Silicon Graphics Prism™ Visualization System
User’s Guide for Power & Team Scalable
Configurations
Document Number 007-4701-003
Page 2
CONTRIBUTORS
Written by Mark Schwenden and Eric Zamost
Illustrated by Chrystie Danzer
Additional contributions by Dick Brownell, Mark Cabrales, Josh Grossman, Eric Kunze, Matt Marchese, Jim Passint, Keith Rich, Victor Riley, Armando
Serrato, Dave Shreiner, Andrew Spray, and Lyle Stoll.
The electronic (software) version of this document was developed at private expense; if acquired under an agreement with the USA government or any
contractor thereto, it is acquired as "commercial computer software" subject to the provisions of its applicable license agreement, as specified in (a) 48 CFR
12.212 of the FAR; or, if acquired for Department of Defense units, (b) 48 CFR 227-7202 of the DoD FAR Supplement; or sections succeeding thereto.
Contractor/manufacturer is Silicon Graphics, Inc., 1500 Crittenden Lane, Mountain View, CA 94043.
TRADEMARKS AND ATTRIBUTIONS
Silicon Graphics, SGI, the SGI logo are registered trademarks and NUMAlink and Silicon Graphics Prism are trademarks of Silicon Graphics, Inc., in the
United States and/or other countries worldwide.
ATI and Radeon are registered trademarks, and FireGL is a trademark, of ATI Technologies, Inc.
Intel and Itanium are trademarks or registered trademarks of Intel Corporation and its subsidiaries in the United States and other countries.
Linux is a registered trademark of Linus Torvalds.
XFree86 is a trademark of The XFree86 Project, Inc.
XWindows is a trademark of MIT.
All other trademarks mentioned herein are the property of their respective owners.
Page 3
Record of Revision
VersionDescription
001October 2004
First Release
002February 2005
Added Prism Team configurations (routed NUMAlink)
Added Multi-Xserver configuration instructions
Added additional rack-handling instructions
Added description of optional IO9 card
This guide provides an overview of the Silicon Graphics Prism Visualization System
components and describes how to set up and operate this system.
The most basic Silicon Graphics Prism consists of a base compute module combined with
an extensible graphics 2-processor capable node module (XG2N module). Larger
systems use a base compute module, XG2N module(s), and other optional modules that
are rackmounted together. The following optional modules are available:
•A CPU expansion module provides zero, one or two additional 64-bit Intel
processors and up to 24 GB of memory. No PCI or disk options are available in this
module.
•A CPU, memory and PCI/PCI-X expansion (CMPX) module provides zero, one or
two optional processors, up to 24 GB of memory, and four PCI and PCI-X card slots.
•A Router module provides eight NUMAlink-4 ports and functions as a high-speed
switch to route network packets between base compute, XG2N, CPU expansion,
and CMPX modules.
•The SGI TP900 storage module provides additional disk storage to the system. For
detailed information about this module, see SGI Total Performance 900 Storage System User’s Guide (007-4428-00x). Note than an optional SCSI PCI card is required to use
this option in a Silicon Graphics Prism.
This guide is written for owners, system administrators, and users of the Silicon Graphics
Prism. It is written with the assumption that the reader has a good general knowledge of
computer graphics and computer operations.
007-4701-003xvii
Page 18
About This Guide
Important Information
Your SGI system support engineer (SSE) should perform the addition or replacement of
parts, cabling, and service of your Silicon Graphics Prism, with the exception of the
following tasks that you may perform yourself:
•Installing your system in a rack.
•Cabling the system modules to each other.
•Using your system console to enter commands and perform system functions such
as powering on and powering off.
•Using the On/Off, reset, and non-maskable interrupt (NMI) switches on the front
panel of your system.
•Removing and replacing XG2N graphics boards.
•Installing and removing PCI and PCI-X cards.
Caution: Exception: Because the installation and removal of an IO10 PCI card, which
installs in the lowermost slot, is more complicated and can cause damage to your
system if not performed properly, it can only be installed and removed by a trained
SGI system support engineer.
•Installing and removing disk drives.
•Installing and removing power supplies.
•Installing and removing DIMMs.
•Installing and removing the L1 controller display.
Warning: To ensure your safety and protect your system, do not add or replace
any components that this guide does not designate as customer replaceable.
Contact your SGI system support engineer (SSE) to install any hardware
components that are not designated as customer replaceable in this guide.
xviii 007-4701-003
Page 19
Chapter Descriptions
The following topics are covered in this guide:
•Chapter 1, “Getting Started with the Silicon Graphics Prism,” provides introductory
•Chapter 2, “System Overview and Options,” provides a general overview of the
•Chapter 3, “Configurations and Cabling,”
•Chapter 4, “Installing and Removing Customer-Replaceable Units,” describes how
About This Guide
information, instructions for cabling, and quick start operation of the Silicon
Graphics Prism.
Silicon Graphics Prism and its topology. This chapter also includes a quick
description of the various components and modules that can be part of a Silicon
Graphics Prism.
to install and remove the following customer-replaceable units (CRUs):
–PCI and PCI-X cards
–Graphics boards
–Disk drives
–Power supplies
–Memory (DIMMs)
–L1 system controller display
•Chapter 5, “Troubleshooting,” describes how to troubleshoot your system by using
the L1 controller and your system LEDs. Information on reconfiguring the system’s
XF86Config file for changes in hardware usage is included.
•Appendix A, “Technical Specifications,” contains environmental and physical
specifications for the Silicon Graphics Prism, as well as pin assignments for
non-proprietary connectors for the various modules that can be part of a Silicon
Graphics Prism.
•Appendix B, “Installing Silicon Graphics Prism Modules Into a Rack,” provides
instructions for rack mounting modules with optional slide rails.
•Appendix C, “Installing Rack Systems,” provides instructions for installing a
pre-assembled rack system.
•Appendix D, “Regulatory Specifications and Safety Information,” contains
regulatory specifications and safety information for the Silicon Graphics Prism.
•An index completes this guide.
007-4701-003 xix
Page 20
About This Guide
Related Publications
This section lists various information sources and explains how to access them. The
following SGI publications relate to the Silicon Graphics Prism:
•SGI L1 and L2 Controller Software User’s Guide (007-3938-00x) (available online). This
•SGI Total Performance 900 Storage System User’s Guide (007-4428-00x) (optional). This
•SGIconsole Hardware Connectivity Guide (007-4340-00x) (optional). This guide
•SGI Altix 350 User’s Guide (007-4660-00x). This guide contains detailed information
You can obtain SGI documentation, release notes, or man pages in the following ways:
guide describes the L1 and L2 controller functions, commands, and error messages
that you may need to operate and maintain your system.
guide describes the optional SGI TP900 storage module, which provides additional
storage for the Silicon Graphics Prism.
describes how to connect an optional SGIconsole to SGI systems. You can use an
optional SGIconsole to manage and monitor multiple Silicon Graphics systems.
on many of the same optional modules that you may use with your Silicon Graphics
Prism.
•See the SGI Technical Publications Library at http://docs.sgi.com. Various formats
are available. This library contains the most recent and most comprehensive set of
online books, release notes, man pages, and other information.
•SGI ProPack for Linux documentation, and all other documentation included in the
RPMs on the distribution CDs can be found on the CD titled “SGI ProPack vX.X for
Linux - Documentation CD.” To access the information on the documentation CD,
open the index.html file with a web browser. Because this online file can be updated
later in the release cycle than this document, you should check it for the latest
information.
•The release notes, which contain the latest information about software and
documentation in this release, are on the SGI Pr oPack for Linux Documentation CD
in the root directory, in a file named README.TXT.
Note: There are no command line grelnotes or relnotes available on an SGI
Linux system. The InfoSearch tool is not available with Linux.
xx 007-4701-003
Page 21
Conventions
About This Guide
The following conventions are used throughout this document:
ConventionMeaning
CommandThis fixed-space font denotes literal items such as commands, files,
routines, path names, signals, messages, and pr ogramming language
structures.
variableThe italic typeface denotes variable entries and words or concepts
being defined. Italic typeface is also used for book titles.
user inputThis fixed-space font denotes literal items that the user enters in
interactive sessions. Output is shown in nonbold, fixed-space font.
[ ]Brackets enclose optional portions of a command or directive line.
...Ellipses indicate that a preceding element can be repeated.
man page(x)Man page section identifiers appear in parentheses after man page
names.
GUI elementThis font denotes the names of graphical user interface (GUI)
elements such as windows, screens, dialog boxes, menus, toolbars,
icons, buttons, boxes, fields, and lists.
