SuperComputing 2014 (SC14) is a premier conference in the scientific computing field. Attendees include industry leaders in high performance computing, networking, storage, and analysis. At the conference, research and innovation will be highlighted to showcase new scientific and economic opportunities.
Kitware’s participation in SC14 includes:
- Exhibiting a ParaView Showcase at our booth (#1354). If you are intersted in sharing your ParaView-generated visualizations to be featured in the showcase, please read the SC14 blog entry.
- Presenting tutorials on ‘Large Scale Visualization with ParaView’ and ‘In Situ Data Analysis and Visualization with ParaView Catalyst.’
- Presenting a paper on extreme scale in situ visualization and analysis.
- Taking part in the SC14 Student Job/Opportunity Fair on November 19, 2014, from 10:00 am to 3:00 pm.
- Authoring a paper on sustainable software ecosystems for the 2nd Workshop on Sustainable Software for Science: Practice and Experiences (WSSSPE2).
- Presenting a movie on In Situ MPAS-Ocean Image-based Visualization at the Visualization and Data Analytics Showcase.
- Co-authoring a presentation on ‘Instruction Memory Overhead of In Situ Visualization Libraries on HPC Machines.’
- Presenting an invited talk on ‘VTK-M: Uniting GPU Acceleration Successes’
Descriptions of the talks, presentations, and papers are provided below. To learn how Kitware can help you meet your HPC and visualization needs, please contact (518) 371-3971 or kitware@kitware.com.
Be sure to sure to stop by and visit us at our booth!
Large Scale Visualization with ParaView
Kenneth Moreland (Sandia), W. Alan Scott (Sandia), David E. DeMarle (Kitware), Joseph Insley (Argonne), Ollie Lo (Los Alamos), Robert Maynard (Kitware), and Sebastien Jourdain (Kitware) will present this tutorial on November 16, 2014, from 8:30 am to 5:00 pm in room 389.
Abstract
ParaView is a powerful open-source turnkey application for analyzing and visualizing large data sets in parallel. Designed to be configurable, extendible, and scalable, ParaView is built upon the Visualization Toolkit (VTK) to allow rapid deployment of visualization components. This tutorial presents the architecture of ParaView and the fundamentals of parallel visualization. Attendees will learn the basics of using ParaView for scientific visualization with hands-on lessons. The tutorial features detailed guidance in visualizing the massive simulations run on today’s supercomputers and an introduction to scripting and extending ParaView. Attendees should bring laptops to install ParaView and follow along with the demonstrations.
In Situ Data Analysis and Visualization with ParaView Catalyst
David H. Rogers (LANL), Nathan Fabian (Sandia), Thierry Carrard (French Alternative Energies and Atomic Energy Commission), and Andy Bauer (Kitware) will present this tutorial on November 17, 2014, from 8:30 am to 12:00 pm in room 394.
Abstract
As supercomputing moves towards exascale, scientists, engineers and medical researchers will look for efficient and cost effective ways to enable data analysis and visualization for the products of their computational efforts. The ‘exa’ metric prefix stands for quintillion, and the proposed exascale computers would approximately perform as many operations per second as 50 million laptops. Clearly, typical spatial and temporal data reduction techniques employed for post processing will not yield desirable results where reductions of 10-3, 10-6, or 10-9 may still produce petabytes, terabytes or gigabytes of data to transfer or store. Since transferring or storing data may no longer be viable for many simulation applications, data analysis and visualization must now be performed in situ. ParaView Catalyst is an open-source data analysis and visualization library, which aims to reduce IO by tightly coupling simulation, data analysis and visualization codes. This tutorial presents the architecture of ParaView Catalyst and the fundamentals of in situ data analysis and visualization. Attendees will learn the basics of using ParaView Catalyst with hands-on exercises. The tutorial features detailed guidance in implementing C++, Fortran and Python examples. Attendees should bring laptops to install a VirtualBox image and follow along with the demonstrations.
An Image-Based Approach to Extreme Scale In Situ Visualization and Analysis
By James Ahrens (LANL), Sebastien Jourdain (Kitware), Patrick O’Leary (Kitware), John Patchett (LANL), David H. Rogers (LANL), Mark Petersen (LANL)
This paper will be presented on November 19, 2014, during the Big Data Analysis session in rooms 391-92.
