0% found this document useful (0 votes)
102 views4 pages

Ansys 2023 R2 - GPU Accelerator Capabilities

The document discusses GPU accelerator capabilities in ANSYS applications. It provides details on the applications that support GPU acceleration, the GPU cards that have been tested with each application, and the operating systems and platforms tested.

Uploaded by

NH Kim
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
102 views4 pages

Ansys 2023 R2 - GPU Accelerator Capabilities

The document discusses GPU accelerator capabilities in ANSYS applications. It provides details on the applications that support GPU acceleration, the GPU cards that have been tested with each application, and the operating systems and platforms tested.

Uploaded by

NH Kim
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

**************************GPU Accelerator Capabilities *

***************************Release 2023 R2

* Used in support of the CPU to process certain calculations and key solver computations for faster performance during a solution.
- Acceleration can be used for both shared-memory parallel processing (shared-memory Ansys) and distributed-memory parallel processing (Distributed Ansys).
- Acceleration is available for both Windows and Linux.

Support by Application
AVxcelerate supports NVIDIA's CUDA-enabled series workstation and server cards.

Ansys EMIT and EMIT Classic support NVIDIA CUDA-enabled workstation, data center and server cards.

Fluent supports NVIDIA's CUDA-enabled workstation, data center and server cards.

HFSS Frequency-domain and Time-domain solvers support NVIDIA CUDA-enabled workstation, data center, and server cards.

HFSS SBR+ solver supports NVIDIA CUDA-enabled workstation, data center, and server cards.

ICEPAK supports NVIDIA's CUDA-enabled workstation, data center, and server cards.

Maxwell solvers support NVIDIA CUDA-enabled workstation, data center, and server cards.

Mechanical APDL supports the AMD Instinct MI Series Accelerators and NVIDIA's CUDA-enabled workstation, data center, and server cards. When using the sparse solver or eigen solvers based on the sparse solver with NVIDIA
cards additional considerations apply (please consult the ANSYS installation guide for details).

Polyflow supports NVIDIA's CUDA-enabled workstation, data center, and server cards.

Cards Tested **
The following cards have been tested by ANSYS, Inc.

Application Manufacturer Card / GPU Tested Platform Tested Operating System Version Notes

Nvidia GV100 Linux x64 Ubuntu 20.04

P5200 Windows x64 Windows 10

RTX 5000 Windows x64 Windows 10

RTX 6000 Windows x64 Windows 10

Windows 11

Linux x64 CentOS 7.9


AVxcelerate
Ubuntu 20.04

RTX 8000 Linux x64 CentOS 7.8

RTX A5000 Windows x64 Windows 10

Linux x64 Ubuntu 20.04

RTX A5500 Windows x64 Windows 11

RTX A6000 Linux x64 Ubuntu 20.04


Application Manufacturer Card / GPU Tested Platform Tested Operating System Version Notes

Nvidia A100 Windows x64 Windows Server 2019

A6000 Windows x64 Windows Server 2019

GP100 Windows x64 Windows 10

EMIT and P40 Windows x64 Windows Server 2019

EMIT Classic P100 Windows x64 Windows Server 2022

P4000 Windows x64 Windows 10

RTX 6000 Windows x64 Windows Servers 2019

V100 Windows x64 Windows Server 2019

Nvidia A100 Linux x64 CentOS 7.9

P4000 Linux x64 SLES 15 SP4

Fluent RTX 4000 Windows x64 Windows 11

RTX 6000 Windows x64 Windows 11

Linux x64 SLES 12 SP5

Nvidia A100 Windows x64 Windows Server 2019

Windows Server 2022

Linux x64 Ubuntu 20.04

GV100 Linux x64 Ubuntu 20.04

P40 Windows x64 Windows Server 2022


HFSS
(Frequency-domain P100 Windows x64 Windows Server 2022
solver, Time-domain Linux x64 CentOS 7.9
solver)
RTX A6000 Windows x64 Windows Server 2019

RTX 6000 Windows x64 Windows Server 2019

Linux x64 Red Hat 8.5

V100 Windows x64 Windows Server 2019

Linux x64 Ubuntu 20.04


Application Manufacturer Card / GPU Tested Platform Tested Operating System version Notes

Nvidia A100 Windows x64 Windows Server 2019

Windows Server 2022

Linux x64 Ubuntu 20.04

GV100 Linux x64 Ubuntu 20.04

P40 Windows x64 Windows Server 2022

P100 Windows x64 Windows Server 2022


HFSS SBR+ solver
Linux x64 CentOS 7.9

RTX 6000 Windows x64 Windows Server 2019

Linux x64 Red Hat 8.5

RTX A6000 Windows x64 Windows Server 2019

V100 Windows x64 Windows Server 2019

Linux x64 Ubuntu 20.04

Nvidia 8000P-8Q Windows x64 Windows 10

A2000 Windows x64 Windows 10

GV100 Linux x64 Ubuntu 20.04

K40m Windows x64 Windows Server 2019

M4000 Windows x64 Windows 10

Icepak Linux x64 CentOS 7.9

P40 Windows x64 Windows Server 2022

P100 Linux x64 CentOS 7.9

RTX 6000 Linux x64 Red Hat 8.5

V100 Windows x64 Windows Server 2019

Linux x64 Ubuntu 20.04

Nvidia A100 Windows x64 Windows Server 2019

Windows Server 2022

Linux x64 Ubuntu 20.04

GV100 Linux x64 Ubuntu 20.04

P40 Windows x64 Windows Server 2022

P100 Windows x64 Windows Server 2022


Maxwell
Linux x64 CentOS 7.9

RTX 6000 Windows x64 Windows Server 2019

Linux x64 Red Hat 8.5

RTX A6000 Windows x64 Windows Server 2019

V100 Windows x64 Windows Server 2019

Linux x64 Ubuntu 20.04


Application Manufacturer Card / GPU Tested Platform Tested Operating System version Notes

AMD MI100 Linux x64 Red Hat 8.6

MI210 Linux x64 Red Hat 8.7

Nvidia A100 Windows x64 Windows Server 2019

Linux x64 CentOS 7.9

Mechanical APDL Red Hat 7.9

H100 Windows x64 Windows Server 2022

Linux x64 CentOS 7.9

P100 Windows x64 Windows 10

Linux x64 CentOS 7.9

V100 Linux x64 CentOS 7.9

Nvidia A100 (dual) Windows x64 Windows Server 2022

GV100 Windows x64 Windows 11

P4000 Linux x64 Ubuntu Server 20.04

P6000 (dual) Windows x64 Windows 10

RTX 4000 Windows x64 Windows 10


Windows 11
Polyflow Linux x64 Red Hat 7.9
Red Hat 8.6
SLES 12.5
SLES 15.4
Ubuntu Server 22.04
RTX A4000 Windows x64 Windows 11
Linux x64 SLES 15.4

** The performance benefit of using a GPU Accelerator will depend on the card selected and the overall system configuration.

You might also like