High-performance Parallel Computing Research Articles

Four-Input Multi-Layer Majority Logic Circuit Based on DNA Strand Displacement Computing

Biomolecules have the advantage of high performance parallel computing and large information capacity. The use of biochemical circuits to solve computational problems has been studied by many researchers. In this paper, we use DNA strand displacement technology to construct complex molecular circuits as logic gates. The experimental process is demonstrated by a series of strand displacement reactions, and the feasibility of the design is verified by the strand displacement simulation platform Visual DSD. The key feature of this logic gate design is that when two inputs of the same signal are controlled, the remaining two different input signals implement AND and OR function to determine the output. Based on this feature, a four-input multi-layer logic circuit is designed and implemented. The calculation mode of the other three inputs AND and OR combinations is implemented by controlling each logic gate input.

Pedagogical Foundations of Learning Parallel Computing

Currently, leading countries are considering and paying particular attention to parallel computing as an important area of research.In connection with the digitalization of society, the possibilities of using parallel computing in the practical life of the city are expanding. For example, digital support for urban bus traffic schedules, etc. Therefore, professional training of specialists is required in accordance with modern requirements. The purpose of this work is to determine the pedagogical features, didactic principles and practical implementation in teaching parallel computing at the university. To achieve this goal the following tasks were set. 1. To determine the pedagogical features of teaching high-performance parallel computing. 2. Refinement of didactic principles in teaching high-performance parallel computing. 3. The practical implementation of pedagogical features and didactic principles in teaching parallel computing. In the article, the pedagogical system for introducing special courses is divided into a substantive, organizational and methodological structure. Theoretical and practical basics of introducing special courses on parallel computing, setting up a hardware and software complex of an educational cluster of parallel computing and didactic materials are considered. As a result, the problem of complex computations in solving complex problems is outlined and the training of specialists for the purpose of their application to the future professional activity of graduates of information technologies is envisaged. Key words: parallel computing, parallel computing cluster, information technologies, educational cluster

Development of “Parameter space screening”-based single-wavelength anomalous diffraction phasing and structure determination pipeline

In this paper, we present a highly efficient structure determination pipeline software suite (X2DF) that is based on the “Parameter space screening” method, by combining the popular crystallographic structure determination programs and high-performance parallel computing. The phasing method employed in X2DF is based on the single-wavelength anomalous diffraction (SAD) theory. In the X2DF, the choice of crystallographic software, the input parameters to this software and the results display layout, are all parameters which users can select and screen automatically. Users may submit multiple structure determination jobs each time, and each job uses a slightly different set of input parameters or programs. Upon completion, the results of the calculation performed can be displayed, harvested, and analyzed by using the graphical user interface (GUI) of the system. We have applied the X2DF successfully to many cases including the cases that the structure solutions fail to be yielded by using manual approaches.

A parallel workflow implementation for PEST version 13.6 in high-performance computing for WRF-Hydro version 5.0: a case study over the midwestern United States

Abstract. The Weather Research and Forecasting Hydrological (WRF-Hydro) system is a state-of-the-art numerical model that models the entire hydrological cycle based on physical principles. As with other hydrological models, WRF-Hydro parameterizes many physical processes. Hence, WRF-Hydro needs to be calibrated to optimize its output with respect to observations for the application region. When applied to a relatively large domain, both WRF-Hydro simulations and calibrations require intensive computing resources and are best performed on multimode, multicore high-performance computing (HPC) systems. Typically, each physics-based model requires a calibration process that works specifically with that model and is not transferrable to a different process or model. The parameter estimation tool (PEST) is a flexible and generic calibration tool that can be used in principle to calibrate any of these models. In its existing configuration, however, PEST is not designed to work on the current generation of massively parallel HPC clusters. To address this issue, we ported the parallel PEST to HPCs and adapted it to work with WRF-Hydro. The porting involved writing scripts to modify the workflow for different workload managers and job schedulers, as well as to connect the parallel PEST to WRF-Hydro. To test the operational feasibility and the computational benefits of this first-of-its-kind HPC-enabled parallel PEST, we developed a case study using a flood in the midwestern United States in 2013. Results on a problem involving the calibration of 22 parameters show that on the same computing resources used for parallel WRF-Hydro, the HPC-enabled parallel PEST can speed up the calibration process by a factor of up to 15 compared with commonly used PEST in sequential mode. The speedup factor is expected to be greater with a larger calibration problem (e.g., more parameters to be calibrated or a larger size of study area).

