Nvidia TESLA K20 Installation Manual
Text of the manual
Table of ConTenTs
Table of ConTenTs
Introduction
1
about This Guide
1
Minimum system Requirements
2
Unpacking
3
equipment
3
Hardware Installation
5
safety Instructions
5
before You begin
6
Installing the Tesla K20 Graphics Card
6
Driver Installation
11
Downloading and Installing Windows Driver
11
Verifying the Windows Driver Installation
13
linux Installation
14
Register, Warranty, and Support
15
Compliances
17
With many mainstream applications now taking
advantage of the GPu computing found in the
nVIDIa® Tesla™ K20, leading-edge customers
are producing breakthroughs in their industries
by achieving better results in a shorter period
of time. adding the nVIDIa Tesla K20 to an
industry-standard workstation and configuring
it with an nVIDIa Quadro Professional Graphics
solution enables performance scaling across a
wide range of professional applications.
About This Guide
This installation guide discusses the installation and configuration of
the Tesla K20 active accelerator for Workstations.
01
Minimum System Requirements
Prior to unpacking your new Tesla K20, confirm that your system meets
all the requirements for a smooth installation.
>
Operating System
z
Microsoft Windows Vista, Windows 7 (32-bit versions of
Windows are not supported, 64-bit only)
z
linux 32-bit and 64-bit on:
z
fedora 16
z
RHel 5.x
z
RHel 6.x
>
Processor
z
Intel Pentium 4 or Xeon processor or higher
z
aMD athlon processor or higher
>
RAM
z
5 Gb recommended per Tesla K20
>
PCI Express Slot
z
PCI express x16 slot, Gen2 recommended but not required
>
Power Consumption
z
225 W maximum power consumption
z
Power supply must have two 6-pin power connectors.
Prior to unpacking your new nVIDIa Tesla
K20 active accelerator graphics card, it is
important to make sure you meet all the system
requirements listed on page 2 for a smooth
installation.
be sure to inspect each piece of equipment
shipped in the packing box. If anything is missing
or damaged, contact your reseller.
Equipment
The following equipment and documentation are included in the
graphics card box.
WelCoMe
Registration Card
Register to gain priority access to online and
phone support.
Tesla K20 Active Accelerator
Installs into the PCI express x16 slot in your computer.
(an image of the card showing the connectors is on the
following page.
02
slI and framelock
connectors disabled
Power connectors
back-edge of card
Tesla K20 Computing Processor
Installing the nVIDIa Tesla K20 active
accelerator graphics card hardware involves
opening up your computer. follow all of the
safety instructions provided here to ensure that
there is no damage to you, your computer, or the
graphics board.
Safety Instructions
To reduce the risk of fire, electric shock, or injury, always follow basic
safety precautions.
Note: all hardware must be installed prior to installation of
the drivers.
>
Remove power from your computer by disconnecting the aC main
source before installation.
>
Do not operate this product near water or when your hands or
body are wet.
>
Do not place this product on soft surfaces that could block the
ventilation slots and cause overheating.
>
Do not place this product near a heating register or radiator.
>
Place this product securely on a stable surface. serious damage
to this product may result if it falls.
>
Do not allow anything to rest on the power cord. Do not place
this product where a person can step or trip on the power cord.
03
Before You Begin
The Tesla K20 active accelerator graphics card is a PCI express ×16
graphics card. Your computer may already have a graphics card installed
in the PCI express slot. If so, you will need to remove that graphics card
and replace it with the Tesla K20 active accelerator graphics card.
If you do not have a graphics card, this means that your motherboard
has on-board graphics (there is a graphics chip installed on your
motherboard or integrated in the motherboard chipset). If this is the
case, there is no action that needs to be taken before installing your
new graphics card.
Installing the Tesla K20 Graphics Card
because there are so many different computer systems on the market,
the procedure to install the graphics card can vary from system to
system. use the following instructions as a guideline and consult the
documentation for your computer system for any further information
on your individual system.
Note: It is important that all power to the computer be
disconnected before you install the graphics card.
Discharge your body’s static electricity by touching a grounded surface
before touching the graphics card. a grounded surface is the computer
chassis, or some other surface you know to be grounded.
use the following procedure to install the Tesla K20 active accelerator
graphics card into your computer system.
1 Turn off your computer and monitor and disconnect the power cord.
Depending on your computer system, you may need to disconnect
the cable going to the back of your system. Mark the cables so you
can make sure you reconnect them properly.
2 open your computer by removing the cover/side panel. Refer to
your computer documentation from the original manufacturer
for assistance.
3 Remove any existing graphics card (if there is one). save hardware
(such as screws and brackets) to use when installing the nVIDIa
graphics card.
!
