An improved memory management scheme for large scale graph computing engine GraphChi

GraphChi is the first reported disk-based graph engine that can handle billion-scale graphs on a single PC efficiently. GraphChi is able to execute several advanced data mining, graph mining and machine learning algorithms on very large graphs. With the novel technique of parallel sliding windows (PSW) to load subgraph from disk to memory for vertices and edges updating, it can achieve data processing performance close to and even better than those of mainstream distributed graph engines. GraphChi mentioned that its memory is not effectively utilized with large dataset, which leads to suboptimal computation performances. In this paper we are motivated by the concepts of 'pin ' from TurboGraph and 'ghost' from GraphLab to propose a new memory utilization mode for GraphChi, which is called Part-in-memory mode, to improve the GraphChi algorithm performance. The main idea is to pin a fixed part of data inside the memory during the whole computing process. Part-in-memory mode is successfully implemented with only about 40 additional lines of code to the original GraphChi engine. Extensive experiments are performed with large real datasets (including Twitter graph with 1.4 billion edges). The preliminary results show that Part-in-memory mode memory management approach effectively reduces the GraphChi running time by up to 60% in PageRank algorithm. Interestingly it is found that a larger portion of data pinned in memory does not always lead to better performance in the case that the whole dataset cannot be fitted in memory. There exists an optimal portion of data which should be kept in the memory to achieve the best computational performance.

Controlled synthesis of poly(neopentyl p-styrene sulfonate) via reversible addition-fragmentation chain transfer polymerisation

The controlled synthesis of poly(neopentyl p-styrene sulfonate) (PNSS) using RAFT polymerisation has been studied. Selected experimental conditions led to the production of PNSS with variable molecular weights and low dispersities (D{stroke}≤1.50). The controlled synthesis of poly(neopentyl p-styrene sulfonate) (PNSS) using reversible addition-fragmentation chain transfer polymerisation has been studied under a wide range of experimental conditions. PNSS can be used as an organic-soluble, thermally labile precursor for industrially valuable poly(p-styrene sulfonate), widely employed in technologies such as ionic exchange membranes and organic electronics. The suitability of two different chain transfer agents, three solvents, three different monomer concentrations and two different temperatures for the polymerisation of neopentyl p-styrene sulfonate is discussed in terms of the kinetics of the process and characteristics of the final polymer. Production of PNSS with systematically variable molecular weights and low dispersities (D{stroke} ≤1.50 in all cases) has been achieved using 2-azidoethyl 2-(dodecylthiocarbonothioylthio)-2-methylpropionate in anisole at 75°C, with an initial monomer concentration of 4.0molL-1. Finally, a poly(neopentyl p-styrene sulfonate)-b-polybutadiene-b-poly(neopentyl p-styrene sulfonate) (PNSS-b-PBD-b-PNSS) triblock copolymer has been synthesised via azide-alkyne click chemistry. Moreover, subsequent thermolysis of the PNSS moieties generated poly(p-styrene sulfonate) end blocks. This strategy allows the fabrication of amphiphilic copolymer films from single organic solvents without the need for post-deposition chemical treatment.

Two-Language, Two-Paradigm Introductory Computing Curriculum Model and its Implementation

This paper analyzes difficulties with the introduction of object-oriented concepts in introductory computing education and then proposes a two-language, two-paradigm curriculum model that alleviates such difficulties. Our two-language, two-paradigm curriculum model begins with teaching imperative programming using Python programming language, continues with teaching object-oriented computing using Java, and concludes with teaching object-oriented data structures with Java.

Understanding Computing through Defining its Lexicon

Бойко Банчев - Понятието пресмятане в широкия му смисъл и неговото присъствие в природата, науката, технологията и други области е свързано с редица неизяснени въпроси. Дори в по-тесните рамки на програмирането и използването на компютри то не е адекватно разбрано. Представяме тезата, че един начин за приближаване към такова разбиране е разкриването на дълбинните структури и отношения, свързани с пресмятането, и на тази основа построяване на речник на пресмятането.

The Cloud Computing and Computer Virology

Евгений Николов, Димитрина Полимирова - Докладът представя текущото състояние на “облачните изчисления” и “облачните информационни атаки” в светлината на компютърната вирусология и информационната сигурност. Обсъдени са категориите “облачни възможни информационни атаки” и “облачни успешни информационни атаки”. Коментирана е архитектурата на “облачните изчисления” и основните компоненти, които изграждат тяхната инфраструктура, съответно “клиенти” (“clients”), „центрове за съхранение на данни“ (“datacenters”) и „разпределени сървъри“ (“dirstributed servers”). Коментирани са и услугите, които се предлагат от “облачните изчисления” – SaaS, HaaS и PaaS. Посочени са предимствата и недостатъците на компонентите и услугите по отношение на “облачните информационни атаки”. Направен е анализ на текущото състояние на “облачните информационни атаки” на територията на България, Балканския полуостров и Югоизточна Европа по отношение на компонентите и на услугите. Резултатите са представени под формата на 3D графични обекти. На края са направени съответните изводи и препоръки под формата на заключение.