Lenovo

Lenovo Press

ThinkSystem and ThinkAgile GPU SummaryReference Information

Author
Updated
24 May 2022
Form Number
LP0768
PDF size
100 pages, 4.1 MB
Full Change History
Rate & Provide Feedback
Download PDF

* Only available in selected markets

Abstract

Lenovo ThinkSystem servers support GPU technology to accelerate different computing workloads, maximize performance for graphic design, virtualization, artificial intelligence and high performance computing applications in Lenovo servers. This document summarizes the features of the GPUs available for supported ThinkSystem servers and ThinkAgile HX, VX and MX systems.

Change History

Changes in the May 24, 2022 update:

  • Additional feature codes for existing NVIDIA GPUs:
    • ThinkSystem NVIDIA A100 80GB PCIe Gen4 Passive GPU w/o CEC, BQZP
    • ThinkSystem NVIDIA A40 48GB PCIe Gen4 Passive GPU w/o CEC, BQZQ
    • ThinkSystem NVIDIA A30 24GB PCIe Gen4 Passive GPU w/o CEC, BQZR
    • ThinkSystem NVIDIA A10 24GB PCIe Gen4 Passive GPU w/o CEC, BQZS

Introduction

Lenovo ThinkSystem servers support GPU technology to accelerate different computing workloads, maximize performance for graphic design, virtualization, artificial intelligence and high performance computing applications in Lenovo servers. This document summarizes the features of the GPUs available for supported ThinkSystem servers and ThinkAgile HX, VX and MX systems.

ThinkSystem NVIDIA A100 PCIe 4.0 Passive GPU
Figure 1. ThinkSystem NVIDIA A100 PCIe 4.0 Passive GPU
 

The following table shows GPUs families and the target workloads

Table 1. GPU families and workloads
Form factor NVIDIA AI and Virtualization AMD AI and Virtualization NVIDIA 3D Graphics
Dual slot HGX A100
A100
Tesla V100S
Tesla V100
A30
A16
Tesla P100
Tesla P40
Tesla M60 (VDI workloads)
Tesla M10 (VDI workloads)		 Instinct MI210
Radeon Pro V340
Instinct MI25		 A40
Quadro RTX 8000
Quadro RTX A6000
Quadro RTX 6000
Quadro P6000
Quadro RTX 5000
Single slot Tesla V100 FHFL
A10
A2
Tesla T4
Tesla P4		   Quadro RTX 4000
Quadro RTX T1000
Quadro RTX T400
Quadro P4000
Quadro P2200
Quadro P2000
Quadro P620
Quadro P600

ThinkSystem server support

The following tables list the ThinkSystem servers that are compatible.

Table 2. ThinkSystem server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
BCSL ThinkSystem NVIDIA HGX A100 40GB 400W 4-GPU Board N N N N N N N N 11 N N N N N N 11 N N N N
BHT3 ThinkSystem NVIDIA HGX A100 80GB 500W 4-GPU Board N N N N N N N N 1 N N N N N N 11 N N N N
4X67A76715 ThinkSystem NVIDIA A100 80GB PCIe Gen4 Passive GPU N N N N N N N 3 8 N 2 N 3 N N N N N 4 N
4X67A13135 ThinkSystem NVIDIA A100 40GB PCIe Gen4 Passive GPU N N N N N N N 3 8 N 2 N 32 N N N N N 4 N
4X67A72593 ThinkSystem NVIDIA A40 48GB PCIe Gen4 Passive GPU N N N N N N N 33 83 N 2 N 3 N N N N N N N
4X67A76727 ThinkSystem NVIDIA A16 64GB Gen4 PCIe Passive GPU N N N N N N N 3 N N N N 3 N N N N N N N
4X67A71311 ThinkSystem NVIDIA A10 24GB PCIe Gen4 Passive GPU N N N N N N N 4 N N N N 3 N N N N N N N
4X67A76581 ThinkSystem NVIDIA A30 24GB PCIe Gen4 Passive GPU N 2 N N N N N 3 8 N 2 N 3 N N N N N 4 N
4X67A81547 ThinkSystem NVIDIA A2 16GB PCIe Gen4 Passive GPU 1 4 N N N 8 3 8 N 3 6 3 8 N N N N 2 8 N
4X67A13124 ThinkSystem NVIDIA Tesla V100S 32GB PCIe Passive GPU N N N N N N N 34 N N 3 N 3 N N N N N 4 N
4X67A12088 ThinkSystem NVIDIA Tesla V100 32GB PCIe Passive GPU N N N N N N N N N N 3 N N N N N N N N N
4C57A09498 ThinkSystem NVIDIA Tesla V100 16GB PCIe Passive GPU N N N N N N N N N N 3 N 3 N N N N N N N
4X67A11524 ThinkSystem NVIDIA Tesla V100 FHHL 16GB GPU PCIe N N N N N N N N N N N N N N N N N N N N
7X67A00068 ThinkSystem NVIDIA Tesla P100 PCIe 16GB N N N N N N N N N N N N N N N N N N N N
7C57A02888 NVIDIA Tesla P40 GPU, PCIe (passive) N N N N N N N N N N N N N N N N N N N N
4X67A14926 ThinkSystem NVIDIA T4 16GB PCIe Passive GPU 1 N N N N 8 3 8 N 3 6 3 8 N N N N 2 8 N
7C57A02892 ThinkSystem NVIDIA Tesla P4 8GB PCIe Passive GPU N N N N N N N N N N N N N N N N N N N N
00KG655 NVIDIA Tesla M60 GPU, PCIe Passive N N N N N N N N N N N N N N N N N N N N
7C57A02891 NVIDIA Tesla M10 GPU, PCIe (passive) N N N N N N N N N N N N N N N N N N N N
4X67A81102 ThinkSystem AMD Instinct MI210 PCIe Gen4 Passive Accelerator N N N N N N N 3 8 N 25 N 35 N N N N N N N
4C57A09497 ThinkSystem AMD Radeon Pro V340 32GB PCIe Passive GPU N N N N N N N N N N N N N N N N N N N N
7C57A02897 ThinkSystem AMD Radeon Instinct MI25 16GB PCIe Passive GPU N N N N N N N N N N N N N N N N N N N N
4C57A16224 ThinkSystem SR670 AMD Radeon Instinct MI25 16Gb PCIe Passive GPU N N N N N N N N N N N N N N N N N N N N
4X67A65441 ThinkSystem NVIDIA Quadro RTX 8000 48GB PCIe Passive GPU N N N N N N N N N N N N 36 N N N N N N N
4X67A71310 ThinkSystem NVIDIA RTX A6000 48GB PCIe Active GPU N N N N N 4 N 3 N N N N N N N N N N N N
4X67A13125 ThinkSystem NVIDIA Quadro RTX 6000 24GB PCIe Passive GPU N N N N N N N 3 N N N N N N N N N N N N
4X67A17267 ThinkSystem NVIDIA Quadro RTX 5000 16GB PCIe Active GPU N N N N N N N N N N N N N N N N N N N N
7C57A02895 ThinkSystem NVIDIA Quadro P6000 PCIe Active GPU N N N N N N N N N N N N N N N N N N N N
4X67A14934 ThinkSystem NVIDIA Quadro RTX 4000 8GB PCIe Active GP N N N N N 8 N N N N N N N N N N N N N N
4X67A79777 ThinkSystem NVIDIA T1000 8GB PCIe Active GPU N N 1 1 1 N N N N N N N N N N N N N N N
4X67A79778 ThinkSystem NVIDIA T400 4GB PCIe Active GPU N N N N 1 N N N N N N N N N N N N N N N
4V17A10255 ThinkSystem NVIDIA Quadro P4000 8GB PCIe Active GPU N N N N N N N N N N N N N N N N N N N N
4X67A14935 ThinkSystem NVIDIA Quadro P2200 5GB PCIe Active GPU N N N N N N 1 N N N N 1 N N N N N N N N
7C57A02877 ThinkSystem NVIDIA Quadro P2000 L1 BOM N N N N N N N N N N N N N N N N N N N N
4X67A11584 ThinkSystem NVIDIA Quadro P620 2GB PCIe Active GPU N N N N N 8 3 8 N 3 6 3 8 N N N N N N N
7C57A02894 ThinkSystem NVIDIA Quadro P600 2GB PCIe Active GPU N N N N N N N N N N N N N N N N N N N N
  1. Contains 4 separate GPUs connected via NVLink bridges
  2. For SR665 systems with AMD EPYC 7003 "Milan" processors, the A100 is supported in either factory orders (CTO) or field upgrades. For SR665 systems with AMD EPYC 7002 "Rome" processors, the A100 is only supported under Special Bid conditions and is not supported as a field upgrade. Requires the refreshed system board.
  3. DisplayPort ports not supported and are disabled
  4. Only available via Lenovo Scalable Infrastructure (LeSI). Select "AI & HPC – LeSI Solutions" in the DCSC configurator. See the LeSI product guide for details.
  5. Supported only with EPYC 7003 "Milan" processors. Not supported with EPYC 7002 "Rome" processors
  6. Special Bid only
Table 3. ThinkSystem server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
BCSL ThinkSystem NVIDIA HGX A100 40GB 400W 4-GPU Board N N N N N N N N N N N N N N N N N N N
BHT3 ThinkSystem NVIDIA HGX A100 80GB 500W 4-GPU Board N N N N N N N N N N N N N N N N N N N
4X67A76715 ThinkSystem NVIDIA A100 80GB PCIe Gen4 Passive GPU N N N N N N N N N N 2 4 N N N N N N N
4X67A13135 ThinkSystem NVIDIA A100 40GB PCIe Gen4 Passive GPU N N N N N N N N N N 2 4 N N N N N N N
4X67A72593 ThinkSystem NVIDIA A40 48GB PCIe Gen4 Passive GPU N N N N N N N N N N N 41, 2 N N N N N N N
4X67A76727 ThinkSystem NVIDIA A16 64GB Gen4 PCIe Passive GPU N N N N N N N N N N 2 N N N N N N N N
4X67A71311 ThinkSystem NVIDIA A10 24GB PCIe Gen4 Passive GPU N N N N N N N N N N 4 N N N N N N N N
4X67A76581 ThinkSystem NVIDIA A30 24GB PCIe Gen4 Passive GPU N N N N N N N N N N 2 N N N N N N N N
4X67A81547 ThinkSystem NVIDIA A2 16GB PCIe Gen4 Passive GPU N N N N N N N N N 2 5 N N N N N N N N
4X67A13124 ThinkSystem NVIDIA Tesla V100S 32GB PCIe Passive GPU N N N N N N N N N N 2 4 N N N N N N N
4X67A12088 ThinkSystem NVIDIA Tesla V100 32GB PCIe Passive GPU N N N N N N N N N N 2 4 2 N N N N N 2
4C57A09498 ThinkSystem NVIDIA Tesla V100 16GB PCIe Passive GPU N N N N N N N N N N 2 4 2 N N N N N 2
4X67A11524 ThinkSystem NVIDIA Tesla V100 FHHL 16GB GPU PCIe N N N N N N N N N N 3 N N N N N N N N
7X67A00068 ThinkSystem NVIDIA Tesla P100 PCIe 16GB N N N N N N N N N N 2 N 2 N N N N N N
7C57A02888 NVIDIA Tesla P40 GPU, PCIe (passive) N N N N N N N N N N 2 4 2 N N N N N N
4X67A14926 ThinkSystem NVIDIA T4 16GB PCIe Passive GPU N N N N N N N N N 2 53 8 N N N N N N N
7C57A02892 ThinkSystem NVIDIA Tesla P4 8GB PCIe Passive GPU N N N N N N N N N 2 53 N N N N N N N N
00KG655 NVIDIA Tesla M60 GPU, PCIe Passive N N N N N N N N N N 2 N 2 N N N N N 2
7C57A02891 NVIDIA Tesla M10 GPU, PCIe (passive) N N N N N N N N N N 2 N 2 N N N N N N
4X67A81102 ThinkSystem AMD Instinct MI210 PCIe Gen4 Passive Accelerator N N N N N N N N N N N N N N N N N N N
4C57A09497 ThinkSystem AMD Radeon Pro V340 32GB PCIe Passive GPU N N N N N N N N N N 2 N 2 N N N N N N
7C57A02897 ThinkSystem AMD Radeon Instinct MI25 16GB PCIe Passive GPU N N N N N N N N N N 2 N 2 N N N N N N
4C57A16224 ThinkSystem SR670 AMD Radeon Instinct MI25 16Gb PCIe Passive GPU N N N N N N N N N N N 4 N N N N N N N
4X67A65441 ThinkSystem NVIDIA Quadro RTX 8000 48GB PCIe Passive GPU N N N N N N N N N N 24 44 N N N N N N N
4X67A71310 ThinkSystem NVIDIA RTX A6000 48GB PCIe Active GPU N N N N N N N N N N 2 N N N N N N N N
4X67A13125 ThinkSystem NVIDIA Quadro RTX 6000 24GB PCIe Passive GPU N N N N N N N N N N N 4 N N N N N N N
4X67A17267 ThinkSystem NVIDIA Quadro RTX 5000 16GB PCIe Active GPU N N N N N N N N N N 2 N N N N N N N N
7C57A02895 ThinkSystem NVIDIA Quadro P6000 PCIe Active GPU N N N N 2 N N N N N 2 N N N N N N N N
4X67A14934 ThinkSystem NVIDIA Quadro RTX 4000 8GB PCIe Active GP N N N N 2 N N N N 1 3 N N N N N N N N
4X67A79777 ThinkSystem NVIDIA T1000 8GB PCIe Active GPU N N N N N N N N N N N N N N N N N N N
4X67A79778 ThinkSystem NVIDIA T400 4GB PCIe Active GPU N N N N N N N N N N N N N N N N N N N
4V17A10255 ThinkSystem NVIDIA Quadro P4000 8GB PCIe Active GPU N N N N 2 N N N N 1 3 N N N N N N N N
4X67A14935 ThinkSystem NVIDIA Quadro P2200 5GB PCIe Active GPU N 1 N N 2 N N N N 1 N N N N N N N N N
7C57A02877 ThinkSystem NVIDIA Quadro P2000 L1 BOM N 1 N N 2 N N N N 1 N N N N N N N N N
4X67A11584 ThinkSystem NVIDIA Quadro P620 2GB PCIe Active GPU 1 1 N 1 2 N N N N 3 3 N N N N N N N N
7C57A02894 ThinkSystem NVIDIA Quadro P600 2GB PCIe Active GPU N N N N 2 N N N N 3 3 N N N N N N N N
  1. Only available via Lenovo Scalable Infrastructure (LeSI). Select "AI & HPC – LeSI Solutions" in the DCSC configurator. See the LeSI product guide for details.
  2. DisplayPort ports not supported and are disabled.
  3. The SR650 has support for 5x T4 or 5x P4 GPUs in servers with second-generation Intel Xeon Scalable processors only. SR650 systems originally with first-generation processors have support for up to 4x T4 or 2x P4 GPUs.
  4. Special Bid only

ThinkAgile HX support

The following tables summarize the ThinkAgile HX appliance and certified node support for the GPUs. The numbers listed in the server columns represent the number of GPUs supported.

Table 4. ThinkAgile HX appliance and certified node GPU support - Purley systems
Part
number		 Description HX Appliances HX Certified Nodes
HX1320 (7X83)
HX1520-R (7X84)
HX3320 (7X83)
HX3375 (7D2U)
HX3520-G (7X84)
HX3720 (7X81)
HX5520 (7X84)
HX5520-C (7X84)
HX7520 (7X84)
HX7820 (7Y95)
HX1021 (7D20)
HX1321 (7Y89)
HX1521-R (7Y90)
HX3321 (7Y89)
HX3376 (7D2U)
HX3521-G (7Y90)
HX3721 (7Y88)
HX5521 (7Y90)
HX5521-C (7Y90)
HX7521 (7Y90)
HX7821 (7Y96)
4X67A13135 NVIDIA A100 N N N N N N N N N N N N N N N N N N N N N
4X67A72593 NVIDIA A40 N N N N N N N N N N N N N N N N N N N N N
4X67A13124 NVIDIA Tesla V100S 32GB N N N N N N N N N N N N N N N N N N N N N
4X67A12088 NVIDIA Tesla V100 32GB N N N N 2* N N N N N N N N N N 2* N N N N N
4C57A09498 NVIDIA Tesla V100 16GB N N N N 2* N N N N N N N N N N 2* N N N N N
4X67A11524 NVIDIA Tesla V100 FHHL N N N N 3* N N N N N N N N N N 3* N N N N N
7X67A00068 NVIDIA Tesla P100 N N N N N N N N N N N N N N N N N N N N N
7C57A02888 NVIDIA Tesla P40 N N N N 2 N N N N N N N N N N 2 N N N N N
4X67A14926 NVIDIA T4 N N N 2 5* N N N N N 1 N N N 2 5* N N N N N
7C57A02892 NVIDIA Tesla P4 N N N N N N N N N N N N N N N N N N N N N
00KG655 NVIDIA Tesla M60 N N N N 2 N N N N N N N N N N 2 N N N N N
7C57A02891 NVIDIA Tesla M10 N N N N 2 N N N N N N N N N N 2 N N N N N
4C57A09497 AMD Radeon Pro V340 N N N N N N N N N N N N N N N N N N N N N
7C57A02897 AMD Radeon Instinct MI25 N N N N N N N N N N N N N N N N N N N N N
4C57A16224 AMD Radeon Instinct MI25 (SR670) N N N N N N N N N N N N N N N N N N N N N
4X67A65441 NVIDIA Quadro RTX 8000 N N N N N N N N N N N N N N N N N N N N N
4X67A71310 NVIDIA Quadro RTX A6000 N N N N N N N N N N N N N N N N N N N N N
4X67A13125 NVIDIA Quadro RTX 6000 N N N N N N N N N N N N N N N N N N N N N
4X67A17267 NVIDIA Quadro RTX 5000 N N N N N N N N N N N N N N N N N N N N N
7C57A02895 NVIDIA Quadro P6000 N N N N N N N N N N N N N N N N N N N N N
4X67A14934 NVIDIA Quadro RTX 4000 N N N N N N N N N N N N N N N N N N N N N
4V17A10255 NVIDIA Quadro P4000 N N N N N N N N N N N N N N N N N N N N N
4X67A14935 NVIDIA Quadro P2200 N N N N N N N N N N N N N N N N N N N N N
7C57A02877 NVIDIA Quadro P2000 N N N N N N N N N N N N N N N N N N N N N
4X67A11584 NVIDIA Quadro P620 N N N N N N N N N N N N N N N N N N N N N

* These GPUs are only supported in HX appliances and certified nodes with second-generation Intel Xeon Scalable processors.

