The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
As hardware becomes more flexible in terms of programming, software APIs must expose hardware features in a portable way. Thread to thread communication is being exposed in OpenCL 2.0 through the newly defined work-group functions. In this paper we analyze the work-group broadcast functionality in the OpenCL compiler backend for Intel's GPUs. We first describe the particularities of Intel's GEN GPU...
WIEN2k is a program package that utilizes Density Functional Theory (DFT) to describe materials and calculate their properties. This is done by numerically solving the Schrödinger equation. The most expensive part of such calculations in terms of consumption of computational resources is the numerical solution of hermitian (or symmetric) generalized eigenvalue problems that involve large matrices...
In order to obtain maximum throughput (i.e. jobs/second) and maximum hardware utilization in a highperformance computing (HPC) scenario, it is necessary to use proper scheduling of the different jobs among the available resources. In the case of heterogeneous platforms combining both CPUs and GPUs, an entire job could be delayed because of the lack of GPU resources (e.g. GPU memory), while CPU resources...
Deep neural networks are more accurate, but require more computational power in the learning process. Moreover, it is an iterative process. The goal of the research is to investigate efficiency of solving this problem on MIC architecture without changing baseline algorithm. Well-known code vectorization and parallelization methods are used to increase the effectiveness of the program on MIC architecture...
Usual Parallel Discrete Event System Specification (P-DEVS) allows specifying systems from modeling to simulation. However, the framework does not incorporate parallel and stochastic simulations. This work intends to extend P-DEVS to parallel simulations and pseudorandom number generators in the context of a spiking neural network. The discrete event specification presented here makes explicit and...
Modern HPC clusters are increasingly heterogeneous both in processor types, topologies of computing, communication and storage resources. In this paper, we describe how to use benchmarking, to characterize the high-speed interconnect, NumaConnect, associated with a shared-memory Numascale cluster system with GPUs, constituting a novel testbed at NTNU. Numascale systems include a unique node controller,...
Phase clustering and identification schemes provide useful insights to optimize the application execution, providing the means to accurately control scheduling and migration mechanisms in heterogeneous and reconfigurable architectures. However, while conventional coarse-grained classification mechanisms can be used for most straightforward optimizations, finegrained resolutions are often required...
Ineffective data access of cache memory has become a bottleneck for efficient 2-dimensional (2-D) data processing, such as image processing and matrix multiplication. To solve this problem, a cache memory with both unit tile and unit line accessibility, based on a 4-level Z-order tiling layout is proposed. Conventional raster scan order access to this layout is enabled via a hardware-based address...
Most of today's processors provide strong support for single instruction multiple data (SIMD, or vector) operations. But because modern compilers often fail to generate optimal SIMD code, explicitly written SIMD code is still the most performant. However, native SIMD code has some major disadvantages, mainly that it is quite cumbersome, that it is not easily ported to different instruction sets, and...
A very important component of modern weather forecasting is the use of numerical weather prediction (NWP) models. In the last years, the forecast quality of those models constantly improved, mostly due to major improvements in highperformance computing, which allows a finer horizontal grid resolution. Mountainous terrain, however, still poses a challenge for NWP models, mainly due to not sufficient...
Partial Differential Equations (PDEs) lie at the heart of numerous scientific simulations depicting physical phenomena. The parallelization of such simulations introduces additional performance penalties in the form of local and global synchronization among cooperating processes. Domain decomposition partitions the largest shareable data structures into sub-domains and attempts to achieve perfect...
The heat induced by computing resources is generally a waste of energy in supercomputers. This is especially true in very large scale supercomputers, where the produced heat has to be compensated with expensive and energy consuming cooling systems. Energy is a critical point for future supercomputing trends that currently try to achieve exascale, without having its energy consumption reaching an important...
Finite Information Limit (FIL) variance-covariance structures for hierarchical data are introduced and examined: for such data, it is often possible to analyze only a sometimes very small subset, leading to considerable computation time gain, with almost no efficiency loss. A central example is compound-symmetry. A simple approach is proposed to detect this property in a given dataset.
Wildland fires at any location are a result of complex interactions between fuel, forest structure, topography, ignitions and weather conditions. Therefore, there is great interest in the development of computational tools for the prediction of these interactions during a wildland fire. A computational model that attempts to predict the spread of flames must provide a representation of the evolution...
The use of high performance computing has been gaining more and more followers in the different branches of Science and Engineering given the potential offered to deal with complex and big problems. However, the parallel programming paradigm involves additional aspects to the merely functional, which could provoke different kinds of bottlenecks in the performance of the applications. Such diff culties...
The acoustic cardiopulmonary signals contain complex but quantifiable essential diagnostic signs. Particularly, the lung sounds associated with inhalation and exhalation, and the heart sounds as particularly characterized by their principal components S1 and S2 when quantitatively utilized could improve the classification accuracy of diverse disease conditions. This project is related to the events...
This paper presents a MapReduce-based implementation of using high-dimensional image streams from inside-out and outside-in views applied to a simplistic SIFT-based feature extraction method to provide a fast and more accurate object recognition algorithm. We have combined multiple camera streams and have shown that using inside-out vision significantly improves the recognition precision. We show...
Modern computer systems typically conbine multicore CPUs with accelerators like GPUs for inproved performance and energy efficiency. However, these systems suffer from poor performance portability — code tuned for one device must be retuned to achieve high performance on another. Image processing is increasing in importance, with applications ranging from seismology and medicine to Photoshop. Based...
Recent developments in cloud storage architectures have originated new models of online storage as cooperative storage systems and interconnected clouds. Such distributed environments involve many organizations, thus ensuring confidentiality becomes crucial: only legitimate clients should recover the information they distribute among storage nodes. In this work we present a unified framework for verifying...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.