Abstract
Extreme scale scientific simulations are leading a charge to exascale computation, and data analytics runs the risk of being a bottleneck to scientific discovery. Due to power and I/O constraints, we expect in situ visualization and analysis will be a critical component of these workflows. Options for extreme scale data analysis are often presented as a stark contrast: write large files to disk for interactive, exploratory analysis, or perform in situ analysis to save detailed data about phenomena that a scientists knows about in advance. We present a novel framework for a third option – a highly interactive, image-based approach that promotes exploration of simulation results, and is easily accessed through extensions to widely used open source tools. This in situ approach supports interactive exploration of a wide range of results, while still significantly reducing data movement and storage.
Sustainable Software Ecosystems: Software Engineers, Domain Scientists, and Engineers Collaborating for Science
By Marcus Hanwell (Kitware), Patrick O’Leary (Kitware), Bob O’Bara (Kitware)
This paper has been accepted to the 2nd Workshop on Sustainable Software for Science: Practice and Experiences (WSSSPE2). The full paper is available on figshare.
Abstract
The development of scientific software is often a partnership between domain scientists and scientific software engineers. It is especially important to embrace these collaborations when developing advanced scientific software, where sustainability, reproducibility, and extensibility are important. In the ideal case, as discussed in this manuscript, this brings together teams composed of the world’s foremost scientific experts in a given field with seasoned software developers experienced in forming highly collaborative teams working on software to further scientific research [1].
In addition to enabling scientists to perform research more effectively, enriching the field by offering well-engineered software, sustainable software frees researchers from performing tasks that do not offer the rewards that their institution values. When these software platforms are developed as collaborative R&D platforms, it also empowers both the team developing the software and the wider community. We will present case studies of two DOE sponsored SBIR projects–one in nuclear engineering that began in 2013, and another in scanning transmission electron microscopy tomography (S/TEM) for materials. These projects build upon the Visualization Toolkit (VTK), and ParaView, each of which has over a decade of development history funded by multiple
agencies in collaboration with many institutions [2].
It is clear that there are examples where heroic efforts created sustainable software, but this is clearly the exception–not the rule. Many of these projects required significant sacrifice, and some risky bets outside of established career paths. Their efforts should be applauded, but we must as a community develop the necessary governance, policy, and credit mechanisms to make sustainable, reproducible scientific software a reality. Its importance in the sphere of scientific investigation is getting increasingly important. Many of these points were touched upon in the first Workshop on Sustainable Software Ecosystems for Open Science [3].
[1] Ibanez L, Schroeder W, Hanwell MD. Practicing Open Science. In: Implementing Reproducible Computational Research. Chapman and Hall/CRC; 2014. p. 241{280.
[2] Hanwell MD, Perera A, Turner W, O’Leary P, Osterdahl K, Hoffman B, et al. Sustainable Software Ecosystems for Open Science. figshare; 2013. 790756. Available from: http://dx.doi.org/10.6084/m9.figshare.790756.
[3] Katz D, Choi SC, Lapp H, Maheshwari K, Lofer F, Turk M, et al. Summary of the First Workshop on Sustainable Software for Science: Practice and Experiences (WSSSPE1). Journal of Open Research Software. 2014;2(1). Available from: http://openresearchsoftware.metajnl.com/article/view/jors.an.
Instruction Memory Overhead of In Situ Visualization Libraries on HPC Machines
By Nathan Fabian (Sandia), Ken Moreland (Sandia), Jeff Mauldin (Sandia), Ben Boeckel (Kitware), Utkarsh Ayachit (Kitware), Andy Bauer (Kitware), Berk Geveci (Kitware)
This presentation will be given by Nathan Fabian from Sandia at the Ultrascale Visualization Workshop, which will take place on November 16, 2014.
VTK-M: Uniting GPU Acceleration Successes
This talk will be presented by Robert Maynard (Kitware) on November 19, 2014, from 3:00 pm to 3:30 pm at the NVIDIA booth.
Description
Designed by the developers of the EAVL, DAX, and PISTON visualization libraries, VTK-M seeks to be the reference accelerator based visualization library for the next generation of HPC machines. Learn both the success stories of each project and how they have influenced the design of VTK-M.
Physical Event