UCS B200 M4 Installation Service
UCS B200 M4 Installation Service
UCS B200 M4 Installation Service
Americas Headquarters
Cisco Systems, Inc.
170 West Tasman Drive
San Jose, CA 95134-1706
USA
http://www.cisco.com
Tel: 408 526-4000
800 553-NETS (6387)
Fax: 408 527-0883
THE SPECIFICATIONS AND INFORMATION REGARDING THE PRODUCTS IN THIS MANUAL ARE SUBJECT TO CHANGE WITHOUT NOTICE. ALL STATEMENTS,
INFORMATION, AND RECOMMENDATIONS IN THIS MANUAL ARE BELIEVED TO BE ACCURATE BUT ARE PRESENTED WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED. USERS MUST TAKE FULL RESPONSIBILITY FOR THEIR APPLICATION OF ANY PRODUCTS.
THE SOFTWARE LICENSE AND LIMITED WARRANTY FOR THE ACCOMPANYING PRODUCT ARE SET FORTH IN THE INFORMATION PACKET THAT SHIPPED WITH
THE PRODUCT AND ARE INCORPORATED HEREIN BY THIS REFERENCE. IF YOU ARE UNABLE TO LOCATE THE SOFTWARE LICENSE OR LIMITED WARRANTY,
CONTACT YOUR CISCO REPRESENTATIVE FOR A COPY.
The following information is for FCC compliance of Class A devices: This equipment has been tested and found to comply with the limits for a Class A digital device, pursuant to part 15
of the FCC rules. These limits are designed to provide reasonable protection against harmful interference when the equipment is operated in a commercial environment. This equipment
generates, uses, and can radiate radio-frequency energy and, if not installed and used in accordance with the instruction manual, may cause harmful interference to radio communications.
Operation of this equipment in a residential area is likely to cause harmful interference, in which case users will be required to correct the interference at their own expense.
The following information is for FCC compliance of Class B devices: 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 harmful interference to radio communications. However, there is no guarantee that interference
will not occur in a particular installation. If the equipment causes interference to radio or television reception, which can be determined by turning the equipment off and on, users are
encouraged to try to correct the interference by using one or more of the following measures:
• Connect the equipment into an outlet on a circuit different from that to which the receiver is connected.
Modifications to this product not authorized by Cisco could void the FCC approval and negate your authority to operate the product.
The Cisco implementation of TCP header compression is an adaptation of a program developed by the University of California, Berkeley (UCB) as part of UCB’s public domain version of
the UNIX operating system. All rights reserved. Copyright © 1981, Regents of the University of California.
NOTWITHSTANDING ANY OTHER WARRANTY HEREIN, ALL DOCUMENT FILES AND SOFTWARE OF THESE SUPPLIERS ARE PROVIDED "AS IS" WITH ALL FAULTS.
CISCO AND THE ABOVE-NAMED SUPPLIERS DISCLAIM ALL WARRANTIES, EXPRESSED OR IMPLIED, INCLUDING, WITHOUT LIMITATION, THOSE OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OR ARISING FROM A COURSE OF DEALING, USAGE, OR TRADE PRACTICE.
IN NO EVENT SHALL CISCO OR ITS SUPPLIERS BE LIABLE FOR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, OR INCIDENTAL DAMAGES, INCLUDING, WITHOUT
LIMITATION, LOST PROFITS OR LOSS OR DAMAGE TO DATA ARISING OUT OF THE USE OR INABILITY TO USE THIS MANUAL, EVEN IF CISCO OR ITS SUPPLIERS
HAVE BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
Any Internet Protocol (IP) addresses and phone numbers used in this document are not intended to be actual addresses and phone numbers. Any examples, command display output, network
topology diagrams, and other figures included in the document are shown for illustrative purposes only. Any use of actual IP addresses or phone numbers in illustrative content is unintentional
and coincidental.
All printed copies and duplicate soft copies of this document are considered uncontrolled. See the current online version for the latest version.
Cisco has more than 200 offices worldwide. Addresses and phone numbers are listed on the Cisco website at www.cisco.com/go/offices.
