Quadro Power Guidelines 4

Download as pdf or txt
Download as pdf or txt
You are on page 1of 19

Power Guidelines for Workstation

Products
Application Note

DA-07261-001_v14 | July 2023


Document History
DA-07261-001_v14
Version Date Authors Description of Change
01 June 6, 2014 VL, SM Initial Release
02 June 2, 2015 JK, SM • Updated to include Quadro M6000, Quadro K5200,
Quadro K4200, Quadro K2200, Quadro K1200,
Quadro K620, and Quadro K420
• Updated with Quadro M6000 power guidelines
• Updated PCIe connectors figure (Figure 2)
• Added a power requirements for 250 W cards
(single 8-pin connector) section
• Added a dual 6-pin to 8-pin adapter cable section
03 July 8, 2015 JK, SM Updated error Table 1
04 May 5, 2017 JK, SM Updated to include Quadro GP100, Quadro P6000,
Quadro P5000, Quadro P4000, Quadro P2000, Quadro
P1000, Quadro P600, and Quadro P400
05 March 21, 2018 PV, SM • Updated Figure 1
• Updated Table 1
06 December 12, 2018 JK, SM Updated to include Quadro RTX 4000, Quadro RTX
5000, Quadro RTX 6000, and Quadro RTX 8000
07 January 25, 2019 HG, SM Updated pin numbers in Figure 2
08 October 22, 2020 AS, SM • Added NVIDIA RTX A6000 information to Table 1
• Updated “Power Connectors” section and Figure 2
to reflect CPU 8-Pin connection option
• Updated “Power Adapters” section with CPU 8-Pin
standard cable information
09 July 29, 2021 AS, SM Added NVIDIA RTX A5000, A4000, and A2000
information to Table 1
10 February 1, 2022 AS, SM • Added NVIDIA RTX A5500, RTX A4500 and RTX
A2000-12GB information to Table 1
• Updated application meet to current NVIDIA
standards
11 April 15, 2022 AS, SM Updated power connector diagram in Figure 2
12 October 3, 2022 AS, SM • Added 2 separate notes within “Power
Requirements for 250 W Cards with a Single PCIe
8-Pin Connector” section.
• Added “PCIe CEM 5.0 16-Pin Power Connector”
chapter

Power Guidelines for Workstation Products DA-07261-001_v14 | ii


Version Date Authors Description of Change
13 April 21, 2023 AS, SM Updated both power connectors 2 x PCIe 8-pin to 1 x
CEM5 16-pin and 1 x CPU 8-pin to 1 x CEM5 16-pin
part number (NVPN) and mechanical drawing.
14 July 24, 2023 AS, SM Updated Table 1 to include NVIDIA RTX 6000 Ada
Generation, RTX 5000 Ada Generation, RTX 4000 SFF
Ada Generation, and RTX 4000 Ada Generation
information.

Power Guidelines for Workstation Products DA-07261-001_v14 | iii


Table of Contents
Overview .....................................................................................................................1
Power Requirements .................................................................................................2
Power Connectors ......................................................................................................4
Power Requirements for 250 W Cards with a Single PCIe 8-Pin Connector..............5
Power Adapters ..........................................................................................................6
PCIe 6-Pin Y-Splitter Cable ......................................................................................................... 6
PCIe 8-Pin to 6-Pin Adapter Cable .............................................................................................. 7
PCIe Dual 6-Pin to 8-Pin Adapter Cable ..................................................................................... 7
CPU 8-Pin Standard Power Adapter Cable ................................................................................ 8
PCIe CEM 5.0 16-Pin Power Connector .....................................................................9
CEM5 Sense Pin Power Classes ............................................................................................... 10
Power Adaptors .......................................................................................................................... 10
2 x PCIe 8-pin to 1 x CEM5 16-pin Power Adapter ............................................................... 10
1 x PCIe 8-pin to 1 x CEM5 16-pin Power Adapter ............................................................... 11
1 x CPU 8-pin to 1 x CEM5 16-pin Power Adapter ................................................................ 11
System Power Solution .............................................................................................................. 11
Approved Power Adaptor Vendor List ................................................................................... 13

Power Guidelines for Workstation Products DA-07261-001_v14 | iv


List of Figures
Figure 1. NVIDIA Workstation Graphics Cards ........................................................................... 1
Figure 2. Power Connectors ........................................................................................................ 4
Figure 3. 6-Pin Y-Splitter Cable .................................................................................................. 6
Figure 4. 8-Pin to 6-Pin Adapter Cable ....................................................................................... 7
Figure 5. Dual 6-Pin to 8-Pin Adapter Cable .............................................................................. 7
Figure 6. CPU 8-Pin Standard Adapter Cable ............................................................................ 8
Figure 7. PCIe CEM5 16-Pin Power Connector Header and Plug .............................................9

