An efficient parallel implementation of a least squares problem

Least squares solutions are a very important problem, which appear in a broad range of disciplines (for instance, control systems, statistics, signal processing). Our interest in this kind of problems lies in their use of training neural network controllers.

An efficient parallel implementation of a least squares problem

Least squares solutions are a very important problem, which appear in a broad range of disciplines (for instance, control systems, statistics, signal processing). Our interest in this kind of problems lies in their use of training neural network controllers.

Parallel implementation of a learning algorithm for multilayer perceptrons using transputers

In this paper the parallelization of a new learning algorithm for multilayer perceptrons, specifically targeted for nonlinear function approximation purposes, is discussed. Each major step of the algorithm is parallelized, a special emphasis being put in the most computationally intensive task, a least-squares solution of linear systems of equations.

Coreference resolution for portuguese using parallel corpora word alignment

A área de Extração da Informação tem como objetivo essencial investigar métodos e técnicas para transformar a informação não estruturada presente em textos de língua natural em dados estruturados. Um importante passo deste processo é a resolução de correferência, tarefa que identifica diferentes sintagmas nominais que se referem a mesma entidade no discurso. A área de estudos sobre resolução de correferência tem sido extensivamente pesquisada para a Língua Inglesa (Ng, 2010) lista uma série de estudos da área, entretanto tem recebido menos atenção em outras línguas. Isso se deve ao fato de que a grande maioria das abordagens utilizadas nessas pesquisas são baseadas em aprendizado de máquina e, portanto, requerem uma extensa quantidade de dados anotados.

A spectral estimator using parallel-processing for use in a doppler blood-flow instrument

The work described here is part of a research program aiming to increase the sensitivity to disease detection using Doppler ultrasound by reducing the effects to the measurement procedure on the estimation of blood velocity and detection of flow disturbance.

Parallel decoding of turbo codes using multi-point trellis termination and collision-free interleavers

The UMTS turbo encoder is composed of parallel concatenation of two Recursive Systematic Convolutional (RSC) encoders which start and end at a known state. This trellis termination directly affects the performance of turbo codes. This paper presents performance analysis of multi-point trellis termination of turbo codes which is to terminate RSC encoders at more than one point of the current frame while keeping the interleaver length the same. For long interleaver lengths, this approach provides dividing a data frame into sub-frames which can be treated as independent blocks. A novel decoding architecture using multi-point trellis termination and collision-free interleavers is presented. Collision-free interleavers are used to solve memory collision problems encountered by parallel decoding of turbo codes. The proposed parallel decoding architecture reduces the decoding delay caused by the iterative nature and forward-backward metric computations of turbo decoding algorithms. Our simulations verified that this turbo encoding and decoding scheme shows Bit Error Rate (BER) performance very close to that of the UMTS turbo coding while providing almost %50 time saving for the 2-point termination and %80 time saving for the 5-point termination.

Increasing the speed of parallel decoding of turbo codes

Turbo codes experience a significant decoding delay because of the iterative nature of the decoding algorithms, the high number of metric computations and the complexity added by the (de)interleaver. The extrinsic information is exchanged sequentially between two Soft-Input Soft-Output (SISO) decoders. Instead of this sequential process, a received frame can be divided into smaller windows to be processed in parallel. In this paper, a novel parallel processing methodology is proposed based on the previous parallel decoding techniques. A novel Contention-Free (CF) interleaver is proposed as part of the decoding architecture which allows using extrinsic Log-Likelihood Ratios (LLRs) immediately as a-priori LLRs to start the second half of the iterative turbo decoding. The simulation case studies performed in this paper show that our parallel decoding method can provide %80 time saving compared to the standard decoding and %30 time saving compared to the previous parallel decoding methods at the expense of 0.3 dB Bit Error Rate (BER) performance degradation.