Cisco and the Cisco logo are trademarks or registered trademarks of Cisco and/or its affiliates in the U.S. and other countries. To view a list of Cisco trademarks, go to this URL:
https://www.cisco.com/c/en/us/about/legal/trademarks.html. Third-party trademarks mentioned are the property of their respective owners. The use of the word partner does not imply a
partnership relationship between Cisco and any other company. (1721R)
© 2016–2020 Cisco Systems, Inc. All rights reserved.
CONTENTS
CHAPTER 1 Overview 1
Installing on Windows 40
Installing on Linux 40
Installing GRID Licenses From the NVIDIA Licensing Portal to the License Server 41
Accessing the GRID License Server Management Interface 41
Reading Your License Server's MAC Address 41
Installing Licenses From the Licensing Portal 42
Viewing Available Licenses 42
Viewing Current License Usage 42
Managing GRID Licenses 43
Acquiring a GRID License on Windows 43
Acquiring a GRID License on Linux 44
Installing Drivers to Support the NVIDIA GPU Cards 44
1. Updating the Server BIOS Firmware 45
2. Activating the Server BIOS Firmware 45
3. Updating the NVIDIA Drivers 46
Audience
To use this installation guide, you must be familiar with electronic circuitry and wiring practices and preferably
be an electronic or electromechanical technician who has experience with electronic and electromechanical
equipment.
Only trained and qualified service personnel (as defined in IEC 60950-1 and AS/NZS60950) should install,
replace, or service the equipment. Install the system in accordance with the U.S. National Electric Code if
you are in the United States.
Conventions
Text Type Indication
GUI elements GUI elements such as tab titles, area names, and field labels appear in this font.
Main titles such as window, dialog box, and wizard titles appear in this font.
TUI elements In a Text-based User Interface, text the system displays appears in this font.
System output Terminal sessions and information that the system displays appear in this
font.
string A nonquoted set of characters. Do not use quotation marks around the string or
the string will include the quotation marks.
!, # An exclamation point (!) or a pound sign (#) at the beginning of a line of code
indicates a comment line.
Note Means reader take note. Notes contain helpful suggestions or references to material not covered in the
document.
Tip Means the following information will help you solve a problem. The tips information might not be
troubleshooting or even an action, but could be useful information, similar to a Timesaver.
Timesaver Means the described action saves time. You can save time by performing the action described in the paragraph.
Caution Means reader be careful. In this situation, you might perform an action that could result in equipment damage
or loss of data.
LEDs
Server LEDs indicate whether the blade server is in active or standby mode, the status of the network link,
the overall health of the blade server, and whether the server is set to give a blinking blue locator light from
the locator button.
The removable drives also have LEDs indicating hard disk access activity and disk health.
Buttons
The Reset button is recessed in the front panel of the server. You can press the button with the tip of a paper
clip or a similar item. Hold the button down for five seconds, and then release it to restart the server if other
methods of restarting do not work.
The locator function for an individual server may get turned on or off by pressing the locator button/LED.
The front-panel power button is disabled by default. It can re-enabled through Cisco UCS Manager. After it's
enabled, The power button allows you to manually take a server temporarily out of service but leave it in a
state where it can be restarted quickly. If the desired power state for a service profile associated with a blade
server is set to "off," using the power button or Cisco UCS Manager to reset the server will cause the desired
power state of the server to become out of sync with the actual power state and the server may unexpectedly
shut down at a later time. To safely reboot a server from a power-down state, use the Boot Server action in
Cisco UCS Manager.
4
2 3
1
192621
1 Connector to blade server 2 DB9 serial connector
local console connection
The SD cards can be uesd to store operating system boot images or other information. Once the server has
been removed from the chassis, you can access the SD card slots by rotating the latch up so that it does not
cover the slots. Remove or insert the SD cards as needed. Either or both slots may be used. Rotate the latch
down to cover the slots before installing the server in the chassis.
Storage Module
The Cisco UCS B200 M4 blade server has an optional storage module that can be configured with SAS or
SATA hard drives or solid state disks (SSDs). Because the UCS B200 M4 can be used without disk drives,
it does not necessarily come with the storage module installed. A blanking panel (UCSB-LSTOR-BK) can
be used to cover an empty drive bay. Order the same number of blanking panels as there are empty drive bays.