Product Support
SGI provides a comprehensive product support and maintenance program for its
products, as follows:
•If you are in North America, contact the Technical Assistance Center at
1 (800) 800 4SGI or contact your authorized service provider.
•If you are outside North America, contact the SGI subsidiary or authorized
distributor in your country.
007-4701-003 xxi
Page 22
About This Guide
Reader Comments
If you have comments about the technical accuracy, content, or organization of this
document, contact SGI. Be sure to include the title and document number of the manual
with your comments. (Online, the document number is located in the front matter of the
manual. In printed manuals, the document number is located at the bottom of each
page.)
You can contact SGI in any of the following ways:
•Send e-mail to the following address:
techpubs@sgi.com
•Use the Feedback option on the Technical Publications Library website:
http://docs.sgi.com
•Contact your customer service representative and ask that an incident be filed in the
SGI incident tracking system.
•Send mail to the following address:
Technical Publications
SGI
1500 Crittenden Lane, M/S 535
Mountain View, California 94043
SGI values your comments and will respond to them promptly.
xxii 007-4701-003
Page 23
Chapter 1
1.Getting Started with the Silicon Graphics Prism
The Silicon Graphics Prism Visualization System platform is a high-performance
highly-scalable system running the SGI Linux + ProPack operating system. The platform
is available in a number of configurations to meet your visualization and compute
requirements.
This chapter introduces the two primary modules used in the system, and provides an
abbreviated overview (quick start) on how to begin using your system. The following
chapters elaborate on various topics relating to larger systems, configuration and cabling
questions, component replacement and upgrades, basic troubleshooting, rack mounting,
and connector functionality.
007-4701-0031
Page 24
1: Getting Started with the Silicon Graphics Prism
XG2N and Compute Modules
The most basic Silicon Graphics Prism uses two modules:
•A graphics 2-processor and memory capable node module (called an XG2N
module).
•A base compute module that provides base I/O as well as processors and memory.
The XG2N module is a 2U rack mountable enclosure which, in addition to the two
high-performance graphics pipes, adds to the host system a node board with two CPUs
and four, eight, or twelve memory DIMMs. This module connects as an integral part of
the system’s compute/memory fabric. Though it contains CPUs and memory, the XG2N
module does not have boot I/O functionality, and therefore may not be used as a
standalone system.
The rear panel of the XG2N module
page 3. The rear panel of the XG2N modul e
with FireGL X2PRO-256 is shown in Figure 1 -1 on
with FireGL X3-256 is shown in Figure 1-3 on
page 4.
The XG2N module is a node-connected module, and therefore connects to the host
system using NUMAlink, either directly or through an optional NUMAlink module
(router). This way the XG2N module becomes an integral part of the system, and can
contain both CPUs and memory, in addition to graphics output capabilities. Note that
NUMAlink routers may be available only with specific system configurations. Check
with your SGI sales or service representative for information on available configurations.
Each XG2N module contains two graphics pipes, each capable of supporting two display
devices. In systems with only two pipes, the pipe and channel designations are defined
as in Figure 1-1 and Figure 1-3. In systems with more than one XG2N graphics module
the pipes are numbered as shown in Figure 1-2 and Figure 1-4.
2 007-4701-003
Page 25
XG2N and Compute Modules
Power
connector
L1 console port
CONSOLE
Left channelRight channel
Bus 2
slot 1
(Pipe 1)
REPEAT
L1 PORT
NUMALINK 0
IS2
IS1
NUMALINK 1
Bus1
slot 1
(Pipe 0)
USB-B L1 port
NUMAlink 0
connector
NUMAlink 1
connector
StereoSync
connector
Figure 1-1Rear View of XG2N Graphics Module with Fir eGL X2PRO-256 (Showing First
Module Pipe Numbering)
Pipe n+1, left channel
Pipe n+1, right channel
Pipe n+1
L! Port
CONSOLE
Figure 1-2Pipe Numbering of Additional XG2N Graphics Modules with FireGL X2PRO-256
007-4701-003 3
Repeat
NUMALINK 0
IS2
IS1
NUMALINK 1
Pipe n, left channel
Pipe n, right channel
Pipe n
Page 26
1: Getting Started with the Silicon Graphics Prism
Left channelRight channel
Bus 2, slot 1
(Pipe 1)
Power
connector
L1 console port
CONSOLE
CONSOLE
REPEAT
L1 PORT
USB-B L1 port
NUMAlink 0
connector
NUMALINK 0
IS2
IS1
NUMALINK 1
NUMAlink 1
Bus1, slot 1
(Pipe 0)
StereoSync
connector
connector
Figure 1-3Rear View of XG2N Graphics Module with Fir eGL X3-256 (Sho wing First Module
Pipe Numbering)
L1 PORT
REPEAT
NUMALINK 0
Pipe n+1, left channel
IS2
IS1
NUMALINK 1
Pipe n+1, right channel
Pipe n+1
Pipe n
Figure 1-4Pipe Numbering of Additional XG2N Graphics Modules with FireGL X3-256
4 007-4701-003
Pipe n, left channel
Pipe n, right channel
Page 27
Front Panel Controls
2
TM
XG2N and Compute Modules
This section describes the front panel controls and indicators of the XG2N and compute
modules as shown in Figure 1-5.
L1 controller display
Failure LED
Service-required LED
Power button
with LED
Reset
NMI
Figure 1-5Silicon Graphics Prism XG2N and Compute Module Front Panel Controls
The front panels of the modules have the following controls:
•L1 controller display. A liquid crystal display (LCD) that shows status and error
messages generated by the L1 controller.
Note: Refer to the SGI L1 and L2 Controller Software User’s Guide (007-3938-00x) for
more information on the L1 controller.
•Status LEDs. The front panel has the following LEDs:
–Power-button LED. This green LED illuminates when the internal components
are on.
–Service-required LED. This amber LED illuminates to indicate that an item is
not functioning properly (for example, a fan is off), but the system is still
operating.
–Failure LED. This red LED illuminates to indicate that a failure has occurred
and the system or module has shut down.
007-4701-003 5
Page 28
1: Getting Started with the Silicon Graphics Prism
•Power button. Press this button to power on the individual module. Alternatively,
you can power on all the system modules at once from an optional system console.
•Reset button. Press this button to reset the internal processors and ASICs. The reset
will cause a memory loss.
•NMI button. Pressing this button issues a non-maskable interrupt command to a
module. When the system hangs, you can send the affected module an NMI
interrupt. The interrupt goes to PROM and causes the CPU state to be captured for
that module. This information is saved in flash PROM and in the system log, and
can assist SGI technicians in debugging system hangs and customer problems.
6 007-4701-003
Page 29
Compute Module Rear Panel Items
Figure 1 -6 shows a view of the rear panel of a Silicon Graphics Prism compute module.
XG2N and Compute Modules
PCI/PCI-X slots:
connector
CONSOLE
CONSOLE
port
L1 portPower
PCI 4
PCI 3
PCI 2
L1 PORT
NUMALINK 0NUMALINK 1
CPU
PCI 1
NUMAlink connectorNUMAlink connector
Ethernet port
Multi-port serial
connector
Figure 1-6Silicon Graphics Prism Compute Module Rear Panel With ImageSync
The rear panel of the module has the following items:
•AC power input. This connector connects the graphics module to an AC power
outlet.
•Console port. This DB-9 serial port (console and diagnostic port) enables you to
connect a system console to the L1 controller on the graphics module.
•L1 port (USB type B). This universal serial bus (USB) type B connector connects the
graphics module L1 controller to an optional L2 controller.
Bus 2, slot 2
(with USB)
Bus 2, slot 1
Bus 1, slot 2
(with ImageSync)
Bus 1, slot 1
(with IO10)
•NUMAlink connectors. These NUMAlink connectors are used to connect base
compute, XG2N, CPU expansion, or CMPX modules to each other or to optional
router modules. These connections are made with a NUMAlink cable at 3.2 GB/s in
each direction.
•NUMAlink LEDs. Each NUMAlink connector has a yellow LED and a green LED
(both located to the right of the NUMAlink connector). These LEDs provide
information about this specific NUMAlink connection:
–The yellow LED illuminates when this module and the module to which this
007-4701-003 7
port is connected are both powered on.
Page 30
1: Getting Started with the Silicon Graphics Prism
–The green LED illuminates when a link has been established to another module
through this NUMAlink connector.
Internal Components
Figure 1 -7 shows an internal view of the XG2N module.
