GPUs on supported platforms

AMD
PLATFORM
A100 40GB SXM4 A100 80GB SXM4
A100 80GB PCIe A40 A30 A16 A10 A2 M10 T4 MI100 MI210
(Nvlink) (Nvlink)

1 1
XE8545 Shipping (4 ) Shipping (4 )

R750xa
Shipping (43) Shipping (43) Shipping (43) Shipping (43) Shipping (43) Shipping (63) Shipping (23) Shipping (63) Shipping (43)

R750 Shipping (2) Shipping (2) Shipping (2) Shipping (2) Shipping (3) Shipping (6) Shipping (2) Shipping (6)

R650 Shipping (3) Shipping (3)

C6520 Shipping (1) Shipping (1)

R7525 - Milan
Shipping (3) Shipping (3) Shipping (3) Shipping (3) Shipping (3) Shipping (6) Shipping (2) Shipping (6) Shipping (3) Shipping (3)

R7525 - Rome
Shipping (3) Shipping (3) Shipping (3) Shipping (3) Shipping (3) Shipping (6) Shipping (2) Shipping (6) Shipping (3) Shipping (3)

R7515 - Milan Shipping (1) Shipping (1) Shipping (4) Shipping (4) Shipping (1)

R7515 - Rome Shipping (1) Shipping (1) Shipping (4) Shipping (4) Shipping (1)

R6525 - Rome & Milan Shipping (3) Shipping (3)

R6515 - Rome & Milan Shipping (2) Shipping (1)

C6525 - Rome & Milan Shipping (1) Shipping (1)

XR12 Shipping (2) Shipping (2) Shipping (2) Shipping (2) Shipping (2)

XR11 Shipping (2) Shipping (2)

DSS8440 Shipping (4/8/10 )

1 1
Shipping (4/8/10 ) Shipping (4/8/10 )
1
Shipping (8/12/16 )
1

R940XA Shipping (4)

R840 Shipping (2)

R740/XD Shipping (3) Shipping (3) Shipping (3) Shipping (3) Shipping (3) Shipping (6) Shipping (2) Shipping (6**)

R640 Shipping (3) Shipping (3)

T640 Shipping (2)

T550 Shipping(2) Shipping(2) Shipping (5) Shipping (5)

XR2 Shipping (1)

XE2420 Shipping (2) Shipping (2) Shipping (4)

1 – XE8545, DSS8440 are set configs

2 – subject to change
3 - R750XA at a minimum requires 2GPUs to be installed at the factory
(qty) - max number of GPUs allowed, maximum number of GPUs allowed might differ in different configurations on the same platform
Version: August 2022

© 2022 Dell Technologies Inc. or its subsidiaries. All Rights Reserved.

Dell, EMC, and other trademarks are trademarks of Dell Inc. or its subsidiaries.
1 Other trademarks may be trademarks of their respective owners.
 GPUs on supported platforms

