In this paper, the author presents a simple and fast C++ thread pool implementation capable of running task graphs. The implementation is publicly available on GitHub, see https://github.com/dpuyda/scheduling.
${\cal A}_\mathsf{deg}$ is a self-stabilizing algorithm that computes a maximal independent set in a finite graph with approximation ratio $(Δ+ 2)/3$. In this note we show that under the central scheduler the number of moves of ${\cal A}_\mathsf{deg}$ is not bounded by a polynomial in $n$.
Safe memory reclamation (SMR) schemes for concurrent data structures offer trade-offs between three desirable properties: ease of integration, robustness, and applicability. In this paper we rigorously define SMR and these three properties, and we present the ERA theorem, asserting that any SMR scheme can only provide at most two of the three properties.
A survey is given of approaches to the problem of distributed consensus, focusing particularly on methods based on cellular automata and related systems. A variety of new results are given, as well as a history of the field and an extensive bibliography. Distributed consensus is of current relevance in a new generation of blockchain-related systems.
Collection of manuscripts accepted for presentation at the Student Forum and Fast Abstracts tracks of the 17th European Dependable Computing Conference (EDCC 2021).
The rat dentate gyrus is unusual among mammalian brain regions in that it shows cell birth well into adulthood. During development, dentate gyrus cell birth is regulated by adrenal steroids. However, it is presently unknown whether cell division in the adult is also mediated by these same factors. In order to determine whether this is the case, we combined adrenalectomy, with or without corticosterone (CORT) replacement, and 3H-thymidine autoradiography, Nissl staining, and immunohistochemistry for the glial cell markers vimentin and glial fibrillary acidic protein (GFAP) as well as for the neuronal marker neuron-specific enolase. Removal of circulating adrenal steroids resulted in a greater density of both GFAP-immunoreactive and vimentin- immunoreactive cells compared to sham-operated animals; CORT replacement prevented increases in both of these cell types. The increase in the density of vimentin-immunoreactive cells probably resulted from an increase in the birth of these cells, as adrenalectomized rats showed greater numbers of 3H-thymidine-labeled vimentin-positive cells compared to sham rats. In contrast, no changes in the number of 3H-thymidine-labeled GFAP-positive cells were observed with adrenalectomy, indicating that the increase in this cell type probably does not involve cell birth. In addition, the density of 3H- thymidine-labeled cells that were not immunoreactive for either glial cell marker and that showed neuronal characteristics was dramatically increased with adrenalectomy. These results suggest that adrenal hormones normally suppress the birth of both glia and neurons in the adult rat dentate gyrus.
This paper identifies a problem in both the TLA+ specification and the implementation of the Egalitarian Paxos protocol. It is related to how replicas switch from one ballot to another when computing the dependencies of a command. The problem may lead replicas to diverge and break the linearizability of the replicated service.
Mokka is a partial-synchronous, strong consistent BFT consensus algorithm for reaching the consensus about a certain value in open networks. This algorithm has some common approaches nested from RAFT, but its nature and design make Mokka a better solution for DLT (distributed ledger).
One of the services of DSCloud Platform is to provide the global directory service to solve the problems of dispersed, difficult retrieved and isolated information. In this paper, we describe DSCloud Platform's authorization policies and co-operating strategies for articles and comments, and usage scenery for co-editing posts and tables in the platform.
We propose a decentralized routing algorithm that can be implemented in Bitcoin Lightning Network. All nodes in the network contribute equally to path searching. The algorithm is inspired from ant path searching algorithms.
This is a correction by the authors to "Byzantine Agreement in Expected Polynomial Time" which appeared in the Journal of the ACM in 2016. It corrects a failure in the paper to consider the adversary's ability to decide the number of fair coinflips in an iteration, where this number ranges between n(n-t) and n(n-2t).
Supercomputer building is a many sceene, many authors game, comprising a lot of different technologies, manufacturers and ideas. Checking data available in the public database in a systematic way, some general tendencies and limitations can be concluded, both for the past and the future. The feasibility of building exa-scale computers as well as their limitations and utilization are also discussed. The statistical considerations provide a strong support for the conclusions.
A way to accelerate DEM calculations on the GPUs is developed. We examined how warp divergences take place in the contact detection and the force calculations taking account of the GPU architecture. Then we showed a strategy to reduce the impact of the warp divergences on the runtime of the DEM force calculations.
In this article, Conway's Game of Life using OpenMP parallel processing to simulate several different parallel methods, experimental performance results and compare to find the optimal solution of the parallelization of the Game of Life. Finally pointed out the importance of the design of parallel algorithms in solving the parallel problem.
In this thesis report, we have a survey on state-of-the-art methods for modelling resource utilization of MapReduce applications regard to its configuration parameters. After implementation of one of the algorithms in literature, we tried to find that if CPU usage modelling of a MapReduce application can be used to predict CPU usage of another MapReduce application.
This paper describes the overlay protocol Chord using the formalism of Abstract State Machines. The formalization concerns Chord actions that maintain ring topology and manipulate distributed keys. We define a class of runs and prove the correctness of our formalization with respect to it.