Towards Accelerated Genome Informatics on Parallel HPC Platforms: The ReneGENE-GI Perspective

Genome Informatics (GI) involves accurate computational investigations of strongly correlated subsystems that demands inter-disciplinary approaches for problem solving. With the growing volume of genomic sequencing data at an alarming rate, High Performance Computing (HPC) solutions offer the right platform to address the computational needs. GI requires algorithm-architecture co-design of parallel and accelerated biocomputing involving reconfigurable hardware like FPGAs and graphics accelerators or GPUs, to bridge the gap between growing data volumes and compute capabilities. Such platforms offer high degrees of parallelism and scalability, while accelerating the multi-stage GI computational pipeline. Amidst such high computing power, it is the choice of algorithms and implementations in the entirety of the GI pipeline that decides the precision of bio-computing in revealing biologically relevant information. Through this paper, we present ReneGENE-GI, an innovatively engineered GI pipeline. This paper details the performance analysis of ReneGENE-GI’s Comparative Genomics Module (CGM), the compute intensive stage of the pipeline. This module comes in two flavours, designed to run on GPUs and FPGAs respectively, hosted on HPC platforms. The pipeline uses a very efficient reference indexing algorithm based on the dynamic Monotonic Minimal Perfect Hashing Function (MMPH), allowing an absolute indexing for the reference genome, thus avoiding heuristics. Alignment time for our FPGA version is about one-tenth the time taken by our single GPU implementation, which itself is 2.62x faster than CUSHAW2-GPU (the GPU CUDA implementation of CUSHAW). With the single-GPU implementation demonstrating a speed up of 150+ x over standard heuristic aligners in the market like BFAST, the FPGA version of our CGM is several orders faster than the competitors, offering precision over heuristics.

Design and Evaluation of a Scalable Engine for 3D-FFT Computation in an FPGA Cluster

The Three Dimensional Fast Fourier Transform (3D-FFT) is commonly used to solve the partial differential equations describing the system evolution in several physical phenomena, such as the motion of viscous fluids described by the Navier-Stokes equations. Simulation of such problems requires the use of a parallel High-Performance Computing architecture since the size of the problem grows with the cube of the FFT size, and the representation of the single point comprises several double precision floating- point complex numbers. Modern High-Performance Computing (HPC) systems are considering the inclusion of FPGAs as components of this computing architecture because they can combine effective hardware acceleration capabilities and dedicated communication facilities. Furthermore, the network topology can be optimized for the specific calculation that the cluster must perform, especially in the case of algorithms limited by the data exchange delay between the processors. In this paper, we explore an HPC design that uses FPGA accelerators to compute the 3DFFT. We devise a scalable FFT engine based on a custom radix-2 double-precision core that is used to implement the Decimation in Frequency version of the Cooley-Tukey FFT algorithm. The FFT engine can be adapted to different technology constraints and networking topologies by adjusting the number of cores and configuration parameters in order to minimize the overall calculation time. We compare the various possible configurations with the technological limits of available hardware. Finally, we evaluate the bandwidth required for continuous FFT execution in the APEnet toroidal mesh network.

Compact Version of the Quasi-Gasdynamic System for Modeling a Viscous Compressible Gas

We consider a compact version (the CQGD system) of the quasi-gasdynamic system. All algorithms that have been used to approximate the spatial derivatives in the Navier–Stokes equations can also be applied to the CQGD system. At the same time, the use of the CQGD system permits significantly improving the stability of explicit schemes, which is important for ensuring high-performance parallel computations. As examples of the use of algorithms based on the CQGD system, we present the results of computations of a laminar boundary layer on a plate and of a hypersonic laminar separated flow in a compression angle.

Adaptive control in roll-forward recovery for extreme scale multigrid

With the increasing number of compute components, failures in future exa-scale computer systems are expected to become more frequent. This motivates the study of novel resilience techniques. Here, we extend a recently proposed algorithm-based recovery method for multigrid iterations by introducing an adaptive control. After a fault, the healthy part of the system continues the iterative solution process, while the solution in the faulty domain is reconstructed by an asynchronous online recovery. The computations in both the faulty and the healthy subdomains must be coordinated in a sensitive way, in particular, both under- and over-solving must be avoided. Both of these waste computational resources and will therefore increase the overall time-to-solution. To control the local recovery and guarantee an optimal recoupling, we introduce a stopping criterion based on a mathematical error estimator. It involves hierarchically weighted sums of residuals within the context of uniformly refined meshes and is well-suited in the context of parallel high-performance computing. The recoupling process is steered by local contributions of the error estimator before the fault. Failure scenarios when solving up to 6.9 × 1011 unknowns on more than 245,766 parallel processes will be reported on a state-of-the-art peta-scale supercomputer demonstrating the robustness of the method.