GPU
Memory Memory Max Power Slot Auxiliary
Brand Model GPU Memory Graphic Bus/ System Interface Interconnect Bandwidth Height/Lengt Workload1
ECC Bandwidth Consumption Width Cable
h
AMD MI210 64 GB HBM2e Y 1638 GB/sec 300W PCIe Gen4x16/ Infinity Fabric Link bridge 64 GB/sec (PCIe 4.0) DW FHFL CPU 8 pin HPC/Machine learning training
AMD MI100 32 GB HBM2 Y 1228 GB/sec 300W PCIe Gen4x16 64 GB/sec (PCIe 4.0) DW FHFL PCIe 8 pin HPC/Machine learning training
Nvidia A100 80 GB HBM2 Y 2039 GB/sec 500W NVIDIA NVLink 600 GB/sec (3rd Gen NVLink) N/A N/A N/A HPC/AI/Database Analytics
Nvidia A100 40 GB HBM2 Y 1555 GB/sec 400W NVIDIA NVLink 600 GB/sec (3rd Gen NVLink) N/A N/A N/A HPC/AI/Database Analytics
Nvidia A100 80 GB HBM2e Y 1935 GB/sec 300W PCIe Gen4x16/ NVLink bridge8 64 GB/sec5 (PCIe 4.0) DW FHFL CPU 8 pin HPC/AI/Database Analytics
Nvidia A30 24 GB HBM2 Y 933 GB/sec 165W PCIe Gen4x16/ NVLink bridge8 64 GB/sec5 (PCIe 4.0) DW FHFL CPU 8 pin mainstream AI
8 5
Nvidia A40 48 GB GDDR6 Y 696 GB/sec 300W PCIe Gen4x16/ NVLink bridge 64 GB/sec (PCIe 4.0) DW FHFL CPU 8 pin Performance graphics/VDI
Nvidia A16 64 GB GDDR6 Y 800 GB/sec 250W PCIe Gen4x16 64 GB/sec (PCIe 4.0) DW FHFL CPU 8 pin VDI
Nvidia A2 16 GB GDDR6 Y 200 GB/sec 60W PCIe Gen 4x8 32 GB/sec (PCIe 4.0) SW HHHL N/A Inferencing/Edge/VDI
Nvidia A2 (v2) 16 GB GDDR6 Y 200 GB/sec 60W PCIe Gen 4x8 32 GB/sec (PCIe 4.0) SW HHHL N/A Inferencing/Edge/VDI
Nvidia A2 16 GB GDDR6 Y 200 GB/sec 60W PCIe Gen 4x8 32 GB/sec (PCIe 4.0) SW FHHL N/A Inferencing/Edge/VDI
Nvidia A2 (v2) 16 GB GDDR6 Y 200 GB/sec 60W PCIe Gen 4x8 32 GB/sec (PCIe 4.0) SW FHHL N/A Inferencing/Edge/VDI
Nvidia A10 24 GB GDDR6 Y 600 GB/sec 150W PCIe Gen4x16 64 GB/sec (PCIe 4.0) SW FHFL PCIe 8 pin mainstream graphics/VDI
Nvidia M10 32 GB GDDR5 N 332 GB/sec 225W PCIe Gen3x16 32 GB/sec (PCIe 3.0) DW FHFL PCIe 8 pin VDI
Nvidia T4 16 GB GDDR6 Y 300 GB/sec 70W PCIe Gen3x16 32 GB/sec (PCIe 3.0) SW HHHL N/A Inferencing/Edge/VDI
Nvidia T4 16 GB GDDR6 Y 300 GB/sec 70W PCIe Gen3x16 32 GB/sec (PCIe 3.0) SW FHHL N/A Inferencing/Edge/VDI
Nvidia A100 40 GB HBM2 Y 1555 GB/sec 250W PCIe Gen4x16/ NVLink bridge8 64 GB/sec5 (PCIe 4.0) DW FHFL CPU 8 pin HPC/AI/Database Analytics
Nvidia V100S 32 GB HBM2 Y 1134 GB/sec 250W PCIe Gen3x16 32 GB/sec (PCIe 3.0) DW FHFL CPU 8 pin HPC/AI/Database Analytics
Nvidia V100 32 GB HBM2 Y 900 GB/sec 250W PCIe Gen3x16 32 GB/sec (PCIe 3.0) DW FHFL CPU 8 pin HPC/AI/Database Analytics
Nvidia V100 16 GB HBM2 Y 900 GB/sec 250W PCIe Gen3x16 32 GB/sec (PCIe 3.0) DW FHFL CPU 8 pin HPC/AI/Database Analytics
Nvidia V100 32 GB HBM2 Y 900 GB/sec 300W NVIDIA NVLink 300 GB/sec (2nd Gen NVLink) N/A N/A N/A HPC/AI/Database Analytics
Nvidia V100 16 GB HBM2 Y 900 GB/sec 300W NVIDIA NVLink 300 GB/sec (2nd Gen NVLink) N/A N/A N/A HPC/AI/Database Analytics
Nvidia RTX6000 24 GB GDDR6 Y 624 GB/sec 250W PCIe Gen3x16/ NVLink bridge3 32 GB/sec3 (PCIe 3.0) DW FHFL CPU 8 pin VDI/ Performance Graphics
Nvidia RTX8000 48 GB GDDR6 Y 624 GB/sec 250W PCIe Gen3x16/ NVLink bridge3 32 GB/sec3 (PCIe 3.0) DW FHFL CPU 8 pin VDI/ Performance Graphics
Nvidia P100 16 GB HBM2 Y 732 GB/sec 300W NVIDIA NVlink 160 GB/sec (1st Gen NVLink) N/A N/A N/A HPC/AI/Database Analytics
Nvidia P100 16 GB HBM Y 732 GB/sec 250W PCIe Gen3x16 32 GB/sec (PCIe 3.0) DW FHFL CPU 8 pin HPC/AI/Database Analytics
Nvidia P100 12 GB HBM2 Y 549 GB/sec 250W PCIe Gen3x16 32 GB/sec (PCIe 3.0) DW FHFL CPU 8 pin HPC/AI/Database Analytics
Nvidia P40 24 GB DDR5 N 346 GB/sec 250W PCIe Gen3x16 32 GB/sec (PCIe 3.0) DW FHFL CPU 8 pin HPC/AI/Database Analytics

1
suggested ideal workloads, but can be used for other workloads
2
Different SKUs are mentioned because different platforms might support different SKUs. This sheet doesn't specifically call out platform-SKU associations
3
upto 100GB/sec when RTX NVLink bridge is used, RTX NVLink bridge is only supported on T640
4
Structural Sparsity enabled
5
upto 600GB/sec for A100 when NVLink bridge is used, upto 200GB/sec for A30 when NVLink bridge is used, upto 112.5GB/sec for A40 when NVLink bridge is used
6
Peak performance numbers shared by Nvidia or AMD for MI100
7
Refer to Max#GPUs on supported platforms tab for detail support on Rome vs Milan processors
8
A100 w/Nvlink bridge is supported on R750XA and DSS8440, A40 w/Nvlink bridge is supported on R750XA, DSS8440 and T550, A30 w/NVLink bridge is supported on
R750XA and T550
DW - Double Wide, SW - Single Wide, FH- Full Height, FL - Full Length, HH - Half Height, HL - Half Length

© 2022 Dell Technologies Inc. or its subsidiaries. All Rights Reserved.

Dell, EMC, and other trademarks are trademarks of Dell Inc. or its subsidiaries.
Aguust 2022 2 Other trademarks may be trademarks of their respective owners.