Current high-performance computer systems used for scientific computing typically combine shared memory computational nodes in a distributed memory environment. Extracting high performance from these complex systems r...
详细信息
Brain strokes are one of the leading causes of disability and mortality in adults in developed countries. Ischemic stroke (85% of total cases) and hemorrhagic stroke (15%) must be treated with opposing therapies, and ...
详细信息
Brain strokes are one of the leading causes of disability and mortality in adults in developed countries. Ischemic stroke (85% of total cases) and hemorrhagic stroke (15%) must be treated with opposing therapies, and thus, the nature of the stroke must be determined quickly in order to apply the appropriate treatment. Recent studies in biomedical imaging have shown that strokes produce variations in the complex electric permittivity of brain tissues, which can be detected by means of microwave tomography. Here, we present some synthetic results obtained with an experimental microwave tomography-based portable system for the early detection andmonitoring of brain strokes. The determination of electric permittivity first requires the solution of a coupled forward-inverse problem. We make use of massive parallel computation from domain decomposition method and regularization techniques for optimization methods. Synthetic data are obtained with electromagnetic simulations corrupted by noise, which have been derived from measurements errors of the experimental imaging system. Results demonstrate the possibility to detect hemorrhagic strokes with microwave systems when applying the proposed reconstruction algorithm with edge preserving regularization.
A fundamental problem in parallel and distributed processing is the partial serialization that is imposed due to the need for mutually exclusive access to common resources. In this article, we investigate the problem ...
详细信息
A fundamental problem in parallel and distributed processing is the partial serialization that is imposed due to the need for mutually exclusive access to common resources. In this article, we investigate the problem of optimally scheduling (in terms of makespan) a set of jobs, where each job consists of the same number L of unit-duration tasks, and each task either accesses exclusively one resource from a given set of resources or accesses a fully shareable resource. We develop and establish the optimality of a fast polynomial-time algorithm to find a schedule with the shortest makespan for any number of jobs and for any number of resources for the case of L = 2. In the notation commonly used for job-shop scheduling problems, this result means that the problem J vertical bar d(ij) = 1, n(j) =2 vertical bar C-max ax is polynomially solvable, adding to the polynomial solutions known for the problems J2 vertical bar n(j) <= 2 vertical bar C-max and J2 vertical bar d(ij) = 1 vertical bar C-max (whereas other closely related versions such as J2 vertical bar n(j)<= 3 vertical bar C-max, J2 vertical bar d(ij) is an element of {1,2}C-max, J3 vertical bar d(ij) =1 vertical bar C-max, J3 vertical bar d(ij) =1 vertical bar and J vertical bar d(ij) =1, n(j) <= 3 vertical bar C-max are all known to be NP-complete). For the general case L > 2 (i.e., for the job-shop problem J vertical bar d(ij) =1, nj = L >2 vertical bar C-max) we present a competitive heuristic and provide experimental comparisons with other heuristic versions and, when possible, with the ideal integer linear programming formulation.
Saccadic eye movements move the high-resolution fovea to point at regions of interest. Saccades can only be generated serially (i.e., one at a time). However, what remains unclear is the extent to which saccades are p...
详细信息
Saccadic eye movements move the high-resolution fovea to point at regions of interest. Saccades can only be generated serially (i.e., one at a time). However, what remains unclear is the extent to which saccades are programmed in parallel (i.e., a series of such moments can be planned together) and how far ahead such planning occurs. In the current experiment, we investigate this issue with a saccade contingent preview paradigm. Participants were asked to execute saccadic eye movements in response to seven small circles presented on a screen. The extent to which participants were given prior information about target locations was varied on a trial-by-trial basis: participants were aware of the location of the next target only, the next three, five, or all seven targets. The addition of new targets to the display was made during the saccade to the next target in the sequence. The overall time taken to complete the sequence was decreased as more targets were available up to all seven targets. This was a result of a reduction in the number of saccades being executed and a reduction in their saccade latencies. Surprisingly, these results suggest that, when faced with a demand to saccade to a large number of target locations, saccade preparation about all target locations is carried out in parallel.
This paper proposes a novel framework to efficiently calculate a large-scale finite element (FE) numerical substructure in real-time hybrid simulation (RTHS). It is composed of a non-real-time Windows computer and a r...
详细信息
This paper proposes a novel framework to efficiently calculate a large-scale finite element (FE) numerical substructure in real-time hybrid simulation (RTHS). It is composed of a non-real-time Windows computer and a real-time Target Computer. The Windows computer is used to solve the FE numerical substructure by parallel computing in soft real-time, while the real-time Target Computer generates displacement signals for the controller in real time. Based on the proposed framework, a RTHS with numerical substructure simulated in Windows environment is developed. It is demonstrated that the computational efficiency of the RTHS could be greatly improved by parallel programming.
Nowadays, performance in processors is increased by adding more cores or wider vector units, or by combining accelerators like GPUs and traditional cores on a chip. programming for these diverse architectures is a cha...
详细信息
In this paper, we present our learning experience on the design and implementation of image dehazing parallel code with OpenMP developed from existing fast sequential version. The aim of this work is to present an ana...
详细信息
In this paper, we present our learning experience on the design and implementation of image dehazing parallel code with OpenMP developed from existing fast sequential version. The aim of this work is to present an analysis of a case study showing the development of parallel haze removal with practical and efficient use of shared memory multi-core servers. Implementation technique and result discussions in terms of program improvements that may be needed to support parallel application developers with similar high performance goals are presented. Preliminary studies, results and experiments on haze removal application program are executed on multi-core shared memory platforms, and results show that the performance of the proposed parallel code is promising.
While the frame rate is higher and the image size is larger, sequence images processing is harder. Good real-time can be ensured by the multi-core DSP in the embedded image processing system. TMS320C6670 which is the ...
详细信息
ABSTRACTAlthough the teaching of programming has evolved over 50 years, all methodologies rely on a simple structure that was born a long time ago: the loop, shared by all high-level programming languages, and th...
详细信息
ABSTRACTAlthough the teaching of programming has evolved over 50 years, all methodologies rely on a simple structure that was born a long time ago: the loop, shared by all high-level programming languages, and the preferred choice for any repetitive task programmers face. We analyze here how “loops” skew the way programmers solve problems, and prevent them from taking advantage of the available parallel/distributed computing architectures. To do so, we state our initial hypothesis: eliminating loops will allow a more natural parallel programming approach. The idea is to mimic a common practice today that was established in the past for a different purpose: prohibiting goto statements to improve code maintainability. This paper describes a new computer programming teaching strategy that we tested for 7 years and provides evidence on how loop prohibition, in the context of Functional programming, makes students aware of data dependencies and produces 21st-century programmers who benefit from widely available parallel architectures.
parallel hardware is today's reality and language extensions that ease exploiting its promised performance ourish. For most mainstream languages, one or more tailored solutions exist that address the specific need...
详细信息
暂无评论