Attention: If your system has been running for a period of
time prior to opening the panels, it is very important that you
wait until the graphics card in your system has cooled before
taking the card out of the system. Graphics cards get very hot
when they have been operating for any length of time.
4 Remove adjacent slot covers if you do not have a graphics card
installed.
Note: The Tesla K20 active accelerator card is double-wide so it
will require removing two slot covers.
5 Plug the graphics card into the Primary PCI express x16 slot on your
motherboard. This is often the slot closest to the CPu but may be the
second or third slot. look for the slot labeled ×16. It will likely be the
only PCI express slot with a retention lever on the end of the slot or
the one closest to the CPu.
Note: It is recommended that you install the graphics card
into the primary PCI express x16 slot. If you install the graphics
card into the secondary slot, your system may not recognize the
graphics card and there will be nothing displayed on the monitor.
also note that on some motherboard sbIos, the physical
location of the primary slot can be configured when there are
more than one PCI express x16 slots.
6 Connect two PCI express 6-pin auxiliary power connectors from the
system power supply to the top edge of the graphics card. note that
the connector and socket on the graphics card have a unique shape
and connect one way only.
7 Reinstall the cover on your computer and reconnect any cables that
you removed earlier in the installation.
8 Reconnect the power cord to your system.
Connect two 6-pin connectors from the
system power supply to the back edge of
the graphics card
With the hardware installed, it is now time to
install the graphics driver. nVIDIa recommends
downloading and installing the most recent
drivers available at:
http://www.nvidia.com/drivers.
Downloading and Installing Windows Driver
use the following procedure to download the
graphics driver.
Note: It is recommended that you uninstall the existing driver
from your system before installing the new driver.
1 Power up your system.
2 Go to www.nvidia.com/drivers.
3 select an option for download. If option 1 is selected, fill the
required information.
04
4 select Agree & Download and follow instructions displayed on the
screen.
5 select Run once the download has completed to begin the
installation.
6 select AGREE AND CONTINUE when the nvIdIa software license
agreement displays.
7 select an Install option and click NEXT.
>
express (recommended) installs the full list of options listed
under Custom install
>
Custom (Advanced) displays a list of options for you to choose to
install. If you would like to clean up your old profiles and settings,
click the Perform a clean installation check box. Performing a
clean install also removes all files related to the previous driver.
Note: If you are installing the Tesla K20 as a companion device
to your primary Quadro board, a clean install is recommended.
9 select an install option and click NEXT when the
Installation Options window displays.
10 Restart the computer if prompted.
11 select Close to complete the installation
Note: nVIDIa recommends that you periodically visit
www.nvidia.com/drivers to update to the latest driver versions.
Verifying Windows Installation
It is recommended that you verify your installation by going to the Win-
dows Device Manager and verifying that the Tesla K20 has been installed
correctly and is recognized by the drivers.
use the following procedure to verify the installation of the board:
1 Go to Start > Computer.
2 select System Properties.
3 Go to Device Manager in the menu bar.
4 expand Display Adapters in the list.
5 nVIDIa Tesla K20 should be shown in the list.
before you begin the installation, you should exit the X server and
close all openGl applications (it is possible that some openGl
applications persist even after the X server has stopped). You
should also set the default run level on your system such that it
will boot to a VGa console and not directly to X. Doing so will make
it easier to recover if there is a problem during the installation
process.
1 Download the 32-bit or 64-bit linux driver (the driver will have a
similar naming convention as NVIDIA-Linux-x86-100.14.11-pkg1.
run or NVIDIA-Linux-x86_64-100.14.11-pkg2.run) from
www.nvidia.com/drivers.
2 Change to the directory containing the downloaded file.
3 Run as root the NVIDIA-Linux*.run file downloaded in step 1.
as the root user you can run the following executable files:
>
cd download_directory
>
NVIDIA-Linux-x86-xxx-xx-xx.run or
NVIDIA-Linux-x86_64-xxx-xx-xx.run
The NVIDIA-Linux*.run file is a self-extracting archive. When
executed, it extracts the content of the archive and runs the contained
nvidia-installer utility, which provides an interactive interface to walk
you through the installation. nvidia-installer will also install itself to
/usr/bin/nvidia-installer which may be used at a later time to unin-
stall drivers, auto download updated drivers, etc.
4 select Accept to accept the license agreement.
04
Registering Your Tesla K20 Active Accelerator
for Workstations
Registering your Tesla K20 active accelerator card gives you priority
access to the nVIDIa Customer Care support center. once you have
completed registration, you will be given a user ID and password
for online customer care. You can also elect to receive automatic
notification of special promotions and software updates through
email to ensure that your Tesla K20 card continues to operate
optimally.