Before you install a Silicon Graphics Prism, you should familiarize yourself with the
safety precautions discussed in the following subsections:
•“Hazard Statements” on page 9
•“ESD Precautions” on page 10
•“Safety Measures” on page 11
Hazard Statements
During the installation of the computer system, be alert for hazard advisory statements
with icons, which signify the following:
•Caution Indicates a potentially hazardous situation that, if not avoided, can result
Safety Precautions
in minor or moderate injury. A caution statement also alerts you to unsafe practices
that can result in equipment damage and/or data corruption. A caution message is
accompanied by an icon as shown in the following example:
Caution:
!
•Warning indicates a potentially hazardous situation that, if not avoided, could
result in death or serious injury. A warning message is accompanied by icon as
shown in the following example:
Warning:
007-4701-003 9
Page 32
1: Getting Started with the Silicon Graphics Prism
ESD Precautions
Observe electrostatic discharge (ESD) precautions during the entire installation process
to eliminate possible ESD damage to the equipment. Wear an SGI-approved wrist strap
when you handle an ESD-sensitive device. Connect the wrist strap cor d dir ectly to earth
ground.
!
Caution: Observe all ESD precautions. Failure to do so can result in damage to the
equipment.
10 007-4701-003
Page 33
Safety Measures
Safety Precautions
Observe the following safety measures when you install the system:
•Use caution when you remove the system from the shipping crate. Failure to handle
the system carefully can result in personal injury or property damage.
Warning: Ensure that the shipping crate is positioned close to its destination
before you unpack the crate.
Warning: Employ a minimum of two people to lift the module or modules off
the shipping pallet, to move the module(s) from one location to another, and to
install the module(s) in a rack. Otherwise, someone could be seriously injured.
•Do not move the system while it is connected to power.
Warning: Keep fingers and conductive tools away from high-voltage areas.
Failure to follow these precautions will result in serio u s in ju ry o r death. The
high-voltage areas of the system are indicated with high-vol tage warning labels.
•Ensure that a qualified electrician has properly installed the power receptacles.
•Set all circuit breakers to the OFF (
cord.
O) position before you plug in the system power
Warning: Use the following guidelines to prevent the rack from toppling over.
Otherwise, people could be seriously injured and/or equipment could be
damaged.
Follow these guidelines to prevent the rack from toppling over:
•Make sure that only one module is extended out of the rack at one time.
•Install all equipment in the lowest available position in the rack.
•Ensure that the tip tray is bolted to the front of the rack.
007-4701-003 11
Page 34
1: Getting Started with the Silicon Graphics Prism
Quick Start Information
The following sections and illustrations are intended to guide a knowledgeable user
through the installation, setup, and simple configuration of a basic Silicon Graphics
Prism visualization system. For more detailed information on system components or
maintenance, go on to the chapter that covers your detailed requirements.
Positioning and Power for Your Silicon Graphics Prism
Depending on the system ordered, your visualization system may have been shipped as
two or more individual modules, or pre-mounted in a rack.
If the system was shipped as a number of individual chas sis, they may be placed on a flat
surface, as shown in Figure 1-8 on page 13, or placed in a rack. For instructions on
mounting modules in a rack see Appendix B, “Installing Silicon Graphics Prism Modules
Into a Rack,”.
If your system was shipped pre-mounted in a rack, see Appendix C, “Installing Rack
Systems,” for important information regarding unloading, unpacking, and installing a
rack system.
Warning: Follow the guidelines in “Safety Measures” on page 11 and Appendix C,
“Installing Rack Systems,” to avoid damage to equipment, injury, or death.
Plug your system into a suitable power outlet, as shown in Figure 1-8 (for non-racked
chassis) or Figure 1-9 (for racked chassis). Refer to Appendix A, “Technical
Specifications,” for detailed power requirements for the system modules.
12 007-4701-003
Page 35
XG2N graphics module
Quick Start Information
Base compute module
Figure 1-8Example Connection of a Non-Racked System to Power
007-4701-003 13
Page 36
1: Getting Started with the Silicon Graphics Prism
Power
source
CMPX module
(optional)
XG2N graphics
module
XG2N graphics
module
Base compute
module
CHANNEL 1
CHANNEL 2
I.D.RANGE
OUTPUT
GOOD
FAULT
Power
distribution
unit (PDU)
CHANNEL 1
CHANNEL 2
I.D.RANGE
OUTPUT
GOOD
FAULT
TP900 storage
module (optional)
Components within rack
Figure 1-9Connection Example of a Racked System to Power
14 007-4701-003
Page 37
NUMAlink Cabling for a Silicon Graphics Prism
If your system was shipped from SGI with the modules already mounted in a rack and
the NUMAlink cables pre installed, you should proceed to “Optional SGI ImageSync
Cabling” on page 16 to continue.
This section describes the NUMAlink cabling for the basic configuration. For additional
NUMAlink cabling information, see “System Configurations ” on p age 60.
Figure 1 -10 shows a system with a base compute module and one XG2N graphics
module.
CONSOLE
L1 PORT
REPEAT
IS2
NUMALINK 0
IS1
NUMALINK 1
Quick Start Information
XG2N
module
CONSOLE
L1 PORT
NUMAlink 0
NUMALINK 0NUMALINK 1
NUMAlink 0
NUMAlink 1
CPU
NUMAlink 1
PCI 4
PCI 3
PCI 2
PCI 1
Figure 1-10NUMAlink Cabling in a Two-module System
Base compute
module
007-4701-003 15
Page 38
1: Getting Started with the Silicon Graphics Prism
Optional SGI ImageSync Cabling
If your system was shipped from SGI with the modules already mounted in a rack and
the SGI ImageSync (IS) cables pre-installed, you should proceed to the next section,
“Connecting a Monitor” on page 18, and continue with the setup.
Note: When using an ImageSync card a monitor must be connected to the left channel
of the first pipe to which the ImageSync card is cabled.
If your system did not come with SGI ImageSync cables pre installed, use the following
steps to install them:
1.Connect the DB9 connector on the IS card in your base compute module to the SGI
ImageSync DB9 connector (labeled
the back of the XG2N using an SGI ImageSync DB9-to-DB9 cable.
2.Daisy-chain the SGI ImageSync cable from this first XG2N to any additional
graphics modules in your system by connecting an ImageSync DB9-to-DB9 cable
from the
to the ImageSync connector (labeled
module, as shown in Figure 1-11.
Repeat connector (located above the NUMAlink 0 connector) and routing it
IS1) located above the NUMAlink 1 connector on
IS1) on the back of the next XG2N graphics
Note: Figure 1-11 is intended only to show an example of how the ImageSync cables
connect. Your system may be configured differently.
Caution: Although the image sync subsystem uses DB9 connectors, these connectors,
!
16 007-4701-003
whether on the ImageSync card or on the XG2N modules, are not serial ports.
Connecting a serial device to these connectors may cause damage to both the ImageSync
devices and the serial devices.
Page 39
CONSOLE
L1 PORT
Quick Start Information
XG2N
REPEAT
IS2
IS1
NUMALINK 0
NUMALINK 1
module
CONSOLE
CONSOLE
L1 PORT
L1 PORT
NUMAlink 0
REPEAT
NUMAlink 0
NUMAlink 0
IS2
NUMALINK 0
CPU
NUMALINK 0NUMALINK 1
NUMAlink 1
IS1
NUMALINK 1
NUMAlink 1
NUMAlink 1
PCI 4
PCI 3
PCI 2
PCI 1
Figure 1-11Cabling Example of SGI ImageSync Card to Graphics
XG2N
module
Base compute
module
007-4701-003 17
Page 40
1: Getting Started with the Silicon Graphics Prism
Connecting a Monitor
Select the monitor on which you want the Linux OS console to appear, and connect this
monitor to the left channel of pipe 0 on your graphics module. The connector for the left
channel of pipe 0 is located in the lower left section of the PCI graphics area on the back
of your primary system graphics module. See Figure 1-1 for reference.
If you have a single XG2N graphics module, pipe 0 will be located in that module.
If you have multiple XG2N graphics modules, pipe 0 will typically be in the XG2N
module located directly above the base compute module. The Silicon Graphics Prism
platform comes with a choice of optional monitor types and sizes.
Caution: Ensure that the electrical rating on the monitor label matches the outlet voltage
!
range (100–120 VAC or 220–240 VAC) before you plug in the monitor.
If you use a monitor in locations that do not have the appropriate outlets, contact your
SGI system support engineer (SSE) before plugging in the monitor power cable.
Plug in and turn on your monitor or display as described in the documentation that
accompanies your monitor.