List of Tables
Table 1. Workstation GPU Power Specifications ...................................................................... 2
Table 2. Power Connectors Pin Description ............................................................................. 4
Table 3. Sense1, Sense0 Power Class Definitions .................................................................. 10
Table 4. NVIDIA 2 x PCIe 8-Pin to 1 x CEM5 16-Pin Adapter Logic........................................ 12
Table 5. CEM5 16-Pin Power Connector ................................................................................. 13

Power Guidelines for Workstation Products DA-07261-001_v14 | v


Overview

This application note discusses the power requirements of the NVIDIA® workstation products
based on NVIDIA RTX™, and Quadro RTX™ line of graphics cards. A suitable power supply is
necessary to maintain system integrity under computational load.

Figure 1. NVIDIA Workstation Graphics Cards

Power Guidelines for Workstation Products DA-07261-001_v14 | 1


Power Requirements

The workstation desktop graphics cards may require auxiliary power within the host chassis.
Ensure that your system can deliver the necessary wattage and auxiliary power connectors for
all cards in the system. If the supplied power is not adequate, the cards will not function
properly. Table 1 specifies the power requirements and power connectors for the various
workstation desktop graphics cards.

Table 1. Workstation GPU Power Specifications


Model TGP Required Auxiliar Power Connectors
NVIDIA RTX 6000 Ada Generation 300 W CEM5 16-pin
NVIDIA RTX 5000 Ada Generation 250 W CEM5 16-pin
NVIDIA RTX 4000 SFF Ada Generation 70 W Not applicable
NVIDIA RTX 4000 Ada Generation 130 W CEM5 16-pin
NVIDIA RTX A6000 300 W CPU 8-pin (EPS-12V)
NVIDIA RTX A5500 230 W PCIe 8-pin
NVIDIA RTX A5000 230 W PCIe 8-pin
NVIDIA RTX A4500 200 W PCIe 8-pin
NVIDIA RTX A4000 140 W PCIe 6-pin
NVIDIA RTX A2000 12GB 70 W Not applicable
NVIDIA RTX A2000 70 W Not applicable
Quadro RTX 8000 260 W PCIe 8-pin + PCIe 6-pin
Quadro RTX 6000 260 W PCIe 8-pin + PCIe 6-pin
Quadro RTX 5000 230 W PCIe 8-pin + PCIe 6-pin
Quadro RTX 4000 125 W PCIe 8-pin
Quadro GV100 250 W
Quadro GP100 235 W
Quadro P6000 250 W PCIe 8-pin
Quadro M6000 24GB 250 W
Quadro M6000 250 W
Quadro K6000 225 W PCIe 6-pin + PCIe 6-pin

Power Guidelines for Workstation Products DA-07261-001_v14 | 2


Power Requirements

Model TGP Required Auxiliar Power Connectors


Quadro P5000 180 W PCIe 8-pin
Quadro M5000 150 W PCIe 6-pin
Quadro K5200 150 W PCIe 6-pin
Quadro K5000 122 W PCIe 6-pin
Quadro P4000 105 W
Quadro M4000 120 W
PCIe 6-pin
Quadro K4200 108 W
Quadro K4000 80 W
Quadro P2000 75 W
Quadro M2000 75 W
Quadro K2200 60 W Not applicable
Quadro K2000 51 W
Quadro K2000D 51 W
Quadro P1000 47 W
Not applicable
Quadro K1200 45 W
Quadro P620 40 W
Quadro P600 40 W Not applicable
Quadro K620 41 W
Quadro P400 30 W
Not applicable
Quadro K420 41 W

The total graphics power (TGP) represents the maximum amount of graphics board power that
the system power supply should be able to provide to the graphics card.

Power Guidelines for Workstation Products DA-07261-001_v14 | 3


Power Connectors

Depending on the workstation graphics card the end customer is utilizing, external power
connectors may be required to fully power up the graphics card. The supported power
connectors on workstation graphics card are CPU 8-pin, PICe 8-pin and PCIe 6-pin.

