High performance computing platform is moving from homogeneous individual unites to heterogeneous systems. Where each unit is a combination of homogeneous cores and accelerator devices. Accelerator such as GPUs, FPGAs, DSPs, these devices usually designed for the specific and intensive type of computing tasks. The presence of these devices have created fresh and attractive development platforms for developers and designers, brand new performance analysis frameworks and optimization tools. This is the cutting edge in the performance of some accelerator devices like GPUs and Intel's Xeon Phi. We outline some of the existing heterogeneous systems and their development frameworks. The core of this study is a review of performance modeling of these devices. In this paper, we address the emerging issues that affect the performance of these devices and associated techniques employed for simulation and evaluation.

No abstract

a b s t r a c tWe propose an extension to multiple dimensions of the univariate index of agreement between Probability Density Functions (PDFs) used in climate studies. We also provide a set of high-performance programs targeted both to single and multi-core processors. They compute multivariate PDFs by means of kernels, the optimal bandwidth using smoothed bootstrap and the index of agreement between multidimensional PDFs. Their use is illustrated with two case-studies. The first one assesses the ability of seven global climate models to reproduce the seasonal cycle of zonally averaged temperature. The second case study analyzes the ability of an oceanic reanalysis to reproduce global Sea Surface Temperature and Sea Surface Height. Results show that the proposed methodology is robust to variations in the optimal bandwidth used. The technique is able to process multivariate datasets corresponding to different physical dimensions. The methodology is very sensitive to the existence of a bias in the model with respect to observations.

Kernel density estimation (KDE) is a statistical technique used to estimate the probability density function of a sample set with unknown density function. It is considered a fundamental data-smoothing problem for use with large datasets, and is widely applied in areas such as climatology and biometry. Due to the large volumes of data that these problems usually process, KDE is a computationally challenging problem. Current HPC platforms with built-in accelerators have an enormous computing power, but they have to be programmed efficiently in order to take advantage of that power. We have developed a novel strategy to compute KDE using bounded kernels, trying to minimize memory accesses, and implemented it as a parallel program targeting multi-core and many-core processors. The efficiency of our code has been tested with different datasets, obtaining impressive levels of acceleration when taking as reference alternative, state-of-the-art KDE implementations.

The increase in the number of large scale events held indoors (i.e. conferences and business events) opens new opportunities for crowd monitoring and access controlling as a way to prevent risks and provide further information about the event's development. In addition, the availability of already connectable devices among attendees allows to perform non-intrusive positioning during the event, without the need of specific tracking devices. We present an algorithm for overcrowding detection based on passive Wi-Fi requests capture and a platform for event monitoring that integrates this algorithm. The platform offers access control management, attendees monitoring and the analysis and visualization of the captured information, using a scalable software architecture. In this paper, we evaluate the algorithm in two ways: first, we test its accuracy with data captured in a real event, and then we analyse the scalability of the code in a multi-core Apache Spark-based environment. The experiments show that the algorithm provides accurate results with the captured data, and that the code scales properly.