18 007-4701-003
Page 41
Connecting a Keyboard and Mouse
Connect a USB keyboard and a USB mouse to your system, as shown in Figure 1-12. The
USB port closest to the side of the chassis is port 1.
Note: Some system configurations may be limited to the use of one keyboard and mouse
set. Check with your SGI sales or service representative if you have questions regarding
the use of multiple keyboards and mice with your system.
Figure 1-12 shows the USB PCI card in bus 2, slot 2 (the top PCI slot) of the base module,
which is the preferred location for this car d. Some configurations may have the USB card
in a different PCI slot in the host system.
Note: If your keyboard/mouse pair will be further than 10 feet (3 meters) away from the
USB ports on the system, please refer to the section “Optional USB Extender” on page 57
for details about how to connect these devices through a USB extender.
Quick Start Information
Figure 1-12Connecting the USB Keyboard and Mouse to the System Compute Module
007-4701-003 19
Keyboard
Mouse
USB type A
connectors
Base compute module
Page 42
1: Getting Started with the Silicon Graphics Prism
Connecting the Multi-Port Serial Cable
A multi-port serial cable that converts the serial output on the IO10 board into four DB-9
serial cables is included with each base compute module containing an IO10.
Figure 1 -13 shows an example connection.
Note: Leave the multi-port serial adapter cable unplugged if you are not using it for
optional serial connections.
Figure 1-13Multi-port Adapter Serial Cable
20 007-4701-003
Page 43
Connecting an L1 System Console
Connect a serial terminal to the Level 1 console connector on the base compute module
as shown in Figure 1-14.
Quick Start Information
Base compute
module
DB-9 serial port
connector (L1 console)
DB-9
connector
Serial terminal
Figure 1-14Connecting a Serial Terminal to the Base Compute Console Port
007-4701-003 21
Page 44
1: Getting Started with the Silicon Graphics Prism
Power-On the System
If your Silicon Graphics Prism does not have a a local system console, you can manually
power it on and off by using the power buttons. To power on your system or an
individual module manually, follow these steps:
1.If the monitors and other peripherals are equipped with voltage select switches,
verify that they are set for the appropriate AC voltage and plug them in. Note that
they are normally plugged into power sources outside a rack system.
2.Turn on the circuit breaker switch of the PDU if applicable.
3.Press the power buttons on each of the modules that you want to power on in the
following order:
a.For the optional TP900 storage module, press the rear-panel power button to
ON (
I).
b.Power on all the XG2N graphics modules.
c.Power on any optional compute expansion or CMPX modules.
d.Power on the base (system) compute module last.
T o boot the system from the L1 interface you must have a console connected to the system
via the console port on the base compute module. The serial connection parameters are:
•38400 baud
•1 stop bit
•no parity
Use the following command at the L1 prompt to bring up all the system modules:
001c01-L1> * power up
If the system does not boot, recheck all power, and cable connections to be sure they are
properly plugged in. See Chapter 5, “Troubleshooting,” for additional trouble shooting
tips and L1 messaging.
To contact the SGI Customer Service Center, call 1-800-800-4SGI, or visit
http://www.sgi.com/support/customerservice.html. From outside the United States
contact your local SGI sales office.
22 007-4701-003
Page 45
Verifying System Connections
Once your Silicon Graphics Prism Vis ualiz ation System is installed in a rack (or
otherwise situated), is cabled to gether via NUMAlink, and is powered on, you should
verify that all modules are being seen by Linux + ProPack. To do this, follow these steps:
1.From a Linux prompt, type hinv <Enter>
2.To verify the connection of all the graphics modules check the output for lines
similar to the following examples:
VGA compatible controller: ATI Technologies Inc Radeon R350 NG [FireGL X2] (rev xxx). on
pci11.01.0
Display controller: ATI Technologies Inc Radeon R350 [FireGL X2] (Secondary) (rev xxx). on
pci11.01.1
VGA compatible controller: ATI Technologies Inc Radeon R350 NG [FireGL X2] (#2) (rev xxx).
on pci12.01.0
Display controller: ATI Technologies Inc Radeon R350 [FireGL X2] (Secondary) (#2) (r ev xxx).
on pci12.01.1
3.To verify all graphics boards in the system are seen, count the number of entries in
the output similar to the example output in step 2. Each two-line entry represents
one graphics pipe.
Quick Start Information
4.If the output does not show all the graphics pipes present, recheck all power, and
cable connections to be sure they are properly plugged in. See Chapter 5,
“Troubleshooting,” for additional trouble shooting tips and L1 messaging.
To confirm the presence of the graphics boards in the system using a Linux
command-line, use the following:
1.Enter /sbin/lspci from a Linux prompt.
2.Check the output for information similar to the following:
11:01.0 VGA compatible contr oller: ATI Technologies Inc Radeon R350 NG [FireGL X2] (rev
xx)
11:01.1 Display controller: ATI Technologies Inc Radeon R350 [FireGL X2] (Secondary) (rev
xx)
12:01.0 VGA compatible controller: ATI Technologies Inc Radeon R350 NG [FireGL X2] (rev
xx)
12:01.1 Display controller: ATI Technologies Inc Radeon R350 [FireGL X2] (Secondary) (rev
xx)
007-4701-003 23
Page 46
1: Getting Started with the Silicon Graphics Prism
3.If the output does not show all the graphics pipes present, recheck all power, and
cable connections to be sure they are properly plugged in. See Chapter 5,
“Troubleshooting,” for additional trouble shooting tips and L1 messaging.
24 007-4701-003
Page 47
Powering Off Manually
!
Quick Start Information
To power off your system manually, follow these steps:
Caution: If you power off the system before you halt the operating system, you can lose
data.
1.Shut down the operating system by entering the following command:
# init 0
2.Press the power buttons or power switches on each of the modules that you want to
power off. You may power off the modules in any order:
•To power off the TP900 storage module, press the power button on its rear
panel to the OFF (
To power off the base compute, XG2N, expansion compute , or CMPX module, pr ess the
power button on the front panel of each module.
O) position.
007-4701-003 25
Page 48
Page 49
Chapter 2
2.System Overview and Options
This chapter provides an overview of the physical and architectural aspects of your
Silicon Graphics Prism platform. System configurations and components are described
and illustrated. This chapter includes the following sections:
•“Physical Features” on page 28
•“Functional Architecture” on page 30
•“System Components” on page 33
•“Power Components” on page 48
•“SGI Racks for Silicon Graphics Prism” on page 49
•“Optional Devices” on page 52
007-4701-00327
Page 50
2: System Overview and Options
Physical Features
The Silicon Graphics Prism platform is the latest advancement in the SGI NUMAflex
approach to Linux based modular visualization and computing. It is designed to deli ver
maximum sustained performance in a compact system footprint. Independent scaling of
graphics pipes, computational power, I/O bandwidth, and in-rack storage lets you
configure a system to meet your unique visualization and computational needs.
The system can be expanded from a two-module system with two graphics pipes, up to
48 GB of memory, and 4 PCI/PCI-X slots to a higher-performance system that contains
16 processors, 192 GB local DIMM memory, and 28 PCI/PCI-X slots. Note that many of
the available PCI/PCI-X slots may be used to support I/O, USB, ImageSync, or optional
audio or SCSI cards needed for the system.
For most configurations, the visualization system is housed in one 17U rack or one 39U
rack as shown in Figure 2-1; however, for small system configurations, the system
modules can be placed on a table top.
Systems that are housed in 17U racks have a maximum weight of approximately 610 lb
(277 kg). The maximum weight of systems that are housed in 39U racks is approximately
1,366 lb (620 kg). The racks have casters that enable you to remove the system from the
shipping container and roll it to its placement at your site.
Check with your SGI service representative for additional physical planning information
or documentation that may be available.
For more information about the technical specifications of your system and individual
modules, see Appendix A, “Technical Specifications,” in this manual.
28 007-4701-003
Page 51
17U rack
Physical Features
39U rack
2
2
TM
TM
Figure 2-1Example of Silicon Graphics Prism Rack Systems
007-4701-003 29
Page 52
2: System Overview and Options
Functional Architecture
The Silicon Graphics Prism is based on the SGI NUMAflex architecture, which is a
shared-memory system architecture that is the basis of SGI HPC servers and
supercomputers. The NUMAflex architecture is specifically engineered to provide
technical professionals with superior performance and scalability in a design that is easy
to deploy, program, and manage. It has the following features:
Shared access of processors, memory, and I/O. The Super Hub (SHub) ASICs and the
NUMAlink interconnect functions of the NUMAflex architecture enable applications to
share processors, memory, and I/O devices.