For information on installing the storage module, see Installing the FlexStorage Module, on page 17.
Procedure
Step 1 Grasp the front of the blade server and place your other hand under the blade to support it.
Step 2 Open the ejector levers in the front of the blade server.
Step 3 Gently slide the blade into the opening until you cannot push it any farther.
Step 4 Press the ejector so that it catches the edge of the chassis and presses the blade server all the way in.
Step 5 Tighten the captive screw on the front of the blade to no more than 3 in-lbs. Tightening only with bare fingers
is unlikely to lead to stripped or damaged captive screws.
Cisco UCS Manager automatically reacknowledges, reassociates, and recommissions the server, provided
any hardware changes are allowed by the service profile.
Server Configuration
Cisco UCS blade servers should be configured and managed using Cisco UCS Manager. For details, see the
Configuration Guide for the version of Cisco UCS Manager that you are using. The configuration guides are
available at the following URL:
http://www.cisco.com/en/US/products/ps10281/products_installation_and_configuration_guides_list.html
Note The front panel power button is disabled by default to ensure that servers are decommissioned through the
UCS Manager software before shutdown. If you prefer to shut down the server locally with the button, you
can enable front power-button control in UCS Manager.
Tip You can also shut down servers remotely using Cisco UCS Manager. For details, see the Configuration Guide
for the version of Cisco UCS Manager that you are using. The configuration guides are available at the
following URL:
http://www.cisco.com/en/US/products/ps10281/products_installation_and_configuration_guides_list.html
Procedure
Step 1 If you are local to the server, check the color of the Power Status LED for each server in the chassis that you
want to power off.
• Green indicates that the server is running and must be shut down before it can be safely powered off. Go
to Step 2.
• Amber indicates that the server is already in standby mode and can be safely powered off. Go to Step 3.
Step 2 If you previously enabled front power-button control through Cisco UCS Manager, press and release the
Power button, then wait until the Power Status LED changes to amber.
The operating system performs a graceful shutdown and the server goes to standby mode.
Caution To avoid data loss or damage to your operating system, you should always invoke a graceful
shutdown of the operating system.
Step 3 (Optional) If you are shutting down all blade servers in a chassis, disconnect the power cords from the chassis
to completely power off the servers.
Step 4 Remove the appropriate servers from the chassis.
Procedure
Server Troubleshooting
For general troubleshooting information, see the Cisco UCS Manager Troubleshooting Reference Guide.
Replacing a Drive
The Cisco UCS B200 M4 blade server uses an optional Cisco UCS FlexStorage modular storage subsystem
that can provide support for two drive bays and RAID controller, or NVMe-based PCIe SSD support
functionality. If you purchased the UCS B200 M4 blade server without the modular storage system configured
as a part of the system, a pair of blanking panels may be in place. These panels should be removed before
installing hard drives, but should remain in place to ensure proper cooling and ventilation if the drive bays
are unused.
You can remove and install hard drives without removing the blade server from the chassis.
The drives supported in this blade server come with the hot-plug drive sled attached. Empty hot-plug drive
sled carriers (containing no drives) are not sold separately from the drives. A list of currently supported drives
is in the Cisco UCS B200 M4 Blade Server Specification Sheet.
Before upgrading or adding a drive to a running blade server, check in the service profile and make sure the
new hardware configuration will be within the parameters allowed by the service profile.
Note See also 4K Sector Format SAS/SATA Drives Considerations, on page 12.
Procedure
Step 1 Push the button to release the ejector, and then pull the hard drive from its slot.
Step 2 Place the hard drive on an antistatic mat or antistatic foam if you are not immediately reinstalling it in another
server.
Step 3 Install a hard disk drive blank faceplate to keep dust out of the blade server if the slot will remain empty.
Procedure
Step 1 Place the drive ejector into the open position by pushing the release button.
Step 2 Gently slide the drive into the opening in the blade server until it seats into place.
Step 3 Push the drive ejector into the closed position.
You can use Cisco UCS Manager to format and configure RAID services. For details, see the Configuration
Guide for the version of Cisco UCS Manager that you are using. The configuration guides are available at
the following URL:
http://www.cisco.com/en/US/products/ps10281/products_installation_and_configuration_guides_list.html
If you need to move a RAID cluster, see the Cisco UCS Manager Troubleshooting Reference Guide.
