Wyszukiwarka
Filtry
wszystkich: 1752
wybranych: 1585
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: PERFORMANCE/ENERGY OPTIMIZATION, POWER CAPPING, GPU, NAS PARALLEL BENCHMARKS
-
Performance/energy aware optimization of parallel applications on GPUs under power capping
PublikacjaIn the paper we present an approach and results from application of the modern power capping mechanism available for NVIDIA GPUs to the bench- marks such as NAS Parallel Benchmarks BT, SP and LU as well as cublasgemm- benchmark which are widely used for assessment of high performance computing systems’ performance. Specifically, depending on the benchmarks, various power cap configurations are best for desired trade-off of performance...
-
Extended investigation of performance-energy trade-offs under power capping in HPC environments
Publikacja—In the paper we present investigation of performance-energy trade-offs under power capping using modern processors. The results are presented for systems targeted at both server and client markets and were collected from Intel Xeon E5 and Intel Xeon Phi server processors as well as from desktop and mobile Intel Core i7 processors. The results, when using power capping, show that we can find various interesting combinations of...
-
DEPO: A dynamic energy‐performance optimizer tool for automatic power capping for energy efficient high‐performance computing
PublikacjaIn the article we propose an automatic power capping software tool DEPO that allows one to perform runtime optimization of performance and energy related metrics. For an assumed application model with an initialization phase followed by a running phase with uniform compute and memory intensity, the tool performs automatic tuning engaging one of the two exploration algorithms—linear search (LS) and golden section search (GSS), finds...
-
Performance and Energy Aware Training of a Deep Neural Network in a Multi-GPU Environment with Power Capping
PublikacjaIn this paper we demonstrate that it is possible to obtain considerable improvement of performance and energy aware metrics for training of deep neural networks using a modern parallel multi-GPU system, by enforcing selected, non-default power caps on the GPUs. We measure the power and energy consumption of the whole node using a professional, certified hardware power meter. For a high performance workstation with 8 GPUs, we were...
-
Dynamic GPU power capping with online performance tracing for energy efficient GPU computing using DEPO tool
PublikacjaGPU accelerators have become essential to the recent advance in computational power of high- performance computing (HPC) systems. Current HPC systems’ reaching an approximately 20–30 mega-watt power demand has resulted in increasing CO2 emissions, energy costs and necessitate increasingly complex cooling systems. This is a very real challenge. To address this, new mechanisms of software power control could be employed. In this...
-
GPU Power Capping for Energy-Performance Trade-Offs in Training of Deep Convolutional Neural Networks for Image Recognition
PublikacjaIn the paper we present performance-energy trade-off investigation of training Deep Convolutional Neural Networks for image recognition. Several representative and widely adopted network models, such as Alexnet, VGG-19, Inception V3, Inception V4, Resnet50 and Resnet152 were tested using systems with Nvidia Quadro RTX 6000 as well as Nvidia V100 GPUs. Using GPU power capping we found other than default configurations minimizing...
-
Analyzing energy/performance trade-offs with power capping for parallel applications on modern multi and many core processors
PublikacjaIn the paper we present extensive results from analyzing energy/performance trade-offs with power capping observed on four different modern CPUs, for three different parallel applications such as 2D heat distribution, numerical integration and Fast Fourier Transform. The CPU tested represent both multi-core type CPUs such as Intel⃝R Xeon⃝R E5, desktop and mobile i7 as well as many-core Intel⃝R Xeon PhiTM x200 but also server, desktop...
-
Investigation of Performance and Energy Consumption of Tokenization Algorithms on Multi-core CPUs Under Power Capping
PublikacjaIn this paper we investigate performance-energy optimization of tokenizer algorithm training using power capping. We focus on parallel, multi-threaded implementations of Byte Pair Encoding (BPE), Unigram, WordPiece, and WordLevel run on two systems with different multi-core CPUs: Intel Xeon 6130 and desktop Intel i7-13700K. We analyze execution times and energy consumption for various numbers of threads and various power caps and...
-
Performance evaluation of parallel background subtraction on GPU platforms
PublikacjaImplementation of the background subtraction algorithm on parallel GPUs is presented. The algorithm processes video streams and extracts foreground pixels. The work focuses on optimizing parallel algorithm implementation by taking into account specific features of the GPU architecture, such as memory access, data transfers and work group organization. The algorithm is implemented in both OpenCL and CUDA. Various optimizations of...