Figure 2. Power Connectors

Table 2. Power Connectors Pin Description


Pin CPU 8-Pin PCIe 8-Pin PCIe 6-Pin
1 GND (0) 12V 12V
2 GND (0) 12V 12V
3 GND (0) 12V 12V
4 GND (0) SENSE1 GND (0)
5 12V GND (0) SENSE
6 12V SENSE0 GND (0)
7 12V GND (0) Not applicable
8 12V GND (0) Not applicable

Power Guidelines for Workstation Products DA-07261-001_v14 | 4


Power Requirements for 250 W Cards
with a Single PCIe 8-Pin Connector

Typically, the PCIe slot is rated for 75 W and a PCIe 8-pin connector is rated for 150 W.
However, based on NVIDIA testing and surveying of the current ecosystem, it is found that the
PCIe 8-pin connector can carry up to 175 W. Along with the PCIe slot power, a graphics card
consuming up to 250 W can potentially be supported.
Note that if a PCIe 8-pin connector is used to carry up to 175 W to the NVIDIA card, the system
PSU must be able to drive at least 18 A of dedicated current to that PCIe 8-pin connector.
Note also that the auxiliary power input of some NVIDIA cards is specified at the full TGP of the
card. If so then a card TGP of 250 W will require the auxiliary power input to be able to supply
up to the entire 250 W. This power is beyond the capability of a single PCIe 8-pin connector.

Power Guidelines for Workstation Products DA-07261-001_v14 | 5


Power Adapters

It is extremely important to understand the board power requirements when selecting power
supplies. It is recommended to use a power supply that has all the required connectors.
However, if the required connector is not available on a given power supply, it is possible to
use adapters to convert existing connectors to PCIe or CPU auxiliary connectors.
When using power adapters, it is important to evaluate the rated amperage on the 12V rail that
is being used to source the adapter cable. The information is available in the power supply’s
user manual, or it is printed on the power supply casing.

! CAUTION: System builders should review the power specifications and guidelines outlined on
their system power supply to ensure that the connector limits are not exceeded when using
adapters.

PCIe 6-Pin Y-Splitter Cable


It is possible to split a single 6-pin auxiliary PCIe connector into two 6-pin auxiliary PCIe
connectors. While NVIDIA does not recommend using the Y-splitter with the Quadro cards, it is
extremely important to ensure that the 12V rail on the power supply driving this can handle the
additional connector if one must use the splitters.

Figure 3. 6-Pin Y-Splitter Cable

Power Guidelines for Workstation Products DA-07261-001_v14 | 6


Power Adapters

PCIe 8-Pin to 6-Pin Adapter Cable


It is possible to split a single 8-pin auxiliary PCIe connector into a single or two 6-pin auxiliary
PCIe connectors. If you are using such a splitter, it is important to ensure that the 12V rail on
the power supply driving this can handle the additional connector. Refer to the rated amperage
on the 12V rail sourcing the splitter to ensure that the connector limits are not exceeded.

Figure 4. 8-Pin to 6-Pin Adapter Cable

PCIe Dual 6-Pin to 8-Pin Adapter Cable


It is possible to combine two 6-pin auxiliary PCIe connectors into a single 8-pin auxiliary PCIe
connector. If you are using such an adapter, it is important to ensure that the 12V rail on the
power supply driving this adapter is rated for at least 18A.

Figure 5. Dual 6-Pin to 8-Pin Adapter Cable

Power Guidelines for Workstation Products DA-07261-001_v14 | 7


Power Adapters

CPU 8-Pin Standard Power Adapter Cable


For NVIDIA products with a CPU 8-pin connector, a power adapter to convert two PCIe 8-pin
connectors to a single CPU 8-pin may be used.

Figure 6. CPU 8-Pin Standard Adapter Cable

Power Guidelines for Workstation Products DA-07261-001_v14 | 8


PCIe CEM 5.0 16-Pin Power Connector

This chapter contains details on the PCIe CEM5 16-pin power connector that is used on the
next generation NVIDIA ProViz workstation graphics cards. The information in this chapter is
intended for OEM and power supply vendors. This chapter also discusses active power and idle
power recommendations for OEM partners and system builders.
OEMs, and PSU vendors are recommended to use the CEM5 16-pin connector for CDP designs
and partners should refer to this connector as “CEM5 16-pin” in all documents and
communication. The CEM5 16-pin power connector is described as follows. For pinout
information, refer to the PCIe CEM 5.0 Specification.
 Connector has six 12 V power pins and up to six GND (0) pins.
 Sense and Sideband pins are present on this connector.
 The exact connector orientation may depend on the NVIDIA graphics card product.