•Each Super-Hub (SHUB) ASIC in the system acts as a memory controller between
processors and memory for both local and remote memory references.
•The NUMAlink interconnect channels information between all the modules in the
system to create a single contiguous memory in the system of up to 192 GB and
enables every processor in a system direct access to every I/O slot in the system.
Together, the SHub ASICs and the NUMAlink interconnect enable efficient access to
processors, local and remote memory, and I/O devices without the bottlenecks
associated with switches, backplanes, and other commodity interconnect technologies.
System scalability. The NUMAflex architecture incorporates a low-latency,
high-bandwidth interconnect that is designed to maintain performance as you scale
system computing, I/O, and storage functions. For example, the computing dimension
in some system configurations can range from 4 to 16 processors in a single system image
(SSI).
Efficient resource management. The NUMAflex arc hitecture is designed to run complex
models and, because the entire memory space is shared, large models can fit into
memory with no programming restrictions. Rather than waiting for all of the processors
to complete their assigned tasks, the system dynamically reallocates memory, resulting
in faster time to solution.
30 007-4701-003
Page 53
Functional Architecture
A Silicon Graphics Prism system contains a combination of the following modules:
•Base compute module. All Silicon Graphics Prism systems include at least one base
compute module that contains the following components:
–A node board with two Intel Itanium 2 processors (each processor has
integrated L1, L2, and L3 caches), between 2 GB and 24 GB of local memory,
and a SHUB ASIC (the crossbar between the processors, local memory, the
network interface, and the I/O interface).
–Four PCI/PCI-X slots
–One four-port USB card that comes factory-installed in the top PCI/PCI-X slot
–One IO10 PCI card that comes factory-installed in the lowermost PCI/PCI-X
slot
Note: See “Optional IO9 PCI Card” on page 53 for information about the
optional IO9 card.
Note: Each system or partition requires a minimum of base I/O card. The
standard card providing this base I/O functionality is an IO10 PCI card.
Additional IO10 cards are required if you want additional serial ATA hard drives
and/or DVD-ROM drives in additional modules. These cards must reside in
additional base compute modules (no more than one card per module).
The IO10 card has real-time interrupt input and output ports, an Ethernet port,
and a multi-port serial adapter connector. The IO10 card is also needed to
support a base module’s serial ATA disk drive(s), and DVD-ROM.
Note: The RT interrupt input and RT interrupt output functionality of the IO10
PCI card is not supported under SGI Linux + ProPack.
–A bootable hard drive
–A DVD-ROM drive
007-4701-003 31
Page 54
2: System Overview and Options
•XG2N graphics module. All systems contain at least one graphics module that has
•CPU Expansion module. Like the base compute module, the CPU module contains
•CMPX module. Like the base compute module, the CMPX module contains a node
the following components:
–A node board with zero or two Intel Itanium 2 processors (each processor has
integrated L1, L2, and L3 caches), between 0 GB and 24 GB of local memory,
and a SHUB ASIC (the crossbar between the processors, local memory, the
network interface, and the I/O interface).
–Two graphics pipes
a node board and local memory. This module is different from the base compute
module, however, in the following ways:
–It has zero, one, or two CPUs (the base compute module must have two CPUs)
–It does not contain PCI/PCI-X slots, hard drives, or a removable media device.
board and local memory. This module is different from the base compute module,
however, in the following ways:
–It has zero, one, or two CPUs (the base compute module must have two CPUs)
–It does not contain an IO10 PCI card, hard drives, or a removable media device.
•Router module. The router module is an eight-port optional router that functions as
a high-speed switch to route network packets between modules through the
NUMAlink interconnect fabric.
When the system consists of a base compute module and XG2N graphics module only, it
may contain a maximum of 4 processors and a maximum of 48 GB of memory. T o increase
the number of graphics pipes, processors, and/or memory in the system, the base
compute module can connect to additional XG2N, CPU expansion and/or CMPX
modules via direct NUMAlink or through router modules.
32 007-4701-003
Page 55
System Components
This section briefly describes the standard and optional modules of a Silicon Graphics
Prism, in the following subsections:
•“Base Compute Module” on page 33
•“XG2N Graphics Module” on page 35
•“CPU Expansion Module” on page 36
•“CMPX Module” on page 38
•“Router Module” on page 40
Base Compute Module
The base compute module is a 2U AC-powered device that consists of the following:
•Two Intel Itanium 2 processors (each with integrated L1, L2, and L3 caches)
•Between 2 GB and 24 GB of local DIMM memory (4, 8, or 12 DIMMs)
System Components
•One to four PCI/PCI-X cards
Note: At least one base compute module comes factory-installed with a base I/O
card in the bottom PCI/PCI-X slot and a four-port USB card in the upper slot. This
base I/O card is typically an IO10 card, but may optionally be an IO9 card (described
in “Optional IO9 PCI Card” on page 53).
•One or two sled-mounted serial ATA disk drives (at least one disk drive is requir ed
in the system). The serial ATA disk drive(s) and the DVD-ROM require an IO10
card.
•DVD-ROM
Each base compute module also contains an L1 controller that provides the following:
•Controls and sequences power
•Controls and monitors the environment
•Initiates a reset
•Stores identification and configu ra ti o n information
007-4701-003 33
Page 56
2: System Overview and Options
Figure 2 -2 shows the front and rear views of a base compute module.
2
TM
Front view
Rear view
Figure 2-2Front and Rear View s of Base Compute Module with IO10 PCI Card
34 007-4701-003
Page 57
XG2N Graphics Module
The XG2N graphics module (see Figure 2-3) is a 2U AC-powered device that consists of
the following:
•Two graphics pipes
•Zero or two Intel Itanium 2 processors (each with integrated L1, L2, and L3 caches)
•Between 0 GB and 24 GB of local DIMM memory (4, 8, or 12 DIMMs)
•One L1 controller that provides the following services:
System Components
–Controls and sequences power
–Controls and monitors the environment
–Initiates a reset
–Stores identification and configuration information
2
M
T
Front view
Rear view
Figure 2-3Front and Rear V iew s of X G2N Module
007-4701-003 35
Page 58
2: System Overview and Options
CPU Expansion Module
The CPU expansion module is a 2U AC-powered device that consists of the following:
•Zero, one, or two Intel Itanium 2 processors (each with integrated L1, L2, and L3
•Between 2 GB and 24 GB of local DIMM memory (4, 8, or 12 DIMMs)
•One L1 controller that provides the following services:
Figure 2 -4 shows the front and rear views of a CPU expansion module.
caches)
–Controls and sequences power
–Controls and monitors the environment
–Initiates a reset
–Stores identification and configu ration information
36 007-4701-003
Page 59
2
M
T
System Components
Front view
Rear view
Figure 2-4Front and Rear V iew s of CPU Expansi on Modu le
007-4701-003 37
Page 60
2: System Overview and Options
CMPX Module
The CMPX module (see Figure 2-5) is a 2U AC-powered module that offers:
•Zero, one, or two Intel Itanium 2 processors (each with integrated L1, L2, and L3
•Between 2 and 24 GB of local DIMM memory (4, 8, or 12 DIMMs)
•Four PCI/PCI-X slots
•One L1 controller that provides the following services:
caches)
–Controls and sequences power
–Controls and monitors the environment
–Initiates a reset
–Stores identification and configu ration information
38 007-4701-003
Page 61
2
TM
System Components
Front view
Rear view
Figure 2-5Front and Rear V iew s of CMPX Option Module
007-4701-003 39
Page 62
2: System Overview and Options
Router Module
The optional router module (sometimes called an R-brick) is an eight-port 2U-high
module that functions as a high-speed switch to route network packets between base
compute, XG2N, CPU expansion, and CMPX modules. This creates a NUMAlink-4
interconnect fabric (as opposed to the ring topology normally used in smaller system
configurations). The optional router is generally only used when ther e are four and eight
modules interconnected as a single system image.
The section “NUMAlink Cabling in Routed Systems” on page 65 details the cable
connection points used in a system with a router.
The key component within the module is the router chip, an SGI custom-designed ASIC.
The router chip is an eight-port crossbar that connects any input-link channel to any of
the seven possible output-link channels (ports).
The router module contains the following front panel items (as shown in Figure 2-7):
•L1 display. The L1 display is a 55.7 mm X 32 mm backlit liquid crystal display
(LCD) that displays system messages. It displays two lines with a maximum of 12
characters on each line.
