This article examines the significant challenges encountered in implementing sharding within distributed replication systems. It identifies the impediments of achieving consensus among large participant sets, leading to scalability, throughput, and performance limitations. These issues primarily arise due to the message complexity inherent in consensus mechanisms. In response, we investigate the potential of sharding to mitigate these challenges, analyzing current implementations within distributed replication systems. Additionally, we offer a comprehensive review of replication systems, encompassing both classical distributed databases as well as Distributed Ledger Technologies (DLTs) employing sharding techniques. Through this analysis, the article aims to provide insights into addressing the scalability and performance concerns in distributed replication systems.
Frédéric Hecht, Sidi-Mahmoud Kaber, Lucas Perrin
et al.
In this work, we consider a rational approximation of the exponential function to design an algorithm for computing matrix exponential in the Hermitian case. Using partial fraction decomposition, we obtain a parallelizable method, where the computation reduces to independent resolutions of linear systems. We analyze the effects of rounding errors on the accuracy of our algorithm. We complete this work with numerical tests showing the efficiency of our method and a comparison of its performances with Krylov algorithms.
With the release of the Apple Silicon System-on-a-Chip processors, and the impressive performance shown in general use by both the M1 and M1 Ultra, the potential use for Apple Silicon processors in scientific computing is explored. Both the M1 and M1 Ultra are compared to current state-of-the-art data-center GPUs, including an NVIDIA V100 with PCIe, an NVIDIA V100 with NVLink, and an NVIDIA A100 with PCIe. The scientific performance is measured using the Scalable Heterogeneous Computing (SHOC) benchmark suite using OpenCL benchmarks. We find that both M1 processors outperform the GPUs in all benchmarks.
In this paper, we show how different types of distributed mutual algorithms can be compared in terms of performance through simulations. A simulation-based approach is presented, together with an overview of the relevant evaluation metrics and approach for statistical processing of the results. The presented simulations can be used to learn master students of a course on distributed software the basics of algorithms for distributed mutual exclusion, together with how to properly conduct a detailed comparison study. Finally, a related work section is provided with relevant use cases where distributed mutual exclusion algorithm can be beneficial.
Growing power dissipation due to high performance requirement of processor suggests multicore processor technology, which has become the technology for present and next decade. Research advocates asymmetric multi-core processor system for better utilization of chip real state. However, asymmetric multi core architecture poses a new challenge to operating system scheduler, which traditionally assumes homogeneous hardware. So, scheduling threads to core has become a major issue to operating system kernel. In this paper, proposed scheduling algorithms for asymmetric multicore processors have been categorized. This paper explores some representative algorithms of these classes to get an overview of scheduling algorithms for asymmetric multicore system.
Fast Abstracts are short presentations of work in progress or opinion pieces and aim to serve as a rapid and flexible mechanism to (i) Report on current work that may or may not be complete; (ii) Introduce new ideas to the community; (iii) State positions on controversial issues or open problems. Student Forum is a vibrant and friendly environment where students can present their work, exchange ideas and experiences, get feedback on their work, get new inspirations and points of view. In addition, the forum stimulates interaction between young researchers, experienced researchers, and industry.
This research presents a model of a complex dynamic object running on a multi-core system. Discretization and numerical integration for multibody models of vehicle rail elements in the vertical longitudinal plane fluctuations is considered. The implemented model and solution of the motion differential equations allow estimating the basic processes occurring in the system with various external influences. Hence the developed programming model can be used for performing analysis and comparing new vehicle designs. Keywords-dynamic model; multi-core system; SMP system; rolling stock.
Networks protocols are the heart of communication networks. An efficient network protocol does maximum utilization of the underlying network capabilities. Network Protocol synthesis is the process of synthesizing or deriving network specific protocols from the requirements of a given specific network. In this report, we present a step-by-step approach for the automated synthesis of network protocols from the network specifications. Using SMT solvers to automate the protocol generation is the key idea behind the presented synthesis approach. The protocols generated using this approach followed the most optimal way of data transmission for the given network requirements.
This article presents a new high-level parallel computational model named BSF - Bulk Synchronous Farm. The BSF model extends the BSP model to deal with the compute-intensive iterative numerical methods executed on distributed-memory multiprocessor systems. The BSF model is based on the master-worker paradigm and the SPMD programming model. The BSF model makes it possible to predict the upper scalability bound of a BSF-program with great accuracy. The BSF model also provides equations for estimating the speedup and parallel efficiency of a BSF-program.
Mads R. B. Kristensen, Simon A. F. Lund, Troels Blum
et al.
We address the problem of fusing array operations based on criteria such as shape compatibility, data reusability, and communication. We formulate the problem as a graph partition problem that is general enough to handle loop fusion, combinator fusion, and other types of subroutines.
All modern processors include a set of vector instructions. While this gives a tremendous boost to the performance, it requires a vectorized code that can take advantage of such instructions. As an ideal vectorization is hard to achieve in practice, one has to decide when different instructions may be applied to different elements of the vector operand. This is especially important in implicit vectorization as in NVIDIA CUDA Single Instruction Multiple Threads (SIMT) model, where the vectorization details are hidden from the programmer. In order to assess the costs incurred by incompletely vectorized code, we have developed a micro-benchmark that measures the characteristics of the CUDA thread divergence model on different architectures focusing on the loops performance.
This paper presents a parallel genetic algorithm for generalised vertex cover problem (GVCP) using Hadoop Map-Reduce framework. The proposed Map-Reduce implementation helps to run the genetic algorithm for generalized vertex cover problem (GVCP) on multiple machines parallely and computes the solution in relatively short time.
There is no existence of dedicated simulators on the Internet that studies the impact of load balancing principles of the cloud architectures. Request Assignment Simulator (RAS) is a customizable, visual tool that helps to understand the request assignment to the resources based on the load balancing principles. We have designed this simulator to fit into Infrastructure as a Service (IaaS) cloud model. In this paper, we present a working manual useful for the conduct of experiment with RAS. The objective of this paper is to instill the user to understand the pertinent parameters in the cloud, their metrics, load balancing principles, and their impact on the performance.
In this paper, the main aim is to exhibit swarm intelligence power in cloud based scenario. Heterogeneous environment has been configured at server-side network of the whole cloud network. In the proposed system, different types of servers are being used to manage useful assorted atmosphere. Swarm intelligence has been adopted for enhancing the performance of overall system network. Specific location at server-side of the network is going to be selected by the swarm intelligence concept for accessing desired elements. Flexibility, robustness and self-organization, which are to be considered at the time of designing the system environment, are the main features of swarm intelligence.
Bertrand Ducourthial, Sofiane Khalfallah, Franck Petit
We propose a group membership service for dynamic ad hoc networks. It maintains as long as possible the existing groups and ensures that each group diameter is always smaller than a constant, fixed according to the application using the groups. The proposed protocol is self-stabilizing and works in dynamic distributed systems. Moreover, it ensures a kind of continuity in the service offer to the application while the system is converging, except if too strong topology changes happen. Such a best effort behavior allows applications to rely on the groups while the stabilization has not been reached, which is very useful in dynamic ad hoc networks.