Table 5. ThinkAgile HX appliance and certified node GPU support - Whitley systems
Part number Feature Description Maximum supported
HX1330
HX1331
HX2330
HX2331
HX3330
HX3331
HX5530
HX5531
HX7530
HX7531
4X67A13135 BEL5 ThinkSystem NVIDIA A100 40GB PCIe Gen4 Passive GPU No No No No No No 2 2 2 2
4X67A72593 BEL4 ThinkSystem NVIDIA A40 48GB PCIe Gen4 Passive GPU No No No No No No 2 2 2 2
4X67A71311 BFTZ ThinkSystem NVIDIA A10 24GB PCIe Gen4 Passive GPU No No No No No No 4 4 4 4
4X67A14926 B4YB ThinkSystem NVIDIA T4 16GB PCIe Passive GPU 1 1 2 2 2 2 6 6 7 7
4X67A13125 BB2D ThinkSystem NVIDIA Quadro RTX 6000 24GB PCIe Passive GPU No No No No No No 2 2 2 2

ThinkAgile VX support

The following tables summarize the ThinkAgile VX appliance and certified node support for the GPUs. The numbers listed in the server columns represent the number of GPUs supported.

Table 6. ThinkAgile VX appliance and certified node GPU support - Purley systems
Part
number		 Description VX Appliances Certified
Nodes
VX2320 (7Y93)
VX3320 (7Y93)
VX3520-G (7Y94)
VX3720 (7Y92)
VX5520 (7Y94)
VX7320-N (7Y93)
VX7520 (7Y94)
VX 1U Cert. Node (7Y93)
VX 2U Cert. Node (7Y94)
VX 2U4N Cert. Node (7Y92)
4X67A13135 NVIDIA A100 N N N N N N N N N N
4X67A72593 NVIDIA A40 N N N N N N N N N N
4X67A13124 NVIDIA Tesla V100S 32GB N N N N N N N N N N
4X67A12088 NVIDIA Tesla V100 32GB N N N N N N N N 2 N
4C57A09498 NVIDIA Tesla V100 16GB N N N N N N N N 2 N
4X67A11524 NVIDIA Tesla V100 FHHL N N 3 N N N N N 3 N
7X67A00068 NVIDIA Tesla P100 N N N N N N N N N N
7C57A02888 NVIDIA Tesla P40 N N N N N N N N 2 N
4X67A14926 NVIDIA T4 16GB N N 5* N N N N N 5* N
7C57A02892 NVIDIA Tesla P4 N N N N N N N N N N
00KG655 NVIDIA Tesla M60 N N 2 N N N N N 2 N
7C57A02891 NVIDIA Tesla M10 N N 2 N N N N N 2 N
4C57A09497 AMD Radeon Pro V340 N N 2 N N N N N 2 N
7C57A02897 AMD Radeon Instinct MI25 N N 2 N N N N N 2 N
4C57A16224 AMD Radeon Instinct MI25 (SR670) N N N N N N N N N N
4X67A65441 NVIDIA Quadro RTX 8000 N N N N N N N N N N
4X67A71310 NVIDIA Quadro RTX A6000 N N N N N N N N N N
4X67A13125 NVIDIA Quadro RTX 6000 N N N N N N N N N N
4X67A17267 NVIDIA Quadro RTX 5000 N N N N N N N N N N
7C57A02895 NVIDIA Quadro P6000 N N N N N N N N N N
4X67A14934 NVIDIA Quadro RTX 4000 N N N N N N N N N N
4V17A10255 NVIDIA Quadro P4000 N N 3 N N N N N 3 N
4X67A14935 NVIDIA Quadro P2200 N N N N N N N N N N
7C57A02877 NVIDIA Quadro P2000 N N N N N N N N N N
4X67A11584 NVIDIA Quadro P620 N N 3 N N N N N 3 N

* The VX3520-G and VX 2U Certified Node have support for five T4 GPUs in servers with second-generation Intel Xeon Scalable processors only. Servers originally with first-generation processors have support for up to three T4 GPUs.

Table 7. ThinkAgile VX appliance and certified node GPU support - Whitley systems
Part number Description Maximum supported
VX2330
VX3330
VX3331
VX3530-G
VX5530
VX7330-N
VX7530
VX7531
4X67A13135 ThinkSystem NVIDIA A100 40GB PCIe Gen4 Passive GPU No No No 3 No No No 3
4X67A72593 ThinkSystem NVIDIA A40 48GB PCIe Gen4 Passive GPU No No No 3 No No No 3
4X67A71311 ThinkSystem NVIDIA A10 24GB PCIe Gen4 Passive GPU No No No 4 No No No 4
4X67A14926 ThinkSystem NVIDIA T4 16GB PCIe Passive GPU No No 3 8 No No No 8
4X67A13125 ThinkSystem NVIDIA Quadro RTX 6000 24GB PCIe Passive GPU No No No 3 No No No 3
4X67A14935 ThinkSystem NVIDIA Quadro P2200 5GB PCIe Active GPU No No 1 No No No No No
4X67A11584 ThinkSystem NVIDIA Quadro P620 2GB PCIe Active GPU No No 3 8 No No No 8

ThinkAgile MX support

The following tables summarize the ThinkAgile MX appliance and certified node support for the GPUs. The numbers listed in the server columns represent the number of GPUs supported.

Table 8. ThinkAgile MX appliance and certified node GPU support - Purley systems
Part number Feature Description Maximum supported
MX1020
MX1021
MX3520-F
MX3520-H
MX All Flash
MX Hybrid
4X67A14926 B4YB ThinkSystem NVIDIA T4 16GB PCIe Passive GPU 1 1 5 5 5 5
4X67A65441 BCGR ThinkSystem NVIDIA Quadro RTX 8000 48GB PCIe Passive GPU No No 2 2 No No
4X67A13125 BB2D ThinkSystem NVIDIA Quadro RTX 6000 24GB PCIe Passive GPU No No 2 2 No No
Table 9. ThinkAgile MX appliance and certified node GPU support - Whitley systems
Part number Description Maximum supported
MX3330-F
MX3330-H
MX3331-F
MX3331-H
MX3530-F
MX3530-H
MX3531-F
MX3531-H
4X67A13135 ThinkSystem NVIDIA A100 40GB PCIe Gen4 Passive GPU No No No No 3 3 3 3
4X67A72593 ThinkSystem NVIDIA A40 48GB PCIe Gen4 Passive GPU No No No No 3 3 3 3
4X67A71311 ThinkSystem NVIDIA A10 24GB PCIe Gen4 Passive GPU No No No No 4 4 4 4
4X67A14926 ThinkSystem NVIDIA T4 16GB PCIe Passive GPU 3 3 3 3 8 8 8 8
4X67A13125 ThinkSystem NVIDIA Quadro RTX 6000 24GB PCIe Passive GPU No No No No 3 3 3 3

NVIDIA software

This section lists the NVIDIA software that is available from Lenovo.

NVIDIA vGPU Software (vApps, vPC, RTX vWS, and vCS)

Lenovo offers the following virtualization software for NVIDIA GPUs:

  • Virtual Applications (vApps)

    For organizations deploying Citrix XenApp, VMware Horizon RDSH or other RDSH solutions. Designed to deliver PC Windows applications at full performance. NVIDIA Virtual Applications allows users to access any Windows application at full performance on any device, anywhere. This edition is suited for users who would like to virtualize applications using XenApp or other RDSH solutions. Windows Server hosted RDSH desktops are also supported by vApps.

  • Virtual PC (vPC)

    This product is ideal for users who want a virtual desktop but need great user experience leveraging PC Windows® applications, browsers and high-definition video. NVIDIA Virtual PC delivers a native experience to users in a virtual environment, allowing them to run all their PC applications at full performance.

  • NVIDIA RTX Virtual Workstation (RTX vWS)

    NVIDIA RTX vWS is the only virtual workstation that supports NVIDIA RTX technology, bringing advanced features like ray tracing, AI-denoising, and Deep Learning Super Sampling (DLSS) to a virtual environment. Supporting the latest generation of  www.nvidia.com/en-us/data-center/graphics-cards-for-virtualization/">NVIDIA GPUs unlocks the best performance possible, so designers and engineers can create their best work faster. IT can virtualize any application from the data center with an experience that is indistinguishable from a physical workstation — enabling workstation performance from any device.

  • Virtual Compute Server (vCS)

    NVIDIA Virtual Compute Server (vCS) enables data centers running on Red Hat Enterprise Linux, Red Hat Virtualization, and other supported KVM-based hypervisors to accelerate server virtualization with the latest NVIDIA data center GPUs, including NVIDIA A100 Tensor Core GPU and A30, so that the most compute-intensive workloads, such as artificial intelligence, deep learning, and data science, can be run in a virtual machine (VM) powered by NVIDIA vGPU technology.

The following license types are offered:

  • Perpetual license

    A non-expiring, permanent software license that can be used on a perpetual basis without the need to renew. Each Lenovo part number includes a fixed number of years of Support, Upgrade and Maintenance (SUMS).

  • Annual subscription

    A software license that is active for a fixed period as defined by the terms of the subscription license, typically yearly. The subscription includes Support, Upgrade and Maintenance (SUMS) for the duration of the license term.

  • Concurrent User (CCU)

    A method of counting licenses based on active user VMs. If the VM is active and the NVIDIA GRID vGPU software is running, then this counts as one CCU. A vGPU CCU is independent of the connection to the VM.

The following table lists the ordering part numbers and feature codes.

Table 10. NVIDIA vGPU Software (vApps, vPC, RTX vWS, and vCS)
Part number Feature code Description
NVIDIA vApps
7S020003WW B1MP NVIDIA vApps Perpetual License and SUMS 5Yr, 1 CCU
7S020004WW B1MQ NVIDIA vApps Subscription License 1 Year, 1 CCU
7S020005WW B1MR NVIDIA vApps Subscription License 3 Years, 1 CCU
7S02003DWW S832 NVIDIA vApps Subscription License 4 Years, 1 CCU
7S02003EWW S833 NVIDIA vApps Subscription License 5 Years, 1 CCU
NVIDIA vPC
7S020009WW B1MV NVIDIA vPC Perpetual License and SUMS 5Yr, 1 CCU
7S02000AWW B1MW NVIDIA vPC Subscription License 1 Year, 1 CCU
7S02000BWW B1MX NVIDIA vPC Subscription License 3 Years, 1 CCU
7S02003FWW S834 NVIDIA vPC Subscription License 4 Years, 1 CCU
7S02003GWW S835 NVIDIA vPC Subscription License 5 Years, 1 CCU
NVIDIA RTX vWS
7S02000FWW B1N1 NVIDIA RTX vWS Perpetual License and SUMS 5Yr, 1 CCU
7S02000GWW B1N2 NVIDIA RTX vWS Subscription License 1 Year, 1 CCU
7S02000HWW B1N3 NVIDIA RTX vWS Subscription License 3 Years, 1 CCU
7S02000LWW B1N6 NVIDIA RTX vWS EDU Perpetual License and SUMS 5Yr, 1 CCU
7S02000MWW B1N7 NVIDIA RTX vWS EDU Subscription License 1 Year, 1 CCU
7S02000NWW B1N8 NVIDIA RTX vWS EDU Subscription License 3 Years, 1 CCU
7S02003BWW S830 NVIDIA RTX vWS EDU Subscription License 4 Years, 1 CCU
7S02003CWW S831 NVIDIA RTX vWS EDU Subscription License 5 Years, 1 CCU
7S02000XWW S6YJ NVIDIA RTX vWS Subscription License 4 Years, 1 CCU
7S02000YWW S6YK NVIDIA RTX vWS Subscription License 5 Years, 1 CCU

NVIDIA Omniverse Software (OVE)

Lenovo offers the following NVIDIA Omniverse Software software. 3D workflows are now an essential component of every industry. Efficient design collaboration between teams is crucial. NVIDIA Omniverse™ Enterprise is an end-to-end collaboration and simulation platform that fundamentally transforms complex design workflows, creating a more harmonious environment for creative teams.

  • NVIDIA Omniverse Enterprise Nucleus

    Collaboration service which enables a variety of Omniverse Enterprise-enabled client applications (Apps, Connectors, and others) to share and modify authoritative representations of virtual worlds in USD. Omniverse Nucleus is built for collaboration across multiple users. Omniverse Nucleus is the database and collaboration engine of Omniverse.

    Includes:

    • Collaboration and scalable core microservices deployed on servers and/or workstations.
    • Nucleus Workstation
    • Enterprise Nucleus Server
    • NVIDIA Enterprise Support

    Note: The Omniverse Enterprise Nucleus Subscription is priced and licensed per named user.

  • NVIDIA Omniverse Enterprise Creator

    App for accelerated advanced scene composition and world building. Creator enables scene composition, simulation, and rendering on workstations and virtual workstations.

    Includes:

    • Omniverse Create
    • Omniverse Kit
    • Omniverse Extensions
    • Batch microservices (on up to 64 GPUs)
    • NVIDIA Enterprise Support

    Note: Collaboration via Nucleus requires a Nucleus subscription.

  • NVIDIA Omniverse Enterprise Reviewer

    Simple app designed to visualize projects in stunning, physically accurate photorealism and enable minor editing and comment permissions. Reviewer enables review and approval for workstations and virtual workstations.

    Includes:

    • Omniverse View
    • NVIDIA Enterprise Support

    Note: Editing and commenting via Nucleus requires a Nucleus subscription.

The following license types are offered:

  • Concurrent User (CCU) License

    A method of allocating licenses based on the number of users that are concurrently using the software. As an example, one CCU license allows only one concurrent user to use the software. 

  • Floating User License

    For licensing, same as Concurrent User License.

  • Named User License

    A method of licensing based on the number of named authorized users who may not re-assign or share the license with any other person.

  • Subscription

    A software license that is active for a fixed period as defined by the terms of the subscription. An annual subscription includes SUMS for the duration of the license term.

The following table lists the ordering part numbers and feature codes.

Table 11. NVIDIA Omniverse Software (OVE)
Part number Feature code Description
Omniverse Enterprise Nucleus
7S02002MWW S82A NVIDIA Omniverse Enterprise Nucleus Subscription per Named User, 1 Year
7S02002NWW S82B NVIDIA Omniverse Enterprise Nucleus Subscription per Named User, 3 Years
7S02002PWW S82C NVIDIA Omniverse Enterprise Nucleus Subscription per Named User, 4 Years
7S02002QWW S82D NVIDIA Omniverse Enterprise Nucleus Subscription per Named User, 5 Years
7S02002RWW S82E NVIDIA Omniverse Enterprise Nucleus Subscription per Named User, EDU, 1 Year
7S02002SWW S82F NVIDIA Omniverse Enterprise Nucleus Subscription per Named User, EDU, 3 Years
7S02002TWW S82G NVIDIA Omniverse Enterprise Nucleus Subscription per Named User, EDU, 4 Years
7S02002UWW S82H NVIDIA Omniverse Enterprise Nucleus Subscription per Named User, EDU, 5 Years
Omniverse Enterprise Creator
7S02002VWW S82J NVIDIA Omniverse Enterprise Creator Subscription per CCU, 1 Year
7S02002WWW S82K NVIDIA Omniverse Enterprise Creator Subscription per CCU, 3 Years
7S02002XWW S82L NVIDIA Omniverse Enterprise Creator Subscription per CCU, 4 Years
7S02002YWW S82M NVIDIA Omniverse Enterprise Creator Subscription per CCU, 5 Years
7S02002ZWW S82N NVIDIA Omniverse Enterprise Creator Subscription per CCU, EDU, 1 Year
7S020030WW S82P NVIDIA Omniverse Enterprise Creator Subscription per CCU, EDU, 3 Years
7S020031WW S82Q NVIDIA Omniverse Enterprise Creator Subscription per CCU, EDU, 4 Years
7S020032WW S82R NVIDIA Omniverse Enterprise Creator Subscription per CCU, EDU, 5 Years
Omniverse Enterprise Reviewer
7S020033WW S82S NVIDIA Omniverse Enterprise Reviewer Subscription per CCU, 1 Year
7S020034WW S82T NVIDIA Omniverse Enterprise Reviewer Subscription per CCU, 3 Years
7S020035WW S82U NVIDIA Omniverse Enterprise Reviewer Subscription per CCU, 4 Years
7S020036WW S82V NVIDIA Omniverse Enterprise Reviewer Subscription per CCU, 5 Years
7S020037WW S82W NVIDIA Omniverse Enterprise Reviewer Subscription per CCU, EDU, 1 Year
7S020038WW S82X NVIDIA Omniverse Enterprise Reviewer Subscription per CCU, EDU, 3 Years
7S020039WW S82Y NVIDIA Omniverse Enterprise Reviewer Subscription per CCU, EDU, 4 Years
7S02003AWW S82Z NVIDIA Omniverse Enterprise Reviewer Subscription per CCU, EDU, 5 Years

NVIDIA AI Enterprise Software (NVAIE)

Lenovo offers the NVIDIA AI Enterprise cloud-native enterprise software. NVIDIA AI Enterprise is an end-to-end, cloud-native suite of  AI and data analytics software, optimized, certified, and supported by NVIDIA to run on VMware vSphere and bare-metal  with NVIDIA-Certified  Systems™.  It includes key enabling technologies from NVIDIA for rapid deployment, management, and scaling of AI workloads in the modern hybrid cloud.