Procedure
Step 6 (Optional) After you make changes to the boot order, check the Reboot on Boot Order Change check box
to reboot all servers that use this boot policy.
For boot policies applied to a server with a non-Cisco VIC adapter, even if the Reboot on Boot Order Change
check box is not checked, when SAN devices are added, deleted, or their order is changed, the server always
reboots when boot policy changes are saved.
Step 7 (Optional) If desired, check the Enforce vNIC/vHBA/iSCSI Name check box.
• If checked, Cisco UCS Manager displays a configuration error and reports whether one or more of the
vNICs, vHBAs, or iSCSI vNICs listed in the Boot Order table match the server configuration in the
service profile.
• If not checked, Cisco UCS Manager uses the vNICs or vHBAs (as appropriate for the boot option) from
the service profile.
Step 8 In the Boot Mode field, choose the UEFI radio button.
Step 9 Check the Boot Security check box if you want to enable UEFI boot security.
Step 10 Configure one or more of the following boot options for the boot policy and set their boot order:
• Local Devices boot—To boot from local devices, such as local disks on the server, virtual media, or
remote virtual disks, continue with Configuring a Local Disk Boot for a Boot Policy in the Cisco UCS
Manager Server Management Guide for your release.
• SAN boot—To boot from an operating system image on the SAN, continue with Configuring a SAN
Boot for a Boot Policy in the Cisco UCS Manager Server Management Guide for your release.
You can specify a primary and a secondary SAN boot. If the primary boot fails, the server attempts to boot
from the secondary.
• LAN boot—To boot from a centralized provisioning server, continue with Configuring a LAN Boot For
a Boot Policy in the Cisco UCS Manager Server Management Guide for your release.
• iSCSI boot—To boot from an iSCSI LUN, continue with Creating an iSCSI Boot Policy in the Cisco
UCS Manager Server Management Guide for your release.
Step 1 Press and hold the button down as shown in the figure below.
Step 2 While holding the back end of the cover, pull the cover back and then up.
Air Baffles
The air baffles direct and improve air flow for the server components. Two identical baffles ship with each
B200 M4 server. No tools are necessary to install them, just place them over the DIMMs as shown, with the
holes in the center of the baffles aligned with the corresponding motherboard standoffs.
Figure 5: Cisco UCS B200 M4 Air Baffles
Internal Components
Figure 6: Inside View of the UCS B200 M4 Blade Server
Note When the storage module is installed, the USB connector is underneath it. Use the small cutout opening in
the storage module to visually determine the location of the USB connector when you need to insert it.
Warning There is danger of explosion if the battery is replaced incorrectly. Replace the battery only with the same or
equivalent type recommended by the manufacturer. Dispose of used batteries according to the manufacturer’s
instructions.
Procedure
Procedure
Step 1 Place the FlexStorage module over the two standoff posts on the motherboard at the front of the server.
Step 2 Press down on the drive bay cage where it is labeled "Press Here to Install" until the FlexStorage module
clicks into place.
Figure 7: FlexStorage Module
Step 3 Using a Phillips-head screwdriver, tighten the four screws to secure the FlexStorage module. The locations
of the screws are labeled "Secure Here."
Caution When disconnecting the SuperCap module, disconnect the ribbon cable from the module only. Do not disconnect
the cable from the board. The board connection and the tape that secures the cable must remain connected
and undamaged.
Procedure
Step 1 Grasp the cable connector at the SuperCap module and gently pull to disconnect the cable from the SuperCap
module.
Do not grasp the cable itself, the tape, or the board connector.
Figure 8: Disconnecting the SuperCap Cable from the Module, Not the Board
Step 2 Before removing the SuperCap module, note its orientation in the tray.
When correctly oriented, the connector is on the bottom half of the module and faces the cable. You will need
to install the new SuperCap module with the same orientation.
Step 3 Grasp the sides of the SuperCap module, but not the connector, and lift the SuperCap module out of the tray.
Figure 9: Removing the SuperCap Module
You might feel some resistance because the tray is curved to secure the module.