High Resolution and Fast Processing of Spectral Reconstruction in Fourier Transform Imaging Spectroscopy.

High-resolution spectrum estimation has continually attracted great attention in spectrum reconstruction based on Fourier transform imaging spectroscopy (FTIS). In this paper, a parallel solution for interference data processing using high-resolution spectrum estimation is proposed to reconstruct the spectrum in a fast high-resolution way. In batch processing, we use high-performance parallel-computing on the graphics processing unit (GPU) for higher efficiency and lower operation time. In addition, a parallel processing mechanism is designed for our parallel algorithm to obtain higher performance. At the same time, other solving algorithms for the modern spectrum estimation model are introduced for discussion and comparison. We compare traditional high-resolution solving algorithms running on the central processing unit (CPU) and the parallel algorithm on the GPU for processing the interferogram. The experimental results illustrate that runtime is reduced by about 70% using our parallel solution, and the GPU has a great advantage in processing large data and accelerating applications.

A fast reconstruction method for three-dimensional shape measurement using dual-frequency grating projection and phase-to-height lookup table

Phase-to-height mapping is indispensable part of three-dimensional (3D) shape measurement system based on phase analysis, which guarantees the accuracy of 3D reconstruction. In this paper, a fast 3D shape reconstruction method based on dual-frequency grating projection and phase-to-height lookup table is proposed. In this proposed method, the reference plane is moved with known interval along the measurement depth direction to establish the mapping lookup table between the phase of the high and low frequency projected grating and their corresponding spatial height pixel by pixel respectively. Then, two methods to establish the lookup table with the unwrapped and the wrapped phase have been respectively introduced according to the characteristics of dual-frequency grating. The actual experimental results show that the two methods can effectively extend the measurement range of the current wrapped phase-to-height lookup method, and the reconstruction accuracy is better than the traditional phase-to-height quadratic fitting method. At the same time, the consumed time for 3D shape reconstruction of the tested object by the two methods is compared and analyzed. Finally, combining the high performance parallel computation of GPU, the fast 3D shape reconstruction is realized with the speed of 60fps.

Multi-objective optimization using parallel simulation for space situational awareness

Improving space situational awareness (SSA) remains one of the Department of Defense’s (DoD) top priorities. Current research has shown that the modeling of geosynchronous orbit (GEO) SSA architectures can help identify optimal combinations of ground- and space-based sensors. This paper extends previous research by expanding design boundaries and refining the methodology. A multi-objective genetic algorithm was used to examine this increased trade-space containing 1022 possible design combinations. The results of the optimizer clearly favor 1.0 m aperture ground telescopes combined with 0.15 m aperture sensors in a 12-satellite geosynchronous polar orbit (GPO) constellation. The GPO regime offers increased access to GEO resident space objects (RSO) since other orbits are restricted by a 40° solar exclusion angle. When performance is held constant, a GPO satellite constellation offers a 22.4% reduction in total system cost when compared to Sun synchronous orbit (SSO), equatorial low earth orbit (LEO), and near-GEO constellations. Parallel high-performance computing provides the possibility of solving an entirely new class of complex problems of interest to the DoD. The results of this research can educate national policy makers on the benefits of proposed upgrades to current and future SSA systems.

Online Tuning of EASY-Backfilling using Queue Reordering Policies

The EASY-FCFS heuristic is the basic building block of job scheduling policies in most parallel High Performance Computing platforms. Despite its simplicity, and the guarantee of no job starvation, it could still be improved on a per-system basis. Such tuning is difficult because of non-linearities in the scheduling process. The study conducted in this paper considers an online approach to the automatic tuning of the EASY heuristic for HPC platforms. More precisely, we consider the problem of selecting a reordering policy for the job queue under several feedback modes. We show via a comprehensive experimental validation on actual logs that periodic simulation of historical data can be used to recover existing in-hindsight results that allow to divide the average waiting time by almost 2. This results holds even when the simulator results are noisy. Moreover, we show that good performances can still be obtained without a simulator, under what is called bandit feedback - when we can only observe the performance of the algorithm that was picked on the live system. Indeed, a simple multi-armed bandit algorithm can reduce the average waiting time by 40 percent.

