Dell Technologies: ANSYS® Performance with AMD EPYC™ 7002 Series Processors

Dell Technologies: ANSYS® Performance with AMD EPYC™ 7002 Series Processors




This article was written by Joshua Weage of the Dell EMC HPC & AI Innovation Lab in October 2019.


Introduction

This blog discusses the performance of ANSYS® CFX® and ANSYS Fluent® on the Dell EMC Ready Solution for HPC Digital Manufacturing with AMD EPYC™ 7002 series processors. This Dell EMC Ready Solution for HPC was designed and configured specifically for digital manufacturing workloads, where computer aided engineering (CAE) applications are critical for virtual product development. The Dell EMC Ready Solution for HPC Digital Manufacturing uses a flexible building block approach to HPC system design, where individual building blocks can be combined to build HPC systems which are optimized for customer-specific workloads and use cases.

The Dell EMC Ready Solution for HPC Digital Manufacturing is one of many solutions in the Dell EMC HPC solution portfolio. Please visit www.dellemc.com/hpc for a comprehensive overview of the HPC solutions offered by Dell EMC.


Benchmark System Configuration

Performance benchmarking was performed using dual-socket Dell EMC PowerEdge servers with 7001 and 7002 series AMD EPYC processors. All servers were populated with two processors and one DIMM per channel memory configuration. The system configurations used for the performance benchmarking are shown in Table 1 and Table 2. The BIOS configuration used for the benchmarking systems is shown in Table 3.

Table 1 7001 Series AMD EPYC System Configuration
Server Dell EMC PowerEdge R7425
Processor 2x AMD EPYC 7601 32-core Processors
Memory 16x16GB 2400 MTps RDIMMs
BIOS Version 1.10.6
Operating System Red Hat Enterprise Linux Server release 7.5
Kernel Version 3.10.0-862.el7.x86_64

Table 1: 7001 Series AMD EPYC System Configuration


Table 2 7002 Series AMD EPYC System Configuration

Server

Dell EMC PowerEdge C6525

Processors

2x AMD EPYC 7702 64-Core Processors

2x AMD EPYC 7502 32-Core Processors

2x AMD EPYC 7452 32-Core Processors

2x AMD EPYC 7402 24-Core Processors

Memory

16x16GB 3200 MTps RDIMMs

BIOS Version

1.0.1

Operating System

Red Hat Enterprise Linux Server release 7.6

Kernel Version

3.10.0-957.27.2.el7.x86_64

Table 2: 7002 Series AMD EPYC System Configuration


Table 3 BIOS Configuration

System Profile

Performance Optimized

Logical Processor

Disabled

Virtualization Technology

Disabled

NUMA Nodes Per Socket

4 (PowerEdge C6525 only)

Table 3: BIOS Configuration


Software Versions

Application software versions are as described in Table 4.

Table 4 Software Versions

ANSYS CFX

2019R3 with Intel MPI

ANSYS Fluent

2019R3 with IBM MPI

Table 4: Software Versions


ANSYS CFX Performance

ANSYS CFX software is a computational fluid dynamics (CFD) application recognized for its accuracy, robustness and speed with rotating machinery applications. CFD applications typically scale well across multiple processor cores and servers, have modest memory capacity requirements, and typically perform minimal disk I/O while in the solver section. However, some simulations, such as large transient analysis, may have greater I/O demands. The benchmark results reported here are single-server performance results, with the benchmark run using all processor cores available in the server. Figure 1 shows the measured performance of the standard CFX benchmarks using CFX 2019R3. The performance for each benchmark is measured using the solver elapsed time.


Figure 1: ANSYS CFX Single Server Performance

The results in Figure 1 are plotted relative to the performance of a single server configured with AMD EPYC 7601 processors. Larger values indicate better overall performance. These results show the performance advantage available with 7002 series AMD EPYC processors. The 32-core AMD EPYC 7452 and 7502 processors provide very good performance for these benchmarks. The 64-core AMD EPYC 7702 provides a significant performance advantage over the 32-core processors, particularly for the LeMans and Pump benchmark cases.


ANSYS Fluent Performance

ANSYS Fluent is a computational fluid dynamics (CFD) application commonly used across a very wide range of CFD and multi-physics applications. CFD applications typically scale well across multiple processor cores and servers, have modest memory capacity requirements and typically perform minimal disk I/O while in the solver section. However, some simulations may have greater I/O demands, such as large transient analysis.

Fluent benchmark performance is measured using the Solver Rating metric which is the number of 25 iteration solves that can be completed in a day. That is, (total seconds in a day)/(25 iteration solve time in seconds). A higher value represents better performance. The benchmark results reported here are single-server performance results, with the benchmark run using all processor cores available in the server. Figure 2 shows the measured performance for six of the ANSYS Fluent benchmarks.

Figure 2: ANSYS Fluent Single Server Performance

Figure 2 presents the results for six standard Fluent benchmark cases plotted relative to the performance of a single server configured with AMD EPYC 7601 processors. Larger values indicate better overall performance. These results show the performance advantage available with 7002 series AMD EPYC processors. The 32-core AMD EPYC 7452 and 7502 processors provide good performance for these benchmarks. Per server, the 64-core AMD EPYC 7702 provides a significant performance advantage over the 32-core processors for these benchmark cases.


Conclusion

The results presented in this blog show that 7002 series AMD EPYC processors offer a significant performance improvement for ANSYS CFX and ANSYS Fluent relative to 7001 series AMD EPYC processors.




Article ID: SLN319367

Last Date Modified: 11/05/2019 07:35 AM


Rate this article

Accurate
Useful
Easy to understand
Was this article helpful?
Yes No
Send us feedback
Comments cannot contain these special characters: <>()\
Sorry, our feedback system is currently down. Please try again later.

Thank you for your feedback.