|
|
February 12 Covise users can download and compile our Qt-based desktop renderer sources from HLRS GForge server:
https://gforge.hlrs.de/projects/qtrenderer
Short Description
CovRemote can be used on Windows XP/2000/2003 to launch applications in a given user's environment.
It can be installed and run as a service on the clients. The controller runs with a GUI.
Features
Interactive applications can be launched on top of the Logon-Desktop. It is possible to add, remove and extend environment variables and to consistently mount network shares.
We created this application as there was a need to startup rendering clients from remote in the HLRS CAVE without the necessity of logging in to all the client machines.
Maintenance tasks (e.g. reboot, shutdown etc.) can be started as well as user-defined commands.
An AES encrypted communication is used for the communication with the controller instance.
The Controller application (GUI) and the windows service are integrated in one executable.
An Optional line-based interface in controller enables spawned applications to launch other instances of themselves on different nodes. This can be used with netcat as well to launch one of the predefined command templates.
Usage
The CovRemote-service is statically linked to the runtime-libraries (QT is used for the GUI part, which is also statically linked).
Deployment: simply copy covremote.exe and covremote.ini to a directory on the nodes and install the service with “covremote –i”
Other commandline-options:
u to uninstall
e to execute
t to terminate
gui to launch CovRemote-Controller
DEP (Data Execution Protection) should be set to “OptOut” and disabled for the CovRemote-Service.
A mapping of User-Shares can be enabled/disabled in the covremote.ini. It can cause problems (timeouts) if the shares cannot be mapped. Problems or errors can be resolved by checking the output in the controller GUI or the covremote.log – file created by the service.
Download
Covremote sources and binary can be downloaded from HLRS GForge website.
Pictures
GUI.gif shows the user interface of CovRemote
AppOnLogon.jpg shows a launched application on top of the windows logon screen
CommandTemplate.gif shows the command template window in CovRemote GUI
Communication1&2.png show two different usage scenarios
August 14 Since last Thursday (10th August) our visualization cluster is connected via Infiniband hardware, a Silverstorm switch and 32 HCAs, all double data rate (DDR). We are currently installing the drivers. Here is a picture of the switch:
June 01 We are glad to inform you that HLRS installed it's brand-new visualization cluster. The cluster is manufactured by DALCO AG, the swiss market leader for cluster solutions. We want to express our gratitude to Microsoft who funded the cluster within the HPC institutes project. The cluster is used to drive our CAVE, but it is not only used as a powerful visualization machine, but also as a compute cluster for online simulations and postprocessing. As we want to improve the parallel rendering capabilities of our visualization software COVISE, every node is equipped with a powerful Nvidia Quadro FX4500. That means that we intend to use 8 nodes to render each couple of stereo images on the 4 walls of the CAVE.The cluster will mostly run Windows Server 2003 Compute Cluster Server. Here are the specs of the machine:
- 32 nodes Dual Opteron 250 2.4 GHz, each equipped with
- 4 GB DDR400 ECC RAM
- Nvidia Quadro FX 4500 graphics board
- 2 x Gigabit Ethernet
- Infiniband switch and HCAs (both DDR) are already ordered and will arrive soon
Here you can find some pictures of the machine: 
More information and details about our experiences with the machine will follow soon. February 02 here is a list of users and application examples of our software. The list is not complete yet and still needs some work ... | | 
Click on the image to enlarge | |  Air Flow Consulting , Zürich, Switzerland
Visualisation of unsteady CFX simulation of a spreading fire in a flat
unsing COVISE. The concentration of burnt gases can be examined as well
as the temperature. By modelling the whole surrounding house, it can be
judged whether the existing emergency exits can be accessed securely
while the fire advances. | | |
|  | | | 
Click on the image to enlarge | | Calit² (California Institute for Telecommunications and Information Technology), San Diego, CA, USA Calit² installed a virtual reality wall driven by Covise and OpenCOVER.
Jürgen Schulze-Döbold and his colleagues have an ongoing project
concerning interactive visualisation of proteins from the Protein Data
Bank (PDB). They also visualize 3D earthquake locations on a
world-wide scale. Currently, they are integrating a method to
automatically access the latest measurements from the web.
Another
field of activity is the development of real-time volume rendering
algorithms for virtual environments. The algorithm has recently been
integrated with UIC/EVL's SAGE library to drive high-resolution tiled
displays.