Procedure
Caution Make sure the SuperCap module is properly oriented before proceeding. If the module is installed
incorrectly, the ribbon cable can get snagged or damaged.
Step 2 When the module is correctly oriented, lower the module and press down until it clips into the tray.
You might feel some resistance while the module passes the curved clips at the top of the tray.
Figure 10: Orienting and Installing the SuperCap Module
Step 3 When the module is seated in the tray, reconnect the cable (2):
a) Grasp the cable connector and verify that the pins and sockets on the cable connector and module connector
are correctly aligned.
b) When the cable connector and module connector are properly aligned, plug the cable into the SuperCap
module.
What to do next
Reinstall the blade server. Go to Installing a Blade Server, on page 7.
Note Cisco UCS Manager Release 2.2(4) introduced a server pack feature that allows Intel E5-2600 v4 CPUs to
run with Cisco UCS Manager Release 2.2(4) or later, provided that the Cisco IMC, BIOS and Capability
Catalog are all running Release 2.2(7) or later.
Caution Ensure that the server is running the required software and firmware before installing the Intel E5-2600 v4
Series CPUs. Failure to do so can result in a non-bootable CPU.
Step 3 Unhook the self-loading socket (SLS) lever that has the unlock icon .
Step 4 Unhook the SLS lever that has the lock icon .
Step 5 Grasp the sides of the CPU carrier (indicated by the arrows in the illustration) and swing it into a standing
position in the SLS plug seat.
Figure 12: CPU Carrier and SLS Plug Seat
Step 6 Pull the CPU carrier up and out of the SLS plug seat.
Procedure
Step 1 Hold the CPU carrier by its sides (indicated by the arrows). Insert and align the two CPU carrier pegs into
the self-loading socket (SLS) plug seat. To ensure proper seating, verify that the horizontal yellow line below
the word ALIGN is straight.
Step 2 Press gently on the top of the CPU carrier from the exterior side until it snaps into place.
Step 3 Close the socket latch.
Step 4 Hook the self-loading socket (SLS) lever that has the lock icon .
Step 5 Hook the SLS lever that has the unlock icon .
Step 6 Thermally bond the CPU and heat sink. Using the syringe of thermal grease provided with the replacement
CPU, apply 2 cubic centimeters of thermal grease to the top of the CPU where it will contact the heat sink.
Apply the grease in the pattern shown in the following figure, which should use approximately half the contents
of the syringe.
Step 7 Replace the heat sink. The yellow CPU heat sink install guide pins that are attached to the motherboard must
align with the cutout on the heat sink to ensure proper installation of the heat sink.
Figure 15: Replacing the Heat Sink
Installing Memory
To install a DIMM into the blade server, follow these steps:
Procedure
Step 1 Press the DIMM into its slot evenly on both ends until it clicks into place.
DIMMs are keyed. If a gentle force is not sufficient, make sure the notch on the DIMM is correctly aligned.
Note Be sure that the notch in the DIMM aligns with the slot. If the notch is misaligned you may damage
the DIMM, the slot, or both.
Step 2 Press the DIMM connector latches inward slightly to seat them fully.
Supported DIMMs
Do not use any memory DIMMs other than those listed in the specification sheet. Doing so may irreparably
damage the server and require down time.
Memory Population
The blade server contains 24 DIMM slots—12 for each CPU. Each set of 12 DIMM slots is arranged into
four channels, where each channel has three DIMMs.
The figure below shows a logical view of the DIMMs and channels.
Figure 17: Logical Representation of DIMMs and Channels
DIMMs can be used in the blade server in a one DIMM per Channel (1DPC) configuration, in a two DIMMs
per Channel (2DPC) configuration, or a three DIMMs per Channel (3DPC) configuration.
The following tables show recommended DIMM population order for non-mirroring and mirroring
configurations. For single-CPU configurations, read only the CPU 1 columns of the tables.
1 A1 E1
2 A1, B1 E1, F1
8 A1, B1, C1, D1, A2, B2, C2, D2 E1, F1, G1, H1, E2, F2, G2, H2
12 A1, B1, C1, D1, A2, B2, C2, D2, E1, F1, G1, H1, E2, F2, G2, H2,
A3, B3, C3, D3 E3, F3, G3, H3
Note System performance is optimized when the DIMM type and quantity are equal for both CPUs, and when each
populated channel is filled equally across the CPUs in the server.