Parallel languages in the history of language ideology in Norway and the lesson for Nordic higher education

This chapter compares recent policy on the use of English and Norwegian in Higher Education with earlier policies on the relationship between the two standard varieties of Norwegian, and it charts how and why English became a policy issue in Norway. Based on the experience of over a century of language planning, a highly interventionist approach is today being avoided and language policies in the universities of Norway seek to nurture a situation where English and Norwegian may be used productively side-by-side. However, there remain serious practical challenges to be overcome. This paper also builds on a previous analysis (Linn 2010b) of the metalanguage of Nordic language policy and seeks to clarify the use of the term ‘parallelingualism’.

Median Filter Architecture by Accumulative Parallel Counters

The time to process each of the W/B processing blocks of a median calculation method on a set of N W-bit integers is improved here by a factor of three compared with literature. The parallelism uncovered in blocks containing B-bit slices is exploited by independent accumulative parallel counters so that the median is calculated faster than any known previous method for any N, W values. The improvements to the method are discussed in the context of calculating the median for a moving set of N integers, for which a pipelined architecture is developed. An extra benefit of a smaller area for the architecture is also reported.

KDD, SEMMA and CRISP-DM: a parallel overview

In the last years there has been a huge growth and consolidation of the Data Mining field. Some efforts are being done that seek the establishment of standards in the area. Included on these efforts there can be enumerated SEMMA and CRISP-DM. Both grow as industrial standards and define a set of sequential steps that pretends to guide the implementation of data mining applications. The question of the existence of substantial differences between them and the traditional KDD process arose. In this paper, is pretended to establish a parallel between these and the KDD process as well as an understanding of the similarities between them.

O crime de fraude fiscal: o impacto na receita pública do Estado

Orientador: Doutor, José Domingos Silva Fernandes

A framework for the development of parallel and distributed real-time embedded systems

Embedded real-time applications increasingly present high computation requirements, which need to be completed within specific deadlines, but that present highly variable patterns, depending on the set of data available in a determined instant. The current trend to provide parallel processing in the embedded domain allows providing higher processing power; however, it does not address the variability in the processing pattern. Dimensioning each device for its worst-case scenario implies lower average utilization, and increased available, but unusable, processing in the overall system. A solution for this problem is to extend the parallel execution of the applications, allowing networked nodes to distribute the workload, on peak situations, to neighbour nodes. In this context, this report proposes a framework to develop parallel and distributed real-time embedded applications, transparently using OpenMP and Message Passing Interface (MPI), within a programming model based on OpenMP. The technical report also devises an integrated timing model, which enables the structured reasoning on the timing behaviour of these hybrid architectures.

Dynamic global scheduling of parallel real-time tasks

High-level parallel languages offer a simple way for application programmers to specify parallelism in a form that easily scales with problem size, leaving the scheduling of the tasks onto processors to be performed at runtime. Therefore, if the underlying system cannot efficiently execute those applications on the available cores, the benefits will be lost. In this paper, we consider how to schedule highly heterogenous parallel applications that require real-time performance guarantees on multicore processors. The paper proposes a novel scheduling approach that combines the global Earliest Deadline First (EDF) scheduler with a priority-aware work-stealing load balancing scheme, which enables parallel realtime tasks to be executed on more than one processor at a given time instant. Experimental results demonstrate the better scalability and lower scheduling overhead of the proposed approach comparatively to an existing real-time deadline-oriented scheduling class for the Linux kernel.

Software transactional memory as a building block for parallel embedded realtime systems

The recent trends of chip architectures with higher number of heterogeneous cores, and non-uniform memory/non-coherent caches, brings renewed attention to the use of Software Transactional Memory (STM) as a fundamental building block for developing parallel applications. Nevertheless, although STM promises to ease concurrent and parallel software development, it relies on the possibility of aborting conflicting transactions to maintain data consistency, which impacts on the responsiveness and timing guarantees required by embedded real-time systems. In these systems, contention delays must be (efficiently) limited so that the response times of tasks executing transactions are upper-bounded and task sets can be feasibly scheduled. In this paper we assess the use of STM in the development of embedded real-time software, defending that the amount of contention can be reduced if read-only transactions access recent consistent data snapshots, progressing in a wait-free manner. We show how the required number of versions of a shared object can be calculated for a set of tasks. We also outline an algorithm to manage conflicts between update transactions that prevents starvation.