See a more detailed list of projects here | | |
|  | | |  | | Department FT1/MS (Motor Simulation) Stuttgart, Germany The picture shows the visualization in COVISE of an engine simulation (intake stroke at partload) with STAR-CD. | | |  | | Department FT1/AK (Akustik und Klima), Stuttgart, Germany
The picture shows the visualization of a climate simulation in a truck
cabin. It's a coupled simulation consisting of three parts: Flow
simulation with heat transfer and radiation. The flow simulation was
performed with STAR-CD on a NEC SX-4 by Daimler-Benz (SFB 374, Rapid
Prototyping). | | |
| | |  | | Department xy, Bremen, Germany
Daimler-Benz Aerospace has been partner on the projects PAGEIN and
ADONNIS and is now involved into the projects EFENDA and SPOCK. In
Efenda the steps "grid generation", "simulation", "postprocessing and
visualization" are integrated into COVISE for efficient access of
remote supercomputers and for collaborative working. In SPOCK COVISE is
the integration platform for the aerodynamic disciplines "simulation",
"wind tunnel test" and "free flight test". | | |
| | | 
Click on the image to enlarge | | Fachhochschule Konstanz - Digitale Medien und Architekturdarstellung , Konstanz, Germany
FH Konstanz installed the "Immersive_Room", a “cave”-like immersive
virtual reality installation where they are using COVISE for projects
in teaching and research in architecture, urban planning simulation,
virtual words for humans, learning environments and communication
design. . | | |
| | | 
Click on the image to enlarge | | HS Mannheim - VRC (Virtual Reality Center) , Fakultät Maschinenbau Hochschule, Mannheim, Germany CAD, FEM, CFD, simulation and animated visualization of - machines,
- mechanical devices,
- systems,
- methods, and
- structures.
Developing and calculating of machines in mechanical engineering. | | |
| | | 
Click on the image to enlarge | | Hewlett Packard With HP, we are working on getting COVISE running on the SVA platform. On a tiled display visualization array we showed a COVISE application example at SC05 in Seattle.
At TechEd 2004 in Amsterdam, we showed a 3D online simulation demo
using HP Hardware for the keynote speech of Microsoft's vice president
and CTO of EMEA, Jonathan Murray.
| | |
| | | 
Click on the image to get a Quicktime-Movie | | IAG (Institut für Aerodynamik und Gasdynamik), Universität Stuttgart, Germany The department Transition and Turbulence
investigates the laminar-turbulent breakdown of a flat plate boundary
layer by Direct Numerical Simulation (DNS) solving the complete
incompressible Navier-Stokes equations. The evolving (Lambda)-Vortices
- 3D vortical structures within the boundary layer - are identified by
a vortex criterion, traced in time and visualized in a virtual reality
environment (CUBE) using COVISE. | | |
|  | | | 
Click on the image to enlarge | | IHS (Institut für Strömungsmechanik und Hydraulische Strömungsmaschinen), Universität Stuttgart, Germany
The long time collaboration with IHS focuses on the areas of
interactive simulation and Virtual Reality based techniques for
analyzing large scale CFD data mostly from the field of water turbine
design and optimization. The simulation code FENFLOSS developed at IHS
can be coupled to COVISE to perform online simulations. It is possible
to attach and deattach to and from running simulations. IHS has been
equipped with a large stereo projection wall complementing the CUBE
environment at HLRS. The picture shows automatically generated meshes
of wicked gate and runner in a radial turbine. | | |
| | | 
Click on the image to enlarge | | IMK (Institut für Meteorologie und Klimaforschung), Universität Karlsruhe, Germany The image shows a simulation of wind. | | |
| | | 
Click on the image to enlarge | | Intel Corporation
Demo using Intel Hardware showing an online Simulation at 2004 WinHEC
conference in Seattle for the keynote speech of Microsofts Chairman and
Chief Software Architect Bill Gates' keynote speech.
| | |
| | |  | | IFSW (Institut für Strahlwerkzeuge), Universität Stuttgart, Germany
The laser institute of the University of Stuttgart is cooperating with
us in the project SFB374 (Rapid Prototyping) in the field of
interactive analysis of laser hardening simulations (DIABLO) and VR
based analysis of laser welding processes (HEAT3D, picture). | | |
| | | 
Click on the image to enlarge
Click here to see a video of the deep drawing process (21,3 MB) | | IfU (Institut für Umformtechnik), Universität Stuttgart, Germany Institute for Metal Forming Technology
- deep drawing simulation
- VR system "Cycloop"
- SFB 374
| | |
| | | 
Click on the image to enlarge | | ISW, (Institut für Steuerungstechnik der Werkzeugmaschinen und Fertigungseinrichtungen), Universität Stuttgart, Germany The ISW (Institute for Control Engineering of Machine Tools and Manufacturing Units) was a partner in the ProSi
project. COVISE is used to visualize digital programs and their
different parameters as well as the movement of digitally programmed
machine tools.
