Motivation: The motivation to raise the issue was to draw attention to disadvantages as and advantages of various project management concepts, in particular the group of agile and traditional ...methodologies within information technology (IT) projects.Aim: The aim was to demonstrate the statistical profitability of migration to the methodologies better suited for the adaptive industry in which the software-producing enterprises operate. The detailed aim was to show positive dependencies, if the management concept is correctly selected to meet the expectations of the client and the project.Materials and methods: The conclusions were based on a comparative analysis of a group of methodologies, as well as a verification of the research carried out by Scott Ambler + Associates company.Results: The conclusion was that the traditional approach to project management does not fit into the canon of modern and adaptive techniques, that would meet the requirements set in the era of globalization by flexible IT projects. In addition, the analysis of responses provided by the respondents shows how drastically a change in approach to the entire project cycle affects the probability of success and reduces misunderstandings between client and contractor.
15 lake islands and two mainland sites of Mamry lake in Poland were sampled to investigate community structures and patterns of co-occurrences of ground beetles (Carabidae). The total ground beetle ...metacommunity of 71 species was divided into a group of core species occupying at least half of all study sites and of satellite species, which occurred at two sites or less. This division is mirrored by reduced dispersal abilities and non-random patterns of site occupancy. Core and satellite species also differed in patterns of relative abundance. The core group followed a lognormal distribution, the satellite group a power function as predicted by the self-similarity model of occurrence. We conclude that the division into core and satellite species is not a sample artefact but reflects different life history strategies. We also conclude that current models of niche division and co-occurrence might miss important aspects of community structure if they do not refer to patterns of dispersal. From these findings we infer that the regional distribution of core species might be shaped by species interactions and processes of niche divisions whereas the spatial distribution of satellite species are best interpreted as stemming from random dispersal.
In order to study the influence of dispersal ability on community structure of ground beetles (carabidae), 15 lake islands and 2 mainland sites of the lake Mamry archipelago, northern Poland, were ...sampled by using pitfall traps. Of the 71 ground beetle species detected, 47 were macropterous, 16 wing-dimorphic and 8 brachypterous. Macropterous species had lower site abundances and occupied fewer sites than dimorphic and brachypterous species. There were trends from macropterous to brachypterous species towards a nested distribution across the sites and towards over-dispersed (aggregated) species co-occurrences. Canonical correspondence analysis pointed to site isolation and area as main factors influencing site abundance and spatial distribution. Our results imply that further studies on species co-occurrences and community assembly have to consider dispersal ability as a key element influencing ecological distributions at the regional scale.
In this paper, we propose a distributed, unordered, label-correcting distance-1 Grundy (vertex) coloring algorithm, namely, Distributed Control (DC) coloring algorithm. Our algorithm eliminates the ...need for vertex-centric barriers and global synchronization for color refinement, relying only on atomic operations and local termination detection to update vertex color. DC proceeds optimistically, correcting the colors asynchronously as the algorithm progresses and depends on local ordering of tasks to minimize the execution of sub-optimal work. We implement our DC coloring algorithm and the well-known Jones-Plassmann algorithm and compare their performance with 4 different types of standard RMAT graphs and real-world graphs. We show that the elimination of waiting time of global and vertex-centric barriers and investing this time for local ordering leads to improved scaling for graphs with prominent power-law characteristics and densely interconnected local subgraphs.
Synchronization-Avoiding Graph Algorithms Firoz, Jesun Sahariar; Zalewski, Marcin; Kanewala, Thejaka ...
2018 IEEE 25th International Conference on High Performance Computing (HiPC)
Conference Proceeding
Because they were developed for optimal sequential complexity, classical graph algorithms as found in textbooks have strictly-defined orders of operations. Enforcing a prescribed order of operations, ...or even an approximate order, in a distributed memory setting requires significant amounts of synchronization, which in turn can severely limit scalability. As a result, new algorithms are typically required to achieve scalable performance, even for solving well-known graph problems. Yet, even in these cases, parallel graph algorithms are written according to parallel programming models that evolved for, e.g., scientific computing, and that still have inherent, and scalability-limiting, amounts of synchronization. In this paper we present a new approach to parallel graph algorithms: synchronization-avoiding algorithms. To eliminate synchronization and its associated overhead, synchronization-avoiding algorithms perform work in an unordered and fully asynchronous fashion in such a way that the result is constantly refined toward its final state. "Wasted" work is minimized by locally prioritizing tasks using problem-dependent task utility metrics. We classify algorithms for graph applications into two broad categories: algorithms with monotonic updates (which evince global synchronization) and algorithms with non-monotonic updates (which evince vertex-centric synchronization). We apply our approach to both classes and develop novel, synchronization-avoiding algorithms for solving exemplar problems: SSSP and connected components for the former, graph coloring for the latter. We demonstrate that eliminating synchronization in conjunction with effective scheduling policies and optimizations in the runtime results in improved scalability for both classes of algorithms.