NVIDIA AI Enterprise is licensed on a per-CPU Socket basis and can be purchased through the Power of 2 partnership between Lenovo and NVIDIA.

NVIDIA AI Enterprise products can be purchased as either a perpetual license with support services, or as an annual or multi-year subscription.

  • The perpetual license provides the right to use the NVIDIA AI Enterprise software indefinitely, with no expiration. NVIDIA AI Enterprise with perpetual licenses must be purchased in conjunction with one-year, three-year, or five-year support services. A one-year support service is also available for renewals.
  • The subscription offerings are an affordable option to allow IT departments to better manage the flexibility of license volumes. NVIDIA AI Enterprise software products with subscription includes support services for the duration of the software’s subscription license

The features of NVIDIA AI Enterprise Software are listed in the following table.

Table 12. Features of NVIDIA AI Enterprise Software (NVAIE)
Features Supported in NVIDIA AI Enterprise
Per CPU Socket Licensing Yes
Compute Virtualization Supported
Windows Guest OS Support No support
Linux Guest OS Support Supported
Maximum Displays 1
Maximum Resolution 4096 x 2160 (4K)
OpenGL and Vulkan In-situ Graphics only
CUDA and OpenCL Support Supported
ECC and Page Retirement Supported
MIG GPU Support Supported
Multi-vGPU Supported
NVIDIA GPUDirect Supported
Peer-to-Peer over NVLink Supported
GPU Pass Through Support Supported
Baremetal Support Supported
AI and Data Science applications and Frameworks Supported
Cloud Native ready Supported

Note: Maximum 10 concurrent VMs per product license

The following table lists the ordering part numbers and feature codes.

Table 13. NVIDIA AI Enterprise Software (NVAIE)
Part number Feature code Description
AI Enterprise Perpetual License
7S020019WW S6YW NVIDIA AI Enterprise Perpetual License and Support per CPU Socket, 1 Year
7S02001AWW S6YX NVIDIA AI Enterprise Perpetual License and Support per CPU Socket, 3 Years
7S02001BWW S6YY NVIDIA AI Enterprise Perpetual License and Support per CPU Socket, 5 Years
7S02001CWW S6YZ NVIDIA AI Enterprise Perpetual License and Support per CPU Socket, EDU, 1 Year
7S02001DWW S6Z0 NVIDIA AI Enterprise Perpetual License and Support per CPU Socket, EDU, 3 Years
7S02001EWW S6Z1 NVIDIA AI Enterprise Perpetual License and Support per CPU Socket, EDU, 5 Years
AI Enterprise Subscription License
7S02001FWW S6Z2 NVIDIA AI Enterprise Subscription License and Support per CPU Socket, 1 Year
7S02001GWW S6Z3 NVIDIA AI Enterprise Subscription License and Support per CPU Socket, 3 Years
7S02001HWW S6Z4 NVIDIA AI Enterprise Subscription License and Support per CPU Socket, 5 Years
7S02001JWW S6Z5 NVIDIA AI Enterprise Subscription License and Support per CPU Socket, EDU, 1 Year
7S02001KWW S6Z6 NVIDIA AI Enterprise Subscription License and Support per CPU Socket, EDU, 3 Years
7S02001LWW S6Z7 NVIDIA AI Enterprise Subscription License and Support per CPU Socket, EDU, 5 Years

Find more information in the NVIDIA AI Enterprise Sizing Guide.

NVIDIA-Certified Systems

NVIDIA-Certified Systems create the essential platform for the evolution of enterprise data centers, delivering the necessary infrastructure for running a diverse range of accelerated workloads. The certification test suite is designed to exercise the performance and functionality of the configured server by running a set of software that represents a wide range of real-world applications. This includes deep learning training, AI inference, end-to-end AI frameworks including NVIDIA Riva and NVIDIA Clara™, data science including Spark, intelligent video analytics (IVA), high-performance computing (HPC) and CUDA functions, and rendering. It also covers infrastructure performance acceleration such as network and storage offload, security features, and remote management capabilities. The certification covers compute-oriented and general-purpose data center servers as well as edge servers and workstations.  

In addition to supporting hundreds of commercial applications, NVIDIA-Certified Systems enable enterprises to easily deploy software solutions from NVIDIA and partners for AI, Data Analytics, Visualization, and more. They also provide the best foundation for enterprise solutions such as NVIDIA AI Enterprise and NVIDIA Omniverse Enterprise.

The following table lists the Lenovo servers that are NVIDIA-Certified and are NVIDIA AI Enterprise Compatible systems.

Table 14. NVIDIA-Certified Systems
Server NVIDIA
GPU		 GPU
Form Factor		 Processor Type MAX GPU
Per Node		 MAX CPU
Per Node		 Validation Type
SR650 V2 A100 40GB PCIe Gen 4 Intel Ice Lake 3 2 NVIDIA-Certified
SR650 V2 A30 PCIe Gen 4 Intel Ice Lake 3 2 NVIDIA-Certified
SR650 V2 A40 PCIe Gen 4 Intel Ice Lake 3 2 NVIDIA-Certified
SR650 V2 A100 80GB PCIe Gen 4 Intel Ice Lake 3 2 NVIDIA-Certified
SR665 A100 40GB PCIe Gen 4 AMD Rome 3 2 NVIDIA-Certified
SR665 A30 PCIe Gen 4 AMD Rome 3 2 NVIDIA-Certified
SR665 A100 80GB PCIe Gen 4 AMD Rome 3 2 NVIDIA-Certified
SR670 V2 A100 40GB PCIe Gen 4 Intel Ice Lake 8 2 NVIDIA-Certified
SR670 V2 A30 PCIe Gen 4 Intel Ice Lake 8 2 NVIDIA-Certified
SR670 V2 A100 80GB PCIe Gen 4 Intel Ice Lake 8 2 NVIDIA-Certified
ST650 V2 RTX A6000 PCIe Gen 4 Intel Ice Lake 4 2 NVIDIA-Certified

Visit the NVIDIA Certified Systems Catalog for more information.

To learn more, download the Lenovo NVIDIA-Certified datasheet.

 

NVIDIA HGX A100 4-GPU Board

NVIDIA HGX A100 combines NVIDIA A100 Tensor Core GPUs with high-speed interconnects to form the world’s most powerful servers. With A100 80GB GPUs, an HGX A100 4-GPU complex has up to 320 GB of GPU memory and over 2 TB/s of memory bandwidth, delivering unprecedented acceleration. In ThinkSystem servers, HGX A100 is implemented as a single baseboards with four A100 GPUs with all GPUs fully interconnected with NVIDIA NVLink.

NVIDIA HGX A100 4-GPU Board in the water-cooled ThinkSystem SD650-N V2
Figure 2. NVIDIA HGX A100 4-GPU Board in the water-cooled ThinkSystem SD650-N V2 server

Part numbers

Table 15. Ordering information
Feature code Description
BCSL ThinkSystem NVIDIA HGX A100 40GB 400W 4-GPU Board
BHT3 ThinkSystem NVIDIA HGX A100 80GB 500W 4-GPU Board

Technical specifications

The following table lists the specifications of the NVIDIA HGX A100 GPUs.

Table 16. A100 specifications
Feature Specification (per GPU)
GPU Architecture NVIDIA Ampere
NVIDIA Tensor Cores 432 third-generation Tensor Cores
NVIDIA CUDA Cores Not applicable
Double-Precision Performance FP64: 9.7 TFLOPS
FP64 Tensor Core: 19.5 TFLOPS
Single-Precision Performance FP32: 19.5 TFLOPS
Tensor Float 32 (TF32): 156 TFLOPS, 312 TFLOPS*
Half-Precision Performance FP16 Tensor Core: 312 TFLOPS, 624 TFLOPS*
Bfloat16 312 TFLOPS, 624 TFLOPS*
Integer Performance INT8: 624 TOPS, 1,248 TOPS
INT4: 1,248 TOPS, 2,496 TOPS*
GPU Memory 40GB GPU: 40 GB HBM2
80GB GPU: 80 GB HBM2
Memory Bandwidth 40GB GPU: 1,555 GB/sec
80GB GPU: 2,039 GB/sec
ECC Yes
Interconnect Bandwidth 600 GB/sec
System Interface PCIe Gen 4, x16 lanes
Form Factor 4x SXM4 modules
Multi-Instance GPU (MIG) Up to 7 GPU instances
Max Power Consumption 40GB GPU: 400W
80GB GPU: 500W
Thermal Solution Water cooled
Compute APIs CUDA, DirectCompute, OpenCL, OpenACC

* With structural sparsity enabled

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 17. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
BCSL ThinkSystem NVIDIA HGX A100 40GB 400W 4-GPU Board N N N N N N N N 11 N N N N N N 11 N N N N
BHT3 ThinkSystem NVIDIA HGX A100 80GB 500W 4-GPU Board N N N N N N N N 1 N N N N N N 11 N N N N
  1. Contains 4 separate GPUs connected via NVLink bridges
Table 18. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
BCSL ThinkSystem NVIDIA HGX A100 40GB 400W 4-GPU Board N N N N N N N N N N N N N N N N N N N
BHT3 ThinkSystem NVIDIA HGX A100 80GB 500W 4-GPU Board N N N N N N N N N N N N N N N N N N N

Auxiliary power cables

The power cables needed for the HGX A100 are included with the supported servers.

ThinkSystem NVIDIA A100 GPU

The NVIDIA A100 Tensor Core GPU delivers acceleration at every scale for AI, data analytics, and HPC to tackle the world’s toughest computing challenges. As the engine of the NVIDIA data center platform, A100 can efficiently scale up to thousands of GPUs or, using new Multi-Instance GPU (MIG) technology, can be partitioned into seven isolated GPU instances to accelerate workloads of all sizes. A100’s third-generation Tensor Core technology now accelerates more levels of precision for diverse workloads, speeding time to insight as well as time to market.

NVIDIA A100 GPU
Figure 3. ThinkSystem NVIDIA A100 40GB PCIe 4.0 Passive GPU

Part numbers

Table 19. Ordering information
Part number Feature code Description
4X67A13135 BEL5 ThinkSystem NVIDIA A100 40GB PCIe Gen4 Passive GPU
4X67A76715 BLK1 ThinkSystem NVIDIA A100 80GB PCIe Gen4 Passive GPU
CTO only BQZP ThinkSystem NVIDIA A100 80GB PCIe Gen4 Passive GPU w/o CEC

Note: This GPU is available as two feature codes, one with a CEC chip and one without a CEC chip (the one without the CEC chip has "w/o CEC" in the name).The CEC is a secondary Hardware Root of Trust (RoT) module that provides an additional layer of security, which can be used by customers who have high regulatory requirements or high security standards. NVIDIA uses a multi-layered security model and hence the protection offered by the primary Root of Trust embedded in the GPU is expected to be sufficient for most customers. The CEC defeatured products still offer Secure Boot, Secure Firmware Update, Firmware Rollback Protection, and In-Band Firmware Update Disable. Specifically, without the CEC chip, the GPU does not support Key Revocation, Firmware Attestation, and Out-Of-Band Firmware Upgrade. CEC and non-CEC GPUs of the same type of GPU can be mixed in field upgrades.

Technical specifications

The following table lists the specifications of the NVIDIA A100 PCIe GPU.

Table 20. A100 specifications
Feature A100 40GB A100 80GB
GPU Architecture NVIDIA Ampere
NVIDIA Tensor Cores 432 third-generation Tensor Cores per GPU
NVIDIA CUDA Cores (shading units) 6912 FP32 CUDA Cores per GPU
Double-Precision Performance FP64: 9.7 TFLOPS
FP64 Tensor Core: 19.5 TFLOPS
Single-Precision Performance FP32: 19.5 TFLOPS
Tensor Float 32 (TF32): 156 TFLOPS, 312 TFLOPS*
Half-Precision Performance 312 TFLOPS, 624 TFLOPS*
Bfloat16 312 TFLOPS, 624 TFLOPS*
Integer Performance INT8: 624 TOPS, 1,248 TOPS*
INT4: 1,248 TOPS, 2,496 TOPS*
GPU Memory 40 GB HBM2 80 GB HBM2
Memory Bandwidth 1,555 GB/sec 1,935 GB/sec
ECC Yes
Interconnect Bandwidth 32 GB/sec
System Interface PCIe Gen 4, x16 lanes
Form Factor PCIe full height/length, double width
Multi-Instance GPU (MIG) Up to 7 GPU instances, 5GB each Up to 7 GPU instances, 10GB each
Max Power Consumption 250 W 300 W
Thermal Solution Passive
Compute APIs CUDA, DirectCompute, OpenCL, OpenACC

* With structural sparsity enabled

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 21. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
4X67A13135 ThinkSystem NVIDIA A100 40GB PCIe Gen4 Passive GPU N N N N N N N 3 8 N 2 N 31 N N N N N 4 N
4X67A76715 ThinkSystem NVIDIA A100 80GB PCIe Gen4 Passive GPU N N N N N N N 3 8 N 2 N 3 N N N N N 4 N
  1. For SR665 systems with AMD EPYC 7003 "Milan" processors, the A100 is supported in either factory orders (CTO) or field upgrades. For SR665 systems with AMD EPYC 7002 "Rome" processors, the A100 is only supported under Special Bid conditions and is not supported as a field upgrade. Requires the refreshed system board.
Table 22. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
4X67A13135 ThinkSystem NVIDIA A100 40GB PCIe Gen4 Passive GPU N N N N N N N N N N 2 4 N N N N N N N
4X67A76715 ThinkSystem NVIDIA A100 80GB PCIe Gen4 Passive GPU N N N N N N N N N N 2 4 N N N N N N N

Operating system support

The following table lists the supported operating systems:

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 23. Operating system support for ThinkSystem NVIDIA A100 40GB PCIe Gen4 Passive GPU, 4X67A13135
Operating systems
SR650 V2
SR670 V2
SR860 V2
SR655
SR665
SR650 (Gen 2)
SR670 (Gen 2)
SR650 (Gen 1)
SR670 (Gen 1)
Microsoft Windows Server 2016 Y Y Y Y Y 1 Y N Y N
Microsoft Windows Server 2019 Y Y Y Y Y 1 Y N Y N
Microsoft Windows Server 2022 Y Y Y Y Y 1 Y Y Y Y
Red Hat Enterprise Linux 7.7 N N N Y Y 1 Y Y Y Y
Red Hat Enterprise Linux 7.8 N N N Y Y 1 Y Y Y Y
Red Hat Enterprise Linux 7.9 Y Y Y Y Y 1 Y Y Y Y
Red Hat Enterprise Linux 8.0 N N N Y N Y Y Y Y
Red Hat Enterprise Linux 8.1 N N N Y Y 1 Y Y Y Y
Red Hat Enterprise Linux 8.2 Y Y Y Y Y 1 Y Y Y Y
Red Hat Enterprise Linux 8.3 Y Y Y Y Y 1 Y Y Y Y
Red Hat Enterprise Linux 8.4 Y Y Y Y Y 1 Y Y Y Y
Red Hat Enterprise Linux 8.5 Y Y Y Y Y 1 Y Y Y Y
SUSE Linux Enterprise Server 12 SP2 N N N N N N N Y N
SUSE Linux Enterprise Server 15 N N N N N Y N Y N
SUSE Linux Enterprise Server 15 SP1 N N N Y Y 1 Y Y Y Y
SUSE Linux Enterprise Server 15 SP2 Y Y Y Y Y 1 Y Y Y Y
SUSE Linux Enterprise Server 15 SP3 Y Y Y Y Y 1 Y Y Y Y
Ubuntu 18.04.5 LTS Y Y N N N N N N N
VMware vSphere Hypervisor (ESXi) 6.5 N N N N N N N Y N
VMware vSphere Hypervisor (ESXi) 6.5 U1 N N N N N N N Y N
VMware vSphere Hypervisor (ESXi) 6.5 U2 N N N N N Y N Y N
VMware vSphere Hypervisor (ESXi) 6.5 U3 N N N Y N Y N Y N
VMware vSphere Hypervisor (ESXi) 6.7 N N N N N N N Y N
VMware vSphere Hypervisor (ESXi) 6.7 U1 N N N N N Y N Y N
VMware vSphere Hypervisor (ESXi) 6.7 U2 N N N N N Y N Y N
VMware vSphere Hypervisor (ESXi) 6.7 U3 Y Y N Y Y 1 Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 N N N Y Y 1 Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U1 N N Y Y Y 1 Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y Y Y Y 1 Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U3 Y Y Y Y Y 1 Y Y Y Y

1 For SR665 systems with AMD EPYC 7002 "Rome" processors, the A100 is only supported under Special Bid conditions and is not supported as a field upgrade.

