Ideal Parallelism Research Articles

“Canine First Technique”, An Innovative Approach in Maxillary Impacted Canines: A Case Report

Background: Maxillary canine impaction is one of the most challenging issues in orthodontics. The best treatment protocol in these cases is still debated. The purpose of this study is to describe the management of maxillary canine impaction in an adult female patient with the “Canine First Technique”. Case Report: A 21-years-old female attended our dental unit seeking orthodontic treatment. Clinical examination revealed a class II relationship, the persistence of both upper deciduous canines. The panoramic X-ray and Cone Beam Computed Tomography showed bilateral palatal permanent canine displacements and close proximity between crowns of impacted canines and roots of lateral incisors. The canines were disimpacted by means of two cantilevers inserted directly in two Temporary Anchorage Devices placed palatally and when canines were near the crest, the fixed orthodontic treatment was started. Results: At the end of the treatment, canine Class I relationships with torque correction of canines, normal overjet and overbite, and good alignment of dental arches were achieved. The radiographic evaluation showed ideal root parallelism and preserved periodontal health in the canine region. Conclusion: The Canine First Technique could provide some advantages compared to conventional approaches in terms of biomechanics, esthetics, oral hygiene, and risk reduction of root resorption of upper lateral incisors.

A Transformation Framework for Optimizing Task-Parallel Programs

Task parallelism has increasingly become a trend with programming models such as OpenMP 3.0, Cilk, Java Concurrency, X10, Chapel and Habanero-Java (HJ) to address the requirements of multicore programmers. While task parallelism increases productivity by allowing the programmer to express multiple levels of parallelism, it can also lead to performance degradation due to increased overheads. In this article, we introduce a transformation framework for optimizing task-parallel programs with a focus on task creation and task termination operations. These operations can appear explicitly in constructs such as async, finish in X10 and HJ, task, taskwait in OpenMP 3.0, and spawn, sync in Cilk, or implicitly in composite code statements such as foreach and ateach loops in X10, forall and foreach loops in HJ, and parallel loop in OpenMP. Our framework includes a definition of data dependence in task-parallel programs, a happens-before analysis algorithm, and a range of program transformations for optimizing task parallelism. Broadly, our transformations cover three different but interrelated optimizations: (1) finish-elimination , (2) forall-coarsening , and (3) loop-chunking . Finish-elimination removes redundant task termination operations, forall-coarsening replaces expensive task creation and termination operations with more efficient synchronization operations, and loop-chunking extracts useful parallelism from ideal parallelism. All three optimizations are specified in an iterative transformation framework that applies a sequence of relevant transformations until a fixed point is reached. Further, we discuss the impact of exception semantics on the specified transformations, and extend them to handle task-parallel programs with precise exception semantics. Experimental results were obtained for a collection of task-parallel benchmarks on three multicore platforms: a dual-socket 128-thread (16-core) Niagara T2 system, a quad-socket 16-core Intel Xeon SMP, and a quad-socket 32-core Power7 SMP. We have observed that the proposed optimizations interact with each other in a synergistic way, and result in an overall geometric average performance improvement between 6.28× and 10.30×, measured across all three platforms for the benchmarks studied.

GPU Acceleration of Runge-Kutta Integrators

We consider the use of commodity graphics processing units (GPUs) for the common task of numerically integrating ordinary differential equations (ODEs), achieving speedups of up to 115-fold over comparable serial CPU implementations, and 15-fold over multithreaded CPU code with SIMD intrinsics. Using Lorenz '96 models as a case study, single and double precision benchmarks are established for both the widely used DOPRI5 method and computationally tailored low-storage RK4(3)5[2R+]C. A range of configurations are assessed on each, including multithreading and SIMD intrinsics on the CPU, and GPU kernels parallelized over both the dimensionality of the ODE system and number of trajectories. On the GPU, we draw particular attention to the problem of variable task-length among threads of the same warp, proposing a lightweight strategy of assigning multiple data items to each thread to reduce the prevalence of redundant operations. A simple analysis suggests that the strategy can draw performance close to that of ideal parallelism, while empirical results demonstrate up to a 10 percent improvement over the standard approach.

SIMPLE PERFORMANCE BOUNDS FOR MULTICORE AND PARALLEL CHANNEL SYSTEMS

A simple modification of existing divisible load scheduling algorithms, boosting link speed by M for M parallel channels per link, allows time optimal load scheduling and performance prediction for parallel channel systems. The situation for multicore models is more complex but can be handled by a substitution involving equivalent processor speed. These modifications yield upper bounds on such parallel systems' performance. This concept is illustrated for ideal single level (star) tree networks under a variety of scheduling policies. Less than ideal parallelism can also be modeled though mechanisms of inefficiency require further research.

Silicon microstructure for bringing closer parallel beams of laser diodes

A spatial silicon structure containing parallel {111} faces forming two pairs of micromirrors used for making close two parallel optical beams at micrometric distance has been designed. The structure was fabricated in a single (113) oriented Si wafer. The fabrication process involved one stage double-side anisotropic etching in KOH solution. The structure employs natural arrangement of crystallographic planes in silicon, which assures an ideal parallelism of beam axes of reflected light. The reduction of the distance between the laser beams is possible without the need of setting up and adjusting a complex optical system.