-
Performance Evaluation of Selected Parallel Object Detection and Tracking Algorithms on an Embedded GPU Platform
PublikacjaPerformance evaluation of selected complex video processing algorithms, implemented on a parallel, embedded GPU platform Tegra X1, is presented. Three algorithms were chosen for evaluation: a GMM-based object detection algorithm, a particle filter tracking algorithm and an optical flow based algorithm devoted to people counting in a crowd flow. The choice of these algorithms was based on their computational complexity and parallel...
-
Optimization of hybrid parallel application execution in heterogeneous high performance computing systems considering execution time and power consumption
PublikacjaMany important computational problems require utilization of high performance computing (HPC) systems that consist of multi-level structures combining higher and higher numbers of devices with various characteristics. Utilizing full power of such systems requires programming parallel applications that are hybrid in two meanings: they can utilize parallelism on multiple levels at the same time and combine together programming interfaces...
-
Investigation of Parallel Data Processing Using Hybrid High Performance CPU + GPU Systems and CUDA Streams
PublikacjaThe paper investigates parallel data processing in a hybrid CPU+GPU(s) system using multiple CUDA streams for overlapping communication and computations. This is crucial for efficient processing of data, in particular incoming data stream processing that would naturally be forwarded using multiple CUDA streams to GPUs. Performance is evaluated for various compute time to host-device communication time ratios, numbers of CUDA streams,...
-
Efficient parallel implementation of crowd simulation using a hybrid CPU+GPU high performance computing system
PublikacjaIn the paper we present a modern efficient parallel OpenMP+CUDA implementation of crowd simulation for hybrid CPU+GPU systems and demonstrate its higher performance over CPU-only and GPU-only implementations for several problem sizes including 10 000, 50 000, 100 000, 500 000 and 1 000 000 agents. We show how performance varies for various tile sizes and what CPU–GPU load balancing settings shall be preferred for various domain...
-
Parallel Background Subtraction in Video Streams Using OpenCL on GPU Platforms
PublikacjaImplementation of the background subtraction algorithm using OpenCL platform is presented. The algorithm processes live stream of video frames from the surveillance camera in on-line mode. Processing is performed using a host machine and a parallel computing device. The work focuses on optimizing an OpenCL algorithm implementation for GPU devices by taking into account specific features of the GPU architecture, such as memory access,...
-
Implementation of FDTD-compatible Green's function on heterogeneous CPU-GPU parallel processing system
PublikacjaThis paper presents an implementation of the FDTD-compatible Green's function on a heterogeneous parallel processing system. The developed implementation simultaneously utilizes computational power of the central processing unit (CPU) and the graphics processing unit (GPU) to the computational tasks best suited to each architecture. Recently, closed-form expression for this discrete Green's function (DGF) was derived, which facilitates...
-
Optimization of Execution Time under Power Consumption Constraints in a Heterogeneous Parallel System with GPUs and CPUs
PublikacjaThe paper proposes an approach for parallelization of computations across a collection of clusters with heterogeneous nodes with both GPUs and CPUs. The proposed system partitions input data into chunks and assigns to par- ticular devices for processing using OpenCL kernels defined by the user. The sys- tem is able to minimize the execution time of the application while maintaining the power consumption of the utilized GPUs and...
-
Energy-Aware High-Performance Computing: Survey of State-of-the-Art Tools, Techniques, and Environments
PublikacjaThe paper presents state of the art of energy-aware high-performance computing (HPC), in particular identification and classification of approaches by system and device types, optimization metrics, and energy/power control methods. System types include single device, clusters, grids, and clouds while considered device types include CPUs, GPUs, multiprocessor, and hybrid systems. Optimization goals include various combinations of...
-
Modeling energy consumption of parallel applications
PublikacjaThe paper presents modeling and simulation of energy consumption of two types of parallel applications: geometric Single Program Multiple Data (SPMD) and divide-and-conquer (DAC). Simulation is performed in a new MERPSYS environment. Model of an application uses the Java language with extension representing message exchange between processes working in parallel. Simulation is performed by running threads representing distinct process...
-
Energy-Aware Scheduling for High-Performance Computing Systems: A Survey
PublikacjaHigh-performance computing (HPC), according to its name, is traditionally oriented toward performance, especially the execution time and scalability of the computations. However, due to the high cost and environmental issues, energy consumption has already become a very important factor that needs to be considered. The paper presents a survey of energy-aware scheduling methods used in a modern HPC environment, starting with the...