Table 24. Operating system support for ThinkSystem NVIDIA A100 80GB PCIe Gen4 Passive GPU, 4X67A76715
Operating systems
SR650 V2
SR670 V2
SR860 V2
SR655
SR665
SR650 (Gen 2)
SR650 (Gen 1)
Microsoft Windows Server 2016 Y Y Y Y Y 1 Y Y
Microsoft Windows Server 2019 Y Y Y Y Y 1 Y Y
Microsoft Windows Server 2022 Y Y Y Y Y 1 Y Y
Red Hat Enterprise Linux 7.7 N N N Y Y 1 Y Y
Red Hat Enterprise Linux 7.8 N N N Y Y 1 Y Y
Red Hat Enterprise Linux 7.9 Y Y Y Y Y 1 Y Y
Red Hat Enterprise Linux 8.0 N N N Y N Y Y
Red Hat Enterprise Linux 8.1 N N N Y Y 1 Y Y
Red Hat Enterprise Linux 8.2 Y Y Y Y Y 1 Y Y
Red Hat Enterprise Linux 8.3 Y Y Y Y Y 1 Y Y
Red Hat Enterprise Linux 8.4 Y Y Y Y Y 1 Y Y
Red Hat Enterprise Linux 8.5 Y Y Y Y Y 1 Y Y
SUSE Linux Enterprise Server 15 SP1 N N N Y Y 1 Y Y
SUSE Linux Enterprise Server 15 SP2 Y Y Y Y Y 1 Y Y
SUSE Linux Enterprise Server 15 SP3 Y Y Y Y Y 1 Y Y
Ubuntu 18.04.5 LTS Y Y N N N N N
VMware vSphere Hypervisor (ESXi) 6.5 N N N N N N Y
VMware vSphere Hypervisor (ESXi) 6.5 U1 N N N N N N Y
VMware vSphere Hypervisor (ESXi) 6.5 U2 N N N N N Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U3 N N N Y N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 N N N N N N Y
VMware vSphere Hypervisor (ESXi) 6.7 U1 N N N N N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U2 N N N N N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U3 Y Y N Y Y 1 Y Y
VMware vSphere Hypervisor (ESXi) 7.0 N N N Y Y 1 Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U1 N N Y Y Y 1 Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y Y Y Y 1 Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U3 Y Y Y Y Y 1 Y Y

1 Not support with EPYC 7002 processors

Auxiliary power cables

The A100 option part number does not ship with auxiliary power cables. For use in the SR670, the needed power cables are ordered with the server as listed in the table below. For the SR650, the needed cable is part of ThinkSystem SR650 GPU Cable Kit, 4XH7A08794.

Table 25. Auxiliary power cables for A100 (click images to show larger versions)
Auxiliary power cables supplied with the SR670 (configure-to-order)

SBB7A10375900mm SR670 Cage 1 power cable
Feature: B3Y3
SBB: SBB7A10375
Base: SC17A10876
FRU: 01PG448

Notes:

  • Feature & SBB also include PCIe data cable
  • Cable also supplies power to the riser

SBB7A103741100mm SR670 Cage 2 power cable
Feature: B3Y2
SBB: SBB7A10374
Base: SC17A10863
FRU: 01PG426

Notes:

  • Feature & SBB also include PCIe data cable
  • Cable also supplies power to the riser
Auxiliary power cables supplied with the SR655 (configure-to-order or field upgrade)

SBB7A14640350mm 8pin (2x4) cable
Server support: SR655 (Riser 1 or Riser 2)
Option: 4X97A59853,  ThinkSystem  SR655 GPU Cable Kit
Feature: B5T5
SBB: SBB7A14640
Base: SC17A50848
FRU: 02JK011

SBB7A10974250mm 8pin (2x4) cable
Server support: SR655 (Riser 3)
Option: 4X97A59853,  ThinkSystem SR655 GPU Cable Kit 
Feature: B5TS
SBB: SBB7A10974
Base: SC17A50844
FRU: 02JK010
Auxiliary power cables needed with the SR650 (configure-to-order or field upgrade)

SBB7A00299300mm 8pin (2x4) cable
Option: 4XH7A08794, ThinkSystem SR650 GPU Cable Kit
Feature: AUSR
SBB: SBB7A00299
Base: SC17A02296
FRU: 01KN066
Auxiliary power cables needed with the SR860 V2 (configure-to-order or field upgrade)

SBB7A17004190mm 8pin (2x4) cable
Option: 4X97A76342, GPU Riser to GPU Power Cable, 190mm
Feature: BAX5
SBB: SBB7A17004
Base: SC17A78231
FRU: 02JJ637
Auxiliary power cables needed with the SR665 (EPYC 7003 "Milan" processors only) or SR650 V2

SBB7A21691360mm 8pin (2x4) cable
Option: 4M17A80478 / 4M17A11759 (SR665) or 4H47A38666 / 4H47A80491 (SR650 V2)*
Feature: BAD8
SBB: SBB7A49792 or SBB7A21691
Base: SC17A59596
FRU: 02YE420

* The option part numbers are for thermal kits and include other components needed to install the GPU. See the SR665 product guide or SR650 V2 product guide for details.

ThinkSystem NVIDIA A40 GPU

The NVIDIA A40 is a powerful data center GPU for visual computing, delivering high performance and capabilities to professionals for graphics-based workloads such as ray traced rendering, high-performance virtual workstations, simulation, 3D design, VR, and virtual production. The A40 GPU is a graphics-based virtualization solution for designers, engineers, scientists, and creatives that need this performance from anywhere in the world.

ThinkSystem NVIDIA A40 48GB PCIe Gen4 Passive GPU
Figure 4. ThinkSystem NVIDIA A40 48GB PCIe Gen4 Passive GPU

Part numbers

Table 26. Ordering information
Part number Feature code Description
4X67A72593 BEL4 ThinkSystem NVIDIA A40 48GB PCIe Gen4 Passive GPU
CTO only BQZQ ThinkSystem NVIDIA A40 48GB PCIe Gen4 Passive GPU w/o CEC

Note: This GPU is available as two feature codes, one with a CEC chip and one without a CEC chip (the one without the CEC chip has "w/o CEC" in the name).The CEC is a secondary Hardware Root of Trust (RoT) module that provides an additional layer of security, which can be used by customers who have high regulatory requirements or high security standards. NVIDIA uses a multi-layered security model and hence the protection offered by the primary Root of Trust embedded in the GPU is expected to be sufficient for most customers. The CEC defeatured products still offer Secure Boot, Secure Firmware Update, Firmware Rollback Protection, and In-Band Firmware Update Disable. Specifically, without the CEC chip, the GPU does not support Key Revocation, Firmware Attestation, and Out-Of-Band Firmware Upgrade. CEC and non-CEC GPUs of the same type of GPU can be mixed in field upgrades.

Technical specifications

The following table lists the specifications of the NVIDIA A40 PCIe GPU.

Table 27. A40 specifications
Feature Specification
GPU Architecture NVIDIA Ampere
NVIDIA CUDA Parallel Processing Cores 10,752
NVIDIA Tensor Cores (3rd gen) 336
NVIDIA RT Cores (2nd Gen) 84
Peak FP32 performance (non-Tensor) 37.4 TFLOPS
Peak FP16 Tensor performance with FP16 Accumulate 149.7 TFLOPS, 299.4 TFLOPS*
Peak Tensor Float 32 (TF32) performance 74.8 TFLOPS, 149.6 TFLOPS*
Peak Bfloat16 (BF16) performance with FP32 Accumulate 149.7 TFLOPS, 299.4 TFLOPS*
Peak Integer Performance INT8: 299.3 TOPS, 598.6 TOPS*
INT4: 598.7 TOPS, 1197.4 TOPS*
RT Core performance 73.1 TFLOPS
GPU Memory 48 GB GDDR6
Memory Bandwidth 696 GB/s
ECC Yes
Interconnect Bandwidth NVIDIA NVLink 112.5 GB/s (bidirectional)
PCIe Gen4 x16 31.5 GB/s (bidirectional)
System Interface PCIe Gen 4, x16 lanes
Form Factor PCIe full height/length, double width (10.5" x 4.4")
Multi-Instance GPU (MIG) No support
Max Power Consumption 300 W
Thermal Solution Passive
vGPU Software Support NVIDIA GRID®, NVIDIA Quadro® Virtual Data Center Workstation, NVIDIA Virtual Compute Server
vGPU Profiles Supported 1 GB, 2 GB, 3 GB, 4 GB, 6 GB, 8 GB, 12 GB, 16 GB, 24 GB, 48 GB
Display connectors 3x DisplayPort 1.4 (disabled and not supported on ThinkSystem servers)
Graphics APIs DirectX 12.07, Shader Model 5.17, OpenGL 4.68, Vulkan 1.18
Compute APIs CUDA, DirectCompute, OpenCL, OpenACC

* With structural sparsity enabled

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 28. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
4X67A72593 ThinkSystem NVIDIA A40 48GB PCIe Gen4 Passive GPU N N N N N N N 31 81 N 2 N 3 N N N N N N N
  1. DisplayPort ports not supported and are disabled
Table 29. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
4X67A72593 ThinkSystem NVIDIA A40 48GB PCIe Gen4 Passive GPU N N N N N N N N N N N 41, 2 N N N N N N N
  1. Only available via Lenovo Scalable Infrastructure (LeSI). Select "AI & HPC – LeSI Solutions" in the DCSC configurator. See the LeSI product guide for details.
  2. DisplayPort ports not supported and are disabled.

Operating system support

The following table lists the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 30. Operating system support for ThinkSystem NVIDIA A40 48GB PCIe 4.0 Passive GPU, 4X67A72593
Operating systems
SR650 V2
SR670 V2
SR655
SR665
SR670 (Gen 2)
SR670 (Gen 1)
Microsoft Windows Server 2016 Y Y Y Y N N
Microsoft Windows Server 2019 Y Y Y Y N N
Microsoft Windows Server 2022 Y Y Y Y Y Y
Red Hat Enterprise Linux 7.7 N N Y Y Y Y
Red Hat Enterprise Linux 7.8 N N Y Y Y Y
Red Hat Enterprise Linux 7.9 Y Y Y Y Y Y
Red Hat Enterprise Linux 8.0 N N Y N Y Y
Red Hat Enterprise Linux 8.1 N N Y Y Y Y
Red Hat Enterprise Linux 8.2 Y Y Y Y Y Y
Red Hat Enterprise Linux 8.3 Y Y Y Y Y Y
Red Hat Enterprise Linux 8.4 Y Y Y Y Y Y
Red Hat Enterprise Linux 8.5 Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP1 N N Y Y Y Y
SUSE Linux Enterprise Server 15 SP2 Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP3 Y Y Y Y Y Y
Ubuntu 18.04.5 LTS Y Y N N N N
VMware vSphere Hypervisor (ESXi) 6.5 U3 N N Y N N N
VMware vSphere Hypervisor (ESXi) 6.7 U3 Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 N N Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U1 N N Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U3 Y Y Y Y Y Y

Auxiliary power cables

The A40 option part number does not ship with auxiliary power cables. For use in the SR670, the needed power cables are ordered with the server as listed in the table below.

Table 31. Auxiliary power cables for A40 (click images to show larger versions)
Auxiliary power cables needed with the SR665 or SR650 V2

SBB7A21691

360mm 8pin (2x4) cable
Option: 4M17A80478 / 4M17A11759 (SR665) or 4H47A38666 / 4H47A80491 (SR650 V2)*
Feature: BAD8
SBB: SBB7A49792 or SBB7A21691
Base: SC17A59596
FRU: 02YE420

* The option part numbers are for thermal kits and include other components needed to install the GPU. See the SR665 product guide or SR650 V2 product guide for details.
Auxiliary power cable needed with the SR670 V2 (configure-to-order or field upgrade)

SBB7A40281215mm 8pin (2x4) cable
Option: 4X97A69627, ThinkSystem SR670 V2 GPU Option Power Cable
Feature: BFNL
SBB: SBB7A40281
Base: SC17A10990
FRU: 02YE945
Auxiliary power cables supplied with the SR670 (configure-to-order)

SBB7A10375900mm SR670 Cage 1 power cable
Feature: B3Y3
SBB: SBB7A10375
Base: SC17A10876
FRU: 01PG448

Notes:

  • Feature & SBB also include PCIe data cable
  • Cable also supplies power to the riser

SBB7A103741100mm SR670 Cage 2 power cable
Feature: B3Y2
SBB: SBB7A10374
Base: SC17A10863
FRU: 01PG426

Notes:

  • Feature & SBB also include PCIe data cable
  • Cable also supplies power to the riser

ThinkSystem NVIDIA A30 GPU

The NVIDIA A30 offers versatile compute acceleration for mainstream enterprise servers. With NVIDIA Ampere architecture Tensor Cores and Multi-Instance GPU (MIG), it delivers speedups securely across diverse workloads, including AI inference at scale and HPC applications. The A30 combines fast memory bandwidth and low-power consumption in a PCIe form factor to enable an elastic data center and delivers maximum value for enterprises.

ThinkSystem NVIDIA A30 24GB PCIe Gen4 Passive GPU
Figure 5. ThinkSystem NVIDIA A30 24GB PCIe Gen4 Passive GPU

Part numbers

Table 32. Ordering information
Part number Feature code Description
4X67A76581 BJHG ThinkSystem NVIDIA A30 24GB PCIe Gen4 Passive GPU
CTO only BQZR ThinkSystem NVIDIA A30 24GB PCIe Gen4 Passive GPU w/o CEC

Note: This GPU is available as two feature codes, one with a CEC chip and one without a CEC chip (the one without the CEC chip has "w/o CEC" in the name).The CEC is a secondary Hardware Root of Trust (RoT) module that provides an additional layer of security, which can be used by customers who have high regulatory requirements or high security standards. NVIDIA uses a multi-layered security model and hence the protection offered by the primary Root of Trust embedded in the GPU is expected to be sufficient for most customers. The CEC defeatured products still offer Secure Boot, Secure Firmware Update, Firmware Rollback Protection, and In-Band Firmware Update Disable. Specifically, without the CEC chip, the GPU does not support Key Revocation, Firmware Attestation, and Out-Of-Band Firmware Upgrade. CEC and non-CEC GPUs of the same type of GPU can be mixed in field upgrades.

Technical specifications

The following table lists the specifications of the NVIDIA A30 PCIe GPU.

Table 33. A30 specifications
Feature Specification
GPU Architecture NVIDIA Ampere
NVIDIA Tensor Cores 224 third-generation Tensor Cores per GPU
NVIDIA CUDA Cores (shading units) 3584 FP32 CUDA Cores per GPU
Double-Precision Performance FP64: 5.2 TFLOPS
FP64 Tensor Core: 10.3 TFLOPS
Single-Precision Performance FP32: 10.3 TFLOPS
Tensor Float 32 (TF32): 82 TFLOPS, 165 TFLOPS*
Half-Precision Performance FP16: 165 TFLOPS, 330 TFLOPS*
Bfloat16 165 TFLOPS, 330 TFLOPS*
Integer Performance INT8: 330 TOPS, 661 TOPS*
INT4: 661 TOPS, 1321 TOPS*
GPU Memory 24 GB HBM2
Memory Bandwidth 933 GB/sec
ECC Yes
Interconnect Bandwidth 64 GB/sec
System Interface PCIe Gen 4, x16 lanes
Form Factor PCIe full height/length, double width
Multi-Instance GPU (MIG) Up to 4 GPU instances
Max Power Consumption 165 W
Thermal Solution Passive
Compute APIs CUDA, DirectCompute, OpenCL, OpenACC

* With structural sparsity enabled

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 34. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
4X67A76581 ThinkSystem NVIDIA A30 24GB PCIe Gen4 Passive GPU N 2 N N N N N 3 8 N 2 N 3 N N N N N 4 N
Table 35. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
4X67A76581 ThinkSystem NVIDIA A30 24GB PCIe Gen4 Passive GPU N N N N N N N N N N 2 N N N N N N N N

Operating system support

The following table lists the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 36. Operating system support for ThinkSystem NVIDIA A30 24GB PCIe Gen4 Passive GPU, 4X67A76581
Operating systems
SE450
SR650 V2
SR670 V2
SR860 V2
SR655
SR665
SR650 (Gen 2)
SR650 (Gen 1)
Microsoft Windows Server 2016 N Y Y Y Y Y Y Y
Microsoft Windows Server 2019 Y Y Y Y Y Y Y Y
Microsoft Windows Server 2022 Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.7 N N N N Y Y Y Y
Red Hat Enterprise Linux 7.8 N N N N Y Y Y Y
Red Hat Enterprise Linux 7.9 Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.0 N N N N Y N Y Y
Red Hat Enterprise Linux 8.1 N N N N Y Y Y Y
Red Hat Enterprise Linux 8.2 N Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.3 N Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.4 N Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.5 Y Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 N N N N N N Y Y
SUSE Linux Enterprise Server 15 SP1 N N N N Y Y Y Y
SUSE Linux Enterprise Server 15 SP2 N Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP3 N Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 N N N N Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U1 N N N Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U2 N Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U3 Y Y Y Y Y Y Y Y

Auxiliary power cables

The A30 option part number does not ship with auxiliary power cables. For supported servers, the needed power cables are listed in the table below.

Table 37. Auxiliary power cables for A30 (click images to show larger versions)
Auxiliary power cable needed with the SR670 V2 (configure-to-order or field upgrade)

SBB7A40281215mm 8pin (2x4) cable
Option: 4X97A69627, ThinkSystem SR670 V2 GPU Option Power Cable
Feature: BFNL
SBB: SBB7A40281
Base: SC17A10990
FRU: 02YE945

ThinkSystem NVIDIA A16 GPU

Take remote work to the next level with NVIDIA A16. Combined with NVIDIA Virtual PC (vPC)  or NVIDIA RTX Virtual Workstation (vWS) software, the A16 enables virtual desktops and workstations with the power and performance to tackle any project from anywhere. Purpose-built for high-density, graphics-rich virtual desktop infrastructure (VDI) and leveraging the NVIDIA Ampere architecture, A16 provides double the user density versus the previous generation, while ensuring the best possible user experience.

ThinkSystem NVIDIA A16 64GB Gen4 PCIe Passive GPU
Figure 6. ThinkSystem NVIDIA A16 64GB Gen4 PCIe Passive GPU

Part numbers

Table 38. Ordering information
Part number Feature code Description
4X67A76727 BNFE ThinkSystem NVIDIA A16 64GB Gen4 PCIe Passive GPU

Technical specifications

The following table lists the specifications of the NVIDIA A16 PCIe GPU.