•On/Off switch with LED. Press this button to turn on the router internal
components. You can also turn on the router internal components at a system
console.
•Three LEDs:
–Power-button LED. This green LED illuminates when the router internal
components are on and turns off when they are off.
–Service-required LED. This amber LED illuminates to indicate that an item is
broken or not operating properly (for example, a fan is off), but the r outer is still
operating.
–Failure LED. This red LED illuminates to indicate that a system failure has
occurred and the router is down.
•Fans. Two hot-pluggable fans provide N+1 redundant cooling.
L1 controller display
Failure LED
Service-required LED
Power button
with LED
Figure 2-7Front View of the Router Module
42 007-4701-003
Page 65
Router Module Rear Panel Components
The router module has the following rear panel items (see Figure 2-8):
•PWR (power) connector. This connects the router to the power outlet (120V or
220V, autosensing).
•NUMAlink connectors. These NUMAlink connectors connect the router to the
Prism compute or graphics modules to form an interconnect fabric.
•L1 port connector. This connects the internal USB hub of the router to an optional
console/controller. The internal USB hub can receive the USB signals from the
controller via this port and distribute these signals to the L1 of the router.
•Console connector. This serial port provides optional connection to a terminal for
system control purposes.
•Link connector LEDs. Each NUMAlink connector has two LEDs, as follows:
–The yellow LED illuminates to indicate that both the router and the module to
which this NUMAlink port is connected are powered on.
–The green LED illuminates when a link has been established between the router
and the module to which it is connected through this NUMAlink port.
System Components
Port APort H
B
C
D
ELEC RATING
100-240VAC
50-60nz
1.0-0.6A
FUSE 250V-6.3A
AC IN
Power
connector
Console
L1 USB
CONSOLE
L1 USB
H
G
F
E
8A
7
6
1
2
3
45
Port EPort D
Figure 2-8Rear View of Router Module
007-4701-003 43
Page 66
2: System Overview and Options
Storage Expansion
A base compute module contains an IO10 base I/O card and two disk-drive bays. You
can add additional storage to the system as follows:
•For a SCSI (small computer system interface) JBOD (just a bunch of disks) solution,
•For a Fibre Channel solution that supports both JBOD and RAID configurations,
•The Silicon Graphics Prism also supports a number of tape devices; check with your
The various storage devices are discussed in the subsections that follow.
SGI offers the TP900 storage module. With the addition of an optional SCSI PCI
card, the TP900 can be connected to base compute modules or CMPX expansion
modules.
SGI offers the 2Gb SGI TP9100 storage system.
SGI sales or support representative for available options.
44 007-4701-003
Page 67
SGI TP900 Storage Module
System Components
The TP900 storage module, shown in Figure 2-9, is a 2U-high 8-drive storage system that
provides compact, high-capacity, high-availability JBOD storage. The enclosure
backplane connects the 8 drives on one SCSI bus. As an option, the storage module can
also be configured on two SCSI buses (2 strings of 4 drives).
This storage module has the following features:
•It mounts in a standard 19-inch rack; it is available in factory-installed
configurations.
•Its drive carriers accept SGI-qualified 10,000- or 15,000-RPM SCSI disk drives.
For more information about the TP900 storage module, see SGI Total Performance 900 Storage System User’s Guide (007-4428-00x).
Front view
Figure 2-9SGI TP900 Storage Module
007-4701-003 45
OUTPUT
GOOD
FAULT
Rear view
OUTPUT
GOOD
FAULT
Page 68
2: System Overview and Options
2Gb SGI TP9100 Optional Storage System
The 2Gb SGI TP9100, shown in Figure 2-10, is an affordable, entry-level RAID storage
array that is easily expandable and comes in either a deskside tower or a rackmounted
configuration. You can start with a basic JBOD configuration and later add RAID
controllers, or you can start with a RAID configuration.
The 2Gb SGI TP9100 storage system connects to base compute and/or CMPX modules
via an optional Fibre Channel PCI card. For more information about the SGI TP9100
storage system, see SGI Total Performance 9100 (2 Gb TP9100) Storage System User’s Guide
(007-4522-00x).
46 007-4701-003
Page 69
Deskside tower configuration
System Components
Rackmounted configuration
sgi
sgi
sgi
Figure 2-102Gb SGI TP9100 Storage System
007-4701-003 47
Page 70
2: System Overview and Options
Power Co mponents
The Silicon Graphics Prism platform can contain the following power components:
•One or two power distribution units (PDUs). The second PDU is added to the
system only when more than 10 AC power receptacles are needed within the rack.
The PDU inputs AC voltage from an external power receptacle and it can output
AC voltage to the base compute modules, XG2N graphics modules, CPU expansion
modules, CMPX modules, router modules, and TP900 storage modules.
See Figure 1-9 on page 14 for an example.
48 007-4701-003
Page 71
SGI Racks for Silicon Graphics Prism
The system is offered in two rack types: a short rack and a tall rack. The racks are
measured in standard rack units (U); one U is equal to 1.75 in. (4.45 cm). The short rack
is a 17U rack (see Figure 2 -11). The tall rack is a 39U rack (see Figure 2-14).
Each component within the rack is identified by the lowest U number that it occupies.
For example, the top (XG2N) module shown in Figure 2-11 is described as being located
in U12.
17
16
15
XG2N graphics module
Base compute module
14
13
12
11
10
9
8
7
6
5
4
3
2
1
SGI Racks for Silicon Graphics Prism
Figure 2-11Unit Numbering Within Racks
007-4701-003 49
Page 72
2: System Overview and Options
Both rack types are industry-standard 19-inch racks, and they support two types of
mounting rails (shelf rails or optional slide rails) that hold the modules within the rack.
For example, the base compute, XG2N, CPU expansion, and CMPX modules can use
shelf rails or optional slide-mounting rails (see Figure 2-12). The optional TP900 storage
modules always use shelf rails, which are two parallel L-shaped mounting rails within
the rack (see Figure 2-13).
9
7
6
5
4
3
2
1
2
M
T
Slide rail
Figure 2-12Optional Slide Rails
Shelf rails
19 in.
Figure 2-13Shelf Rails
50 007-4701-003
Page 73
SGI Racks for Silicon Graphics Prism
Both short and tall racks, as shown in Figure 2 -14, have front and rear doors that have
keylocks to prevent unauthorized access to the system. The racks also have cable
entry/exit areas at the bottom of the racks. Th e 39U racks have cable management
hardware in the rear.
Both rack types are mounted on four casters, two of which are swivel caste rs. The casters
enable the rack to be rolled out of a shipping crate and to its placement at your site.
Warning: Follow the guidelines in “Safety Measures” on page 11 and Appendix C,
“Installing Rack Systems,” to avoid damage to equipment, injury, or death.
The base of each rack has seismic tie-down attachment points. The base of the tall rack
also has leveling pads.
39U rack
17U rack
2
2
TM
TM
Figure 2-14Front Views of Short and Tall Racks
007-4701-003 51
Page 74
2: System Overview and Options
Optional Devices
This section describes some of the optional devices available for the Silicon Graphics
Prism system, in the following subsections:
•“Optional IO9 PCI Card” on page 53
•“Optional Tape Devices” on page 53
•“Optional DM8 Audio Board” on page 54
•“Optional USB Extender” on page 57
52 007-4701-003
Page 75
Optional IO9 PCI Card
Optional Devices
If you do not wish to use the IO10 base I/O card in your system, an optional IO9 PCI card
is required for base I/O functionality. Each system must contain at least one base I/O PCI
card for base I/O functionality within th e system. This PCI card must r eside in bus 1, slot
1 (the bottom slot) of the lowest base compute module in the system. The IO9 PCI card
has the following connectors:
•External VHDCI 68-pin SCSI co nn ector
•10/100/1000BaseT Ethernet connector
•Real-time interrupt output (RTO) and real-time interrupt input (RTI) connectors
Note: The RT interrupt input and RT interrupt output functionality of the IO9 PCI
card is not supported under SGI Linux + ProPack.
The optional IO9 card also contains an IOC-4 ASIC that supports the following features:
•One IDE channel for the DVD-ROM
Optional Tape Devices
•NVRAM and time-of-day clock
The Silicon Graphics Prism supports optional or third-party tape drives. For current tape
solutions for your system visit:
or check with your SGI sales or service representative.
007-4701-003 53
Page 76
2: System Overview and Options
Optional DM8 Audio Board
The DM8 is a half-size PCI expansion board that provides audio expansion via the PCI
bus. It connects to consumer and professional audio and video equipment via
industry-standard interfaces. Note that not all connector functionality is supported
under Linux. The DM8 interface panel is shown in Figure 2-15.