The image shows the path of the tool on the surface of a workpiece augmented with the tool's angle. | | |
| | |  | | ITB (Institut für Technische Biochemie), Universität Stuttgart, Germany
The Institute of Technical Biochemistry has an ongoing project
regarding the application of virtual reality technology in the area of
molecular modeling. The Highly Immersive Molecular Modeling (HIMM)
project is aimed on the integration of computer aided molecular
modeling tools and virtual reality systems like COVISE.
| | |
| | |  Click on the image to enlarge | | ITM (Institut für Technische Dynamik), Universität Stuttgart, Germany
The Institute of Engineering and Computational Mechanics uses COVISE to
visualize Flexible Multibody Systems. The simulation and animated
visualization enable an evaluation of the system behavior for complex
systems. | | |
| | | 
Click on the movie to enlarge | | IVD (Institut für Verfahrenstechnik und Dampfkesselwesen), Universität Stuttgart, Germany
In our partnership with the Institute of Process Engineering and Power
Plant Technology we are working together in the mathematical modelling
of industrial combustion equipment in coal-, oil-, and gas-fired power
stations. The visualization of the computational results in the Virtual
Reality allows a comprehensive understanding of the complex combustion
processes occuring in the combustion chamber of power stations. | | |
| | | 
Click on the image to enlarge | | IWR , (Interdisziplinäres Zentrum für Wissenschaftliches Rechnen), Universität Heidelberg, Germany
In our cooperation with the Interdisciplinary Center for Scientific
Computing we visualize branches of neurons and examine
neurotransmissions at synapses ... | | |
| | |  | | KiSTi (Korean Institute of Science and Technology), Korea please write me! | | |
| | | 
Click on the image to enlarge | | PDC (Center for Parallel Computers), KTH, Stockholm, Sweden world's first 6-wall Cave is running with COVISE and COVER amongst others | | |
| | | 
Click on the image to enlarge | | Microsoft , Redmond, WA, USA
HLRS and Microsoft are working together in the Microsoft HPC Innovation
Center programme. Windows Server 2003, Compute Cluster Edition, is used
as a platform for high performance computing clusters. The goal of this
cooperation is to evaluate this platform as an alternative for HPC
clusters. To show its potential and possibilities, we implemented
interactive simulations running under Windows Server 2003 Compute
Cluster Edition. The image shows Safeco Field Stadium in Seattle where
we showed a demo during the 2005 company meeting. | | |
| | | 
Click on the image to enlarge | | MPA (Materialprüfungsanstalt), Univerität Stuttgart, Germany The picture shows a surface grid node enhancement done by a COVISE module | | |
| | | 
Click on the image to enlarge | | NCHC (National Center for High-Performance Computing), Hsinchu, Taiwan write me! | | |
| | | 
Click on the movie to enlarge | | NEC HPCE (NEC High Performance Computing Europe GmbH), Düsseldorf, Germany
HLRS and NEC have a very close cooperation in the Teraflop Workbench
project which is enabling sustained Teraflop performance for a wide
range of scientific and industrial applications. The particular
projects are diverse and range from bioinformatics, atomistic
simulation, combustion over fluid-structure interaction, medicine and
nanotechnology to structural mechanics and turbomachinery.
The movie shows a cross-flow breakdown.
In the past, we presented applications - distributed between NEC SX-4
supercomputer and an SGI ONYX workstation - from varios projects with
industrial partners in an virtual reality environment on several
exhibitions (HPCN97 in Vienna, Autofact97 in Detroit and SC97 in San
Jose). | | |
|  |  | | | 
Click on the image to enlarge | | RECOM Services GmbH , Stuttgart, Germany
HLRS and RECOM Services are working together in the mathematical
modelling of industrial combustion equipment in coal-, oil-, and
gas-fired power stations. The visualization of the computational
results in the Virtual Reality allows a comprehensive understanding of
the complex combustion processes occuring in the combustion chamber of
power stations. | | |
| | |  | | Sandia National Laboratories , Alberquerque, NM, USA
In the G7 project Sandia National Labs and RUS/HLRS are working
together in the area of collaborative virtual environments and
metacomputing.