Figure 7. PCIe CEM5 16-Pin Power Connector Header and Plug

Receptacle
Plug

Power Guidelines for Workstation Products DA-07261-001_v14 | 9


PCIe CEM 5.0 16-Pin Power Connector

The allowed configurations for the ProViz workstation power adapter are as follows:
 2 x PCIe 8-pin to 1 x CEM5 16-pin
 1 x PCIe 8-pin to 1 x CEM5 16-pin
 1 x CPU 8-pin to 1 x CEM5 16-pin

CEM5 Sense Pin Power Classes


The PCIe CEM5 specification defines four power classes that a system may signal to the PCIe
card using Sideband signals Sense1 (Sideband signal S4) and Sense0 (Sideband signal S3). See
Table 3 for those levels.

Table 3. Sense1, Sense0 Power Class Definitions


CEM5 16-Pin Connector Sideband Signal
Indicated Power
Sense1 (S4) Sense0 (S3) Availability (Maximum)
GND (0) GND (0) 600 W
GND (0) OPEN (1) 450 W
OPEN (1) GND (0) 300 W
OPEN (1) OPEN (1) 150 W

Power Adaptors
NVIDIA workstation power adaptor designs are described as follows.

2 x PCIe 8-pin to 1 x CEM5 16-pin Power Adapter


For NVIDIA PCIe card products requiring power input into single CEM5 16-pin connectors, a
power adaptor exists to deliver power up to 300 W from dual PCIe 8-pin connectors to the
single CEM5 16-pin connectors of the NVIDIA card. The dual PCIe 8-pin connector rails are
combined to form a single 12V and single ground rail. This power adaptor makes use of the
CEM5 16-pin connector’s Sense0 and Sense1 pins to signal to the NVIDIA card the power
available to the CEM5 16-pin connectors on the card (Sense1 and Sense0 levels are default-
strapped to [1,0] per Table 3). The Sense1 and Sense0 levels required for a given NVIDIA card
to operate are stated in each card’s product specification.
This adapter also incorporates active circuitry intelligence to ensure both PCIe 8-pin
connectors are sourcing power. With both PCIe 8-pin connectors attached on the adapter’s
power supply end, the adapter’s Sense1 and Sense0 signals indicate that up to 300 W is
available to the CEM5 16-pin connector at the card end (see third row of Table 3). If a single
PCIe 8-pin connector is attached on the adapter’s power supply end, the adapter intelligently
alters the Sense1 and Sense0 signals to indicate less power available on the CEM5 16-pin

Power Guidelines for Workstation Products DA-07261-001_v14 | 10


PCIe CEM 5.0 16-Pin Power Connector

connector (the two sense pins become [1,1] to indicate only 150 W of available power). This
active circuitry intelligence provides a protection mechanism to ensure that the NVIDIA card is
aware of the reduced power availability. If the Sense pin levels indicate insufficient power, the
NVIDIA card will not boot.
The adapter is mechanically compatible only with NVIDIA cards that require power input into
single CEM5 16-pin receptacle connectors.

1 x PCIe 8-pin to 1 x CEM5 16-pin Power Adapter


For NVIDIA products with a single CEM5 16-pin connector, a power adaptor exists to deliver
power up to 150 W from a single PCIe 8-pin connector to the single CEM5 16-pin connector of
the NVIDIA card. This power adaptor does not incorporate active circuitry. The Sense1 and
Sense0 signals are statically configured to indicate to the NVIDIA card that a maximum of 150
W is available to the NVIDIA card (see fourth row of Table 3). If 150 W is insufficient for the
card’s needs, the card will not boot.
The adapter is mechanically compatible only with NVIDIA cards that require power input into
single CEM5 16-pin connectors.

1 x CPU 8-pin to 1 x CEM5 16-pin Power Adapter


For NVIDIA products with a single CEM5 16-pin connector, a power adaptor exists to deliver
power up to 300 W from a single CPU 8-pin connector to the single CEM5 16-pin connector of
the NVIDIA card. This power adaptor does not incorporate active circuitry. The Sense1 and
Sense0 signals are statically configured to indicate to the NVIDIA card that a maximum of 300
W is available to the NVIDIA card (see third row of Table 3). If 300 W is insufficient for the
card’s needs, the card will not boot.
The adapter is mechanically compatible only with NVIDIA cards that require power input into
single CEM5 16-pin connectors.

