scholarly journals A CAPable distributed programming model

2018 ◽  
Author(s):  
Florian Myter ◽  
Christophe Scholliers ◽  
Wolfgang De Meuter
Keyword(s):  
Programming Model ◽  
Distributed Programming

Optimizing parallel particle tracking in Brownian motion using machine learning

2020 ◽  
Vol 34 (5) ◽  
pp. 532-546
Author(s):  
Srđan Nikolić ◽  
Nenad Stevanović ◽  
Miloš Ivanović
Keyword(s):  
Machine Learning ◽  
Brownian Motion ◽  
Particle Tracking ◽  
Particle Motion ◽  
Message Passing ◽  
Programming Model ◽  
Computation Time ◽  
Distributed Programming ◽  
Trajectory Decomposition ◽  
Particle Lifetime

In this paper, we present a generic, scalable and adaptive load balancing parallel Lagrangian particle tracking approach in Wiener type processes such as Brownian motion. The approach is particularly suitable in problems involving particles with highly variable computation time, like deposition on boundaries that may include decay, when particle lifetime obeys exponential distribution. At first glance, Lagranginan tracking is highly suitable for a distributed programming model due to the independence of motion of separate particles. However, the commonly employed Decomposition Per Particle (DPP) method, where each process is in charge of a certain number of particles, actually displays poor parallel efficiency due to the high particle lifetime variability when dealing with a wide set of deposition problems that optionally include decay. The proposed method removes DPP defects and brings a novel approach to discrete particle tracking. The algorithm introduces master/slave model dubbed Partial Trajectory Decomposition (PTD), in which a certain number of processes produce partial trajectories and put them into the shared queue, while the remaining processes simulate actual particle motion using previously generated partial trajectories. Our approach also introduces meta-heuristics for determining the optimal values of partial trajectory length, chunk size and the number of processes acting as producers/consumers, for the given total number of participating processes (Optimized Partial Trajectory Decomposition, OPTD). The optimization process employs a surrogate model to estimate the simulation time. The surrogate is based on historical data and uses a coupled machine learning model, consisting of classification and regression phases. OPTD was implemented in C, using standard MPI for message passing and benchmarked on a model of 220 Rn progeny in the diffusion chamber, where particle motion is characterized by an exponential lifetime distribution and Maxwell velocity distribution. The speedup improvement of OPTD is approximatelly 320% over standard DPP, reaching almost ideal speedup on up to 256 CPUs.

scholarly journals A programming model and foundation for lineage-based distributed computation

2018 ◽  
Vol 28 ◽  
Author(s):  
PHILIPP HALLER ◽  
HEATHER MILLER ◽  
NORMEN MÜLLER
Keyword(s):  
Data Structure ◽  
Functional Data ◽  
Formal Model ◽  
Programming Model ◽  
Distributed Computation ◽  
Reduction Theorem ◽  
Distributed Programming ◽  
Distributed Data ◽  
Design Data ◽  
Core Language

AbstractThe most successful systems for “big data” processing have all adopted functional APIs. We present a new programming model, we callfunction passing, designed to provide a more principled substrate, or middleware, upon which to build data-centric distributed systems like Spark. A key idea is to build up a persistent functional data structure representing transformations on distributed immutable data by passing well-typed serializable functions over the wire and applying them to this distributed data. Thus, the function passing model can be thought of as a persistent functional data structure that isdistributed, where transformations performed on distributed data are stored in its nodes rather than the distributed data itself. One advantage of this model is that failure recovery is simplified by design – data can be recovered by replaying function applications atop immutable data loaded from stable storage. Deferred evaluation is also central to our model; by incorporating deferred evaluation into our design only at the point of initiating network communication, the function passing model remains easy to reason about while remaining efficient in time and memory. Moreover, we provide a complete formalization of the programming model in order to study the foundations of lineage-based distributed computation. In particular, we develop a theory of safe, mobile lineages based on a subject reduction theorem for a typed core language. Furthermore, we formalize a progress theorem that guarantees the finite materialization of remote, lineage-based data. Thus, the formal model may serve as a basis for further developments of the theory of data-centric distributed programming, including aspects such as fault tolerance. We provide an open-source implementation of our model in and for the Scala programming language, along with a case study of several example frameworks and end-user programs written atop this model.

scholarly journals The Impact of COVID-19 in Collaborative Programming. Understanding the Needs of Undergraduate Computer Science Students

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1728
Author(s):  
Carmen Lacave ◽  
Ana Isabel Molina
Keyword(s):  
Computer Science ◽  
Programming Model ◽  
Distributed Programming ◽  
Science Students ◽  
Distributed Collaboration ◽  
Cross Sectional ◽  
Model Based ◽  
Collaborative Programming ◽  
Collaboration Tools ◽  
The Impact

Collaborative learning activities have become a common practice in current university studies due to the implantation of the EHEA. However, the COVID-19 pandemic has led to a radical and abrupt change in the teaching–learning model used in most universities, and in the way students’ group work is carried out. Given this new situation, our interest is focused on discovering how computer science students have approached group programming tasks. For this purpose, we have designed a cross-sectional pilot study to explore, from both social and technological points of view, how students carried out their group programming activities during the shutdown of universities, how they are doing them now, when social distance must be maintained, and what they have missed in both situations. The results of the study indicate that during the imposed confinement, the students adopted a programming model based on work division or distributed peer programming, and very few made use of synchronous distributed collaboration tools. After the lockdown, the students mostly opted for a model based on collaborative programming and there was an increased use of synchronous distributed collaboration tools. The specific communication, synchronization, and coordination functionalities they considered most useful or necessary were also analyzed. Among the desirable features included in a software for synchronous distributed programming, the students considered that having an audio-channel can be very useful and, possibly, the most agile method to communicate. The video signal is not considered as very necessary, being in many cases rather a source of distraction, while textual communication through a chat, to which they are very accustomed, is also well valued. In addition, version control and the possibility of recovering previous states of the practical projects were highly appreciated by the students, and they considered it necessary to record the individual contributions of each member of the team to the result.

An Efficient Distributed Programming Model for Mining Useful Patterns in Big Datasets

2013 ◽  
Vol 30 (1) ◽  
pp. 53 ◽  
Author(s):  
Md. Rezaul Karim ◽  
ChowdhuryFarhan Ahmed ◽  
Byeong-Soo Jeong ◽  
Ho-Jin Choi
Keyword(s):  
Programming Model ◽  
Distributed Programming
Sign in / Sign up

Export Citation Format

Share Document