The picture shows the visualization of an comet impacting the earth (near Long Island, USA). | | |
|  | | |  | | TAT (Institute for Theoretical Astrophysik), Universität Tübingen, Germany
In the field of astrophysics simulations of accretion disks TAT
produces large numbers of 3D particle data, which have to be visualized
for proper analysis and interpretation. These simulations might take
several days of cpu time for calculation even on a high performance
supercomputer. So far, the inspection of the simulation data was only
possible after the simulation has finished. For this reason a new data
exchange mechanismn was implemented that supports the visualization of
data from a running simulation. The advantage of this online
visualization is that a better control of the running simulation is
possible. A scientist can now detect a failing simulation run earlier
and stop it if necessary.
The figure shows the online visualization
of the particle data from an accretion disk simulation. With using the
collaborative volume renderer spatial distributed scientists can now
discuss the visualization results of different simulation steps. | | |
|  | | | 
Click on the image to enlarge | | VATech Escher Wyss , Ravensburg, Germany Simulation of tip vortex using Navier-Stokes-Solver FENFLOSS with Very Large Eddy Simulation (VLES) | | |
| January 16
“Online simulation” means that it is possible to engage into a running simulation and that an immediate validation of the simulation results is possible. Standing inside the virtual turbine, the designer can change parameters of the machine, e.g. blade profiles or the shape of the flow channel. A new computational grid is generated immediately. Within a short time range, new stable simulation results are obtained. COVISE simulation library is used to couple FENFLOSS, the Navier-Stokes based flow solver developed at IHS, with the Fenfloss Covise module. As the communication uses a TCP-socket connection, the simulation part can run on any computer.
To achieve an intuitive design process, it is important to have short and almost on-line response times from the simulation. The engineer uses his expert knowledge to decide whether the changes led to the desired result or not and tries to optimize the turbine in an iterative process.
Of course, the intention is to obtain simulation results that are as close to reality as possible.
Since the test bed shall be used for all important components (distributor, runner, draft tube), the use of massively parallel code on supercomputers is essential.
In the computer-based design process, engineers in the first step define a machine geometry using complex CAD software. Afterwards, they use meshing tools that require a vast amount of expert knowledge to define the computational mesh.
Using the design modules developed at IHS (Institute of Fluid Mechanics and Hydraulic Machinery, University of Stuttgart), designing turbo machinery has become much easier.
The different modules are running under one consistent environment, COVISE, a visualisation package developed at the HLRS. The whole design process is carried out from within the COVISE environment.
There are modules for all parts of the machine. These are the wicked gate, radial or axial runners and the draft tube. The turbine geometry is completely parameterised; a set of parameters describes the whole geometry. These parameters imply the shape of the runner blades and the guide vanes as well as the diameter of the runner or the moulding of the flow channel. The modules are flexible tools, some mouse clicks suffice to change these parameters and thus create a new virtual turbine that can serve as a starting setup for further geometry improvements using flow simulations.
The simulation process starts with the definition of the machine's geometry. Simultaneously, the corresponding boundary conditions that describe the operating point of the turbine are defined.
By pressing a button, an unstructured computational mesh consisting of hexahedron elements is generated. As the modules contain automatic grid generation routines, generating a mesh does not need any user interaction. Generating a grid consisting of 100 000 elements needs about 4 seconds on modern desktop PCs.
In the next step, the mesh is decomposed for parallel processing.
We use the COVISE Visualisation system (which has been developed at HLRS) to integrate the whole process from grid-generation, simulation to analysis. Each of the modules in this workflow can reside on a different computer. This allows distributing the work load among different machines. Typically, the pre- and post processing modules run on a visualisation server while the simulation runs on a remote supercomputer. The display modules either run on a visualisation cluster which drives a CAVE or tiled wall or on the workstation of a user.
COVISE is a modular visualisation system developed at the HLRS. The software uses a data-flow execution model, i.e. the data objects in COVISE flow through a network of modules. The modules all run as separate processes and thus can be distributed among multiple computers.
It is possible to couple COVISE environments for collaborative working.