System Power Solution


A production workstation system power delivery solution would be one of the following:
 Native system cabling that implements sense pin levels as noted in Table 3:
• [Sense1, Sense0] = [1, 0] for 300W-capable power delivery
• [Sense1, Sense0] = [1, 1] for 150W-capable power delivery
 NVIDIA-designed power adapter obtained from a vendor on the Approved Vendor List (see
“Approved Power Adaptor Vendor List“ section of this application note)
 Partner-designed power adapter ensuring proper sense pin levels
When designing a power adapter, care must be taken to ensure sufficient current-handling
ability on the power supply end. PCIe 8-pin connectors are rated to a maximum of 150 W each
Thus, an adapter whose sense pins indicate 300 W of available power would need at least two

Power Guidelines for Workstation Products DA-07261-001_v14 | 11


PCIe CEM 5.0 16-Pin Power Connector

PCIe 8-pin connectors on the power supply end. CPU 8-pin connectors can carry up to 300 W
of power, so an adapter whose sense pins indicate 300 W of available power could use a single
CPU 8-pin connector on the power supply end (However, if the adapter sense pins are
strapped to indicate up to 450 W or 600 W of available power as in rows 1 or 2 of Table 3, then
a single CPU 8-pin connector on the power supply end is insufficient.).
If the power adapter is designed with multiple connectors on the power supply end, there is a
possibility that in operation not all connectors are connected and sourced with power. If this is
the case, for operational and safety reasons the NVIDIA card must be aware that less power is
available on the card end of the adapter. Thus, the adapter should be able to sense whether all
connectors are sourced with power and should reflect the true power availability in its sense
pin settings.
Partners can use a programmable IC such as a CPLD, or alternatively discrete components, to
implement the desired logic for such an intelligent power adaptor design. As an example, the
logic implemented by the NVIDIA 2 x PCIe 8-pin to 1 x CEM5 16-pin adapter is provided in
Table 4 for reference.

Table 4. NVIDIA 2 x PCIe 8-Pin to 1 x CEM5 16-Pin Adapter Logic


PCIe 8-Pin PCIe 8-Pin Resulting Sense Pins of
Receptacle A1 Receptacle B2 16-Pin Power Connector
SENSE1 SENSE0 Indicated Power
Pin 4 (Sense Pin) Pin 4 (Sense Pin) (S4) (S3) Level3
GND (0) GND (0) OPEN (1) GND (0) max 300 W
GND (0) OPEN (1) OPEN (1) OPEN (1) max 150 W
OPEN (1) GND (0) OPEN (1) OPEN (1) max 150 W
OPEN (1) OPEN (1) Not Applicable; no power available on 16-pin
connector
Note:
1“Receptacle A” represents one of the 1 x PCIe 8-pin input connectors. If its Pin 4 is pulled to GND, the
receptacle is determined to be connected to the PSU.
2“Receptacle B” represents one of the 1 x PCIe 8-pin input connectors. If its Pin 4 is pulled to GND, the
receptacle is determined to be connected to the PSU.
3Only the listed power availability levels are supported by this adaptor design.

As Table 4 indicates, the NVIDIA intelligent adapter implements presence detection on each
receptacle connector of the adaptor’s power supply end; it determines connectivity by verifying
a true GND level on sense Pin 4 of the receptacle. If the true GND level is not observed, the
receptacle is considered unconnected.

Power Guidelines for Workstation Products DA-07261-001_v14 | 12


PCIe CEM 5.0 16-Pin Power Connector

Approved Power Adaptor Vendor List


This section provides a list of approved vendors for the NVIDIA CEM5 16-pin power adaptors.
Table 5 lists the components on the approved vendor list.

Note: The mechanical drawings for the components used on the 16-pin power connector and
power plug are in the attached PDF documents.
To access the attached file, click the Attachment icon on the left-hand toolbar on this PDF (using
Adobe Acrobat Reader or Adobe Acrobat). Select the file and use the Tool Bar options (Open,
Save) to retrieve the documents.

The CEM5 16-pin power plug houses two different terminals for power delivery and Sideband
signals respectively. The 3.00 mm pitch terminal is used for power delivery; the 2.00 mm
terminal is used for Sideband signaling. Refer to the PCIe CEM 5.0 Specification for more
information on the two different types of terminals used on the power plug.

