An Experimental Analysis of a New Interval-Based Mutation Operator

2015 ◽  
Vol 14 (03) ◽  
pp. 1550018 ◽  
Author(s):  
K. Liagkouras ◽  
K. Metaxiotis
Keyword(s):  
Experimental Analysis ◽  
Pareto Front ◽  
Computational Experiments ◽  
Coarse Grained ◽  
Mutation Operator ◽  
Fine Grained ◽  
Initial Stage ◽  
Speed Up ◽  
Better Than

In this paper, we present a novel Interval-Based Mutation (IBMU) operator. The proposed mutation operator is performing coarse-grained search at initial stage in order to speed up convergence toward more promising regions of the search landscape. Then, more fine-grained search is performed in order to guide the solutions towards the Pareto front. Computational experiments indicate that the proposed mutation operator performs better than conventional approaches for solving several well-known benchmarking problems.

APPLICATION OF NOVEL CLONAL ALGORITHM IN MULTIOBJECTIVE OPTIMIZATION

2010 ◽  
Vol 09 (02) ◽  
pp. 239-266 ◽  
Author(s):  
JIANYONG CHEN ◽  
QIUZHEN LIN ◽  
QINGBIN HU
Keyword(s):  
Multiobjective Optimization ◽  
Coarse Grained ◽  
Pareto Optimal ◽  
Pareto Optimal Front ◽  
Fine Grained ◽  
Initial Stage ◽  
Speed Up ◽  
Main Notion ◽  
Hybrid Mutation Operator ◽  
Cooling Schedule

In this paper, a novel clonal algorithm applied in multiobjecitve optimization (NCMO) is presented, which is designed from the improvement of search operators, i.e. dynamic mutation probability, dynamic simulated binary crossover (D-SBX) operator and hybrid mutation operator combining with Gaussian and polynomial mutations (GP-HM) operator. The main notion of these approaches is to perform more coarse-grained search at initial stage in order to speed up the convergence toward the Pareto-optimal front. Once the solutions are getting close to the Pareto-optimal front, more fine-grained search is performed in order to reduce the gaps between the solutions and the Pareto-optimal front. Based on this purpose, a cooling schedule is adopted in these approaches, reducing the parameters gradually to a minimal threshold, the aim of which is to keep a desirable balance between fine-grained search and coarse-grained search. By this means, the exploratory capabilities of NCMO are enhanced. When compared with various state-of-the-art multiobjective optimization algorithms developed recently, simulation results show that NCMO has remarkable performance.

scholarly journals Balanced Sparsity for Efficient DNN Inference on GPU

2019 ◽  
Vol 33 ◽  
pp. 5676-5683 ◽  
Author(s):  
Zhuliang Yao ◽  
Shijie Cao ◽  
Wencong Xiao ◽  
Chen Zhang ◽  
Lanshun Nie
Keyword(s):  
Deep Neural Networks ◽  
General Purpose ◽  
Coarse Grained ◽  
Efficient Computation ◽  
Model Accuracy ◽  
Sparse Model ◽  
Model Inference ◽  
Fine Grained ◽  
Practical Inference ◽  
Speed Up

In trained deep neural networks, unstructured pruning can reduce redundant weights to lower storage cost. However, it requires the customization of hardwares to speed up practical inference. Another trend accelerates sparse model inference on general-purpose hardwares by adopting coarse-grained sparsity to prune or regularize consecutive weights for efficient computation. But this method often sacrifices model accuracy. In this paper, we propose a novel fine-grained sparsity approach, Balanced Sparsity, to achieve high model accuracy with commercial hardwares efficiently. Our approach adapts to high parallelism property of GPU, showing incredible potential for sparsity in the widely deployment of deep learning services. Experiment results show that Balanced Sparsity achieves up to 3.1x practical speedup for model inference on GPU, while retains the same high model accuracy as finegrained sparsity.