Adaptively parallelizing distributed range queries

We consider the problem of how to best parallelize range queries in a massive scale distributed database. In traditional systems the focus has been on maximizing parallelism, for example by laying out data to achieve the highest throughput. However, in a massive scale database such as our PNUTS system [11] or BigTable [10], maximizing parallelism is not necessarily the best strategy: the system has more than enough servers to saturate a single client by returning results faster than the client can consume them, and when there are multiple concurrent queries, maximizing parallelism for all of them will cause disk contention, reducing everybody's performance. How can we find the right parallelism level for each query in order to achieve high, consistent throughput for all queries? We propose an adaptive approach with two aspects. First, we adaptively determine the ideal parallelism for a single query execution, which is the minimum number of parallel scanning servers needed to satisfy the client, depending on query selectivity, client load, client-server bandwidth, and so on. Second, we adaptively schedule which servers will be assigned to different query executions, to minimize disk contention on servers and ensure that all queries receive good performance. Our scheduler can be tuned based on different policies, such as favoring short versus long queries or high versus low priority queries. An experimental study demonstrates the effectiveness of our techniques in the PNUTS system.

Contact of languages and populations in Morocco

The objective of this dissertation is language and populations contact in the plain of Tadla, situated in central Morocco around the city of Beni Mellal. This language contact setting presupposes common human and linguistic facts made up of heterogeneity, mixing, variation both within the same language, the same group of people as well as within different human groups. The languages concerned in this study are mainly Amazigh and Arabic and, to some extent, French. The groups investigated are the Chleuh, the Arabized, the Arabs and the Amazighized. The contact between the languages and groups concerns the linguistic ideal parallelism and the ideal identity. This research falls within a larger scope: that of the regionalisation and decentralisation in Morocco and could be introduced as an element for territory planning of the area investigated. This work could be a preliminary initiative study of the region of Tadla from a historical, demographic, geographical, linguistic and anthropological point of view. A good knowledge of the Moroccan territory and populations requires knowledge of the distribution of the languages and the populations and their point of contact. The study of the language and populations contact will help to apprehend the mixing and consequently predict the human and linguistic evolution and changes (i.e. the emergence of a mixed language) and lead to a redefinition of regionalisation on the basis of the linguistic and cultural particularities based on the findings of fieldwork research. From this perspective, our research has the advantage of dealing with a rural micro-structure, which will be described on the basis of the characteristic of the Arabic lect of Tadla, the linguistic features of the contact between Amazigh and Arabic, the impact of the socio-cultural interpenetration between the groups present, the maps of the linguistic boundaries which set the limits of isoglosses, the regional atlases of the lects and populations of the so-called contact areas, i.e. the plain of Tadla. The originality of the research consists in the investigation of both the languages and their populations on the basis of epilinguistic speech. Former works on the region have dealt with either one or the other. The study does not limit itself to the description of the phenomena but it also aims at accounting for and explaining the convergences between the populations and languages thanks to the consideration of all the elements which could influence variation. Our aim, indeed, is not to pre-categorize the range of manifestations of language and populations contact but to apprehend its modes. The general tendency is to show that the different human groupings in Tadla do in no way differ since they have the same representation of the world. The only difference lies in the modes of expression they use i.e. either Amazigh or Arabic to express their perception of the world. The goal is thus to give a general view about the lects in use, to provide a large corpus of epilinguistic speech and to propose a model for its categorization and interpretation. We aim at revealing that what appears to be different and dissimilar on the surface is nothing but the incarnation of the facets of the same and unique, profound and inherent characteristic, i.e. the Moroccan character. Given the dimension and nature of the language and populations contact data in the area of Tadla, we had to opt for an eclectic theoretical and methodological model that would include different models and disciplines such as geography, history, dialectology, sociolinguistics, sociology of language, anthropology, psychology, discourse analysis and linguistics. Thus, on the theoretical and methodological level, we have made use of an eclectic model including different perspectives that allow for the analysis of one or many aspects of the issue. The research methods used in this study (i.e. the indirect interview, participatory observation, direct “in vivo ” testimonies…) and the multi-disciplinary approach initiates a perspective that focuses on the group and the subjectivity of the discursive speech. The description of the language and population context that characterizes the area of Tadla led us to organize the study into two main parts: a descriptive and an interpretative part. This is mainly based on a methodological principle which aims at satisfying both the descriptive and the prescriptive levels. The practices and /or usages and the general theoretical model are raised and described in the first part. The epilinguistic speech is presented, discussed and interpreted in the second part. Since the speech is conceived as a causality that can modify the practices, the speech and practices are not considered at the same level of analysis.

PAWS: a performance evaluation tool for parallel computing systems

A description is given of PAWS (parallel assessment window system), a set of tools that provides an interactive user-friendly environment for analysis of existing, prototype, and conceptual machine architectures running a common application. PAWS consists of an application tool, an architectural characterization tool, a performance assessment tool, and an interactive graphical display tool. The application characterization tool provides a facility for evaluating the level and degree of an application's parallelism. The architecture characterization tool allows users to create, store, and retrieve descriptions of machines in a database. This approach permits users to evaluate conceptual machines before building any hardware. The performance assessment tool generates profile plots through the interactive graphical display tool. It shows both the ideal parallelism inherent in the machine-independent dataflow graph and the predicted parallelism of the partitioned dataflow graph on the target machine.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Assessing the Benefits of Fine- Grain Parallelism in Dataflow Programs

A method for assessing the benefits of fine-grain paral lelism in "real" programs is presented. The method is based on parallelism profiles and speedup curves de rived by executing dataflow graphs on an interpreter under progressively more realistic assumptions about processor resources and communication costs. Even using traditional algorithms, the programs exhibit ample parallelism when parallelism is exposed at all levels. The bias introduced by the language ld and the compiler is examined. A method of estimating speedup through analysis of the ideal parallelism profile is developed, avoiding repeated execution of programs. It is shown that fine-grain parallelism can be used to mask large, unpredictable memory latency and synchronization waits in architectures employing dataflow instruction execu tion mechanisms. Finally, the effects of grouping por tions of dataflow programs, and requiring that the oper ators in a group execute on a single processor, are explored.