Table 39. A16 specifications
Feature Specification
GPU Architecture NVIDIA Ampere
NVIDIA third-generation Tensor Cores 160 total Tensor Cores (40 cores per GPU, 4 GPUs)
NVIDIA CUDA Cores (shading units) 5120 total FP32 CUDA Cores (1280 cores per GPU, 4 GPUs)
NVIDIA RT Cores 40 total RT Cores (10 cores per GPU, 4 GPUs)
Double-Precision Performance (FP64) Not applicable
Single-Precision Performance FP32: 4x 4.5 TFLOPS
Tensor Float 32 (TF32): 4x 9 TFLOPS, 4x 18 TFLOPS*
Half-Precision Performance FP16: 4x 17.9 TFLOPS, 4x 35.9 TFLOPS*
Bfloat16 Not applicable
Integer Performance INT8: 4x 35.9 TOPS, 4x 71.8 TOPS*
GPU Memory 64GB GDDR6 (16 GB per GPU, 4 CPUs)
Memory Bandwidth 4x 200 GB/s
ECC Yes
Interconnect Bandwidth Not applicable
System Interface PCIe Gen 4, x16 lanes
Form Factor PCIe full height/length, double width (dual slot)
Multi-Instance GPU (MIG) No support
Max Power Consumption 250 W
Thermal Solution Passive
Graphics APIs DirectX 12.07, Shader Model 5.17, OpenGL 4.68, Vulkan 1.18
Compute APIs CUDA, DirectCompute, OpenCL, OpenACC

* With structural sparsity enabled

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 40. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
4X67A76727 ThinkSystem NVIDIA A16 64GB Gen4 PCIe Passive GPU N N N N N N N 3 N N N N 3 N N N N N N N
Table 41. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
4X67A76727 ThinkSystem NVIDIA A16 64GB Gen4 PCIe Passive GPU N N N N N N N N N N 2 N N N N N N N N

Operating system support

The following table lists the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 42. Operating system support for ThinkSystem NVIDIA A16 64GB Gen4 PCIe Passive GPU, 4X67A76727
Operating systems
SR650 V2
SR665
SR650 (Gen 2)
SR650 (Gen 1)
Microsoft Windows Server 2019 Y Y Y Y
Microsoft Windows Server 2022 Y Y Y Y
Red Hat Enterprise Linux 7.8 N Y Y Y
Red Hat Enterprise Linux 7.9 Y Y Y Y
Red Hat Enterprise Linux 8.0 N N Y Y
Red Hat Enterprise Linux 8.1 N Y Y Y
Red Hat Enterprise Linux 8.2 Y Y Y Y
Red Hat Enterprise Linux 8.3 Y Y Y Y
Red Hat Enterprise Linux 8.4 Y Y Y Y
Red Hat Enterprise Linux 8.5 Y Y Y Y
SUSE Linux Enterprise Server 15 SP1 N Y Y Y
SUSE Linux Enterprise Server 15 SP2 Y Y Y Y
SUSE Linux Enterprise Server 15 SP3 Y Y Y Y
Ubuntu 18.04.5 LTS Y N N N
Ubuntu 20.04 LTS Y N N N
VMware vSphere Hypervisor (ESXi) 6.5 N N N Y
VMware vSphere Hypervisor (ESXi) 6.5 U1 N N N Y
VMware vSphere Hypervisor (ESXi) 6.5 U2 N N Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U3 N N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 N N N Y
VMware vSphere Hypervisor (ESXi) 6.7 U1 N N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U2 N N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U3 Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 N Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U1 N Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U3 Y Y Y Y

Auxiliary power cables

The A16 option part number does not ship with auxiliary power cables. For supported servers, the needed power cables are listed in the table below.

Table 43. Auxiliary power cables (click images to show larger versions)
Auxiliary power cable needed with the SR665 or SR650 V2

SBB7A21691

360mm 8pin (2x4) cable
Option: 4M17A80478 / 4M17A11759 (SR665) or 4H47A38666 / 4H47A80491 (SR650 V2)*
Feature: BAD8
SBB: SBB7A49792 or SBB7A21691
Base: SC17A59596
FRU: 02YE420

* The option part numbers are for thermal kits and include other components needed to install the GPU. See the SR665 product guide or SR650 V2 product guide for details.

ThinkSystem NVIDIA A10 GPU

The NVIDIA A10 Tensor Core GPU, combined with NVIDIA RTX Virtual Workstation (vWS) software, brings mainstream graphics and video with AI services to mainstream enterprise servers, delivering the solutions that designers, engineers, artists, and scientists need to meet today’s challenges. Built on the latest NVIDIA Ampere architecture, the A10 combines second-generation RT Cores, third-generation Tensor Cores, and new streaming microprocessors with 24 GB of GDDR6 memory for versatile graphics, rendering, AI, and compute performance. From virtual workstations, accessible anywhere in the world, to render nodes to the data centers running a variety of workloads, A10 is built to deliver optimal performance in a single-wide, full-height, full-length PCIe form factor.

ThinkSystem NVIDIA A10 24GB PCIe Gen4 Passive GPU
Figure 7. ThinkSystem NVIDIA A10 24GB PCIe Gen4 Passive GPU

Part numbers

Table 44. Ordering information
Part number Feature code Description
4X67A71311 BFTZ ThinkSystem NVIDIA A10 24GB PCIe Gen4 Passive GPU
CTO only BQZS ThinkSystem NVIDIA A10 24GB PCIe Gen4 Passive GPU w/o CEC

Note: This GPU is available as two feature codes, one with a CEC chip and one without a CEC chip (the one without the CEC chip has "w/o CEC" in the name).The CEC is a secondary Hardware Root of Trust (RoT) module that provides an additional layer of security, which can be used by customers who have high regulatory requirements or high security standards. NVIDIA uses a multi-layered security model and hence the protection offered by the primary Root of Trust embedded in the GPU is expected to be sufficient for most customers. The CEC defeatured products still offer Secure Boot, Secure Firmware Update, Firmware Rollback Protection, and In-Band Firmware Update Disable. Specifically, without the CEC chip, the GPU does not support Key Revocation, Firmware Attestation, and Out-Of-Band Firmware Upgrade. CEC and non-CEC GPUs of the same type of GPU can be mixed in field upgrades.

Technical specifications

The following table lists the specifications of the NVIDIA A10 PCIe GPU.

Table 45. A10 specifications
Feature Specification
GPU Architecture NVIDIA Ampere
NVIDIA Tensor Cores Third-generation Tensor Cores
NVIDIA CUDA Cores (shading units) 9216 FP32 CUDA Cores
NVIDIA RT Cores 72 RT Cores
Double-Precision Performance (FP64) Not applicable
Single-Precision Performance FP32: 31.2 TFLOPS
Tensor Float 32 (TF32): 62.5 TFLOPS, 125 TFLOPS*
Half-Precision Performance FP16: 125 TFLOPS, 250 TFLOPS*
Bfloat16 125 TFLOPS, 250 TFLOPS*
Integer Performance INT8: 250 TOPS, 500 TOPS*
INT4: 500 TOPS, 1000 TOPS*
GPU Memory 24 GB GDDR6
Memory Bandwidth 600 GB/sec
ECC Yes
Interconnect Bandwidth Not applicable
System Interface PCIe Gen 4, x16 lanes
Form Factor PCIe full height/length, single width
Multi-Instance GPU (MIG) Not applicable
Max Power Consumption 150 W
Thermal Solution Passive
Compute APIs CUDA, DirectCompute, OpenCL, OpenACC

* With structural sparsity enabled

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 46. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
4X67A71311 ThinkSystem NVIDIA A10 24GB PCIe Gen4 Passive GPU N N N N N N N 4 N N N N 3 N N N N N N N
Table 47. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
4X67A71311 ThinkSystem NVIDIA A10 24GB PCIe Gen4 Passive GPU N N N N N N N N N N 4 N N N N N N N N

Operating system support

The following table lists the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 48. Operating system support for ThinkSystem NVIDIA A10 24GB PCIe Gen4 Passive GPU, 4X67A71311
Operating systems
SR650 V2
SR670 V2
SR665
SR650 (Gen 2)
SR650 (Gen 1)
Microsoft Windows Server 2016 Y Y Y Y Y
Microsoft Windows Server 2019 Y Y Y Y Y
Microsoft Windows Server 2022 Y Y Y Y Y
Red Hat Enterprise Linux 7.7 N N Y Y Y
Red Hat Enterprise Linux 7.8 N N Y Y Y
Red Hat Enterprise Linux 7.9 Y Y Y Y Y
Red Hat Enterprise Linux 8.0 N N N Y Y
Red Hat Enterprise Linux 8.1 N N Y Y Y
Red Hat Enterprise Linux 8.2 Y Y Y Y Y
Red Hat Enterprise Linux 8.3 Y Y Y Y Y
Red Hat Enterprise Linux 8.4 Y Y Y Y Y
Red Hat Enterprise Linux 8.5 Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP1 N N Y Y Y
SUSE Linux Enterprise Server 15 SP2 Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP3 Y Y Y Y Y
Ubuntu 18.04.5 LTS Y Y N N N
VMware vSphere Hypervisor (ESXi) 6.5 N N N N Y
VMware vSphere Hypervisor (ESXi) 6.5 U1 N N N N Y
VMware vSphere Hypervisor (ESXi) 6.5 U2 N N N Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U3 N N N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 N N N N Y
VMware vSphere Hypervisor (ESXi) 6.7 U1 N N N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U2 N N N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U3 Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 N N Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U1 N N Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U3 Y Y Y Y Y

Auxiliary power cables

The A10 option part number does not ship with auxiliary power cables. For supported servers, the needed power cables are listed in the table below.

For the SR650 V2, the auxiliary power cables are included in the ThinkSystem SR650 V2 GPU Full Length Thermal Option Kit v2, 4H47A80491 or ThinkSystem SR650 V2 GPU Full Length Thermal Option Kit, 4H47A38666.

Table 49. Auxiliary power cables for A10 (click images to show larger versions)
Auxiliary power cable needed with the SR650 V2 (configure-to-order or field upgrade)

SBB7A21686460mm 8-pin (2x4) cable
Option: Part of 4H47A80491 or 4H47A38666
Feature: BACW
SBB: SBB7A21686
Base: SC17A60223
FRU: 02YE421

Note: Use this cable only when there is one A10 GPU per riser. For two GPUs per riser, use Y-cable BC09/SBB7A23757.

SBB7A23757460mm Y-cable 8-pin (2x4) to 2x 8-pin (2x4)
Option: Part of 4H47A80491 or 4H47A38666
Feature: BC09
SBB: SBB7A23757
Base: SC17A60224
FRU: 02YE422

Note: Use this Y-cable when there are two A10 GPUs in a riser.

ThinkSystem NVIDIA A2 GPU

The NVIDIA A2 Tensor Core GPU provides entry-level inference with low power, a small footprint, and high performance for NVIDIA AI at the edge. Featuring a low-profile PCIe Gen4 card and a low 40-60W configurable thermal design power (TDP) capability, the A2 brings versatile inference acceleration to any server for deployment at scale.

ThinkSystem NVIDIA A2 16GB PCIe Gen4 Passive GPU
Figure 8. ThinkSystem NVIDIA A2 16GB PCIe Gen4 Passive GPU

Part numbers

Table 50. Ordering information
Part number Feature code Description
4X67A81547 BP05 ThinkSystem NVIDIA A2 16GB PCIe Gen4 Passive GPU

Technical specifications

The following table lists the specifications of the NVIDIA A2 PCIe GPU.

Table 51. A2 specifications
Feature Specification
GPU Architecture NVIDIA Ampere
NVIDIA RT Cores 10 RT Cores
Double-Precision Performance (FP64) Not applicable
Single-Precision Performance (Tensor Float 32, TF32) 9 TFLOPS, 18 TFLOPS*
Half-Precision Performance FP16: 18 TFLOPS, 36 TFLOPS*
Bfloat16 18 TFLOPS, 36 TFLOPS*
Integer Performance INT8: 36 TOPS, 72 TOPS*
INT4: 72 TOPS, 144 TOPS*
GPU Memory 16 GB GDDR6
Memory Bandwidth 200 GB/sec
ECC Yes
Interconnect Bandwidth Not applicable
System Interface PCIe Gen 4, x8 lanes
Form Factor PCIe low profile, single width
Multi-Instance GPU (MIG) Not applicable
Max Power Consumption 40-60 W
Thermal Solution Passive
Compute APIs CUDA, DirectCompute, OpenCL, OpenACC

* With structural sparsity enabled

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 52. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
4X67A81547 ThinkSystem NVIDIA A2 16GB PCIe Gen4 Passive GPU 1 4 N N N 8 3 8 N 3 6 3 8 N N N N 2 8 N
Table 53. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
4X67A81547 ThinkSystem NVIDIA A2 16GB PCIe Gen4 Passive GPU N N N N N N N N N 2 5 N N N N N N N N

Operating system support

The following table lists the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 54. Operating system support for ThinkSystem NVIDIA A2 16GB PCIe Gen4 Passive GPU, 4X67A81547
Operating systems
SE450
SE350
SR630 V2
SR650 V2
SR850 V2
SR860 V2
ST650 V2
SR635
SR645
SR655
SR665
SR630 (Gen 2)
SR650 (Gen 2)
SR630 (Gen 1)
SR650 (Gen 1)
Microsoft Windows Server 2019 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y
Microsoft Windows Server 2022 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.8 N Y N N N N N Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.9 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.0 N N N N N N N Y N Y N Y Y Y Y
Red Hat Enterprise Linux 8.1 N Y N N N N N Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.2 N Y Y Y Y Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.3 N Y Y Y Y Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.4 N Y Y Y Y Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.5 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP1 N Y N N N N N Y Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP2 N Y Y Y Y Y Y Y Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP3 N Y Y Y Y Y Y Y Y Y Y Y Y Y Y
Ubuntu 18.04.5 LTS N N Y Y N N Y N N N N N N N N
Ubuntu 20.04 LTS N N Y Y N N N N N N N N N N N
VMware vSphere Hypervisor (ESXi) 6.5 N N N N N N N N N N N N N Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U1 N N N N N N N N N N N N N Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U2 N Y N N N N N N N N N Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U3 N N N N N N N Y N Y N Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.7 N N N N N N N N N N N N N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U1 N N N N N N N N N N N Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U2 N Y N N N N N N N N N Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U3 N Y Y Y N N Y Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 N Y N N N N N Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U1 N Y N N Y Y N Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U2 N Y Y Y Y Y Y Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U3 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y

Auxiliary power cables

The NVIDIA A2 does not require an auxiliary power cable.

ThinkSystem NVIDIA Tesla V100S GPU

The NVIDIA V100S Tensor Core GPU is a powerful accelerator for deep learning, machine learning, high performance computing (HPC), and graphics. The V100S GPU offers improved performance over the V100, featuring a ~25% increase in memory bandwidth and higher FLOPS.

Introduction

The NVIDIA Tesla V100S GPU Accelerator for PCIe is a dual-slot 10.5 inch PCI Express Gen3 card with a single NVIDIA Volta GV100 graphics processing unit (GPU), 32GB HBM2 memory with native ECC support. It uses a passive heat sink for cooling. The Tesla V100S GPU supports double precision (FP64), single precision (FP32) and half precision (FP16) compute tasks, unified virtual memory and page migration engine.

NVIDIA V100S GPU
Figure 9. ThinkSystem NVIDIA Tesla V100S

Part numbers

Table 55. Ordering information
Part number Feature code Description
4X67A13124 BB2E ThinkSystem NVIDIA Tesla V100S 32GB PCIe Passive GPU

Technical specifications

The following table lists the specifications of the NVIDIA Tesla V100S GPU.

Table 56. V100S specifications
Feature Specification
GPU Architecture NVIDIA Volta
NVIDIA Tensor Cores 640
NVIDIA CUDA Cores 5,120
Double-Precision Performance 8.2 TFLOPS
Single-Precision Performance 16.4 TFLOPS
Tensor Performance 130 TFLOPS
GPU Memory 32 GB HBM2
Memory Bandwidth 1,134 GB/sec
ECC Yes
Interconnect Bandwidth 32 GB/sec
System Interface PCIe Gen3
Form Factor PCIe Full Height/Length
Max Power Consumption 250 W
Thermal Solution Passive
Compute APIs CUDA, DirectCompute, OpenCL, OpenACC

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 57. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
4X67A13124 ThinkSystem NVIDIA Tesla V100S 32GB PCIe Passive GPU N N N N N N N 31 N N 3 N 3 N N N N N 4 N
  1. Only available via Lenovo Scalable Infrastructure (LeSI). Select "AI & HPC – LeSI Solutions" in the DCSC configurator. See the LeSI product guide for details.
Table 58. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
4X67A13124 ThinkSystem NVIDIA Tesla V100S 32GB PCIe Passive GPU N N N N N N N N N N 2 4 N N N N N N N

Operating system support

The following table lists the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 59. Operating system support for ThinkSystem NVIDIA Tesla V100S 32GB PCIe Passive GPU, 4X67A13124
Operating systems
SR650 V2
SR860 V2
SR655
SR665
SR650 (Gen 2)
SR670 (Gen 2)
SR650 (Gen 1)
SR670 (Gen 1)
Microsoft Windows Server 2012 R2 N N N N N N Y N
Microsoft Windows Server 2016 Y Y Y Y Y N Y N
Microsoft Windows Server 2019 Y Y Y Y Y N Y N
Microsoft Windows Server 2022 Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.5 N N N N N Y Y Y
Red Hat Enterprise Linux 7.6 N N Y Y Y Y Y Y
Red Hat Enterprise Linux 7.7 N N Y Y Y Y Y Y
Red Hat Enterprise Linux 7.8 N N Y Y Y Y Y Y
Red Hat Enterprise Linux 7.9 Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.0 N N Y N Y Y Y Y
Red Hat Enterprise Linux 8.1 N N Y Y Y Y Y Y
Red Hat Enterprise Linux 8.2 Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.3 Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.4 Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.5 Y Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 12 SP4 N N Y N Y N Y N
SUSE Linux Enterprise Server 12 SP5 N Y N N N N N N
SUSE Linux Enterprise Server 15 N N N N Y N Y N
SUSE Linux Enterprise Server 15 SP1 N N Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP2 Y Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP3 Y Y Y Y Y Y Y Y
Ubuntu 18.04.5 LTS Y N N N N N N N
VMware vSphere Hypervisor (ESXi) 6.5 N N N N N N Y N
VMware vSphere Hypervisor (ESXi) 6.5 U1 N N N N N N Y N
VMware vSphere Hypervisor (ESXi) 6.5 U2 N N N N Y N Y N
VMware vSphere Hypervisor (ESXi) 6.5 U3 N N Y N Y N Y N
VMware vSphere Hypervisor (ESXi) 6.7 N N N N N N Y N
VMware vSphere Hypervisor (ESXi) 6.7 U1 N N N N Y N Y N
VMware vSphere Hypervisor (ESXi) 6.7 U2 N N N N Y N Y N
VMware vSphere Hypervisor (ESXi) 6.7 U3 Y N Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 N N Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U1 N Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U3 Y Y Y Y Y Y Y Y

Auxiliary power cables

The V100S option part numbers ship with two auxiliary power cables. These cables are needed when the GPU is installed in specific servers, as listed in the following table. The second cable listed, SBB7A16972, is needed when the GPU is installed in the SR670 and is used in conjunction with the Cage 1 and Cage 2 power cables that are included with the SR670.