Efficient parallelization of perturbative Monte Carlo QM/MM simulations in heterogeneous platforms

2016 ◽  
Vol 31 (6) ◽  
pp. 499-516 ◽  
Author(s):  
Sebastião Miranda ◽  
Jonas Feldt ◽  
Frederico Pratas ◽  
Ricardo A Mata ◽  
Nuno Roma ◽  
...  
Keyword(s):  
Monte Carlo ◽  
Heterogeneous Systems ◽  
Coarse Grained ◽  
Molecular Systems ◽  
Fine Grained ◽  
Central Processing ◽  
Speed Up ◽  
Graphical Processing ◽  
Computational Bottleneck ◽  
The Cost

A novel perturbative Monte Carlo mixed quantum mechanics (QM)/molecular mechanics (MM) approach has been recently developed to simulate molecular systems in complex environments. However, the required accuracy to efficiently simulate such complex molecular systems is usually granted at the cost of long executing times. To alleviate this problem, a new parallelization strategy of multi-level Monte Carlo molecular simulations is herein proposed for heterogeneous systems. It simultaneously exploits fine-grained (at the data level), coarse-grained (at the Markov chain level) and task-grained (pure QM, pure MM and QM/MM procedures) parallelism to ensure an efficient execution in heterogeneous systems composed of central processing units and multiple and possibly different graphical processing units. This is achieved by making use of the OpenCL library, together with appropriate dynamic load balancing schemes. From the conducted evaluation with real benchmarking data, a speed-up of 56x in the computational bottleneck part was observed, which results in a global speed-up of 38x for the whole simulation, reducing the time of a typical simulation from 80 hours to only 2 hours.

Study of Fine-grained Nested Parallelism in CDCL SAT Solvers

2021 ◽  
Vol 8 (3) ◽  
pp. 1-18
Author(s):  
James Edwards ◽  
Uzi Vishkin
Keyword(s):  
Computer Architecture ◽  
Coarse Grained ◽  
Future Research ◽  
Sat Solvers ◽  
Fine Grained ◽  
Nested Parallelism ◽  
Clause Learning ◽  
Speed Up ◽  
Fine Grained Parallelism ◽  
Problem Instances

Boolean satisfiability (SAT) is an important performance-hungry problem with applications in many problem domains. However, most work on parallelizing SAT solvers has focused on coarse-grained, mostly embarrassing, parallelism. Here, we study fine-grained parallelism that can speed up existing sequential SAT solvers, which all happen to be of the so-called Conflict-Directed Clause Learning variety. We show the potential for speedups of up to 382× across a variety of problem instances. We hope that these results will stimulate future research, particularly with respect to a computer architecture open problem we present.

Experimental Study of the Mechanical Behavior of Materials under Transient Regimes of Superplastic Deforming

2012 ◽  
Vol 735 ◽  
pp. 232-239 ◽  
Author(s):  
Olga I. Bylya ◽  
Rudolf Vasin ◽  
Peter Chistyakov ◽  
Anatoly Muravlev
Keyword(s):  
Mechanical Properties ◽  
Experimental Study ◽  
Experimental Analysis ◽  
Constitutive Equations ◽  
Superplastic Deformation ◽  
Coarse Grained ◽  
Stress Strain ◽  
Transient Regimes ◽  
Initial Stage ◽  
Microstructure Of The Material

Transient regimes of deforming are always present in any technological process and can be taken into account and used more widely if properly studied. The behavior of the materials under such regimes is becoming even more interesting if initial microstructure is coarse grained and undergoes transformation in the process of deforming. One of the transient processes which happen in any Superplastic deformation is the initial stage of loading, before steady superplastic flow starts. Initial parts of stress-strain curves during superplastic deformation are not frequently studied experimentally but provide very important information about mechanical properties of material. They are also necessary for development and verification of the constitutive equations. The results of experimental analysis of the behaviour of titanium alloys under superplastic conditions at the initial stages of loading and also under unloading are presented here. Another type of transient regimes of deforming is represented by the strain rate jumps. In such kind of experiments if the amplitudes of the jumps are big enough, the shifts of the corresponding parts of the stress-strain curves about the basic ones (hardening or softening) can be observed depending on the amplitude of the jump and microstructure of the material. Some experimental results related to this effect are discussed in this paper. The applicability of some constitutive equations for description of the observed results is discussed. The necessity of involving visco-elastic properties of material for proper description of its behavior in some regimes of deforming is also mentioned.