Spectrum reconstruction in Fourier transform imaging spectroscopy based on high-performance parallel computing.

In this paper, parallel-processing algorithms for spectrum reconstruction in Fourier transform imaging spectroscopy are proposed using high-performance parallel computing. Because of the huge amount of interference data, traditional algorithms are inefficient and time-consuming. It is necessary to process interference data as soon as possible to form spectral data for research and economy. We take advantage of parallel computing based on the graphics processing unit (GPU) to enable higher efficiency and reduced operation time. Furthermore, traditional algorithms for processing interferograms on the central processing unit are introduced for comparison. The experimental results show that the runtime is reduced from 1.144 to 0.332ms using our parallel algorithms, and for the huge amount of data, the designed parallel-processing mechanism on the GPU has advantages over the traditional pipeline.

A run control framework to streamline profiling, porting, and tuning simulation runs and provenance tracking of geoscientific applications

Abstract. Geoscientific modeling is constantly evolving, with next-generation geoscientific models and applications placing large demands on high-performance computing (HPC) resources. These demands are being met by new developments in HPC architectures, software libraries, and infrastructures. In addition to the challenge of new massively parallel HPC systems, reproducibility of simulation and analysis results is of great concern. This is due to the fact that next-generation geoscientific models are based on complex model implementations and profiling, modeling, and data processing workflows. Thus, in order to reduce both the duration and the cost of code migration, aid in the development of new models or model components, while ensuring reproducibility and sustainability over the complete data life cycle, an automated approach to profiling, porting, and provenance tracking is necessary. We propose a run control framework (RCF) integrated with a workflow engine as a best practice approach to automate profiling, porting, provenance tracking, and simulation runs. Our RCF encompasses all stages of the modeling chain: (1) preprocess input, (2) compilation of code (including code instrumentation with performance analysis tools), (3) simulation run, and (4) postprocessing and analysis, to address these issues. Within this RCF, the workflow engine is used to create and manage benchmark or simulation parameter combinations and performs the documentation and data organization for reproducibility. In this study, we outline this approach and highlight the subsequent developments scheduled for implementation born out of the extensive profiling of ParFlow. We show that in using our run control framework, testing, benchmarking, profiling, and running models is less time consuming and more robust than running geoscientific applications in an ad hoc fashion, resulting in more efficient use of HPC resources, more strategic code development, and enhanced data integrity and reproducibility.

Modeling of Galactic Wind Formation from Supernovae Using High-Performance Computations

Fundamental processes in the dynamics of the interstellar medium, namely, galactic wind, i.e., ejections of interstellar matter from central regions of galaxies, which are presumably caused by the formation of supernovae, are mathematically modeled in detail on high-performance parallel computer systems. The mathematical simulation is based on a kinetically consistent gasdynamic approach developed for such class of problems in astrophysics. A kinetically consistent algorithm is well adapted to the architecture of high-performance computer systems with massive parallelism, so that complex large-scale astrophysical phenomena can be efficiently studied with a high resolution. The approach, method, and algorithms are described, and numerical results are presented.

Visualization in the integrated SimPhoNy multiscale simulation framework

We describe three distinct approaches to visualization for multiscale materials modelling research. These have been developed with the framework of the SimPhoNy FP7 EU-project, and complement each other in their requirements and possibilities. All have been integrated via wrappers to one or more of the simulation approaches within the SimPhoNy project. In this manuscript we describe and contrast their features. Together they cover visualization needs from electronic to macroscopic scales and are suited to simulations made on personal computers, workstations or advanced High Performance parallel computers. Examples as well as recommendations for future calculations are presented.

A Numerical Study of Scalable Cardiac Electro-Mechanical Solvers on HPC Architectures.

