HP Scalable Visualization Array (SVA) Software manual SVA Hardware and Software

Page 21

3 SVA Hardware and Software

This chapter provides information on the hardware and software that make up the SVA. It is a useful reference for anyone involved in managing the SVA. It is also useful for anyone who wants to understand the hardware that makes up the SVA and the software that is installed on it.

The SVA combines commodity hardware components with software that include the following:

A cluster of Intel EM64T or AMD Opteron HP workstations as visualization nodes.

NVIDIA® Quadro® FX 3450 or NVIDIA Quadro FX 4500 graphics cards with optional G-sync or hardware SLI.

InfiniBand, Gigabit Ethernet (GigE), or Myrinet system interconnects.

Third-party software tools and libraries.

Custom and enhanced software tools.

Hardware Component Summary

You can use the SVA with a variety of applications that run on distributed computing systems; in this case, a cluster of Linux workstations. The SVA is a specialized version of the HP Cluster Platform systems; in this case, based on HP ProLiant DL380 G4 and 385 G4 servers and xw8200 or xw9300 visualization nodes.

There are two SVA physical configurations:

Bounded configuration

Contains only visualization nodes and is limited in size to one to three

 

racks. The bounded configuration serves as a standalone visualization

 

cluster. It can be connected to a larger HP XC cluster via external

 

GigE connections. This level of inter-cluster integration supports

 

communication with a compute cluster and data retrieval from a file

 

share such as an HP Scalable File Share (SFS).

Modular, expandable system

This configuration has two or more racks as needed to contain the

 

maximum number of supported nodes. It is based on HP Cluster

 

Platform building blocks. It can be exclusively visualization nodes or

 

be combined with compute nodes as part of an integrated HP Cluster

 

Platform system. When integrated into a larger Cluster Platform system,

 

the visualization nodes can use a high speed system interconnect to

 

load data from an HP SFS.

The two SVA physical configurations are built using one or more of three types of building blocks. Each building block uses a single rack.

Utility Visualization Block (UVB)

Base utility unit of a bounded physical configuration.

Utility Building Block (UBB)

Base utility unit of a modular expandable system.

Visualization Building Block (VBB)

Rack of visualization nodes that can be added to either base units.

 

The VBB contains a maximum of eight nodes.

A bounded physical configuration has the following components as summarized in Chapter 2:

Display nodes.

Render nodes.

Head node (found in HP Cluster Platform systems, and thus not unique to the SVA).

System Interconnect and Administrative Network (found in HP Cluster Platform systems, and thus not unique to the SVA).

The head node is a typical node type found in HP Cluster Platform systems. SVA bounded configurations support either a workstation (xw8200 or xw9300) or server (DL 380 or DL 385) as the head node. Modular configurations support only a DL 380 or a DL 385 as the head node.

Figure 3-1illustrates a sample bounded configuration. The UVB contains the network switches, PDU, five visualization nodes, and the head node. The visualization nodes support a 2x2 multi-tile display. Additional VBBs can be added to this configuration, with up to eight workstations in each rack.

Hardware Component Summary 21

Image 21
Contents HP Scalable Visualization Array Version Page Table of Contents Glossary Index Application ExamplesList of Figures Page List of Tables Page Intended Audience About This DocumentDocument Organization Typographic ConventionsRelated Information Publishing HistoryHP Encourages Your Comments Introduction Where SVA Fits in the High Performance Computing EnvironmentSVA Clusters SVA Functional Attributes DisplaysScalability FlexibilityOpenGL Applications Application SupportScenegraph Applications Page SVA as a Cluster SVA ArchitectureArchitectural Design Background on Linux ClustersMain Visualization Cluster Tasks Components of the HP Cluster PlatformSVA Operation Configuration FlexibilityComponents of an SVA Cluster Data FlowSVA Data Flow Overview File AccessHardware Component Summary SVA Hardware and SoftwareAdministrative Network Connections Network ConfigurationsDisplay Devices System Interconnect SILinux Operating System SVA Software SummaryAdditional System Software HP XC Clustering SoftwareSVA Visualization System Software Reference Guide Page Setting Up and Running a Visualization Session Configuration Data FilesRunning an Application Using Scripts Modifying a Script Template Selecting a TemplateRunning an Interactive Session Using a Script to Launch an ApplicationSetting Up and Running a Visualization Session Application Examples Running an Existing Application on a Single SVA WorkstationAssumptions and Goal Location for Application Execution and Control HP Remote Graphics Software and UseData Access Use of Display SurfacesLaunch Script Non-Interactive Example ParaView Overview Running Render and Display Applications Using ParaViewLocation for Application Execution and Control Paraview Server Launch Script Template Running a Workstation Application Using a Multi-Tile DisplayDistributed Multi-Head X DMX Chromium Overview and Usage NotesApplication Examples Using Display Surfaces Launch Script Is limited in size to one to three racks. The bounded GlossaryHptccluster/sva/job/id.conf. This file has UBB Page RGS IndexSVA