CHN-T model. The strong scaling efficiency can reach 74% with 10.5 billion meshes and 256,000 cores. The weak scaling parallel efficiency can reach 90% with 10 billion meshes and 179,000 cores. This research work has laid an important foundation for the development of the fast design of aircraft and cutting-edge numerical methods.

Chipnet: Enabling Large-scale Backscatter Network with Processor-free Devices

Differing from tremendous existing works that mainly focus on optimizing backscatter communication, Radio-to-Bus (R2B) communication utilizes backscatter to offload processors from IoT devices to the gateway, achieving processor-free devices of significantly reduced power and hardware cost. However, R2B communication is not suitable for large-scale backscatter networks, since R2B cannot support parallel and long-range communication between the gateway and hundreds of R2B devices. In this article, we present Chipnet, a network that supports hundreds of long-range and concurrent connections between the gateway and multiple processor-free devices. The high-level design of Chipnet includes a parallel frequency-division uplink mechanism that can work on processor-free devices and a processor-free MAC layer protocol that supports gateway to broadcast downlink data and individually manage each processor-free device. This design addresses practical issues facing the processor-free device architecture, such as synchronizing hundreds of processor-free devices, assigning unique channel frequencies to every device, and realizing power-efficient processor-free signal conversion. The results demonstrate that a Chipnet network can achieve a task throughput of 2,400 tasks/s with a latency of 72.23 ms. Compared with the R2B network, Chipnet achieves 3×–5× improvements in network coverage range and two orders of magnitude improvement in both network throughput and network latency.

Power allocation algorithm based on Q‐learning for two‐way relaying system with dual‐media parallel communication

Power allocation algorithm based on Q‐learning for two‐way relaying system with dual‐media parallel communication