2 A1, B1 E1, F1
8 A1, B1, C1, D1, A2, B2, C2, D2 E1, F1, G1, H1, E2, F2, G2, H2
8 (CPU1) A1, B1, C1, D1, A2, B2, C2, D2 E1, F1, E2, F2
and 4 (CPU2)
Not recommended for performance
reasons.
12 A1, B1, C1, D1, A2, B2, C2, D2, E1, F1, G1, H1, E2, F2, G2, H2,
A3, B3, C3, D3 E3, F3, G3, H3
Memory Performance
When considering the memory configuration of the blade server, there are several things to consider. For
example:
• When mixing DIMMs of different densities (capacities), the highest density DIMM goes in slot 1 then
in descending density.
• Besides DIMM population and choice, the selected CPU(s) can have some effect on performance.
• DIMMs can be run in a 1DPC, a 2DPC, or a 3DPC configuration. 1DPC and 2DPC can provide the
maximum rated speed that the CPU and DIMMs are rated for. 3DPC causes the DIMMs to run at a slower
speed.
To install a Cisco VIC 1340 or VIC 1240 in the blade server, follow these steps:
Procedure
Step 1 Position the VIC board connector above the motherboard connector and align the captive screw to the standoff
post on the motherboard.
Step 2 Firmly press the VIC board connector into the motherboard connector.
Step 3 Tighten the captive screw.
Tip To remove a VIC, reverse the above procedure. You might find it helpful when removing the
connector from the motherboard to gently rock the board along the length of the connector until it
loosens.
Slot 1 is for the VIC 1340 or VIC 1240 mLOM adapter cards. Slot 2 is for the VIC 1380 and VIC 1280 cards,
and can also be used for the VIC port expander, the nVidia M6 GPU, the Intel Crypto accelerator card, and
non-I/O mezzanine cards, such as Fusion ioMemory 3 Series.
Note When the Cisco Nexus 2104XP Fabric Extender (FEX) module is used, the VIC 1280 and the VIC port
expander cards are ignored because there are no traces on the Cisco 2104XP to connect to any VIC or IO card
installed in Slot 2.
The VIC 1340 and VIC 1380 require a Cisco UCS 6200 Series Fabric Interconnect or Cisco UCS 6300 Series
Fabric Interconnect, and they support the Cisco Nexus 2208XP, 2204XP, 2348UPQ FEX modules.
The VIC 1240 and VIC 1280 support Cisco UCS 6200 and 6100 Series Fabric Interconnects, and they support
the Cisco Nexus 2208XP, 2204XP, and 2104XP FEX modules. When a VIC 1240 or 1280 is used with a UCS
6100 Series Fabric Interconnect, the UCS B200 M4 blade server requires a maximum software release of
2.2(x) for Cisco UCS Manager.
If you are switching from one type of adapter card to another, before you physically perform the switch make
sure that you download the latest device drivers and load them into the server’s operating system. For more
information, see the firmware management chapter of one of the Cisco UCS Manager software configuration
guides.
Procedure
Step 1 Position the adapter board connector above the motherboard connector and align the two adapter captive
screws to the standoff posts on the motherboard.
Step 2 Firmly press the adapter connector into the motherboard connector (callout 2).
Step 3 Tighten the two captive screws (callout 3).
Tip Removing an adapter card is the reverse of installing it. You might find it helpful when removing
the connector from the motherboard to gently rock the board along the length of the connector until
it loosens.
3 Custom standoff
Procedure
Step 1 Use the T-shaped wrench that comes with the GPU to remove the existing standoff at the back end of the
motherboard.
Step 2 Install the custom standoff in the same location at the back end of the motherboard.
Step 3 Position the GPU over the connector on the motherboard and align all captive screws to the standoff posts
(callout 1).
Step 4 Tighten the captive screws (callout 2).
Figure 21: Installing the NVIDIA M6 GPU
The following figure shows an NVIDIA M6 GPU installed in a Cisco UCS B200 M4 blade server.