Board Installation
Surround
Surround
Center L/R
Figure 2-15DM8 Interface Panel and Connectors
L/R
Center/
Subwoofer
Front L/R
PhonesMic in
Line in
Your DM8 audio board is tested for operation in specific SGI visualization systems.
Select SGI Linux based systems support use of a single DM8 audio board (check with
your SGI sales or support representative for functional confirmation). It is recommended
that it not be removed and installed in other SGI systems.
SGI Linux based visualization systems support only one DM8 option board. Under most
circumstances you should always leave the DM8 installed in the original
factory-configured slot. If it does become necessary to either move or replace the board,
use the information on removing and r eplacing PCI cards in your system user’s guide for
step-by-step instructions. If you don’t have the printed user guide handy, it is available
on the Internet in the SGI Technical Publications Library at the following location:
http://docs.sgi.com
Proceed to the next sections for information on cabling, verifying functionality, and basic
operation.
54 007-4701-003
Page 77
Cables and Connectors
Optional Devices
The DM8 audio board has the following connectors on it’s rear panel as shown from le ft
to right in Figure 2-15 on page 54:
•Surround Center L/R (silver) a line-level output connector for powered surround
Center Left and Right channel speakers (not supported under Linux).
•Surround L/R (black) a line-level output that can connect to powered Surround
Left and Right speakers (not supported under Linux).
•Center/Subwoofer (orange) a line-level output that can connect to powered Center
and Subwoofer speakers (not supported under Linux).
•Front L/R Phones (green) a jack that connects to powered Left and Right speakers.
If you are using a basic two-speaker ster eo setup, this is the jack you w ill use. This is
also the jack to use for stereo headphones.
•Line In (blue) a stereo line-level input intended for recording into an audio
record ing p rogram.
•Mic In (pink) a mic input for connecting a mono microphone for recording,
videophone, or voice-recognition applications. This jack is a three-conductor
TRS-type jack for condenser (two-conductor) and electret (three-conductor) type
microphones.
Functional Features
The DM8 PCI audio board has the following functional features:
Line outs:
•Dynamic range of 106 dB (typical, -60 dB input, a-weighted)
•Maximum line output level of 1.26 Vrms (+2 dBV)
•Frequency response of +0.8/-3.0 dB, 20Hz to 80 kHz
•24-bit linear PCM/48kHz playback capability for Linux systems
•24-bit linear PCM/48kHz recording capability for Linux systems
Connector features:
•Analog connector for powered speakers (headphone jack)
•Stereo 1/8-inch mini analog line input
•Mono 1/8-inch mini analog microphone input (with electret mic power)
Troubleshooting Tips
Use the following information to help correct any functional problems with the DM8
audio PCI option board:
If the sound is distorted or a channel is not producing sound, try the following:
•Check all cable connections between the audio card and speakers
•Confirm that any powered speakers are powered on
If the audio is not working at all, try these solutions:
•Reboot the system
•Reseat the PCI audio card
If none of these solutions solve the problem, contact your SGI customer support
representative or local service provider for additional help.
56 007-4701-003
Page 79
Optional USB Extender
You can plug the keyboard and mouse directly into the USB connectors of a compute
module (see “Connecting a Keyboard and Mouse” on page 19), or you can use an
optional USB extender that allows you to place the keyboard and mouse up to 328.68 feet
(100 m) from the compute module, see Figure 2-16 on page 58.
Note: The local extender (LEX) receives AC power from the system power source or
power distribution strip (PDS) in the rack. A 6-ft. (1.82-m) adapter cable connects the
extender’s power adapter to the PDU. The REX requires AC power from a sour ce within
a 6-ft. (1.82-m) range from the keyboard/mouse connection point.
Optional Devices
007-4701-003 57
Page 80
2: System Overview and Options
Power
distribution
unit (PDU)
USB ports
9.84 ft (3 m)
USB type B
connector
LEX
RJ45
connector
30 ft (9.1 m)
6-ft
(1.82 m)
adapter cable
Power
adapter
HOST
1
LINK
POWER
REX
Keyboard
USB type A
connectors
RJ45
connector
Mouse
USB Type A connector
USB Type B connector
Figure 2-16Keyboard and Mouse Connected via Optional USB Extender
58 007-4701-003
Page 81
Chapter 3
3.Configurations and Cabling
This chapter describes the configuration ranges of the Silicon Graphics Prism Power and
Team Systems and provides NUMAlink cabling instructions.
007-4701-00359
Page 82
3: Configurations and Cabling
System Configurations
The minimum and maximum ranges of the configurable items for the Silicon Graphics
Prism Power Systems (ring topology) are listed in Table 3-1, and for the Silicon Graphics
Prism Team Systems (router topology) are listed in Table 3-2.
Table 3-1Silicon Graphics Prism Power System Configuration Ranges
Configuration
Minimum
Configuration
Maximum
a
Compute/expansion modules13
Graphics modules12
Processors48
Memory capacity2 GB96 GB
Internal disk storage1 serial AT A disk6 serial ATA disks
Internal PCI/PCI-X slots
b
416
Storage deviceNoneCustomer configurable
17U short rack
39U tall rack
None
None
1
1
Optional L2 controllerNone1
a. Maximum configurations and peak performance will change over time based on new technology available;
check with your SGI sales or service representative for the latest available options and configurations.
b. Each base compute module has four internal PCI/PCI-X slots; however, one slot is required for the base IO
PCI card, one for the ImageSync card, and one for USB. Therefore, the number of avai lable s lots i n the bas e
compute module is reduced.
60007-4701-003
Page 83
Table 3-2Silicon Graphics Prism Team System Configuration Ranges
System Configurations
Configuration
Minimum
Configuration
Maximum
a
Compute/expansion modules15
Graphics modules24
NUMAlink modules (routers)22
Processors816
Memory capacity8 GB192 GB
Internal disk storage1 serial ATA disk10 serial ATA disks
Internal PCI/PCI-X slots
b
428
Storage deviceNoneCustomer configurable
17U short rack
39U tall rack
None
None
1
2
Optional L2 controllerNone1
a. Maximum configurations and peak performance will change over time based on new technology available;
check with your SGI sales or service representative for the latest available options and configurations.
b. Each base compute module has four internal PCI/PCI-X slots; however, one slot is required for the base IO PCI
card, one for the ImageSync card, and one for USB. Therefore, the number of available slots in the base compute
module is reduced.
007-4701-00361
Page 84
3: Configurations and Cabling
NUMAlink Cabling in Ring Topologies
The basic Silicon Graphics Prism uses a type of network configuration that is referred to
as a ring topology. As the name implies, the network connection between the base
compute module, graphics module, and optional CPU expansion or CMPX modules
forms a ring. A message is passed around the ring until it reaches its destination. The data
flow of this ring topology flows in both directions, enabling the modules to have direct
connection to two other modules and providing an alternative path if a connection fails
between two modules.
The Silicon Graphics Prism system may also be configured in routed configurations,
which are described in “NUMAlink Cabling in Routed Systems” on page 65.
The bisection bandwidth per node depends on the number of modules on the ring, as
well as what type of modules they are; the bisection bandwidth per node is greatest when
there are only two modules on the ring. See Table 3-3.
Figure 3-1 provides an example of the two-module ring topology.
XG2N graphics module
1
2
2
CONSOLE
L! Port
NUMAlink
Repeat
IS2
IS1
NUMALINK 1
NUMAlink
NUMALINK 0
Base compute module
PCI 4
1
CONSOLE
NUMAlink
L1 PORT
NUMAlink
NUMALINK 0NUMALINK 1
CPU
PCI 3
PCI 2
PCI 1
Figure 3-1Two-Module Ring Topology Example
Figure 3-2 shows an example of a three-module ring topology.
XG2N graphics module
1
32
3
CONSOLE
L! Port
NUMAlink
NUMALINK 0
NUMAlink
IS1
NUMALINK 1
IS2
Repeat
XG2N graphics module
2
CONSOLE
L! Port
Repeat
NUMALINK 0
NUMAlink
IS2
IS1
NUMAlink
NUMALINK 1
Base compute module
PCI 4
1
CONSOLE
NUMAlink
L1 PORT
NUMAlink
CPU
NUMALINK 0NUMALINK 1
PCI 3
PCI 2
PCI 1
Figure 3-2Three-Module Ring Topology Example
007-4701-00363
Page 86
3: Configurations and Cabling
Figure 3 -3 shows an exa mple of a fou r-module ring topology.
