A5014158900- Distributed and Parallel Computing Systems
- Parallel Computing and Optimization Techniques
- Scientific Computing and Data Management
- Advanced Data Storage Technologies
- Advanced Numerical Methods in Computational Mathematics
- Cloud Computing and Resource Management
- Scientific Research and Discoveries
- Matrix Theory and Algorithms
- Advanced Data Compression Techniques
- Numerical methods for differential equations
- Image and Signal Denoising Methods
- Algorithms and Data Compression
- Digital Filter Design and Implementation
- Nuclear reactor physics and engineering
- Fusion materials and technologies
- Gene Regulatory Network Analysis
- Theoretical and Computational Physics
- Advanced Data Processing Techniques
- Simulation Techniques and Applications
- Meteorological Phenomena and Simulations
- Risk and Safety Analysis
- Single-cell and spatial transcriptomics
- Bioinformatics and Genomic Networks
- Reservoir Engineering and Simulation Methods
- CO2 Sequestration and Geologic Interactions
Poznan Supercomputing and Networking Center
2011-2021
Polish Academy of Sciences
2019
Abstract Validation, verification, and uncertainty quantification (VVUQ) of simulation workflows are essential for building trust in results, their increased use decision‐making processes. The EasyVVUQ Python library is designed to facilitate implementation advanced VVUQ techniques new or existing workflows, with a particular focus on high‐performance computing, middleware agnosticism, multiscale modeling. Here, the application five very diverse areas demonstrated: materials properties,...
We present the VECMA toolkit (VECMAtk), a flexible software environment for single and multiscale simulations that introduces directly applicable reusable procedures verification, validation (V&V), sensitivity analysis (SA) uncertainty quantification (UQ). It enables users to verify key aspects of their applications, systematically compare validate simulation outputs against observational or benchmark data, run conveniently on any platform from desktop current multi-petascale computers. In...
Summary The goal of this study is to adapt the multiscale fluid solver EULerian or LAGrangian framewrok (EULAG) future graphics processing units (GPU) platforms. EULAG model has proven record successful applications, and excellent efficiency scalability on conventional supercomputer architectures. Currently, being implemented as new dynamical core COSMO weather prediction framework. Within study, two main modules EULAG, namely multidimensional positive definite advection transport algorithm...
We describe our Multiscale Computing Patterns software for High Performance Computing. Following a short review of Patterns, this paper introduces the Software, which consists description, optimisation and execution components. First, description component translates task graph, representing multiscale simulation, to particular type computing pattern. Second, selects applies algorithms find most suitable mapping between submodels available HPC resources. Third, middleware layer maps number...
The use of graphics hardware for non-graphics applications has become popular among many scientific programmers and researchers as we have observed a higher rate theoretical performance increase than the CPUs in recent years. However, gains may be easily lost context specific parallel application due to various both software factors. Consequently, benchmarks testing are still best techniques compare effciency emerging architectures with built-in support parallelism at different levels....
With the recent advent of novel multi- and many-core hardware architectures, application programmers have to deal with many hardware-specific implementation details be familiar software optimization techniques benefit from new high-performance computing machines. Highly effcient parallel design is in fact an interdisciplinary process involving domain specific IT experts. Therefore, this paper aims present early experiences computationally demanding applications, development efforts...
We describe a method for queue wait time prediction in supercomputing clusters. It was designed use as part of multi-criteria brokering mechanisms resource selection multi-site High Performance Computing environment. The aim is to incorporate the jobs stay queued scheduling system into criteria. Our can also be used by end users estimate completion their computing jobs. uses historical data about particular make predictions. returns list probability estimates form ( t i, p i), where i that...
The growing demand for computational power causes that Grids are becoming mission-critical components in research and industry, offering sophisticated solutions leveraging large-scale computing storage resources.The nature a Grid which resources usually shared among multiple organizations under their control based on the "best effort" approach with no guarantee concerning quality-of-service may be inadequate to support simulations.Requirements of such simulations often exceed capabilities...
In large scale production and scientific, academic environments, the information sets to perform computations on come from various sources. particular, some may require obtained as a result of previous computations. Workflow description offers an attractive approach formally deal with such complex processes. Vine Toolkit solution addresses major challenges here synchronization distributed workflows, establishing community driven grid environment for seamless results sharing collaboration....
The extreme scaling pattern of the ComPat project is applied to a multi-scale workflow relevant magnetically confined fusion problem. This combines transport, turbulence and equilibrium codes (together with additional auxiliaries such as initial conditions numerical module), which aims at calculating behaviour plasma on long (transport) time scales based information from much faster (turbulence) scales. Initial findings profile measurements are reported in this paper indicate that, depending...
The recent advent of novel multi- and many-core architectures forces application programmers to deal with hardware-specific implementation details be familiar software optimisation techniques benefit from new high-performance computing machines. Extra care must taken for communication-intensive algorithms, which may a bottleneck forthcoming era exascale computing. This paper aims present high-level stencil framework implemented the EULerian or LAGrangian model (EULAG) that efficiently...