What to do next
After you complete the installation of the NVIDIA M6 GPU, see NVIDIA Licensing Information, on page
37 for information on how to download NVIDIA software and acquire the necessary NVIDIA license. Follow
the instructions to complete these steps in order:
1. Register your product activation keys with NVIDIA.
2. Download the GRID software suite.
3. Install the GRID License Server software to a host.
4. Generate licenses on the NVIDIA Licensing Portal and download them.
5. Manage your GRID licenses.
6. Decide whether to use the GPU in compute mode or graphics mode.
Procedure
If TPM support was disabled for any reason, use the following procedure to enable it.
a) In the Cisco UCS Manager Navigation pane, click the Servers tab.
b) On the Servers tab, expand Servers > Policies.
c) Expand the node for the organization where you want to configure the TPM.
d) Expand BIOS Policies and select the BIOS policy for which you want to configure the TPM.
e) In the Work pane, click the Advanced tab.
f) Click the Trusted Platform sub-tab.
g) To enable TPM support, click Enable or Platform Default.
h) Click Save Changes.
i) Continue with the next step.
Step 3 Enable TXT Support in the BIOS Policy.
Follow the procedures in the Cisco UCS Manager Configuration Guide for the release that is running on the
server.
Weight Base server weight = 9.51 lbs (4.31 kg) (no HDDs,
no CPUs, no DIMMs, no mezzanine adapters or
memory)
Minimally configured server = 11.29 lbs (5.12 kg)
(no HDDs, 1 CPU, 8 DIMMs, VIC 1340/1240 but no
additional mezzanine adapter)
Fully configured server = 15.98 lbs (7.25 kg) (2
HDDs, 2 CPUs, 24 DIMMs, VIC 1340/1240 and
additional mezzanine adapter both populated)
There are three editions of GRID licenses that enable three different classes of GRID features. The GRID
software automatically selects the license edition based on the features that you are using. See the following
table.
GRID Virtual GPU (vGPU) Virtual GPUs for business desktop computing
GRID Virtual Workstation - Extended Virtual GPUs for high-end workstation computing
Workstation graphics on GPU pass-through
Procedure
Step 1 Select the Log In link, or the Register link if you do not already have an account.
The NVIDIA Software Licensing Center > License Key Registration dialog opens.
Step 2 Complete the License Key Registration form and then click Submit My Registration Information.
The NVIDIA Software Licensing Center > Product Information Software Dialog opens.
Step 3 If you have additional PAKs, click Register Additional Keys. For each additional key, complete the form
on the License Key Registration dialog, and then click Submit My Registration Information.
Step 4 Agree to the terms and conditions and set a password when prompted.
Step 1 Return to the NVIDIA Software Licensing Center > Product Information Software dialog box.
Step 2 Click Current Releases.
Step 3 Click the NVIDIA GRID link to access the Product Download dialog. This dialog includes download links
for:
• The NVIDIA License Manager software
• The gpumodeswitch utility
• The host driver software
Installing on Windows
Before you begin
The License Server requires a Java Runtime Environment and an Apache Tomcat installation. Apache Tomcat
is installed when you use the NVIDIA installation wizard for Windows.
Procedure
Step 1 Download and install the latest Java 32-bit Runtime Environment from
https://www.oracle.com/downloads/index.html.
Note Install the 32-bit Java Runtime Environment, regardless of whether your platform is Windows 32-bit
or 64-bit.
Step 6 To verify the installation, open a web browser on the License Server host and connect to the URL
http://localhost:8080/licserver. If the installation was successful, you see the NVIDIA Licenses Client Manager
interface.
Installing on Linux
Before you begin
The License Server requires a Java Runtime Environment and an Apache Tomcat installation. Use the following
commands to install both separately before installing the License Server on Linux.
Procedure
Step 1 Verify that Java was installed with your Linux installation:
java -version
If a Java version does not display, use your Linux package manager to install Java:
Step 2 Use your Linux package manager to install the Tomcat and Tomcat webapp packages.
a) Install Tomcat:
sudo yum install tomcat
b) Enable the Tomcat service for automatic startup on boot:
sudo systemctl enable tomcat.service
c) Start the Tomcat service:
sudo systemctl start tomcat.service
d) To verify that the Tomcat service is operational, open a web browser on the License Server host and
connect to the URL http://localhost:8080. If the installation was successful, you see the Tomcat webapp.
