
2
007-5483-001
SGI Virtu VN200 Overview
Product Description
This document is intended as an overview of some of the common operations that
system administrators may have to perform to set-up, boot, re-configure (upgrade) or
troubleshoot an SGI Altix XE cluster with SGI Virtu VN200 graphics nodes.
The initial release of the SGI Virtu VN200 system (refer to
Figure 1-1
) is one or more
SGI Altix XE320 servers (compute nodes), one or more SGI Altix XE250 servers (head
nodes), and one more SGI Virtu VN200 graphics nodes (visualization/compute nodes).
The nodes are networked together using InfiniBand or Gigabit Ethernet switches and can
run parallel programs using a message passing tool like the Message Passing Interface
(MPI).
An SGI Virtu VN200 system is a distributed memory server as opposed to a shared
memory system like that used in the SGI Altix 450 or SGI Altix 4700 high-performance
compute servers. Instead of passing pointers into a shared virtual address space, parallel
processes in an application pass messages, with each process requiring its own dedicated
processor and address space.
Just like a multi-processor shared memory system, a cluster can be shared among
multiple applications. For instance, one application may run on 16 processors in the
cluster while another application runs on a different set of 8 processors. Very large
clusters may run dozens of separate, independent applications at the same time.
Typically, each process of an MPI job runs exclusively on a processor. Multiple processes
can share a single processor, through standard Linux context switching, but this can have
a significant effect on application performance. A parallel program can only finish when
all of its sub-processes have finished. If one process is delayed because it is sharing a
processor and memory with another application, then the entire parallel program is
delayed. This gets slightly more complicated when systems have multiple processors
(and/or multiple cores) that share memory, but the basic rule is that a process is run on
a dedicated processor core.
Содержание Virtu VN200
Страница 1: ...SGI Virtu VN200 Graphics Node Hardware User s Guide 007 5483 001 ...
Страница 3: ...007 5483 001 iii Record of Revision Version Description 001 April 2008 Original printing ...
Страница 4: ...iv 007 5483 001 ...
Страница 12: ...xii 007 5483 001 ...
Страница 36: ...20 007 5483 001 SGI Virtu VN200 Overview ...
Страница 58: ...42 007 5483 001 System Features ...
Страница 108: ...92 007 5483 001 System Procedures ...