The table also lists the additional cables needed when the GPU is installed in the SR670 and SR665 servers.

Table 60. Auxiliary power cables for V100S (click images to show larger versions)
Auxiliary power cables included with the GPU option part number

SBB7A00299300mm 8pin (2x4) cable
Server support: SR650†
SBB: SBB7A00299
Base: SC17A02296
FRU: 01KN066

† For customers who buy the GPU directly from NVIDIA, this cable is also included in the ThinkSystem SR650 GPU Cable Kit, 4XH7A08794

SBB7A16972100mm PCIe 6pin (2x3) + PCIe 8pin (2x4):
Server support: SR670
Option: 4Z57A26300*
SBB: SBB7A16972
Base: SC17A10850
FRU: 01PG437

Note: This cable is used in conjunction with either SBB7A10375 or SBB7A10374 listed below.

* This cable is also available as a separate option part number for customers that buy the V100S directly from NVIDIA and wish to use the GPU in the SR670 server.
Auxiliary power cables supplied with the SR655 (configure-to-order or field upgrade)

SBB7A14640350mm 8pin (2x4) cable
Server support: SR655 (Riser 1 or Riser 2)
Option: 4X97A59853,  ThinkSystem  SR655 GPU Cable Kit
Feature: B5T5
SBB: SBB7A14640
Base: SC17A50848
FRU: 02JK011

SBB7A10974250mm 8pin (2x4) cable
Server support: SR655 (Riser 3)
Option: 4X97A59853,  ThinkSystem  SR655 GPU Cable Kit
Feature: B5TS
SBB: SBB7A10974
Base: SC17A50844
FRU: 02JK010
Auxiliary power cables supplied with the SR670 (configure-to-order)

SBB7A10375900mm SR670 Cage 1 power cable
Feature: B3Y3
SBB: SBB7A10375
Base: SC17A10876
FRU: 01PG448

Notes:

  • Feature & SBB also include PCIe data cable
  • Cable also supplies power to the riser

SBB7A103741100mm SR670 Cage 2 power cable
Feature: B3Y2
SBB: SBB7A10374
Base: SC17A10863
FRU: 01PG426

Notes:

  • Feature & SBB also include PCIe data cable
  • Cable also supplies power to the riser
Auxiliary power cables needed with the SR665 or SR650 V2 (configure-to-order or field upgrade)

SBB7A21691360mm 8pin (2x4) cable
Option: 4M17A80478 / 4M17A11759 (SR665) or 4H47A38666 / 4H47A80491 (SR650 V2)*
Feature: BAD8
SBB: SBB7A49792 or SBB7A21691
Base: SC17A59596
FRU: 02YE420

* The option part numbers are for thermal kits and include other components needed to install the GPU. See the SR665 product guide or SR650 V2 product guide for details.
Auxiliary power cables needed with the SR860 V2 (configure-to-order or field upgrade)

SBB7A17004190mm 8pin (2x4) cable
Option: 4X97A76342, GPU Riser to GPU Power Cable, 190mm
Feature: BAX5
SBB: SBB7A17004
Base: SC17A78231
FRU: 02JJ637

 

ThinkSystem NVIDIA Tesla V100 GPU

The NVIDIA V100 Tensor Core GPU is the world’s most powerful accelerator for deep learning, machine learning, high performance computing (HPC), and graphics. Powered by NVIDIA Volta, a single V100 Tensor Core GPU offers the performance of nearly 32 CPUs—enabling researchers to tackle challenges that were once unsolvable. The V100 won MLPerf, the first industry-wide AI benchmark, validating itself as the world’s most powerful, scalable, and versatile computing platform.

Introduction

The NVIDIA Tesla V100 GPU Accelerator for PCIe is a dual-slot 10.5 inch PCI Express Gen3 card with a single NVIDIA Volta GV100 graphics processing unit (GPU), 16GB or 32GB HBM2 memory with native ECC support. It uses a passive heat sink for cooling. The Tesla V100 GPU supports double precision (FP64), single precision (FP32) and half precision (FP16) compute tasks, unified virtual memory and page migration engine.

NVIDIA V100 GPU
Figure 10. ThinkSystem NVIDIA Tesla V100

Part numbers

Table 61. Ordering information
Part number Feature code Description
4X67A12088 B34S ThinkSystem NVIDIA Tesla V100 32GB
4C57A09498 B1JY ThinkSystem NVIDIA Tesla V100 16GB

Technical specifications

The following table lists the specifications of the NVIDIA Tesla V100 GPU.

Table 62. V100 specifications
Feature Specification
GPU Architecture NVIDIA Volta
NVIDIA Tensor Cores 640
NVIDIA CUDA Cores 5,120
Double-Precision Performance 7 TFLOPS
Single-Precision Performance 14 TFLOPS
Tensor Performance 112 TFLOPS
GPU Memory 4X67A12088: 32 GB HBM2
4C57A09498: 16 GB HBM2
Memory Bandwidth 900 GB/sec
ECC Yes
Interconnect Bandwidth 32 GB/sec
System Interface PCIe Gen3
Form Factor PCIe Full Height/Length
Max Power Consumption 250 W
Thermal Solution Passive
Compute APIs CUDA, DirectCompute, OpenCL, OpenACC

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 63. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
4X67A12088 ThinkSystem NVIDIA Tesla V100 32GB PCIe Passive GPU N N N N N N N N N N 3 N N N N N N N N N
4C57A09498 ThinkSystem NVIDIA Tesla V100 16GB PCIe Passive GPU N N N N N N N N N N 3 N 3 N N N N N N N
Table 64. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
4X67A12088 ThinkSystem NVIDIA Tesla V100 32GB PCIe Passive GPU N N N N N N N N N N 2 4 2 N N N N N 2
4C57A09498 ThinkSystem NVIDIA Tesla V100 16GB PCIe Passive GPU N N N N N N N N N N 2 4 2 N N N N N 2

Operating system support

The following tables list the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 65. Operating system support for ThinkSystem NVIDIA Tesla V100 32GB PCIe Passive GPU, 4X67A12088
Operating systems
SR655
SD530 (Gen 2)
SR650 (Gen 2)
SR670 (Gen 2)
SR860 (Gen 2)
SD530 (Gen 1)
SR650 (Gen 1)
SR670 (Gen 1)
SR860 (Gen 1)
Microsoft Windows Server 2012 R2 N N N N N Y Y N Y
Microsoft Windows Server 2016 Y Y Y N Y Y Y N Y
Microsoft Windows Server 2019 Y Y Y N Y Y Y N Y
Microsoft Windows Server 2022 Y Y Y Y Y Y Y Y Y
Microsoft Windows Server version 1803 N N N N N N Y N N
Red Hat Enterprise Linux 6.10 N N N N N Y Y N Y
Red Hat Enterprise Linux 6.9 N N N N N Y Y N Y
Red Hat Enterprise Linux 7.3 N N N N N Y Y N N
Red Hat Enterprise Linux 7.4 N N N N N Y Y N Y
Red Hat Enterprise Linux 7.5 N N N Y N Y Y Y Y
Red Hat Enterprise Linux 7.6 Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.7 Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.8 Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.9 Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.0 Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.1 Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.2 Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.3 Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.4 Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.5 Y Y Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 11 SP4 N N N N N Y Y N Y
SUSE Linux Enterprise Server 12 SP2 N N N N N Y Y N N
SUSE Linux Enterprise Server 12 SP3 N N N N N Y Y N Y
SUSE Linux Enterprise Server 12 SP4 Y Y Y N Y Y Y N Y
SUSE Linux Enterprise Server 15 N Y Y N Y Y Y N Y
SUSE Linux Enterprise Server 15 SP1 Y Y Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP2 Y Y Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP3 Y Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.0 U3 N N N N N Y Y N Y
VMware vSphere Hypervisor (ESXi) 6.5 N N N N N Y Y N N
VMware vSphere Hypervisor (ESXi) 6.5 U1 N N N N N Y Y N Y
VMware vSphere Hypervisor (ESXi) 6.5 U2 N Y Y N Y Y Y N Y
VMware vSphere Hypervisor (ESXi) 6.5 U3 Y Y Y N Y Y Y N Y
VMware vSphere Hypervisor (ESXi) 6.7 N N N N N Y Y N Y
VMware vSphere Hypervisor (ESXi) 6.7 U1 N Y Y N Y Y Y N Y
VMware vSphere Hypervisor (ESXi) 6.7 U2 N Y Y N Y Y Y N Y
VMware vSphere Hypervisor (ESXi) 6.7 U3 Y Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 Y Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U1 Y Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U3 Y Y Y Y Y Y Y Y Y
Table 66. Operating system support for ThinkSystem NVIDIA Tesla V100 16GB PCIe Passive GPU, 4C57A09498
Operating systems
SR655
SR665
SD530 (Gen 2)
SR650 (Gen 2)
SR670 (Gen 2)
SR860 (Gen 2)
SD530 (Gen 1)
SR650 (Gen 1)
SR670 (Gen 1)
SR860 (Gen 1)
x3550 M5 (5463)
Microsoft Windows Server 2012 R2 N N N N N N Y Y N Y 1 N
Microsoft Windows Server 2016 Y Y Y Y N Y Y Y N Y 1 N
Microsoft Windows Server 2019 Y Y Y Y N Y Y Y N Y N
Microsoft Windows Server 2022 Y Y Y Y Y Y Y Y Y Y N
Red Hat Enterprise Linux 6.10 N N N N N N Y Y N Y N
Red Hat Enterprise Linux 6.9 N N N N N N Y Y N Y 1 N
Red Hat Enterprise Linux 7.3 N N N N N N Y Y N N N
Red Hat Enterprise Linux 7.4 N N N N N N Y Y N Y 1 N
Red Hat Enterprise Linux 7.5 N N N N Y N Y Y Y Y N
Red Hat Enterprise Linux 7.6 Y Y Y Y Y Y Y Y Y Y N
Red Hat Enterprise Linux 7.7 Y Y Y Y Y Y Y Y Y Y N
Red Hat Enterprise Linux 7.8 Y Y Y Y Y Y Y Y Y Y N
Red Hat Enterprise Linux 7.9 Y Y Y Y Y Y Y Y Y Y N
Red Hat Enterprise Linux 8.0 Y N Y Y Y Y Y Y Y Y N
Red Hat Enterprise Linux 8.1 Y Y Y Y Y Y Y Y Y Y N
Red Hat Enterprise Linux 8.2 Y Y Y Y Y Y Y Y Y Y N
Red Hat Enterprise Linux 8.3 Y Y Y Y Y Y Y Y Y Y N
Red Hat Enterprise Linux 8.4 Y Y Y Y Y Y Y Y Y Y N
Red Hat Enterprise Linux 8.5 Y Y Y Y Y Y Y Y Y Y N
SUSE Linux Enterprise Server 11 SP4 N N N N N N Y Y N Y 1 N
SUSE Linux Enterprise Server 12 SP2 N N N N N N Y Y N N N
SUSE Linux Enterprise Server 12 SP3 N N N N N N Y Y N Y 1 N
SUSE Linux Enterprise Server 12 SP4 Y N Y Y N Y Y Y N Y N
SUSE Linux Enterprise Server 15 N N Y Y N Y Y Y N Y N
SUSE Linux Enterprise Server 15 SP1 Y Y Y Y Y Y Y Y Y Y N
SUSE Linux Enterprise Server 15 SP2 Y Y Y Y Y Y Y Y Y Y N
SUSE Linux Enterprise Server 15 SP3 Y Y Y Y Y Y Y Y Y Y N
VMware vSphere Hypervisor (ESXi) 6.0 U3 N N N N N N Y Y N Y N
VMware vSphere Hypervisor (ESXi) 6.5 N N N N N N Y Y N N Y
VMware vSphere Hypervisor (ESXi) 6.5 U1 N N N N N N Y Y N Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U2 N N Y Y N Y Y Y N Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U3 Y N Y Y N Y Y Y N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 N N N N N N Y Y N Y N
VMware vSphere Hypervisor (ESXi) 6.7 U1 N N Y Y N Y Y Y N Y N
VMware vSphere Hypervisor (ESXi) 6.7 U2 N N Y Y N Y Y Y N Y N
VMware vSphere Hypervisor (ESXi) 6.7 U3 Y Y Y Y Y Y Y Y Y Y N
VMware vSphere Hypervisor (ESXi) 7.0 Y Y Y Y Y Y Y Y Y Y N
VMware vSphere Hypervisor (ESXi) 7.0 U1 Y Y Y Y Y Y Y Y Y Y N
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y Y Y Y Y Y Y Y Y N
VMware vSphere Hypervisor (ESXi) 7.0 U3 Y Y Y Y Y Y Y Y Y Y N

1 2000W PSU x2 and CPU power must less than 200W for NVIDIA V100

Auxiliary power cables

The V100 option part numbers ship with three auxiliary power cables. These cables are needed when the GPU is installed in specific servers, as listed in the following table. For use in the SR670 and SR665, cables ordered with the server are used instead of the cables included with the GPU.

Table 67. Auxiliary power cables for V100 (click images to show larger versions)
Auxiliary power cables included with the GPU option part number

SBB7A09174190mm 8pin (2x4) cable
Server support: SR860
SBB: SBB7A09174
Base: SC17A31157
FRU: 01GT981

SBB7A09053180mm 8pin (2x4) cable
Server support: SD530
SBB: SBB7A09053
Base: SC17A07129
FRU: 00MW584

SBB7A00299300mm 8pin (2x4) cable
Server support: SR650†
SBB: SBB7A00299
Base: SC17A02296
FRU: 01KN066

† For customers who buy the GPU directly from NVIDIA, this cable is also included in the ThinkSystem SR650 GPU Cable Kit, 4XH7A08794
Auxiliary power cables supplied with the SR655 (configure-to-order or field upgrade)

SBB7A14640350mm 8pin (2x4) cable
Server support: SR655 (Riser 1 or Riser 2)
Option: 4X97A59853,  ThinkSystem  SR655 GPU Cable Kit
Feature: B5T5
SBB: SBB7A14640
Base: SC17A50848
FRU: 02JK011

SBB7A10974250mm 8pin (2x4) cable
Server support: SR655 (Riser 3)
Option: 4X97A59853,  ThinkSystem  SR655 GPU Cable Kit
Feature: B5TS
SBB: SBB7A10974
Base: SC17A50844
FRU: 02JK010
Auxiliary power cables supplied with the SR670 (configure-to-order)

SBB7A10375900mm SR670 Cage 1 power cable
Feature: B3Y3
SBB: SBB7A10375
Base: SC17A10876
FRU: 01PG448

Notes:

  • Feature & SBB also include PCIe data cable
  • Cable also supplies power to the riser

SBB7A103741100mm SR670 Cage 2 power cable
Feature: B3Y2
SBB: SBB7A10374
Base: SC17A10863
FRU: 01PG426

Notes:

  • Feature & SBB also include PCIe data cable
  • Cable also supplies power to the riser
Auxiliary power cables needed with the SR665 (configure-to-order or field upgrade)

SBB7A21691360mm 8pin (2x4) cable
Option: 4M17A80478 / 4M17A11759*
Feature: BAD8
SBB: SBB7A49792 or SBB7A21691
Base: SC17A59596
FRU: 02YE420

* The option part number is for the server thermal kit and includes other components needed to install the GPU. See the SR665 product guide for details.

 

ThinkSystem NVIDIA Tesla V100 FHHL GPU

The NVIDIA Tesla V100 FHHL GPU Accelerator is the latest NVIDIA Volta family product, targets for advanced data center to accelerate AI, HPC, and graphics. Tesla V100 FHHL offers significant performance and great power efficiency. The GPU is a full-height half-length (FHHL) form factor.

Introduction

The NVIDIA Tesla V100 FHHL GPU Accelerator for PCIe is a single-slot, full-height half-length (FHHL) PCI Express Gen 3 card with NVIDIA Volta graphics processing unit, 16GB HBM2 memory with native ECC support. It uses a passive heat sink for cooling. The Tesla V100 FHHL PCIe supports double precision (FP64), single precision (FP32) and half precision (FP16) compute tasks, unified virtual memory and page migration engine.

NVIDIA Tesla V100 FHHL GPU
Figure 11. NVIDIA Tesla V100 FHHL GPU

Part numbers

Table 68. Ordering information
Part number Feature code Description
4X67A11524 B32D ThinkSystem NVIDIA Tesla V100 FHHL GPU

Technical specifications

The following table lists the specifications of the NVIDIA Tesla V100 FHHL GPU.