Step 3 Install the License Server.
a) Unpack the License Server tar file:
tar xfz NVIDIA-linux-2015.09-0001.tgz
b) Run the unpacked setup binary as root:
sudo./setup.bin
c) Accept the EULA and then continue with the installation wizard to finish the installation.
Note In the Choose Firewall options dialog, select the ports to be opened in the firewall. NVIDIA
recommends that you use the default setting, which opens port 7070 but leaves port 8080 closed.
Step 4 To verify the installation, open a web browser on the License Server host and connect to the URL
http://localhost:8080/licserver. If the installation was successful, you see the NVIDIA License Client Manager
interface.
Procedure
Procedure
Procedure
Procedure
Step 1 Open the NVIDIA Control Panel using one of the following methods:
• Right-click the Windows desktop and select NVIDIA Control Panel from the menu.
• Open the Windows Control Panel and double-click the NVIDIA Control Panel icon.
Step 2 In the NVIDIA Control Panel left pane under Licensing, select Manage License.
The Manage License task pane opens and shows the current license edition being used. The GRID software
automatically selects the license edition based on the feature that you are using. The default is Tesla
(unlicensed).
Step 3 If you want to acquire a license for GRID Virtual Workstation, under License Edition, select GRID Virtual
Workstation.
Step 4 In the License Server field, enter the address of your local GRID License Server.
The address can be a domain name or an IP address.
Step 5 In the Port Number field, enter your port number or leave it set to the default used by the server, which is
7070.
Step 6 Select Apply.
The system requests the appropriate license edition from your configured License Server. After a license is
successfully acquired, the features of that license edition are enabled.
Note After you configure licensing settings in the NVIDIA Control Panel, the settings persist across
reboots.
Procedure
Step 2 Edit the ServerUrl line with the address of your local GRID License Server.
The address can be a domain name or an IP address. See the Sample Configuration File.
Step 3 Append the port number (default 7070) to the end of the address with a colon. See the Sample Configuration
File.
Step 4 Edit the FeatureType line with an integer for the license type. See the Sample Configuration File.
• GRID vGPU = 1
• GRID Virtual Workstation = 2
Note You must do this procedure before you update the NVIDIA drivers.
Caution Do not remove the hardware that contains the endpoint or perform any maintenance on it until the update
process completes. If the hardware is removed or otherwise unavailable due to maintenance, the firmware
update fails. This failure might corrupt the backup partition. You cannot update the firmware on an endpoint
with a corrupted backup partition.
Procedure
Step 7 (Optional) Monitor the status of the update in the Update Status field.
The update process can take several minutes. Do not activate the firmware until the firmware package you
selected displays in the Backup Version field in the BIOS area of the Inventory tab.
What to do next
Activate the server BIOS firmware.
Step 3 Click the Name of the server for which you want to activate the BIOS firmware.
Step 4 On the Properties page in the Inventory tab, click Motherboard.
Step 5 In the Actions area, click Activate BIOS Firmware.
Step 6 In the Activate Firmware dialog box, do the following:
a) Select the appropriate server BIOS version from the Version To Be Activated drop-down list.
b) If you want to set only the start-up version and not change the version running on the server, check Set
Startup Version Only.
If you configure Set Startup Version Only, the activated firmware moves into the pending-next-reboot
state and the server is not immediately rebooted. The activated firmware does not become the running
version of firmware until the server is rebooted.
c) Click OK.
What to do next
Update the NVIDIA drivers.
Procedure
Step 1 Install your hypervisor software on a computer. Refer to your hypervisor documentation for the installation
instructions.
Step 2 Create a virtual machine in your hypervisor. Refer to your hypervisor documentation for instructions.
Step 3 Install the NVIDIA drivers to the virtual machine. Download the drivers:
• NVIDIA Enterprise Portal for GRID hypervisor downloads (requires NVIDIA login):
https://nvidia.flexnetoperations.com/
• NVIDIA public driver area: http://www.nvidia.com/Download/index.aspx