scholarly journals A Strategy of Data Synchronization in Distributed System with Read Separating from Write

2020 ◽  
Vol 38 (1) ◽  
pp. 209-215 ◽  
Author(s):  
Jintao Gao ◽  
Wenjie Liu ◽  
Zhanhuai Li
Keyword(s):  
Main Idea ◽  
Distributed Database ◽  
Coarse Grained ◽  
Data Synchronization ◽  
Space Utilization ◽  
Relation Database ◽  
Fine Grained ◽  
Network Cost ◽  
Nosql Database ◽  
Better Than

Read separating from write is a strategy that NewSQL adopts to incorporate the advantages of traditional relation database and NoSQL database. Under this architecture, baseline data is split into multiple partitions stored at distributed physical nodes, while delta data is stored at single transaction node. For reducing the pressure of transaction node and improving the query performance, delta data needs to be synchronized into storage nodes. The current strategies trigger the procedure of data synchronization per partition, meaning that unchanged partitions will also participate in data synchronization, which consumes extra network cost, local IO and space resources. For improving the efficiency of data synchronization meanwhile mitigating space utilization, the fine-grained data synchronization strategy is proposed, whose main idea includes that fine-grained logical partitions upon original coarse-grained partitions is established, providing more correct synchronized unit; the delta data sensing strategy is introduced, which records the mapping between changed partitions and its delta data; instead of partition driven, the data synchronization through the delta-broadcasting mechanism is driven, constraining that only changed partitions can participate in data synchronization. The fine-grained data synchronization strategy on Oceanbase is implemented, which is a distributed database with read separating from write, and the results show that our strategy is better than other strategies in efficiency of data synchronizing and space utilization.

scholarly journals Experimental Study on the Self-Healing Behavior of Fractured Rocks Induced by Water-CO2-Rock Interactions in the Shendong Coalfield

Geofluids ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Jinfeng Ju ◽  
Quansheng Li ◽  
Jialin Xu
Keyword(s):  
Clay Minerals ◽  
Water Permeability ◽  
Fractured Rocks ◽  
The Self ◽  
Coarse Grained ◽  
Ionic Exchange ◽  
Self Healing ◽  
Rock Interaction ◽  
Fine Grained ◽  
Initial Stage

This study experimentally investigated the self-healing behavior, referring to the naturally occurring water permeability decrease, of fractured rocks exposed to water-CO2-rock interaction (WCRI). The experiment was conducted on prefractured specimens of three rock types typical of the Shendong coalfield: coarse-grained sandrock, fine-grained sandrock, and sandy mudrock. During the experiment, which ran for nearly 15 months, all three specimens exhibited decreasing permeabilities. The coarse- and fine-grained sandrock specimens exhibited smooth decreases in permeability, with approximately parallel permeability time curves, whereas that of the sandy mudrock specimen decreased rapidly during the initial stage and slowly during later stages. The sandrock specimens were rich in feldspars, which were dissolved and/or corroded and involved in ionic exchange reactions with CO2 and groundwater, thereby generating secondary minerals (such as kaolinite, quartz, and sericite) or CaSO4 sediments. These derivative matters adhered to the fracture surface, thereby gradually repairing fractures and decreasing the water permeability of the fractured rocks. In comparison, the sandy mudrock had a high content of clay minerals, and the water-rock interaction caused rapid expansions of illite, mixed illite-smectite, and other clay minerals, thereby narrowing the fractures and causing the rapid permeability decrease during the initial stage. In later stages, the derivative matters generated by the dissolution and/or corrosion of feldspars and other aluminum silicate minerals in the mudrock filled and sealed the fractures, causing the slow permeability decreases during the later stages, as in the sandrock specimens. Neutral and basic groundwater conditions facilitated better self-healing of fractured mudrocks rich in clay minerals, whereas acidic groundwater conditions and the presence of CO2 facilitated better self-healing of fractured sandrocks. Thus, this study’s results are of significant value to aquifer restoration efforts in the Shendong coalfield and other ecologically vulnerable mining areas.