-
A multithreaded CUDA and OpenMP based power‐aware programming framework for multi‐node GPU systems
PublikacjaIn the paper, we have proposed a framework that allows programming a parallel application for a multi-node system, with one or more GPUs per node, using an OpenMP+extended CUDA API. OpenMP is used for launching threads responsible for management of particular GPUs and extended CUDA calls allow to manage CUDA objects, data and launch kernels. The framework hides inter-node MPI communication from the programmer who can benefit from...
-
Auto-tuning methodology for configuration and application parameters of hybrid CPU + GPU parallel systems based on expert knowledge
PublikacjaAuto-tuning of configuration and application param- eters allows to achieve significant performance gains in many contemporary compute-intensive applications. Feasible search spaces of parameters tend to become too big to allow for exhaustive search in the auto-tuning process. Expert knowledge about the utilized computing systems becomes useful to prune the search space and new methodologies are needed in the face of emerging heterogeneous...
-
Solar Photovoltaic Energy Optimization and Challenges
PublikacjaThe study paper focuses on solar energy optimization approaches, as well as the obstacles and concerns that come with them. This study discusses the most current advancements in solar power generation devices in order to provide a reference for decision-makers in the field of solar plant construction throughout the world. These technologies are divided into three groups: photovoltaic, thermal, and hybrid (thermal/photovoltaic)....
-
Performance evaluation of the parallel object tracking algorithm employing the particle filter
PublikacjaAn algorithm based on particle filters is employed to track moving objects in video streams from fixed and non-fixed cameras. Particle weighting is based on color histograms computed in the iHLS color space. Particle computations are parallelized with CUDA framework. The algorithm was tested on various GPU devices: a desktop GPU card, a mobile chipset and two embedded GPU platforms. The processing speed depending on the number...
-
Solar Photovoltaic Energy Optimization and Challenges
PublikacjaThe study paper focuses on solar energy optimization approaches, as well as the obstacles and concerns that come with them. This study discusses the most current advancements in solar power generation devices in order to provide a reference for decision-makers in the field of solar plant construction throughout the world. These technologies are divided into three groups: photovoltaic, thermal, and hybrid (thermal/photovoltaic)....
-
Interior Point Method Evaluation for Reactive Power Flow Optimization in the Power System
PublikacjaThe paper verifies the performance of an interior point method in reactive power flow optimization in the power system. The study was conducted on a 28 node CIGRE system, using the interior point method optimization procedures implemented in Power Factory software.
-
Optimization of Data Assignment for Parallel Processing in a Hybrid Heterogeneous Environment Using Integer Linear Programming
PublikacjaIn the paper we investigate a practical approach to application of integer linear programming for optimization of data assignment to compute units in a multi-level heterogeneous environment with various compute devices, including CPUs, GPUs and Intel Xeon Phis. The model considers an application that processes a large number of data chunks in parallel on various compute units and takes into account computations, communication including...
-
Parallel Programming for Modern High Performance Computing Systems
PublikacjaIn view of the growing presence and popularity of multicore and manycore processors, accelerators, and coprocessors, as well as clusters using such computing devices, the development of efficient parallel applications has become a key challenge to be able to exploit the performance of such systems. This book covers the scope of parallel programming for modern high performance computing systems. It first discusses selected and...
-
Optimization of Division and Reconfiguration Locations of the Medium-Voltage Power Grid Based on Forecasting the Level of Load and Generation from Renewable Energy Sources
PublikacjaThe article addresses challenges in optimizing the operation of medium voltage networks, emphasizing optimizing network division points and selecting the best network configuration for minimizing power and energy losses. It critically reviews recent research on the issue of network configuration optimization. The optimization of the medium voltage power grid reconfiguration process was carried out using known optimization tools....
-
OPTIMIZATION OF ENERGY CONVERSION IN GOLD NANOPARTICLES IRRADIATED BY LIGHT FOR SUSTAINABLE ENERGY APPLICATIONED BY LIGHT FOR SUSTAINABLE ENERGY APPLICATION
PublikacjaThis study investigates the optimization of light-to-heat conversion in gold nanoparticles under irradiation by continuous- and pulsed-wave laser sources. The conversion process relies on the absorption of electromagnetic energy and the subsequent generation of heat, a phenomenon that is integral to a variety of applications. The photothermal conversion model is based on the Rayleigh-Drude approximation, facilitating predictions...
