Catálogo de publicaciones - libros

Traditionally, checkpointing techniques have been used to secure the execution of sequential and parallel programs. This article shows that checkpointing techniques can also be used to automatically generate a parallel program from a sequential program, this program being executed on any kind of distributed parallel system. The article also presents how this new technique have been included inside the usual compilation chain to provide a distributed implementation of OpenMP. Finally, some performance measurements are discussed.

An approach to generation and optimization of scheduling and resource allocation strategies in scalable computing systems is proposed. The approach allows the decomposition of the problem of multicriteria strategy synthesis for the totality of parameterized models of programs with the use of partial and vector quality criteria including, for instance, a cost function and load balancing factors.

This paper provides a detailed investigation of latency penalties caused by repeated memory writes to nearby memory cells from different threads in parallel programs. When such writes map to the same corresponding cache lines in multiple processors, one can observe the so called effect. This effect can unnecessarily hamper parallel code due to the line granularity based cache hierarchy, which is common on contemporary processor architectures. In this contribution, a benchmark allowing for quantitative estimates about the consequences of the false sharing effect, is presented. Results show that multicore architectures with shared cache can reduce unwanted effects of false sharing.

Internet traffic patterns can cause serious buffer overflow in electronic business (e-business) systems. This leads to widespread retransmission that prolongs the service roundtrip time (RTT). As a result customers are unhappy and avoid returning to do more business. The previous Real-Time Traffic Pattern Detector (RTPD) was proposed to improve Internet channel fault tolerance. With RTPD support time-critical applications can identify the traffic patterns and invoke the corresponding measures to neutralize their ill effects in a dynamic manner. The extant RTPD, however, cannot detect self-similar traffic. This inspired the development of the novel self-similarity () filter proposed in this paper, which makes the RTPD capability more complete. The “RTPD + ” package is the RTPD or ERTPD package. The test results indicate that the addition of the mechanism can indeed contribute to improved e-business communication channels over the Internet.

We propose an approach to speed up the singular value decomposition (SVD) of very large rectangular matrices using the CSX600 floating point coprocessor. The CSX600-based acceleration board we use offers 50GFLOPS of sustained performance, which is many times greater than that provided by standard microprocessors. However, this performance can be achieved only when a vendor-supplied matrix-matrix multiplication routine is used and the matrix size is sufficiently large. In this paper, we optimize two of the major components of rectangular SVD, namely, QR decomposition of the input matrix and back-transformation of the left singular vectors by matrix , so that large-size matrix multiplications can be used efficiently. In addition, we use the Integrable SVD algorithm to compute the SVD of an intermediate bidiagonal matrix. This helps to further speed up the computation and reduce the memory requirements. As a result, we achieved up to 3.5 times speedup over the Intel Math Kernel Library running on an 3.2GHz Xeon processor when computing the SVD of a 100,000 × 4000 matrix.

Shortest-Path-Tree (SPT) computation, as the main load in OSPF protocol, contributes to the slow convergence time in intra-domain routing. With the increasing interest for upcoming routers of multi-core based processing board, efficient parallel routing algorithms are required to take this advantage to speedup SPT computation in order to meet the needs for fast failure recovery applications such as VoIP. However, currently available parallel SPT algorithms are all based on static method, which re-computes the entire tree for each link change. In this paper, we explore parallel algorithms for dynamic SPT update, a more efficient method, which only updates the affected nodes by making use of the previous SPT We first analyze characters of dynamic method to show how they affect parallel design; then we give our parallel dynamic SPT algorithm framework, which uses: (1) parallel distance-updating mode, to get a near liner speedup (assuming perfect load balance) and (2) group-removal schema, to reduce communication cost. Further, to provide load balance, we give a task distribution algorithm called RR_DFS, which makes use of the topology information of the previous SPT. Complexity analysis and simulation result are also presented

The paper presents a set of theoretical experiments performed to evaluate Situated Cellular Agent (SCA) approach within pedestrian dynamics research context. SCA is a modeling and simulation approach based on Multi Agent Systems principles that derives from Cellular Automata. In particular, we focus on two emerging phenomena (freezing by heating and lane formation phenomena) that have been empirically observed and already modeled by analytical particle–based models and Cellular Automata–based models.

Simulating spatial dynamics in physics by Cellular Automata (CA) requires very large computation power, and, hence, CA simulation algorithms are to be implemented on multiprocessors. The preconceived opinion, that no much effort is required to obtain highly efficient coarse grained parallel CA algorithm, is not always true. In fact, a great variety of CA modifications coming into practical use need appropriate, sometimes sophisticated, methods of CA algorithms parallel implementation. Proceeding from the above a general approach to CA parallelization, based on domain decomposition correctness conditions, is formulated. Starting from the correctness conditions particular parallelization methods are developed for the main classes of CA simulation models: synchronous CA with multi-cell updating rules, asynchronous probabilistic CA, and CA compositions. Examples and experimental results are given for each case.

Complex matter may lie in various forms from granular matter, soft matter, fluid-fluid or solid-fluid mixtures to compact heterogeneous material. Cellular automata models make a suitable and powerful tool to catch the influence of the microscopic scale onto the macroscopic behaviour of these complex systems. Rather than a survey, this paper will attempt to bring out the main concepts underlying these models and to give an insight for future work.

The dynamic behaviour of the CO oxidation reaction over Pd(110) has been studied by means of probabilistic asynchronous cellular automata (Dynamic Monte-Carlo). The influence of the internal parameters on the shapes of surface concentration waves obtained in simulations under the limited surface diffusion intensity conditions has been studied. The hysteresis in oscillatory behaviour has been found under step-by-step variation of oxygen partial pressure. Two different oscillatory regimes could exist at one and the same parameters of the reaction. The parameters of oscillations (amplitude, period and the shape of spatio-temporal patterns on the surface) depend on the kinetic prehistory of the system. The possibility for the appearance of the cellular and turbulent patterns, spiral, target and stripe oxygen waves on the surface in the cases under study has been shown.