scholarly journals Microstructure of Plasma Nitrided AISI420 Martensitic Stainless Steel at 673 K

Crystals ◽  
2019 ◽  
Vol 9 (2) ◽  
pp. 60 ◽  
Author(s):  
Tatsuhiko Aizawa ◽  
Tomoaki Yoshino ◽  
Kazuo Morikawa ◽  
Sho-Ichiro Yoshihara
Keyword(s):  
Stainless Steel ◽  
Martensitic Stainless Steel ◽  
Nitrided Layer ◽  
Nitrogen Concentration ◽  
Coarse Grained ◽  
Two Phase ◽  
Fine Grained ◽  
Chromium Nitrides ◽  
Initial Stage ◽  
Highly Strained

Martensitic stainless steel type AISI420 was plasma nitrided at 673 K for 3.6 ks to investigate the initial stage of the nitrogen supersaturation process without the formation of iron and chromium nitrides. SEM-EDX, electron back-scattering diffraction (EBSD), and TEM analyses were utilized to characterize the microstructure of the nitrided layer across the nitriding front end. The original coarse-grained, fully martensitic microstructure turned to be α’- γ two phase and fine-grained by high nitrogen concentration. Below this homogeneously nitrided layer, α’-grains were modified in geometry to be aligned along the plastic slip lines together with the α’ to γ-phase transformation at these highly strained zones. Most of these α’-grains in the two-phase microstructure had a nano-laminated structure with the width of 50 nm.

A framework for scheduling IoT application jobs on fog computing infrastructure based on QoS parameters

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Mandeep Kaur ◽  
Rajinder Sandhu ◽  
Rajni Mohana
Keyword(s):  
Fog Computing ◽  
Physical Distance ◽  
Coarse Grained ◽  
Content Type ◽  
Fine Grained ◽  
Specific Category ◽  
Qos Parameters ◽  
Bayes Algorithm ◽  
Better Than

Purpose The purpose of this study is to verify that if applications categories are segmented and resources are allocated based on their specific category, how effective scheduling can be done?. Design/methodology/approach This paper proposes a scheduling framework for IoT application jobs, based upon the Quality of Service (QoS) parameters, which works at coarse grained level to select a fog environment and at fine grained level to select a fog node. Fog environment is chosen considering availability, physical distance, latency and throughput. At fine grained (node selection) level, a probability triad (C, M, G) is anticipated using Naïve Bayes algorithm which provides probability of newly submitted application job to fall in either of the categories Compute (C) intensive, Memory (M) intensive and GPU (G) intensive. Findings Experiment results showed that the proposed framework performed better than traditional cloud and fog computing paradigms. Originality/value The proposed framework combines types of applications and computation capabilities of Fog computing environment, which is not carried out to the best of knowledge of authors.

scholarly journals Distributed Rendering Based on Fine-Grained and Coarse-Grained Strategy to Speed up Time and Increase Efficiency of Rendering Process

2019 ◽  
Vol 10 (1) ◽  
pp. 15
Author(s):  
Melki Sadekh Mansuan ◽  
Benfano Soewito
Keyword(s):  
Performance Metrics ◽  
Descriptive Analysis ◽  
Coarse Grained ◽  
Primary Data ◽  
Computer Laboratory ◽  
Fine Grained ◽  
Parallel Performance ◽  
Parallel Decomposition ◽  
Speed Up ◽  
Distributed Rendering

The purpose of this research was to solve several problems in the rendering process such as slow rendering time and complex calculations, which caused inefficient rendering. This research analyzed the efficiency in the rendering process. This research was an experimental study by implementing a distributed rendering system with fine-grained and coarse-grained parallel decomposition in computer laboratory. The primary data used was the rendering time obtained from the rendering process of three scenes animation. Descriptive analysis method was used to compare performance using speedup and efficiency of parallel performance metrics. The results show that the distributed rendering method succeeds in increasing the rendering speed with speedup value of 9,43. Moreover, the efficiency of processor use is 94% when it is applied to solve the problem of slow rendering time in the rendering process.

Sign in / Sign up

Export Citation Format

Share Document