the proceedings contain 35 papers. the topics discussed include: signature-free communication and agreement in the presence of byzantine processes;dynamic reconfiguration: a tutorial;time to change: on distributed com...
ISBN:
(纸本)9783939897989
the proceedings contain 35 papers. the topics discussed include: signature-free communication and agreement in the presence of byzantine processes;dynamic reconfiguration: a tutorial;time to change: on distributedcomputing in dynamic networks;space bounds for reliable storage: fundamental limits of coding;approximation of distances and shortest paths in the broadcast congest clique;the cost of global broadcast in dynamic radio networks;bounds for blind rate adaptation;overcoming obstacles with ants;distributed sparse cut approximation;distributed approximation of k-service assignment;the relative power of composite loop agreement tasks;loosely-stabilizing leader election on arbitrary graphs in population protocols without identifiers nor random numbers;and a heap-based concurrent priority queue with mutable priorities for faster parallel algorithms.
In this paper, a parallel loop self-scheduling scheme for heterogeneous PC cluster systems is proposed. though the proposed scheme does allow users to choose parameters before the execution initialization phase, there...
详细信息
Internet of things is a rapidly growing industry, and there are more connected devices than humans. there are unlimited internet of things devices around us. the scope of these devices has increased manifold in recent...
详细信息
ISBN:
(纸本)9781665400916
Internet of things is a rapidly growing industry, and there are more connected devices than humans. there are unlimited internet of things devices around us. the scope of these devices has increased manifold in recent years in different areas like healthcare, unmanned vehicles, automatic monitoring systems, and smart homes, etc. these connected devices produce lots of data that need to be processed to achieve the goal of automation in daily life. the cloud provides many centralized solutions to process data using powerful resources in real-time, but there could be latency issues due to increased network traffic. So a distributed solution is much needed to meet this growing demand of processing data in parallel. In this paper, we propose a distributed shared memory [18] abstraction for the internet of things that uses a graph-aware partitioning algorithm and uses smart message passing techniques to process data in distributed and parallel fashion [19].
this paper introduces FLEX-MPI, a novel runtime approach for the dynamic load balancing of MPI-based SPMD applications running on heterogeneous platforms in the presence of dynamic external loads. To effectively balan...
详细信息
ISBN:
(纸本)9783642400476
this paper introduces FLEX-MPI, a novel runtime approach for the dynamic load balancing of MPI-based SPMD applications running on heterogeneous platforms in the presence of dynamic external loads. To effectively balance the workload, FLEX-MPI monitors the actual performance of applications via hardware counters and the MPI profiling interface-with a negligible overhead and minimal code modifications. Our results show that by using this approach the execution time of an application may be significantly reduced.
distributed heterogeneous computingsystems escalate the problem of choosing the appropriate programming model. Programming models such as message passing are efficient but require low-level management of communicatio...
详细信息
ISBN:
(纸本)9783030715939;9783030715922
distributed heterogeneous computingsystems escalate the problem of choosing the appropriate programming model. Programming models such as message passing are efficient but require low-level management of communications. Higher level of programming such as shared memory are convenient for the application design but they usually have performance issues. Withthe recent development of distributed heterogeneous systems and new protocols to access remote memories, there is an opportunity for distributed shared memory systems to offer a satisfying level of abstraction while not giving up on performance. In this paper a video processing application is written using MPI, 0MQ and an in-house software-distributed shared memory (S-DSM) backend and deployed over a set of heterogeneous computing boards. Results show that 0MQ implementation is the most efficient but at the price of writing the application withthe targeted platform in mind. the S-DSM implementation runs up to 2 times faster than the pure OpenMPI implementation and competes with 0MQ when the data granularity is small.
We present an approach for enabling a distributed anonymization process over large collections of sensor data. Our approach anonymizes large datasets (which might not fit in main memory) using an arbitrary number of w...