Table 69. V100 FHHL specifications
Feature Specification
GPU Architecture NVIDIA Volta
NVIDIA Tensor Cores 640
NVIDIA CUDA® Cores 5,120
Double-Precision Performance 6.5 TFLOPS
Single-Precision Performance 13 TFLOPS
Tensor Performance 105 TFLOPS
GPU Memory 16 GB HBM2
Memory Bandwidth 900 GB/sec
ECC Yes
Interconnect Bandwidth 32 GB/sec
System Interface PCIe Gen3
Form Factor PCIe Full Height/Half Length
Max Power Consumption 150 W
Thermal Solution Passive
Compute APIs CUDA, DirectCompute, OpenCL, OpenACC

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 70. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
4X67A11524 ThinkSystem NVIDIA Tesla V100 FHHL 16GB GPU PCIe N N N N N N N N N N N N N N N N N N N N
Table 71. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
4X67A11524 ThinkSystem NVIDIA Tesla V100 FHHL 16GB GPU PCIe N N N N N N N N N N 3 N N N N N N N N

Operating system support

The following table lists the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 72. Operating system support for ThinkSystem NVIDIA Tesla V100 FHHL 16GB PCIe Passive GPU, 4X67A11524
Operating systems
SR650 (Gen 2)
SR650 (Gen 1)
Microsoft Windows Server 2012 R2 N Y
Microsoft Windows Server 2016 Y Y
Microsoft Windows Server 2019 Y Y
Microsoft Windows Server 2022 Y Y
Red Hat Enterprise Linux 6.10 N Y
Red Hat Enterprise Linux 6.9 N Y
Red Hat Enterprise Linux 7.3 N Y
Red Hat Enterprise Linux 7.4 N Y
Red Hat Enterprise Linux 7.5 N Y
Red Hat Enterprise Linux 7.6 Y Y
Red Hat Enterprise Linux 7.7 Y Y
Red Hat Enterprise Linux 7.8 Y Y
Red Hat Enterprise Linux 7.9 Y Y
Red Hat Enterprise Linux 8.0 Y Y
Red Hat Enterprise Linux 8.1 Y Y
Red Hat Enterprise Linux 8.2 Y Y
Red Hat Enterprise Linux 8.3 Y Y
Red Hat Enterprise Linux 8.4 Y Y
Red Hat Enterprise Linux 8.5 Y Y
SUSE Linux Enterprise Server 11 SP4 N Y
SUSE Linux Enterprise Server 12 SP2 N Y
SUSE Linux Enterprise Server 12 SP3 N Y
SUSE Linux Enterprise Server 12 SP4 Y Y
SUSE Linux Enterprise Server 15 Y Y
SUSE Linux Enterprise Server 15 SP1 Y Y
SUSE Linux Enterprise Server 15 SP2 Y Y
SUSE Linux Enterprise Server 15 SP3 Y Y
VMware vSphere Hypervisor (ESXi) 6.5 N Y
VMware vSphere Hypervisor (ESXi) 6.5 U1 N Y
VMware vSphere Hypervisor (ESXi) 6.5 U2 Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U3 Y Y
VMware vSphere Hypervisor (ESXi) 7.0 Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U1 Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U3 Y Y

Auxiliary power cables

The V100 FHHL option part number ships with one auxiliary power cable. The cable is needed when the GPU is installed in specific servers, as listed in the following table.

Table 73. Auxiliary power cables (click images to show larger versions)
Auxiliary power cables included with the V100 FHHL option part number

SBB7A05971300mm 2x 8pin (2x4) cable
Server support: SR650†
SBB: SBB7A05971
Base: SC17A30059
FRU: 01KR723

† For customers who buy the GPU directly from NVIDIA, this cable is also included in the ThinkSystem SR650 GPU Cable Kit, 4XH7A08794

ThinkSystem NVIDIA Tesla P100 GPU

ThinkSystem NVIDIA Tesla P100 GPU accelerators are the world's first AI supercomputing data center GPUs. They tap into NVIDIA Pascal GPU architecture to deliver a unified platform for accelerating both HPC and AI. With higher performance and fewer, lightning-fast nodes, Tesla P100 enables data centers to dramatically increase throughput while also saving money.

Introduction

ThinkSystem NVIDIA Tesla P100 is a dual-slot 10.5 inch PCI Express Gen3 card with single NVIDIA Pascal GP100 graphics processing unit (GPU). It uses a passive heat sink for cooling. P100 is reimagined from silicon to software, crafted with innovation at every level. Each groundbreaking technology delivers a dramatic jump in performance to inspire the creation of the world's fastest compute node.

P100
Figure 12. ThinkSystem NVIDIA Tesla P100 GPU

Part numbers

Table 74. Ordering information
Part number Feature code Description
7X67A00068 AUV5, B13H, B0M1 ThinkSystem NVIDIA Tesla P100

* Feature code varies by server

Technical specifications

The following table lists the specifications of the NVIDIA Tesla P100 GPU.

Table 75. P100 specifications
Feature Specification
GPU Architecture NVIDIA Pascal
NVIDIA CUDA® Cores 3584
Double-Precision Performance 4.7 TeraFLOPS
Single-Precision Performance 9.3 TeraFLOPS
Half-Precision Performance 18.7 TeraFLOPS
GPU Memory 16GB CoWoS HBM2 at 720 GB/s
System Interface PCIe Gen3
Max Power Consumption 250 W
ECC Yes
Thermal Solution Passive
Form Factor PCIe Full Height/Length
Compute APIs CUDA, DirectCompute, OpenCL, OpenACC

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 76. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
7X67A00068 ThinkSystem NVIDIA Tesla P100 PCIe 16GB N N N N N N N N N N N N N N N N N N N N
Table 77. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
7X67A00068 ThinkSystem NVIDIA Tesla P100 PCIe 16GB N N N N N N N N N N 2 N 2 N N N N N N

Operating system support

The following table lists the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 78. Operating system support for NVIDIA Tesla P100 16GB GPU, PCIe (passive), 7X67A00068
Operating systems
SD530 (Gen 2)
SR650 (Gen 2)
SD530 (Gen 1)
SR650 (Gen 1)
nx360 M5 (5465)
x3650 M5 (8871)
Microsoft Windows Server 2012 N N N N Y Y
Microsoft Windows Server 2012 R2 N N Y Y Y Y
Microsoft Windows Server 2016 Y Y Y Y Y Y
Microsoft Windows Server 2019 Y Y Y Y N N
Red Hat Enterprise Linux 6.10 N N Y Y Y Y
Red Hat Enterprise Linux 6.9 N N Y Y Y Y
Red Hat Enterprise Linux 7.3 N N Y Y Y Y
Red Hat Enterprise Linux 7.4 N N Y Y Y Y
Red Hat Enterprise Linux 7.5 N N Y Y Y Y
Red Hat Enterprise Linux 7.6 Y Y Y Y Y Y
Red Hat Enterprise Linux 7.7 Y Y Y Y Y Y
Red Hat Enterprise Linux 7.8 Y Y Y Y Y Y
Red Hat Enterprise Linux 7.9 Y Y Y Y Y Y
Red Hat Enterprise Linux 8.0 Y Y Y Y N N
Red Hat Enterprise Linux 8.1 Y Y Y Y N N
Red Hat Enterprise Linux 8.2 Y Y Y Y N N
Red Hat Enterprise Linux 8.3 Y Y Y Y N N
Red Hat Enterprise Linux 8.4 Y Y Y Y N N
SUSE Linux Enterprise Server 11 SP4 N N Y Y Y Y
SUSE Linux Enterprise Server 12 SP2 N N Y Y Y Y
SUSE Linux Enterprise Server 12 SP3 N N Y Y Y Y
SUSE Linux Enterprise Server 12 SP4 Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 Y Y Y Y N Y
SUSE Linux Enterprise Server 15 SP1 Y Y Y Y N Y
SUSE Linux Enterprise Server 15 SP2 Y Y Y Y N Y
SUSE Linux Enterprise Server 15 SP3 Y Y Y Y N N
VMware vSphere Hypervisor (ESXi) 6.0 U3 N N Y Y N N
VMware vSphere Hypervisor (ESXi) 6.5 N N Y Y N N
VMware vSphere Hypervisor (ESXi) 6.5 U1 N N Y Y N N
VMware vSphere Hypervisor (ESXi) 6.5 U2 Y Y Y Y N N
VMware vSphere Hypervisor (ESXi) 6.5 U3 Y Y Y Y N N
VMware vSphere Hypervisor (ESXi) 6.7 N N Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U1 Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U2 Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U3 Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 Y Y Y Y N N
VMware vSphere Hypervisor (ESXi) 7.0 U1 Y Y Y Y N N
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y Y Y N N

ThinkSystem NVIDIA Tesla P40 GPU

ThinkSystem NVIDIA Tesla P40 GPU accelerators are purpose-built to deliver maximum throughput for deep learning deployment. Tesla P40 is powered by the revolutionary NVIDIA Pascal architecture provide the computational engine for the new era of artificial intelligence, enabling amazing user experiences by accelerating deep learning applications at scale.

Introduction

ThinkSystem NVIDIA Tesla P40 is a dual-slot 10.5-inch PCIe 3.0 card based on a high-end NVIDIA Pascal graphics processing unit (GPU). It uses a passive heat sink for cooling. P40 has 24GB GDDR5 memory and a 250 W maximum power limit. With 47 TOPS (Tera-Operations Per Second) of inference performance and INT8 operations per GPU, a single server with 8 Tesla P40s delivers the performance of over 140 CPU servers.

NVIDIA Tesla P40
Figure 13. ThinkSystem NVIDIA Tesla P40 GPU

Part numbers

Table 79. Ordering information
Part number Feature code Description
7C57A02888 AVNZ, B0LZ, B15U* ThinkSystem NVIDIA Tesla P40

* Feature code varies by server

Technical specifications

The following table lists the specifications of the NVIDIA Tesla P40 GPU.

Table 80. P40 specifications
Feature Specification
GPU Architecture NVIDIA Pascal
NVIDIA CUDA® Cores 3840
Single-Precision Performance 12 TeraFLOPS
Integer Operations (INT8) 47 TOPS (Tera-Operations per Second)
GPU Memory 24GB
System Interface PCIe Gen3
Max Power Consumption 250 W
ECC Yes
Thermal Solution Passive
Form Factor Dual Slot, Full Height
Hardware-Accelerated Video Engine 1x Decode Engine, 2x Encode Engine

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 81. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
7C57A02888 NVIDIA Tesla P40 GPU, PCIe (passive) N N N N N N N N N N N N N N N N N N N N
Table 82. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
7C57A02888 NVIDIA Tesla P40 GPU, PCIe (passive) N N N N N N N N N N 2 4 2 N N N N N N

Operating system support

The following table lists the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 83. Operating system support for NVIDIA Tesla P40 GPU, PCIe (passive), 7C57A02888
Operating systems
SD530 (Gen 2)
SR650 (Gen 2)
SR670 (Gen 2)
SD530 (Gen 1)
SR650 (Gen 1)
SR670 (Gen 1)
nx360 M5 (5465)
x3650 M5 (8871)
Microsoft Windows Server 2012 N N N N N N Y Y
Microsoft Windows Server 2012 R2 N N N Y Y N Y Y
Microsoft Windows Server 2016 Y Y N Y Y N Y Y
Microsoft Windows Server 2019 Y Y N Y Y N N N
Red Hat Enterprise Linux 6.10 N N N Y Y N Y Y
Red Hat Enterprise Linux 6.9 N N N Y Y N Y Y
Red Hat Enterprise Linux 7.3 N N N Y Y N Y Y
Red Hat Enterprise Linux 7.4 N N N Y Y N Y Y
Red Hat Enterprise Linux 7.5 N N Y Y Y Y Y Y
Red Hat Enterprise Linux 7.6 Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.7 Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.8 Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.9 Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.0 Y Y Y Y Y Y N N
Red Hat Enterprise Linux 8.1 Y Y Y Y Y Y N N
Red Hat Enterprise Linux 8.2 Y Y Y Y Y Y N N
Red Hat Enterprise Linux 8.3 Y Y Y Y Y Y N N
Red Hat Enterprise Linux 8.4 Y Y Y Y Y Y N N
SUSE Linux Enterprise Server 11 SP4 N N N Y Y N Y Y
SUSE Linux Enterprise Server 12 SP2 N N N Y Y N Y Y
SUSE Linux Enterprise Server 12 SP3 N N N Y Y N Y Y
SUSE Linux Enterprise Server 12 SP4 Y Y N Y Y N Y Y
SUSE Linux Enterprise Server 15 Y Y N Y Y N N Y
SUSE Linux Enterprise Server 15 SP1 Y Y Y Y Y Y N Y
SUSE Linux Enterprise Server 15 SP2 Y Y Y Y Y Y N Y
SUSE Linux Enterprise Server 15 SP3 Y Y Y Y Y Y N N
VMware vSphere Hypervisor (ESXi) 6.0 U3 N N N Y Y N N N
VMware vSphere Hypervisor (ESXi) 6.5 N N N Y Y N N N
VMware vSphere Hypervisor (ESXi) 6.5 U1 N N N Y Y N N N
VMware vSphere Hypervisor (ESXi) 6.5 U2 Y Y N Y Y N N N
VMware vSphere Hypervisor (ESXi) 6.5 U3 Y Y N Y Y N N N
VMware vSphere Hypervisor (ESXi) 6.7 N N N Y Y N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U1 Y Y N Y Y N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U2 Y Y N Y Y N Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U3 Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 Y Y Y Y Y Y N N
VMware vSphere Hypervisor (ESXi) 7.0 U1 Y Y Y Y Y Y N N
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y Y Y Y Y N N

Auxiliary power cables

The P40 option part numbers ship with two auxiliary power cables. These cables are needed when the GPU is installed in specific servers, as listed in the following table. For use in the SR670, cables ordered with the server are used instead of the cables included with the GPU.

Table 84. Auxiliary power cables (click images to show larger versions)
Auxiliary power cables included with the P40 option part number

SBB7A09053180mm 8pin (2x4) cable
Server support: SD530
SBB: SBB7A09053
Base: SC17A07129
FRU: 00MW584

SBB7A00299300mm 8pin (2x4) cable
Server support: SR650†, SR655
SBB: SBB7A00299
Base: SC17A02296
FRU: 01KN066
Auxiliary power cables supplied with the SR670 (configure-to-order)

SBB7A10375900mm SR670 Cage 1 power cable
Feature: B3Y3
SBB: SBB7A10375
Base: SC17A10876
FRU: 01PG448

Notes:

  • Feature & SBB also include PCIe data cable
  • Cable also supplies power to the riser

SBB7A103741100mm SR670 Cage 2 power cable
Feature: B3Y2
SBB: SBB7A10374
Base: SC17A10863
FRU: 01PG426

Notes:

  • Feature & SBB also include PCIe data cable
  • Cable also supplies power to the riser

† For customers who buy the GPU directly from NVIDIA, this cable is also included in the ThinkSystem SR650 GPU Cable Kit, 4XH7A08794

ThinkSystem NVIDIA T4 GPU

The NVIDIA T4 GPU supports diverse cloud workloads, including high-performance computing, deep learning training and inference, machine learning, data analytics, and graphics. Based on the new NVIDIA Turing Architecture and packaged in an energy-efficient 70-watt, small PCIe form factor, Tesla T4 is optimized for scale-out computing environments with its multi-precision Turing Tensor Cores and new RT Cores.

Introduction

The NVIDIA T4 GPU is a single-slot, low-profile, 6.6-inch PCIe 3.0 Universal Deep Learning Accelerator. The Tesla T4 has 16GB GDDR6 memory.

The T4 GPU provides revolutionary multi-precision performance to accelerate deep learning and machine learning training and inference, video transcoding and virtual desktops. Powering performance from FP32 to FP16 to INT8, as well as INT4 precisions, T4 delivers up to 40x higher performance than CPUs. As part of the NVIDIA AI platform, Tesla T4 supports all AI frameworks and network types, delivering dramatic performance and efficiency.

ThinkSystem NVIDIA Tesla T4 GPU
Figure 14. ThinkSystem NVIDIA T4 16GB PCIe Passive GPU

Part numbers

Table 85. Ordering information
Part number Feature code Description
4X67A14926 B4YB ThinkSystem NVIDIA T4 16GB PCIe Passive GPU

Technical specifications

The following table lists the specifications of the NVIDIA T4 GPU.

Table 86. Technical Specifications
Feature Specification
GPU Architecture NVIDIA Turing
NVIDIA Turing Tensor Cores 320 cores
NVIDIA CUDA Cores 2560 cores
Single Precision Performance (FP32) 8.1 TFLOPS
Mixed Precision (FP16/FP32) 65 FP16 TFLOPS
INT8 Precision 130 INT8 TOPS
INT4 Precision 260 INT4 TOPS
System Interface PCIe 3.0 x16 or x8 (x16 physical connector)
GPU Memory 16 GB GDDR6
Memory Bandwidth 320+ GB/s
Form Factor single-slot, low-profile
Max Power Consumption 70 W
Thermal Solution Passive
Compute APIs CUDA, DirectCompute, OpenCL, OpenACC

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 87. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
4X67A14926 ThinkSystem NVIDIA T4 16GB PCIe Passive GPU 1 N N N N 8 3 8 N 3 6 3 8 N N N N 2 8 N
Table 88. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
4X67A14926 ThinkSystem NVIDIA T4 16GB PCIe Passive GPU N N N N N N N N N 2 51 8 N N N N N N N
  1. The SR650 has support for 5x T4 or 5x P4 GPUs in servers with second-generation Intel Xeon Scalable processors only. SR650 systems originally with first-generation processors have support for up to 4x T4 or 2x P4 GPUs.