Table 5. CEM5 16-Pin Power Connector


Component Vendor Part Number (NVPN)
2 x PCIe 8-pin to 1 x CEM5 16-pin Astron 930-00030-1633-000
1 x PCIe 8-pin to 1 x CEM5 16-pin Astron 930-00030-1569-000
1 x CPU 8-pin to 1 x CEM5 16-pin Astron 930-00030-1636-000

Power Guidelines for Workstation Products DA-07261-001_v14 | 13


Notice
This document is provided for information purposes only and shall not be regarded as a warranty of a certain functionality, condition, or quality of a
product. NVIDIA Corporation (“NVIDIA”) makes no representations or warranties, expressed or implied, as to the accuracy or completeness of the
information contained in this document and assumes no responsibility for any errors contained herein. NVIDIA shall have no liability for the
consequences or use of such information or for any infringement of patents or other rights of third parties that may result from its use. This document
is not a commitment to develop, release, or deliver any Material (defined below), code, or functionality.
NVIDIA reserves the right to make corrections, modifications, enhancements, improvements, and any other changes to this document, at any time
without notice.
Customer should obtain the latest relevant information before placing orders and should verify that such information is current and complete.
NVIDIA products are sold subject to the NVIDIA standard terms and conditions of sale supplied at the time of order acknowledgement, unless otherwise
agreed in an individual sales agreement signed by authorized representatives of NVIDIA and customer (“Terms of Sale”). NVIDIA hereby expressly
objects to applying any customer general terms and conditions with regards to the purchase of the NVIDIA product referenced in this document. No
contractual obligations are formed either directly or indirectly by this document.
NVIDIA products are not designed, authorized, or warranted to be suitable for use in medical, military, aircraft, space, or life support equipment, nor
in applications where failure or malfunction of the NVIDIA product can reasonably be expected to result in personal injury, death, or property or
environmental damage. NVIDIA accepts no liability for inclusion and/or use of NVIDIA products in such equipment or applications and therefore such
inclusion and/or use is at customer’s own risk.
NVIDIA makes no representation or warranty that products based on this document will be suitable for any specified use. Testing of all parameters of
each product is not necessarily performed by NVIDIA. It is customer’s sole responsibility to evaluate and determine the applicability of any information
contained in this document, ensure the product is suitable and fit for the application planned by customer, and perform the necessary testing for the
application in order to avoid a default of the application or the product. Weaknesses in customer’s product designs may affect the quality and reliability
of the NVIDIA product and may result in additional or different conditions and/or requirements beyond those contained in this document. NVIDIA
accepts no liability related to any default, damage, costs, or problem which may be based on or attributable to: (i) the use of the NVIDIA product in any
manner that is contrary to this document or (ii) customer product designs.
No license, either expressed or implied, is granted under any NVIDIA patent right, copyright, or other NVIDIA intellectual property right under this
document. Information published by NVIDIA regarding third-party products or services does not constitute a license from NVIDIA to use such products
or services or a warranty or endorsement thereof. Use of such information may require a license from a third party under the patents or other
intellectual property rights of the third party, or a license from NVIDIA under the patents or other intellectual property rights of NVIDIA.
Reproduction of information in this document is permissible only if approved in advance by NVIDIA in writing, reproduced without alteration and in full
compliance with all applicable export laws and regulations, and accompanied by all associated conditions, limitations, and notices.
THIS DOCUMENT AND 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 NONINFRINGEMENT,
MERCHANTABILITY, AND FITNESS FOR A PARTICULAR PURPOSE. TO THE EXTENT NOT PROHIBITED BY LAW, IN NO EVENT WILL NVIDIA BE LIABLE
FOR ANY DAMAGES, INCLUDING WITHOUT LIMITATION ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, PUNITIVE, OR CONSEQUENTIAL DAMAGES,
HOWEVER CAUSED AND REGARDLESS OF THE THEORY OF LIABILITY, ARISING OUT OF ANY USE OF THIS DOCUMENT, EVEN IF NVIDIA HAS BEEN
ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. Notwithstanding any damages that customer might incur for any reason whatsoever, NVIDIA’s
aggregate and cumulative liability towards customer for the products described herein shall be limited in accordance with the Terms of Sale for the
product.

Trademarks
NVIDIA, the NVIDIA logo, NVIDIA RTX, Quadro, and Quadro RTX are trademarks and/or registered trademarks of NVIDIA Corporation in the U.S. and
other countries. Other company and product names may be trademarks of the respective companies with which they are associated.

Copyright
© 2014 - 2023 NVIDIA Corporation. All rights reserved.

NVIDIA Corporation | 2788 San Tomas Expressway, Santa Clara, CA 95051


http://www.nvidia.com

You might also like