Related Experiment Video
Updated: May 24, 2026
07:52
Cryo-Electron Microscopy Screening Automation Across Multiple Grids Using Smart Leginon
Published on: December 1, 2023
Parallel computational steering for HPC applications using HDF5 files in distributed shared memory
John Biddiscombe1, Jerome Soumagne, Guillaume Oger
1CSCS Swiss National Supercomputing Centre, Galleria 2, Via Cantonale, Manno 6928, Switzerland. biddisco@cscs.ch
IEEE Transactions on Visualization and Computer Graphics
|February 22, 2012
Summary
Supercomputers become interactive instruments by linking graphical user interface (GUI) analysis tools with high-performance computing (HPC) applications. This enables real-time simulation steering and data manipulation for complex scientific workflows.
Area of Science:
- Computational Science and Engineering
- High-Performance Computing (HPC)
- Scientific Visualization and Analysis
Background:
- Traditional supercomputing workflows often involve batch processing, limiting interactive analysis and rapid parameter exploration.
- Integrating visualization and analysis tools directly with HPC applications is challenging due to data transfer and synchronization issues.
Purpose of the Study:
- To transform supercomputers into interactive instruments by enabling real-time visualization and analysis of simulation data.
- To develop a flexible framework for concurrent parallel simulation and analysis, facilitating dynamic steering of scientific workflows.
Main Methods:
- Replaced the Input/Output (IO) layer of the Hierarchical Data Format 5 (HDF5) library with a custom parallel data transfer driver.
- Utilized ParaView as the graphical user interface (GUI) for concurrent parallel analysis, supporting flexible resource allocation for simulation and analysis.
- Implemented a distributed shared memory file system for seamless bidirectional data flow between simulation and analysis components.
- Developed an XML templating system to automatically generate GUI controls for simulation steering, eliminating manual customization.
Main Results:
- Achieved parallel data transfer between simulation and analysis, allowing concurrent execution on the same or separate machines.
- Enabled dynamic modification of simulation data, including parameter changes, grid remeshing, and field value regeneration, through the GUI.
- Demonstrated the ability to reuse modified data within the simulation loop, creating a closed-loop interactive workflow.
Conclusions:
- The developed framework effectively integrates HPC applications with GUI-driven analysis tools, turning supercomputers into interactive instruments.
- This approach significantly enhances the flexibility and efficiency of scientific workflows by enabling real-time steering and data manipulation.
- Automatic GUI generation using XML templates streamlines the process of adapting the interactive system to diverse simulation applications.
Related Concept Videos
01:17Steady, Laminar Flow Between Parallel Plates
Understanding steady, laminar flow between parallel plates is essential for analyzing and designing flow in narrow rectangular channels, commonly found in various water conveyance and drainage systems. The Navier-Stokes equations govern fluid motion and are generally challenging to solve due to their nonlinearity. However, simplifications are possible in certain cases, like the steady laminar flow between parallel plates. For this scenario, we assume steady, incompressible, laminar flow.
01:21Distributed Loads: Problem Solving
Beams are structural elements commonly employed in engineering applications requiring different load-carrying capacities. The first step in analyzing a beam under a distributed load is to simplify the problem by dividing the load into smaller regions, which allows one to consider each region separately and calculate the magnitude of the equivalent resultant load acting on each portion of the beam. The magnitude of the equivalent resultant load for each region can be determined by calculating...
01:19Distributed Loads
Distributed loads are a common type of load that engineers and scientists encounter in various practical situations. Distributed loads often refer to a type of load spread over a surface or a structure and can be modeled as continuous force per unit area.
For example, consider a bookshelf filled with books stacked vertically adjacent to each other. The weight of the books is evenly distributed over the length of the shelf. As a result, the pressure at different locations on the surface of the...
For example, consider a bookshelf filled with books stacked vertically adjacent to each other. The weight of the books is evenly distributed over the length of the shelf. As a result, the pressure at different locations on the surface of the...
01:25Multimachine Stability
Multimachine stability analysis is crucial for understanding the dynamics and stability of power systems with multiple synchronous machines. The objective is to solve the swing equations for a network of M machines connected to an N-bus power system.
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
01:14Shearing Stresses in a Beam: Problem Solving
A cantilever beam with a rectangular cross-section under distributed and point loads experiences shearing stresses. The analysis begins by identifying the loads acting on the beam. Then, the reactions at the beam's fixed end are calculated using equilibrium equations. The vertical reaction is a combination of the distributed and point loads, while the moment reaction is the sum of their moments. The shear force distribution along the beam, resulting from these loads, is established by creating...
01:06Parallel-axis Theorem
The parallel-axis theorem provides a convenient and quick method of finding the moment of inertia of an object about an axis parallel to the axis passing through its center of mass. Consider a thin rod as an example. There is a striking similarity between the process of finding the moment of inertia of a thin rod about an axis through its middle, where the center of mass lies, and about an axis through its end using the conventional method. In the conventional method, the concept of linear mass...