Operating system support

The following table lists the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 89. Operating system support for ThinkSystem NVIDIA T4 16GB PCIe Passive GPU, 4X67A14926
Operating systems
SE350
SR630 V2
SR650 V2
SR670 V2
SR850 V2
SR860 V2
ST650 V2
SR635
SR645
SR655
SR665
SR630 (Gen 2)
SR650 (Gen 2)
SR670 (Gen 2)
SR630 (Gen 1)
SR650 (Gen 1)
SR670 (Gen 1)
Microsoft Windows Server 2012 R2 N N N N N N N N N N N N N N Y Y N
Microsoft Windows Server 2016 Y Y Y Y Y Y Y Y Y Y Y Y Y N Y Y N
Microsoft Windows Server 2019 Y Y Y Y Y Y Y Y Y Y Y Y Y N Y Y N
Microsoft Windows Server 2022 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 6.10 N N N N N N N N N N N N N N Y Y N
Red Hat Enterprise Linux 6.9 N N N N N N N N N N N N N N Y Y N
Red Hat Enterprise Linux 7.3 N N N N N N N N N N N N N N Y Y N
Red Hat Enterprise Linux 7.4 N N N N N N N N N N N N N N Y Y N
Red Hat Enterprise Linux 7.5 N N N N N N N N N N N N N Y Y Y Y
Red Hat Enterprise Linux 7.6 Y N N N N N N Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.7 Y N N N N N N Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.8 Y N N N N N N Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.9 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.0 N N N N N N N Y N Y N Y Y Y Y Y Y
Red Hat Enterprise Linux 8.1 Y N N N N N N Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.2 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.3 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.4 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.5 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 11 SP4 N N N N N N N N N N N N N N Y Y N
SUSE Linux Enterprise Server 12 SP2 N N N N N N N N N N N N N N Y Y N
SUSE Linux Enterprise Server 12 SP3 N N N N N N N N N N N N N N Y Y N
SUSE Linux Enterprise Server 12 SP4 N N N N N N N Y N Y N Y Y N Y Y N
SUSE Linux Enterprise Server 12 SP5 N N N N Y Y N N N N N N N N N N N
SUSE Linux Enterprise Server 15 Y N N N N N N N N N N Y Y N Y Y N
SUSE Linux Enterprise Server 15 SP1 Y N N N N N N Y Y Y Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP2 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP3 Y Y Y Y Y Y N Y Y Y Y Y Y Y Y Y Y
Ubuntu 18.04.5 LTS N Y Y Y N N Y N N N N N N N N N N
VMware vSphere Hypervisor (ESXi) 6.5 N N N N N N N N N N N N N N Y Y N
VMware vSphere Hypervisor (ESXi) 6.5 U1 N N N N N N N N N N N N N N Y Y N
VMware vSphere Hypervisor (ESXi) 6.5 U2 Y N N N N N N N N N N Y Y N Y Y N
VMware vSphere Hypervisor (ESXi) 6.5 U3 N N N N N N N Y N Y N Y Y N Y Y N
VMware vSphere Hypervisor (ESXi) 6.7 N N N N N N N N N N N N N N Y Y N
VMware vSphere Hypervisor (ESXi) 6.7 U1 N N N N N N N N N N N Y Y N Y Y N
VMware vSphere Hypervisor (ESXi) 6.7 U2 Y N N N N N N N N N N Y Y N Y Y N
VMware vSphere Hypervisor (ESXi) 6.7 U3 N Y Y Y N N Y Y Y Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 Y N N N N N N Y Y Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U1 Y N N N Y Y N Y Y Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 U3 Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y Y

Auxiliary power cables

The T4 does not require an auxiliary power cable.

ThinkSystem NVIDIA Tesla P4 GPU

The NVIDIA Tesla P4 is powered by the revolutionary NVIDIA Pascal architecture and purpose-built to boost efficiency for scale-out servers running deep learning workloads, enabling smart responsive AI-based services. It slashes inference latency by 15X in any hyperscale infrastructure and provides an incredible 60X better energy efficiency than CPUs. This unlocks a new wave of AI services previous impossible due to latency limitations.

Introduction

The NVIDIA Tesla P4 is a single-slot, low profile, 6.6 inch PCI Express Gen3 GPU Accelerator with an NVIDIA Pascal graphics processing unit (GPU). The Tesla P4 has 8 GB GDDR5 memory and a 75 W maximum power limit. The NVIDIA Tesla P4 features optimized INT8 instructions aimed at deep learning inference computations. As a result, the NVIDIA Tesla P4 delivers 22 TOPs (Tera-Operations per second) of inference performance, enabling smart responsive artificial intelligence (AI)-based services.

ThinkSystem NVIDIA Tesla P4
Figure 15. ThinkSystem NVIDIA Tesla P4 GPU

Part numbers

Table 90. Ordering information
Part number Feature code Description
7C57A02892 B227 ThinkSystem NVIDIA Tesla P4

Technical specifications

The following table lists the specifications of the NVIDIA Tesla P4 GPU.

Table 91. Technical specifications
Feature Specification
GPU Architecture NVIDIA Pascal
Single-Precision Performance 5.5 TeraFLOPS
Integer Operations (INT8) 22 TOPS (Tera-Operations per Second)
GPU Memory 8 GB
Memory Bandwidth 192 GB/s
System Interface Low-Profile PCI Express Form Factor
Max Power 75W
Enhanced Programmability with Page Migration Engine Yes
ECC Protection Yes
Server-Optimized for Data Center Deployment Yes
Hardware-Accelerated Video Engine 1x Decode Engine, 2x Encode Engine

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 92. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
7C57A02892 ThinkSystem NVIDIA Tesla P4 8GB PCIe Passive GPU N N N N N N N N N N N N N N N N N N N N
Table 93. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
7C57A02892 ThinkSystem NVIDIA Tesla P4 8GB PCIe Passive GPU N N N N N N N N N 2 51 N N N N N N N N
  1. The SR650 has support for 5x T4 or 5x P4 GPUs in servers with second-generation Intel Xeon Scalable processors only. SR650 systems originally with first-generation processors have support for up to 4x T4 or 2x P4 GPUs.

Operating system support

The following table lists the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 94. Operating system support for ThinkSystem NVIDIA Tesla P4 8GB PCIe Passive GPU, 7C57A02892
Operating systems
SR630 (Gen 2)
SR650 (Gen 2)
SR630 (Gen 1)
SR650 (Gen 1)
x3550 M5 (5463)
Microsoft Windows Server 2012 R2 N N Y Y N
Microsoft Windows Server 2016 Y Y Y Y N
Microsoft Windows Server 2019 Y Y Y Y N
Red Hat Enterprise Linux 6.10 N N Y Y N
Red Hat Enterprise Linux 6.9 N N Y Y N
Red Hat Enterprise Linux 7.3 N N Y Y N
Red Hat Enterprise Linux 7.4 N N Y Y N
Red Hat Enterprise Linux 7.5 N N Y Y N
Red Hat Enterprise Linux 7.6 Y Y Y Y N
Red Hat Enterprise Linux 7.7 Y Y Y Y N
Red Hat Enterprise Linux 7.8 Y Y Y Y N
Red Hat Enterprise Linux 7.9 Y Y Y Y N
Red Hat Enterprise Linux 8.0 Y Y Y Y N
Red Hat Enterprise Linux 8.1 Y Y Y Y N
Red Hat Enterprise Linux 8.2 Y Y Y Y N
Red Hat Enterprise Linux 8.3 Y Y Y Y N
Red Hat Enterprise Linux 8.4 Y Y Y Y N
SUSE Linux Enterprise Server 11 SP4 N N Y Y N
SUSE Linux Enterprise Server 12 SP2 N N Y Y N
SUSE Linux Enterprise Server 12 SP3 N N Y Y N
SUSE Linux Enterprise Server 12 SP4 Y Y Y Y N
SUSE Linux Enterprise Server 15 Y Y Y Y N
SUSE Linux Enterprise Server 15 SP1 Y Y Y Y N
SUSE Linux Enterprise Server 15 SP2 Y Y Y Y N
SUSE Linux Enterprise Server 15 SP3 Y Y Y Y N
VMware vSphere Hypervisor (ESXi) 6.0 U3 N N Y Y N
VMware vSphere Hypervisor (ESXi) 6.5 N N Y Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U1 N N Y Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U2 Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U3 Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.7 N N Y Y N
VMware vSphere Hypervisor (ESXi) 6.7 U1 Y Y Y Y N
VMware vSphere Hypervisor (ESXi) 6.7 U2 Y Y Y Y N
VMware vSphere Hypervisor (ESXi) 6.7 U3 Y Y Y Y N
VMware vSphere Hypervisor (ESXi) 7.0 Y Y Y Y N
VMware vSphere Hypervisor (ESXi) 7.0 U1 Y Y Y Y N
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y Y Y N

ThinkSystem NVIDIA Tesla M60 GPU

ThinkSystem NVIDIA Tesla M60 GPU accelerator works with NVIDIA GRID software to provide the industry’s highest user performance for virtualized applications. This solution allows enterprises to virtualize any application— including professional graphics applications—and deliver them out to any device, anywhere.

Introduction

ThinkSystem NVIDIA Tesla M60 is a dual-slot 10.5 inch PCI Express Gen3 graphics card with two high-end NVIDIA Maxwell graphics processing units (GPUs). The Tesla M60 has 16 GB GDDR5 memory (8 GB per GPU) and a 300 W maximum power limit. M60 is offered as a 300 W passively cooled adapter that uses system airflow to keep the card within its thermal limits.

M60
Figure 16. ThinkSystem NVIDIA Tesla M60 GPU

Part numbers

Table 95. Ordering information
Part number Feature code Description
00KG655 ATZE, B0TB, B13J, B0M0* ThinkSystem NVIDIA Tesla M60

* Feature code varies by server

Technical specifications

The following table lists the specifications of the NVIDIA Tesla M60 GPU.

Table 96. M60 specifications
Feature Specification
Virtualization Use Case Performance-Optimized, Graphics Virtualization
GPU Architecture NVIDIA Maxwell
GPUs per Board 2
Max User per Board 32 (16 per GPU)
NVIDIA CUDA® Cores 4096 NVIDIA CUDA Cores (2048 per GPU)
GPU Memory 16 GB of GDDR5 Memory (8 per GPU)
H.264 1080p30 streams 36
Max Power Consumption 300 W
Thermal Solution Active/Passive Passive
Form Factor PCIe 3.0 Dual Slot PCIe 3.0 Dual Slot

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 97. Servers support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
00KG655 NVIDIA Tesla M60 GPU, PCIe Passive N N N N N N N N N N N N N N N N N N N N
Table 98. Servers support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
00KG655 NVIDIA Tesla M60 GPU, PCIe Passive N N N N N N N N N N 2 N 2 N N N N N 2

Operating system support

The following table lists the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 99. Operating system support for NVIDIA Tesla M60 GPU, PCIe (Passive), 00KG655
Operating systems
SD530 (Gen 2)
SR650 (Gen 2)
SR860 (Gen 2)
SD530 (Gen 1)
SR650 (Gen 1)
SR860 (Gen 1)
nx360 M5 (5465)
Microsoft Windows Server 2012 N N N N N N Y
Microsoft Windows Server 2012 R2 N N N Y Y Y Y
Microsoft Windows Server 2016 Y Y Y Y Y Y Y
Microsoft Windows Server 2019 Y Y Y Y Y Y N
Red Hat Enterprise Linux 6.10 N N N Y Y Y Y
Red Hat Enterprise Linux 6.9 N N N Y Y Y Y
Red Hat Enterprise Linux 7.3 N N N Y Y N Y
Red Hat Enterprise Linux 7.4 N N N Y Y Y Y
Red Hat Enterprise Linux 7.5 N N N Y Y Y Y
Red Hat Enterprise Linux 7.6 Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.7 Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.8 Y Y Y Y Y Y Y
Red Hat Enterprise Linux 7.9 Y Y Y Y Y Y Y
Red Hat Enterprise Linux 8.0 Y Y Y Y Y Y N
Red Hat Enterprise Linux 8.1 Y Y Y Y Y Y N
Red Hat Enterprise Linux 8.2 Y Y Y Y Y Y N
SUSE Linux Enterprise Server 11 SP4 N N N Y Y Y Y
SUSE Linux Enterprise Server 12 SP2 N N N Y Y N Y
SUSE Linux Enterprise Server 12 SP3 N N N Y Y Y Y
SUSE Linux Enterprise Server 12 SP4 Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP1 Y Y Y Y Y Y Y
SUSE Linux Enterprise Server 15 SP2 Y Y Y Y Y Y Y
VMware vSphere 5.1 (ESXi) N N N N N N Y
VMware vSphere Hypervisor (ESXi) 5.5 N N N N N N Y
VMware vSphere Hypervisor (ESXi) 6.0 U3 N N N Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.5 N N N Y Y N Y
VMware vSphere Hypervisor (ESXi) 6.5 U1 N N N Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U2 Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.5 U3 Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.7 N N N Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U1 Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U2 Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 6.7 U3 Y Y Y Y Y Y Y
VMware vSphere Hypervisor (ESXi) 7.0 Y Y Y Y Y Y N
VMware vSphere Hypervisor (ESXi) 7.0 U1 Y Y Y Y Y Y N
VMware vSphere Hypervisor (ESXi) 7.0 U2 Y Y Y Y Y Y N

Auxiliary power cables

The M60 option part numbers ship with three auxiliary power cables. These cables are needed when the GPU is installed in specific servers, as listed in the following table.

Table 100. Auxiliary power cables (click images to show larger versions)
Auxiliary power cables included with the M60 option part number

SBB7A09174190mm 8pin (2x4) cable
Server support: SR860
SBB: SBB7A09174
Base: SC17A31157
FRU: 01GT981

SBB7A09053180mm 8pin (2x4) cable
Server support: SD530
SBB: SBB7A09053
Base: SC17A07129
FRU: 00MW584

SBB7A00299300mm 8pin (2x4) cable
Server support: SR650†
SBB: SBB7A00299
Base: SC17A02296
FRU: 01KN066

† For customers who buy the GPU directly from NVIDIA, this cable is also included in the ThinkSystem SR650 GPU Cable Kit, 4XH7A08794

ThinkSystem NVIDIA Tesla M10 GPU

ThinkSystem NVIDIA Tesla M10 GPU accelerator works with NVIDIA GRID software to provide the industry’s highest user density for virtualized desktops and applications. It supports 64 desktops per board and 128 desktops per server, giving your business the power to deliver great experiences to all of your employees at an affordable cost.

Introduction

ThinkSystem NVIDIA Tesla M10 is a dual-slot 10.5 inch PCI Express 3.0 graphics card with four mid-range NVIDIA Maxwell graphics processing units (GPUs). The Tesla M10 has 32 GB GDDR5 memory (8 GB per GPU) and a 225 W maximum power limit. The board is passively cooled and supports both airflow directions.

NVIDIA Tesla M10
Figure 17. ThinkSystem NVIDIA Tesla M10 GPU

Part numbers

Table 101. Ordering information
Part number Feature code Description
7C57A02891 AX8L, B15V, B0RK* ThinkSystem NVIDIA Tesla M10

* Feature code varies by system

Technical specifications

The following table lists the specifications of the NVIDIA Tesla M10 GPU.

Table 102. M10 specifications
Feature Specification
Virtualization Use Case Performance-Optimized Graphics Virtualization
GPU Architecture NVIDIA Maxwell
GPUs per Board 4
Max User per Board 64 (16 per GPU)
NVIDIA CUDA® Cores 2560 NVIDIA CUDA Cores (640 per GPU)
GPU Memory 32 GB of GDDR5 Memory (8 per GPU)
H.264 1080p30 streams 28
Max Power Consumption 225 W
Thermal Solution Active/Passive Passive
Form Factor PCIe 3.0 Dual Slot PCIe 3.0 Dual Slot

Server support

The following tables list the ThinkSystem servers that are compatible.

Table 103. Server support (Part 1 of 2)
Part Number Description Edge 1S Intel V2 2S Intel V2 AMD Dense V2 4S V2 8S
SE350 (7Z46 / 7D1X)
SE450 (7D8T)
ST50 V2 (7D8K / 7D8J)
ST250 V2 (7D8G / 7D8F)
SR250 V2 (7D7R / 7D7Q)
ST650 V2 (7Z75 / 7Z74)
SR630 V2 (7Z70 / 7Z71)
SR650 V2 (7Z72 / 7Z73)
SR670 V2 (7Z22 / 7Z23)
SR635 (7Y98 / 7Y99)
SR655 (7Y00 / 7Z01)
SR645 (7D2Y / 7D2X)
SR665 (7D2W / 7D2V)
SD630 V2 (7D1K)
SD650 V2 (7D1M)
SD650-N V2 (7D1N)
SN550 V2 (7Z69)
SR850 V2 (7D31 / 7D32)
SR860 V2 (7Z59 / 7Z60)
SR950 (7X11 / 7X12)
7C57A02891 NVIDIA Tesla M10 GPU, PCIe (passive) N N N N N N N N N N N N N N N N N N N N
Table 104. Server support (Part 2 of 2)
Part Number Description 1S Intel V1 2S Intel V1 Dense V1 4S V1
ST50 (7Y48 / 7Y50)
ST250 (7Y45 / 7Y46)
SR150 (7Y54)
SR250 (7Y52 / 7Y51)
ST550 (7X09 / 7X10)
SR530 (7X07 / 7X08)
SR550 (7X03 / 7X04)
SR570 (7Y02 / 7Y03)
SR590 (7X98 / 7X99)
SR630 (7X01 / 7X02)
SR650 (7X05 / 7X06)
SR670 (7Y36 / 7Y37)
SD530 (7X21)
SD650 (7X58)
SN550 (7X16)
SN850 (7X15)
SR850 (7X18 / 7X19)
SR850P (7D2F / 2D2G)
SR860 (7X69 / 7X70)
7C57A02891 NVIDIA Tesla M10 GPU, PCIe (passive) N N N N N N N N N N 2 N 2 N N N N N N

Operating system support

The following table lists the supported operating systems.

Tip: These tables are automatically generated based on data from Lenovo ServerProven.

Table 105. Operating system support for NVIDIA Tesla M10 32GB GPU, PCIe (Passive), 7C57A02891
Operating systems
SD530 (Gen 2)
SR650 (Gen 2)
SD530 (Gen 1)
SR650 (Gen 1)
nx360 M5 (5465)
x3650 M5 (8871)
x240 M5 (9532)
Microsoft Windows Server 2012 N N N N Y Y N
Microsoft Windows Server 2012 R2 N N N N Y Y N
Microsoft Windows Server 2016 Y Y Y Y Y Y N
Microsoft Windows Server 2019 Y Y Y Y N N N
Microsoft Windows Server 2022 Y Y Y Y N N N
Red Hat Enterprise Linux 7.6