-
Modeling and Simulation for Exploring Power/Time Trade-off of Parallel Deep Neural Network Training
PublikacjaIn the paper we tackle bi-objective execution time and power consumption optimization problem concerning execution of parallel applications. We propose using a discrete-event simulation environment for exploring this power/time trade-off in the form of a Pareto front. The solution is verified by a case study based on a real deep neural network training application for automatic speech recognition. A simulation lasting over 2 hours...
-
GPU-Accelerated 3D Mesh Deformation for Optimization Based on the Finite Element Method
PublikacjaThis paper discusses a strategy for speeding up the mesh deformation process in the design-byoptimization of high-frequency components involving electromagnetic field simulations using the 3D finite element method (FEM). The mesh deformation is assumed to be described by a linear elasticity model of a rigid body; therefore, each time the shape of the device is changed, an auxiliary elasticity finite-element problem must be solved....
-
Influence of YARN Schedulers on Power Consumption and Processing Time for Various Big Data Benchmarks
PublikacjaClimate change caused by human activities can influence the lives of everybody onthe planet. The environmental concerns must be taken into consideration by all fields of studyincludingICT. Green Computing aims to reduce negative effects of IT on the environment while,at the same time, maintaining all of the possible benefits it provides. Several Big Data platformslike Apache Spark orYARNhave become widely used in analytics and...
-
New Performance Indices for Power System Stabilizers
PublikacjaThe subject of the article is issues related to innovative indices for power system stabilizers (PSSs). These new indices will be able to quickly show which PSS (among many other PSSs) is not working properly and that advanced optimization and simulation methods should be used to improve the PSS settings. The authors note the fact that the acceptance requirements for PSSs are different in various power systems. Moreover, the authors...
-
Voltage and Reactive Power Load Flow Optimization in the Power System Using Fuzzy Logic
PublikacjaThe paper presents issues related to voltage control in the power system. An original method of reactive power flow optimization is considered, which leads to improved voltages in the power system and reduced active power losses. The optimization method is based on a procedure that employs fuzzy logic and is supported by a gradient search algorithm. The method has been implemented in PLANS software and verified.
-
Survey of Methodologies, Approaches, and Challenges in Parallel Programming Using High-Performance Computing Systems
PublikacjaThis paper provides a review of contemporary methodologies and APIs for parallel programming, with representative technologies selected in terms of target system type (shared memory, distributed, and hybrid), communication patterns (one-sided and two-sided), and programming abstraction level. We analyze representatives in terms of many aspects including programming model, languages, supported platforms, license, optimization goals,...
-
Efficient parallel algorithms in global optimization of potential energy functions for peptides, proteins, and crystals
Publikacja -
Teaching High–performance Computing Systems – A Case Study with Parallel Programming APIs: MPI, OpenMP and CUDA
PublikacjaHigh performance computing (HPC) education has become essential in recent years, especially that parallel computing on high performance computing systems enables modern machine learning models to grow in scale. This significant increase in the computational power of modern supercomputers relies on a large number of cores in modern CPUs and GPUs. As a consequence, parallel program development based on parallel thinking has become...
-
Modular power converter topologies for energy storage and electric power distribution systems
PublikacjaThis paper describes selected issues concerning realization of energy storage system (ESS) designed to operate in power distribution system. In order to achieve scalability of the system a modular approach is proposed. In addition to this different configuration of the system are analyzed, where depending on requirements and application a scalability in power, in energy capacity of energy storage resource and both in power and...
-
Optimization of parallel implementation of UNRES package for coarse‐grained simulations to treat large proteins
PublikacjaWe report major algorithmic improvements of the UNRES package for physics-based coarse-grained simulations of proteins. These include (i) introduction of interaction lists to optimize computations, (ii) transforming the inertia matrix to a pentadiagonal form to reduce computing and memory requirements, (iii) removing explicit angles and dihedral angles from energy expressions and recoding the most time-consuming energy/force terms...
-
Optimization of Nuclear Power Share in the Structure of Electricity Production in Poland in Time Perspective by 2060
PublikacjaThe author of this paper presented the results of a system analysis using MARKAL model, aiming at the optimization of nuclear power share in power generation structure in Poland in time perspective by 2060. Optimization criterion is the minimization of the objective function, i.e. the total cost of energy system, taking into account constraints related to CO2, SOx and NOx emissions and obligatory shares of electricity from renewable...