详细信息
ISBN:
(纸本)9781665404242
We present an approach for enabling a distributed anonymization process over large collections of sensor data. Our approach anonymizes large datasets (which might not fit in main memory) using an arbitrary number of workers within the Spark framework. We describe how to parallelize the anonymization process through a proper partitioning of the dataset. Our experimental evaluation shows that the proposed approach is scalable and do not affect the quality of the anonymized dataset.
thread-throttling and mapping strategies have been used together to make better use of hardware resources and improve the energy-delay product (EDP) of high-performance computing (HPC) systems. However, the design spa...
详细信息
ISBN:
(纸本)9781665414555
thread-throttling and mapping strategies have been used together to make better use of hardware resources and improve the energy-delay product (EDP) of high-performance computing (HPC) systems. However, the design space exploration significantly grows withthe increasing number of cores in those systems, making the task of finding the ideal number of active threads and allocating strategy a challenging task. On top of that, parallel applications present various patterns, such as irregularity, unbalanced computations, or high rates of communications. Given these considerations, we propose ETTM, an EDP-aware thread-throttling and mapping optimization strategy that automatically finds an ideal combination of number of threads and thread mapping strategy. Withthe execution of eighteen well-known benchmarks on three multicore architectures, we show that EDP can be significantly improved when running applications withthe solution found by EETM1 .
Managing continuously changing requirements is adifficult and time consuming task in large projects. Change management if not done properly often leads toproject failure. Requirement Change Management (RCM) process mo...
详细信息
ISBN:
(纸本)9780889867307
Managing continuously changing requirements is adifficult and time consuming task in large projects. Change management if not done properly often leads toproject failure. Requirement Change Management (RCM) process models are surveyed and evaluated on the criteria of roles, activities, artifacts and representation which are fundamental and necessary for a good process model. this evaluation is extended to update the work already done in literature. the deficiencies present in current RCM literature are highlighted. the ontology for process model has already been proposed elsewhere. Using that ontology we propose an RCM process model in this paper. this RCM process model improves upon the deficiencies identified, and it also introduces some new concepts. the process is modeled using UML activity diagram. the purpose of the process model is to provide a more complete and detailed guideline than already present. It will help the practitioners to effectively manage requirement change in large projects.
the proceedings contain 165 papers. the topics discussed include: minimum energy control of positive electrical circuits;a PSO-optimized type-2 fuzzy logic controller for navigation of multiple mobile robots;integrate...
ISBN:
(纸本)9781479950812
the proceedings contain 165 papers. the topics discussed include: minimum energy control of positive electrical circuits;a PSO-optimized type-2 fuzzy logic controller for navigation of multiple mobile robots;integrated phases modular fuzzy logic control with spiral dynamic optimization for stair descending in a wheelchair;development of a therapeutic exercise robot for wrist and forearm rehabilitation;dynamic model and analysis of distributed control system algorithms of three wheel vehicle;modelling and simulation of a surge arrester in the physical domain;heuristic to tune the compensation gain of modeling uncertainties through the robust multi inversion;time-varying IIR multi-notch filter based on all-pass filter prototype;paralleldistributed downsampled spatio-temporal track-before-detect algorithm;improved fractional Kalman filter for variable order systems with lossy and delayed network;and modeling and identification of a fractional-order discrete-time SISO Laguerre-Wiener system.
Two new distributed speed advisory systems (SASs) are introduced in this paper. the systems implement consensus algorithms that guide a set of vehicles toward a common driving speed. A major innovation is that consens...
详细信息
Two new distributed speed advisory systems (SASs) are introduced in this paper. the systems implement consensus algorithms that guide a set of vehicles toward a common driving speed. A major innovation is that consensus is achieved over a multi-layer network, in which parallel network topologies of connected vehicles are superimposed. the reason for the use of these parallel networks is that, in this way, the state obfuscation is possible, withthe benefit that common driving speed is attained with no vehicle knowing the exact state of other vehicles. Convergence of the SASs is formally proved and two new results for the consensus of multi-layer networks modeled via stochastic differential equations are introduced. the SASs are also validated via simulation and via a hardware-in-the-loop setup, in which a real vehicle interacts with simulated entities.
暂无评论