COVISE can be used not only for off-line post processing and visualisation; it can also be used as a general distributed and collaborative integration platform. This allows integrating grid generation, simulation and post-processing modules in a seamless way to create interactive engineering applications.
The simulation process chain consists of three COVISE modules which have been developed to integrate all the aforementioned processing steps into one environment:
At first we need a module that defines the geometry and generates the grid and boundary conditions. This can be the Gate module, one of the runner modules or the DraftTube module. Next, the DomainDecomposition module, which decomposes the grid into multiple domains for parallel simulation, and the Fenfloss module, which couples the simulation code to COVISE. The entire COVISE dataflow network is shown in figure COVISE_Pipeline_coupled.gif. The simulation itself is a separate process that is coupled with the Fenfloss COVISE module using a socket connection. It sends new data to COVISE after each global iteration. All the other modules in COVISE_Pipeline_coupled.gif are used for data analysis and visualisation, e.g. Tracer and CuttingSurface modules.
|  |
Planned visualization cluster
Nodes: 32 dual CPU nodes
Each node equipped with:
CPUs: 2 Dual Opteron 250 2.4 GHz CPUs
GPU: 1 x Nvidia PCI Express Quadro FX 4500 512 MB RAM (option for a second one for Nvidia SLI)
RAM: 4 GB RAM per node
Network: 4x Infiniband, 2 x Gigabit Ethernet
Infiniband interconnect with uplink to existing Infiniband infrastructure
Gigabit Ethernet interconnect
We will use CCS Beta 2 as operating system.
The visualization cluster will be connected to our existing compute cluster via Infiniband.
Description of this Cluster:
Compute Cluster NEC Xeon EM64T
Peak Performance: 2.5 Tflops
Processors: 400 Intel Xeon EM64T CPU's (3.2GHz)
Memory: 160 nodes * 1 GB + 40 nodes * 2 GB
Disk: 1.2 TB distributed scratch, 1 TB shared HOME
Number of Nodes: 200 compute, 1 frontend
Node-node interconnect: Infiniband 1000 MB/s
A part of this cluster will be running under Windows Server 2003 Compute Cluster Edition optionally.
Bull Novascale Itanium2 shared memory machine
Windows Server 2003 Datacenter Edition, Service Pack 1
16 CPUs Intel Itanium2 - 1,3 GHz
32 GB shared Memory
Test systems
3 Dual Opteron workstation running under CCS Beta 2 with 4-8 GB of RAM.
1 AMD64 Barebone with 2 GB RAM running under CCS Beta 2.
Each equipped with Gigabit Ethernet Interface(s) |  | |  |
Interactive Simulation - Virtual Waterturbine Testbed
HLRS and Microsoft are working together in the Microsoft HPC Institutes programme. We use Windows Server 2003 Compute Cluster Edition, as a platform for high performance computing clusters. The goal of this cooperation is to evaluate this platform as an alternative for HPC clusters. To show its potential and possibilities, we implemented interactive simulations running under Windows Server 2003 Compute Cluster Edition.
An example application is the virtual water turbine testbed, which helps turbine designers by simplifying and optimizing the water turbine design process. The virtual turbine testbed is a numerical copy of a real (physical) water turbine testbed. The water flow through an entire turbine is calculated using advanced simulation techniques in order to avoid unwanted flow phenomena and to improve the turbine efficiency.
In order to treat the “virtual turbine” in the same way as in reality, the numerics must run invisible and automatically in the background. That implies the generation of computational meshes, the definition of the boundary conditions according to the operating point of the machine and the computation of the flow.
As the analysis of geometry and simulation results must be fast, detailed and intuitive, there is a demand for a Virtual Reality – Environment (VR), in which the geometry of the turbine is displayed in conjunction with the simulation results in a realistic manner. It is possible to step inside the turbine and have a closer look into every detail of the machine.
Given a specific turbine geometry, the most important target is to simulate the operating behaviour for an arbitrary operating point. Subsequently, the geometry of the machine can be changed using the experiences given by the acquired knowledge. As the response time of the online simulation is in the range of minutes, the turbine designer can immediately evaluate whether his changes had the desired effect or not.
Due to the existence of a virtual turbine testbed, model experiments become less significant. Especially the transferability problem from model experiments to real size prototypes is solved to a certain degree. The simulation of the machine can easily be done in real size without additional costs.
|  |
|
Tools 
Help