CPU expansion or CMPX module
4
NUMAlink
NUMAlink
XG2N graphics module
1
243
Repeat
IS2
3
CONSOLE
L! Port
NUMAlink
NUMALINK 0
IS1
NUMAlink
NUMALINK 1
XG2N graphics module
2
CONSOLE
L! Port
NUMAlink
Repeat
IS2
IS1
NUMALINK 1
NUMAlink
NUMALINK 0
Base compute module
PCI 4
1
CONSOLE
NUMAlink
L1 PORT
NUMAlink
CPU
NUMALINK 0NUMALINK 1
PCI 3
PCI 2
PCI 1
Figure 3-3Four-Module Ring Topology Example
64007-4701-003
Page 87
NUMAlink Cabling in Routed Systems
This section describes the NUMAlink cabling for syst ems containing routers.
Prism systems containing routers will have between four and eight base compute, XG2N,
CPU, or CMPX modules, as well as two routers. This section provides cabling details for
the smallest configuration (four modules, two routers) and largest configuration (eight
modules, two routers). Other configurations are similar to the ones shown.
NUMAlink Cabling in Routed Systems
007-4701-00365
Page 88
3: Configurations and Cabling
Minimum Routed Configuration
This section describes a minimum routed configuration, having four base compute,
XG2N, CPU, or CMPX modules. Table 3-4 details the NUMAlink cabling for th is
configuration, Figure 3-4 provides a conceptual diagram, and Figure 3-5 shows a
representative module ordering.
Table 3-4Minimum Routed Configuration Cable Chart
Router (a) CablesRouter (b) Cables
Router (a), port A to module 1, port NL-0Router (b), port A to module 1, port NL-1
Router (a), port B to module 2, port NL-0Router (b), port B to module 2, port NL-1
Router (a), port C to module 3, port NL-0Router (b), port C to module 3, port NL-1
Router (a), port D to module 4, port NL-0Router (b), port D to module 4, port NL-1
Figure 3-5Module Ordering in Minimum Routed Configuration
007-4701-00367
Page 90
3: Configurations and Cabling
Maximum Routed Configuration
This section describes a maximum routed configuration, having eight base compute,
XG2N, CPU, or CMPX modules. Table 3-5 details the NUMAlink cabling for th is
configuration, Figure 3-6 provides a conceptual diagram, and Figure 3-7 shows a
representative the module or dering.
Table 3-5Maximum Routed Configuration Cable Chart
Router (a) CablesRouter (b) Cables
Router (a), port A to module 1, port NL-0Router (b), port A to module 1, port NL-1
Router (a), port B to module 2, port NL-0Router (b), port B to module 2, port NL-1
Router (a), port C to module 3, port NL-0Router (b), port C to module 3, port NL-1
Router (a), port D to module 4, port NL-0Router (b), port D to module 4, port NL-1
Router (a), port E to module 1, port NL-0Router (b), port E to module 1, port NL-1
Router (a), port F to module 2, port NL-0Router (b), port F to module 2, port NL-1
Router (a), port G to module 3, port NL-0Router (b), port G to module 3, port NL-1
Router (a), port H to module 4, port NL-0Router (b), port H to module 4, port NL-1
Figure 3-7Module Ordering in Maximum Routed Configuration
70007-4701-003
Page 93
Chapter 4
4.Installing and Removing Customer-Replaceable
Units
This chapter provides safety instructions to follow when using and maintaining your
system. It also describes how to install and remove customer-replaceable units (CRUs).
This information is covered in the following sections:
•“Safety Instructions” on page 72
•“Accessing the System’s Internal Components” on page 74
•“PCI and PCI-X Cards” on page 81
•“Replacing an XG2N Graphics Card” on page 91
•“Disk Drives” on page 98
•“Removing and Replacing Power Supplies” on page 103
•“Removing and Replacing Memory DIMMs” on page 107
•“L1 Controller Display” on page 114
007-4701-003 71
Page 94
4: Installing and Removing Customer-Replaceable Units
Safety Instructions
Before you perform any type of maintenance to your system, read the following safety
instructions:
•Follow all warnings and instructions marked on the product and noted in this and
other documentation included with the product.
•Unplug this product from the wall outlet before you clean it. Do not use liquid
cleaners or aerosol cleaners. Use a damp cloth for cleaning.
•Do not use this product near water.
•Do not place this product or components of this product on an unstable cart, stand,
or table. The product may fall, causing serious damage to the product.
•Perforation openings on the cabinet and components are provided for ventilation,
reliable operation, and protection from overheating of the product. These
ventilation holes must not be blocked or covered. This product should never be
placed near or over a radiator or heat register, or in a built-in installation unless
proper ventilation is provided.
•This product should be operated with the type of power indicated on the marking
label. If you are not sure of the type of power available, consult your dealer or local
power company.
•Do not allow anything to rest on the power cord. Do not locate this product where
people will walk on the cord.
•Do not use extension cords with your SGI system.
•Never push objects of any kind into this product through cabinet holes because they
may touch dangerous voltage points or short out parts that could result in a fire or
electric shock.
•Never spill liquid of any kind on the product.
•Do not attempt to service this product yourself except as noted in this guide.
Opening or removing covers of internal components may expose you to dangerous
voltage points or other risks. Refer all servicing to qualified service personnel.
•Unplug this product from the wall outlet and refer servicing to qualified service
personnel under the following conditions:
–If the power cord or plug is damaged or frayed.
–If the product has been exposed to rain, water, or other type of liquid.
72 007-4701-003
Page 95
Safety Instructions
–If the product does not operate normally when the operating instructions are
followed.
Note: Adjust only those controls that are cover ed by the operating instructions,
because improper adjustment of other controls may result in damage and will
often require extensive work by a qualified technician to restore the product to
normal condition.
–If the product has been dropped or if the cabinet has been damaged.
–If the product exhibits a distinct change in performance, which indicates a need
for service.
•Only qualified service personnel should replace the soldered lithium battery (or
batteries) in the Silicon Graphics Prism platform. Please see Appendix D,
“Regulatory Specifications and Safety Information” for more information.
•Use only the proper type of power supply cord set (provided with the system) for
this unit.
007-4701-003 73
Page 96
4: Installing and Removing Customer-Replaceable Units
Accessing the System’s Internal Components
Many of the procedures in this chapter r equir e the r emoval of the top cover, a frame rail,
or a support bracket in order to access the internal components you are removing or
replacing. This section describes how to remove and replace these items.
Opening the Cover
Use the following steps to open the cover:
1.To remove the module’s top cover and access the internal system components,
remove the ten Phillips screws as shown in Figure 4-1.
2.Lift the hinged cover into the fully open position.
Figure 4-1Opening the System Cover
74 007-4701-003
Page 97
Removing the Optional Chassis Rail
If you are installing a card in one of the two lower-most car d slots (or the bottom card, in
the case of an XG2N module), you will need to remove the optional chassis rail. To do
this, unscrew the five Phillips scr ews, as shown in F igure 4-2. (If you are not installing a
card into one of the lower-most card slots, or your module is not slide-rail mounted, you
will not need to perform this step.)
Caution: The module may or may not have a factory-installed IO10 card, which
!
always comes installed in the lowermost slot. To prevent damage to your system,
only a trained SGI service support engineer can install or remove an IO10 card.
Accessing the System’s Internal Components
007-4701-003 75
Page 98
4: Installing and Removing Customer-Replaceable Units
Figure 4-2Removing an Optional Chassis Rail
76 007-4701-003
Page 99
Removing the PCI/PCI-X Support Bracket
If you are accessing one of the two lower-most card slots (or the bottom card, in the case
of an XG2N module), you must remove the lower PCI/PCI-X support bracket that covers
the two lower-most slots. To do this remove the four Phillips screws, as shown in
Figure 4-3. (If you are not installing a card into one of the lower-most card slots you will
not need to perform this step.)
Accessing the System’s Internal Components
Figure 4-3Removing the Lower PCI/PCI-X Support Bracket
007-4701-003 77
Page 100
4: Installing and Removing Customer-Replaceable Units
Reinstalling the PCI/PCI-X Support Bracket
If you removed the PCI/PCI-X support bracket, replace it and scr ew in the four Phillips
screws, as shown in Figure 4-4
Figure 4-4Replacing the Lower PCI/PCI-X Support Bracket
78 007-4701-003
Loading...
+ hidden pages
You need points to download manuals.
1 point = 1 manual.
You can buy points or you can get point for every manual you upload.