HP Hewlett Packard Hewlett Packard Hp Hp Tesla K20 Graphic Card C7S14A User Manual |
TESLA K20 GPU ACCELERATOR
BD-06455-001_v05 | November 2012
Board Specification
TABLE OF CONTENTS
Configuration .................................................................................... 3
Tesla K20 GPU Accelerator
BD-06455-001_v05 | iii
LIST OF FIGURES
LIST OF TABLES
Tesla K20 GPU Accelerator
BD-06455-001_v05 | iv
OVERVIEW
®
®
The NVIDIA Tesla K20 graphics processing unit (GPU) accelerator is a PCI Express,
dual-slot full height (4.376 inches by 10.5 inches by 1.52 inches) form factor computing
module comprising of a single GK110 GPU. The Tesla K20 is designed for servers and
offers a total of 5 GB of GDDR5 on-board memory and supports PCI Express Gen2.
The Tesla K20 can be configured by the OEM or by the end user to enable or disable
ECC or error correcting codes that can fix single-bit errors and detect double-bit errors.
Enabling ECC will cause some of the memory to be used for the ECC bits, so the user
available memory will decrease by 10%. On the Tesla K20, the register files, cache, and
DRAM are ECC protected.
KEY FEATURES
GPU
Number of processor cores: 2496
Processor core clock: 706 MHz
Package size: 45 mm × 45 mm 2397-pin ball grid array (S-FCBGA)
Board
PCI Express Gen2 ×16 system interface
Physical dimensions: 4.376 inches × 10.5 inches, dual-slot
Display Connectors
None
Tesla K20 GPU Accelerator
BD-06455-001_v05 | 1
Overview
Power Connectors
One 6-pin PCI Express power connector
One 8-pin PCI Express power connector
Memory
Memory clock: 2.6 GHz
Memory bandwidth: 208 GB/sec
Interface: 320-bit
● Total board memory: 5 GB
● 20 pieces of 64M × 16 GDDR5, SDRAM
BIOS
2Mbit Serial ROM
TESLA K20 BLOCK DIAGRAM
Figure 1 is the block diagram for the Tesla K20 GPU dual-slot computing processor
module.
Figure 1.
Tesla K20 Block Diagram
Tesla K20 GPU Accelerator
BD-06455-001_v05 | 2
Overview
CONFIGURATION
The Tesla K20 board is available in the following configuration (Table 1).
Table 1.
Board Configuration
Specifications
Tesla K20
Generic SKU reference
Chip
699-22081-0208-xxxx
GK110
Package size GPU
Processor clock
Memory clock
45 mm × 45 mm 2397-pin S-FCBGA
706 MHz
2.6 GHz
Memory size
5 GB
Memory I/O
320-bit GDDR5
Memory configuration
Display connectors
Power connectors
20 pieces of 64M ×16 GDDR5 SDRAM
None
•8-pin PCI Express power connector
•6-pin PCI Express power connector
Board power
225 W
Idle power
25 W
Thermal cooling solution
Passive heat sink
Tesla K20 GPU Accelerator
BD-06455-001_v05 | 3
MECHANICAL SPECIFICATIONS
PCI EXPRESS SYSTEM
The Tesla K20 board (Figure 2) conforms to the PCI Express full height (4.376 inches by
10.5 inches) form factor.
10.5 inches
4.376 inches
Figure 2.
Tesla K20 GPU Accelerator
Note: The final product will ship with shroud.
Tesla K20 GPU Accelerator
BD-06455-001_v05 | 4
Mechanical Specifications
TESLA K20 BRACKET
As shown in Figure 3, the Tesla K20 includes a vented bracket. If you are an OEM who
qualifies for bracket modifications, you have the option of receiving your module with
no bracket installed.
Figure 3.
Tesla K20 Bracket
Tesla K20 GPU Accelerator
BD-06455-001_v05 | 5
Mechanical Specifications
POWER CONNECTORS
The Tesla K20 GPU accelerator is a performance optimized, high-end product and uses
power from the PCI Express connector as well as external power connectors.
Figure 4 and Figure 5 show the specifications and Table 2 and Table 3 show the pinouts
for the 6-pin and 8-pin PCI Express power connectors.
Figure 4.
6-Pin PCI Express Power Connector
Tesla K20 GPU Accelerator
BD-06455-001_v05 | 6
Mechanical Specifications
Table 2.
6-Pin PCI Express Power Connector Pinout
Pin Number
Description
+12 V
1
2
3
4
5
6
+12 V
+12 V
GND
Sense
GND
Table 3.
8-Pin PCI Express Power Connector Pinout
Pin Number
Description
+12 V
1
2
3
4
5
6
7
8
+12 V
+12 V
Sense1
GND
Sense0
GND
GND
Tesla K20 GPU Accelerator
BD-06455-001_v05 | 8
POWER SPECIFICATIONS
The Tesla K20 GPU accelerator requires power from the PCI Express connector as well
as one or two auxiliary power connectors.
Table 4.
Auxiliary Power Connectors
8-Pin Header
6-Pin Header
Support
Yes
Notes
Connect 8-pin cable
Connect 8-pin cable
Connect 6-pin cable
No cable installed
Yes
8-pin cable must supply
150 W
Connect 6-pin cable
Connect 6-pin cable
No
8-pin connector should
always be connected
Note: Detailed information about power draw by rail will be available to
authorized system partners in the Tesla K20 System Design Guide.
Tesla K20 GPU Accelerator
BD-06455-001_v05 | 9
SUPPORT INFORMATION
CERTIFICATES AND AGENCIES
Agencies
Australian Communications Authority and Radio Spectrum Management Group of
New Zealand (C-Tick)
Bureau of Standards, Metrology, and Inspection (BSMI)
Conformité Européenne (CE)
Federal Communications Commission (FCC)
Industry Canada - Interference-Causing Equipment Standard (ICES)
Korean Communications Commission (KCC)
Underwriters Laboratories (cUL)
Voluntary Control Council for Interference (VCCI)
Tesla K20 GPU Accelerator
BD-06455-001_v05 | 10
Support Information
LANGUAGES
Table 5.
Languages Supported
Windows Server
2008 and Windows
Server 2008 R2
Linux
English (US)
English (UK)
Arabic
X
X
X
X
X
X
X
X
X
X
X
X
X
X
x
X
Chinese, Simplified
Chinese, Traditional
Danish
Dutch
Finnish
French
French (Canada)
German
Italian
Japanese
Korean
Norwegian
Portuguese (Brazil)
Russian
X
X
X
X
X
X
Spanish
Spanish (Latin America)
Swedish
Thai
Note: NVIDIA’s CUDA™ software is only supported in English (U.S.)
Tesla K20 GPU Accelerator
BD-06455-001_v05 | 11
Notice
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.
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 of otherwise under
any patent rights of NVIDIA Corporation. Specifications mentioned in this publication are subject to change
without notice. This publication supersedes and replaces all other information previously supplied. NVIDIA
Corporation products are not authorized as critical components in life support devices or systems without
express written approval of NVIDIA Corporation.
Trademarks
NVIDIA, the NVIDIA logo, CUDA, and Tesla 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
© 2012 NVIDIA Corporation. All rights reserved.
|