Warranty and Support
The Tesla K20 is covered by a 36 month warranty.
for support, visit the Customer Care Center at
www.nvidia.com/support.
The Web site offers access to a broad range of product information.
The nVIDIa Geforce GTX 650 Ti graphics card is compliant with the
following regulations:
>
federal Communications Commission (fCC)
>
Industry Canada (IC)
>
Conformité européenne (Ce)
>
australian Communications and Media authority (C-tick)
>
Voluntary Control Council for Interference (VCCI)
>
bureau of standards Metrology and Inspection (bsMI)
>
Korean Certification (KC)
>
underwriters laboratories (ul, cul)
>
Iso 9241-307 Visual Display ergonomics
UNITED STATES
federal Communications Commission (fCC)
NVIDIA CORP
Model: P2030
This equipment has been tested and found to comply with the limits
for a Class b digital device, pursuant to Part 15 of the fCC Rules.
These limits are designed to provide reasonable protection against
harmful interference in a residential installation. This equipment
generates, uses and can radiate radio frequency energy and, if not
installed and used in accordance with the instructions, may cause
06
CoMplIanCes
harmful interference to radio communications. However, there is no
guarantee that interference will not occur in a particular installation.
If this equipment does cause harmful interference to radio or
television reception, which can be determined by turning the
equipment off and on, the user is encouraged to try to correct the
interference by one or more of the following measures:
>
Reorient or relocate the receiving antenna.
>
Increase the separation between the equipment and receiver.
>
Connect the equipment into an outlet on a circuit different
from that to which the receiver is connected.
>
Consult the dealer or an experienced radio/TV technician
for help.
CANADA
Industry Canada (IC)
This Class B digital apparatus complies with ICES-003
Cet appareil numérique de la classe B est conforme à la norme
NMB-003 du Canada.
operation is subject to the following two conditions: (1) this device
may not cause interference, and (2) this device must accept any
interference, including interference that may cause undesired
operation of the device.
EUROPEAN UNION
European Conformity; Conformité Européenne (CE)
This device complies with the eMC Directive for Class b, I.T.e
equipment.
AUSTRALIA & NEW ZEALAND
Australian Communications and Media Authority (C-tick)
This product meets the applicable eMC requirements for Class b,
I.T.e equipement
JAPAN
06
Voluntary Control Council for Interference (VCCI)
This is a Class b product based on the standard of the VCCI Council.
If this is used near a radio or television receiver in a domestic
environment, it may cause radio interference. Install and use the
equipment according to the instruction manual.
KOREA
Radio Research Agency (RRA)
KCC-REM-NVA-P2030
b급 기기(가정용 방송통신기기)
이 기기는 가정용(b급)으로 전자파적합등록을 한
기기로서 주로 가정에서 사용하는 것을 목적으로
하며, 모든 지역에서 사용할 수 있습니다.
Class b equipment (for Home use broadcasting & Communication
equipment)
This equipment is home use (Class b) electromagnetic wave
suitability equipment and to be used mainly at home and it can be
used in all areas.
Bureau of Standards, Metrology and Inspection (BSMI)
This device complies with Cns 13438 (2006) Class b
SAfETY
Underwriters Laboratories (UL)
06
all nVIDIa DesIGn sPeCIfICaTIons, RefeRenCe boaRDs, fIles, DRaWInGs,
DIaGnosTICs, lIsTs, anD oTHeR DoCuMenTs (ToGeTHeR anD sePaRaTelY,
“MaTeRIals”) aRe beInG PRoVIDeD “as Is.” nVIDIa MaKes no WaRRanTIes,
eXPResseD, IMPlIeD, sTaTuToRY, oR oTHeRWIse WITH ResPeCT To THe
MaTeRIals, anD eXPResslY DIsClaIMs all IMPlIeD WaRRanTIes of non-
InfRInGeMenT, MeRCHanTabIlITY, anD fITness foR a PaRTICulaR PuRPose.
Information furnished is believed to be accurate and reliable. However, nVIDIa
Corporation assumes no responsibility for the consequences of use of such
information or for any infringement of patents or other rights of third parties that
may result from its use. no license is granted by implication or otherwise under
any patent or patent rights of nVIDIa Corporation. specifications mentioned in this
publication are subject to change without notice. This publication supersedes and
replaces all information previously supplied. nVIDIa Corporation products are not
authorized for use as critical components in life support devices or systems without
express written approval of nVIDIa Corporation.
Trademarks
nVIDIa, the nVIDIa logo, CuDa, Geforce, GigaThread, lumenex, PureVideo, and
PhysX Technology are trademarks or registered trademarks of nVIDIa Corporation.
other company product names may be trademarks of the respective companies with
which they are associated.
Copyright
© 2013 nVIDIa Corporation. all rights reserved.