Performance of distributed graph algorithms can benefit greatly by forming rapport between algorithmic abstraction and the underlying runtime system that is responsible for scheduling work and ...exchanging messages. However, due to their dynamic and irregular nature of computation, distributed graph algorithms written in different programming models impose varying degrees of workload pressure on the runtime. To cope with such vastly different workload characteristics, a runtime has to make several trade-offs. One such trade-off arises, for example, when the runtime scheduler has to choose among alternatives such as whether to execute algorithmic work, or progress the network by probing network buffers, or throttle sending messages (termed flow control). This trade-off decides between optimizing the throughput of a runtime scheduler by increasing the rate of execution of algorithmic work, and reducing the latency of the network messages. Another trade-off exists when a decision has to be made about when to send aggregated messages in buffers (message coalescing). This decision chooses between trading off latency for network bandwidth and vice versa. At any instant, such trade-offs emphasize either on improving the quantity of work being executed (by maximizing the scheduler throughput) or on improving the quality of work (by prioritizing better work). However, encoding static policies for different runtime features (such as flow control, coalescing) can prevent graph algorithms from achieving their full potentials, thus can under-mine the actual performance of a distributed graph algorithm . In this paper, we investigate runtime support for distributed graph algorithms in the context of two paradigms: variants of well-known Bulk-Synchronous Parallel model and asynchronous programming model. We explore generic runtime features such as message coalescing (aggregation) and flow control and show that execution policies of these features need to be adjusted over time to make a positive impact on the execution time of a distributed graph algorithm. Since synchronous and asynchronous graph algorithms have different workload characteristics, not all of such runtime features may be good candidates for adaptation. Each of these algorithmic paradigms may require different set of features to be adapted over time. We demonstrate which set of feature(s) can be useful in each case to achieve the right balance of work in the runtime layer. Existing implementation of different graph algorithms can benefit from adapting dynamic policies in the underlying runtime.
Classic theories on assembly rules and food-web structure are species-centered, so they largely ignore intraspecific variation. Intraspecific trophic variation, however, might be of key importance in ...understanding community organization. Here we study the variability of isotopic niche spaces of ground beetles and its consequences for the trophic structure of beetle assembly. Stable isotopes ratios (δ13C and δ15N) were measured in 1156 specimens of carabids belonging to 59 species inhabiting 20 island and two mainland sites of the Masuria Lakeland in northern Poland. Carabid species belonged to three different trophic guilds (named “phytophages”, “decomposer feeders” and “generalist predators”). However, this division is not sharp due to high intraspecific variability of isotopic signatures, which indicates the use of very different types of resources by conspecific individuals inhabiting different sites. As a consequence, most species studied did not differ significantly in the isotopic niche space. This high niche overlap corroborates the view that resource competition is not a major factor shaping the composition of ground beetles communities. Future studies should take into account the complex trophic structure of beetle assemblages and explore the intraspecific niche variability of ground beetles.
Aims To test a new concept for island ecology and metapopulation studies: if population persistence is a result of colonization and extinction processes, one would expect remarkable variability in ...the age of neighbouring populations - there would be both old and young (recently established) populations. Location The lake Mamry archipelago, Poland. Methods Forty trap transects with a total of 114 Barber traps were operating from June to September in 1997 and in 1998. The traps (0.5-L plastic beakers, mouth diameter 120 mm, with a 20 x 20 cm wooden roof) were placed by applying a stratified sampling design into 13 habitat types on the 16 islands and two mainland sites. The frequency of macropterous individuals in wingdimorphic populations of three carabid species (Pterostichus melanarius, P. anthracinus and Carabus granulatus) was used as an indicator of population 'age'. Results The frequency of macropterous individuals in the populations varied from 0% to 100% for P. melanarius (18.5% on average), from 0% to 91% for P. anthracinus (12.6%) and from 0% to 29% for C granulatus (8.9%). Populations hosted more long-winged individuals (and were therefore interpreted as being younger) on smaller islands, compared with those inhabiting large islands and the mainland sites. The results also revealed that the viability of the populations of the autumn-breeding P. melanarius might be more affected by population size than that of the two studied spring breeders. Island connectivity did not have a significant effect on the frequency of macropterous individuals in the studied populations. Main conclusions The inverse relationship between the proportion of macropterous individuals and island size contrasts with the accepted theory of dispersal, which assumes that there is selection against dispersal on small islands. A regression analysis for population age and habitat characteristics reveals the extinction probability of a given population. I suggest that investigations based on variability in population age can help in studies of colonization-extinction processes that would otherwise face logistic and methodological obstacles.
Motywacja: Motywacją do podjęcia tematu była chęć zwrócenie uwagi na mankamenty oraz walory poszczególnych koncepcji, w szczególności grupy metodyk zwinnych oraz tradycyjnych dla projektów ...informatycznych.
Cel: Głównym celem jest wykazanie statystycznej opłacalności migracji do metodyk lepiej dopasowanych w przypadku branży adaptacyjnej, w jakiej operują przedsiębiorstwa wytwarzające oprogramowanie. Celem szczegółowym jest wykazanie pozytywnych zależności, w przypadku prawidłowego doboru koncepcji zarządzania do oczekiwań klienta oraz zespołu projektowego.
Materiały i metody: Wnioski opracowano na podstawie analizy porównawczej grupy metodyk, a także przez weryfikację badań przeprowadzonych przez przedsiębiorstwo Scott Ambler + Associates.
Wyniki: W konkluzji stwierdzono przede wszystkim, że nie ujmując tradycyjnemu podejściu do zarządzania, nie wpisuje się ono do kanonu nowoczesnych i adaptacyjnych technik, które sprostałyby wymaganiom stawianym w dobie globalizacji przez elastyczne projekty informatyczne. Ponadto, na podstawie analizy odpowiedzi respondentów, można dostrzec, jak drastycznie zmiana podejścia do całego cyklu projektowego wpływa na prawdopodobieństwo sukcesu oraz niweluje nieporozumienia na linii klient-wykonawca.