We introduce and study some scalable domain decomposition preconditioners for cardiac electro-mechanical 3D simulations on parallel HPC (High Performance Computing) architectures. The electro-mechanical model of the cardiac tissue is composed of four coupled sub-models: (1) the static finite elasticity equations for the transversely isotropic deformation of the cardiac tissue; (2) the active tension model describing the dynamics of the intracellular calcium, cross-bridge binding and myofilament tension; (3) the anisotropic Bidomain model describing the evolution of the intra- and extra-cellular potentials in the deforming cardiac tissue; and (4) the ionic membrane model describing the dynamics of ionic currents, gating variables, ionic concentrations and stretch-activated channels. This strongly coupled electro-mechanical model is discretized in time with a splitting semi-implicit technique and in space with isoparametric finite elements. The resulting scalable parallel solver is based on Multilevel Additive Schwarz preconditioners for the solution of the Bidomain system and on BDDC preconditioned Newton-Krylov solvers for the non-linear finite elasticity system. The results of several 3D parallel simulations show the scalability of both linear and non-linear solvers and their application to the study of both physiological excitation-contraction cardiac dynamics and re-entrant waves in the presence of different mechano-electrical feedbacks.

A survey of GPU-based acceleration techniques in MRI reconstructions.

Image reconstruction in magnetic resonance imaging (MRI) clinical applications has become increasingly more complicated. However, diagnostic and treatment require very fast computational procedure. Modern competitive platforms of graphics processing unit (GPU) have been used to make high-performance parallel computations available, and attractive to common consumers for computing massively parallel reconstruction problems at commodity price. GPUs have also become more and more important for reconstruction computations, especially when deep learning starts to be applied into MRI reconstruction. The motivation of this survey is to review the image reconstruction schemes of GPU computing for MRI applications and provide a summary reference for researchers in MRI community.

High Performance Parallel Computing with Cloud Technologies

Cloud is referred to as a collection of infrastructure services, such as Infrastructure as a service (IaaS) and Platform as a service (PaaS), which are made available to us for utilization by various organizations in which the key factor is virtualization of data as it allow the user to manage, handle and compute a large number of tasks very easily. By referring to Cloud technologies we mean runtime such as Hadoop, Dryad and other Map Reduce frameworks. In this paper we would analyse the above mentioned software’s and techniques for the cloud system by comparing them on the basis of its processing speed, its data handling capacity, the nature of user friendliness. We would discuss large scale data analysis using different implementations on the above mentioned tools and after that we would give a performance analysis of these tools on the given implementation like Cap3, HEP, Cloudburst.

Reducing the number of response time service level objective violations by a cloud‐HPC convergence scheduler

SummaryJob scheduling is an old topic in High‐Performance Computing (HPC), and it is more and more studied in data centers. Large data centers are often split into separate partitions for cloud computing and HPC; each partition normally has its specific scheduler. The possibility of migrating jobs from the HPC partition to the cloud one is a topic widely discussed in the literature. However, job migration from cloud to HPC is a much less explored topic. Nevertheless, such migration may be useful in many situations, in particular when the HPC platform has a low resource usage level, and the cloud usage level is high. A large number of jobs that could migrate from the cloud to the HPC partition may be observed in Google data center workloads. Job scheduling using overbooking strategy is seen as the main reason for the high resource usage level in clouds. However, overbooking can lead to a high rate of rescheduling and job dumping, which potentially causes response time violations. This work shows that HPC platforms can host and execute some cloud jobs with low interference in HPC jobs and a low number of response time violations. We introduce the definition of a cloud‐HPC convergence area and propose a job scheduling strategy for it, aiming at reducing the number of response time violations of cloud jobs without interfering with HPC jobs execution. Our proposal is formally defined and then evaluated in different execution scenarios, using the SimGrid simulation framework, with workload data from production HPC grid. The experimental results show that often, there is a large number of empty areas in the scheduling plan of HPC platforms, which makes it possible to allocate cloud jobs by backfilling. This is due to the sparse HPC job submission pattern and the low resource usage level in some HPC platforms. One performed simulation scenario considered a set of 11K parallel HPC jobs running on a 2560‐processor platform having an average resource usage level of 38.0%. The proposed convergence scheduler succeeded to inject around 267K cloud jobs in the HPC platform, with a response time violation rate under 0.00094% for such jobs, considering 80 processors in the convergence area and no effects on the HPC workload. This experiment considered cloud jobs based on job features of Google public cloud workloads, with a processing time slack factor of 1.25 (which is considered as high priority in the Google cloud SLA—Service Level Agreement). Usually, most cloud jobs show a slack factor higher than 1.25 (most cloud jobs are medium or low priority). The same simulation, repeated with a higher slack factor (4), showed no response time violations.