-
Performance and Power-Aware Modeling of MPI Applications for Cluster Computing
PublikacjaThe paper presents modeling of performance and power consumption when running parallel applications on modern cluster-based systems. The model includes basic so-called blocks representing either computations or communication. The latter includes both point-to-point and collective communication. Real measurements were performed using MPI applications and routines run on three different clusters with both Infiniband and Gigabit Ethernet...
-
Runtime Visualization of Application Progress and Monitoring of a GPU-enabled Parallel Environment
PublikacjaThe paper presents design, implementation and real life uses of a visualization subsystem for a distributed framework for parallelization of workflow-based computations among clusters with nodes that feature both CPUs and GPUs. Firstly, the proposed system presents a graphical view of the infrastructure with clusters, nodes and compute devices along with parameters and runtime graphs of load, memory available, fan speeds etc. Secondly,...
-
Parallel implementation of the DGF-FDTD method on GPU Using the CUDA technology
PublikacjaThe discrete Green's function (DGF) formulation of the finite-difference time-domain method (FDTD) is accelerated on a graphics processing unit (GPU) by means of the Compute Unified Device Architecture (CUDA) technology. In the developed implementation of the DGF-FDTD method, a new analytic expression for dyadic DGF derived based on scalar DGF is employed in computations. The DGF-FDTD method on GPU returns solutions that are compatible...
-
Design and Performance Evaluation of the Energy Subsystem of a Hybrid Light andWave Energy Harvester
PublikacjaThe paper presents the design and performance of an energy subsystem (ES) dedicated to hybrid energy harvesters (HEHs): wave energy converters (WECs) combined with photovoltaic panels (PVPs). The considered ES is intended for compact HEHs powering autonomous end-node devices in distributed IoT networks. The designed ES was tested experimentally and evaluated in relation to the mobile and wireless distributed communication use case....
-
Optimization of using recuperative braking energy on a double-track railway line
PublikacjaIn the introduction, possible ways of reusing energy from recuperation are presented. Next, the paper investigates the possibility of using regenerative braking in the range allowed by the detailed timetable by adopting the method of transferring the recovered electric energy directly to the catenary and immediate use of this energy by another train at the same power section. In the main part of the work, it is shown, that the...
-
Experimental Research on the Energy Efficiency of a Parallel Hybrid Drive for an Inland Ship
PublikacjaThe growing requirements for limiting the negative impact of all modes of transport on the natural environment mean that clean technologies are becoming more and more important. The global trend of e-mobility also applies to sea and inland water transport. This article presents the results of experimental tests carried out on a life-size, parallel diesel-electric hybrid propulsion system. The eciency of the propulsion system was...
-
Voltage control in a power system with renewable sources of energy
PublikacjaIntensive development of distributed generation in power systems, caused by the European Union energy policy, gives possibility for improving safety in power delivery as well as optimizing the costs of the systems functioning. In this context, distributed generation can be used for voltage control in power systems – it can be performed by the control of reactive power of each source of energy or a group of energy sources. This...
-
Performance Assessment of Using Docker for Selected MPI Applications in a Parallel Environment Based on Commodity Hardware
PublikacjaIn the paper, we perform detailed performance analysis of three parallel MPI applications run in a parallel environment based on commodity hardware, using Docker and bare-metal configurations. The testbed applications are representative of the most typical parallel processing paradigms: master–slave, geometric Single Program Multiple Data (SPMD) as well as divide-and-conquer and feature characteristic computational and communication...
-
Generalized regression neural network and fitness dependent optimization: Application to energy harvesting of centralized TEG systems
PublikacjaThe thermoelectric generator (TEG) system has attracted extensive attention because of its applications in centralized solar heat utilization and recoverable heat energy. The operating efficiency of the TEG system is highly affected by operating conditions. In a series-parallel structure, due to diverse temperature differences, the TEG modules show non-linear performance. Due to the non-uniform temperature distribution (NUTD) condition,...
-
Performance Evaluation of the Parallel Codebook Algorithm for Background Subtraction in Video Stream
PublikacjaA background subtraction algorithm based on the codebook approach was implemented on a multi-core processor in a parallel form, using the OpenMP system. The aim of the experiments was to evaluate performance of the multithreaded algorithm in processing video streams recorded from monitoring cameras, depending on a number of computer cores used, method of task scheduling, image resolution and degree of image content variability....