cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Search instead for 
Did you mean: 

4th Gen AMD EPYC™ CPUs Empower Leadership SAP® Sales & Distribution (SAP SD) 2-Tier Performance

raghu_nambiar
Staff
Staff
2 0 3,316
‎04-08-2024 10:29 AM

4th Gen AMD EPYC™ processors continue to redefine data center performance, power efficiency, and total cost of ownership through relentless innovation. This dual focus on performance and efficiency underscores the AMD commitment to empowering businesses with cutting-edge solutions for their data center needs. Presently, the robust AMD EPYC ecosystem comprises over 250 distinct server designs and more than 800 unique cloud instances. AMD EPYC processors hold over 300 world records for performance across various benchmarks, encompassing Business applications, Technical Computing[1], Data Management, Data Analytics, Digital Services, Media and Entertainment, and Infrastructure Solutions.

 

SAP Sales and Distribution (SAP SD) is a pivotal logistics module within SAP ERP (Enterprise Resource Planning) software. This module plays a crucial role in storing and overseeing critical business data across four primary components:

  • Organization Structure: SAP SD manages the organizational setup within the software by defining various units, divisions, and departments involved in the sales and distribution processes.
  • Master Data: SAP SD maintains essential master data that includes both customer information (such as customer profiles, contact details, and transaction history) and material data (such as product specifications, inventory levels, and pricing details).
  • Business Processes: SAP SD orchestrates end-to-end sales cycles, encompassing activities like order processing, pricing, delivery, billing, and payment handling. It ensures seamless coordination and execution of sales-related operations.
  • Reporting: SAP SD facilitates comprehensive reporting capabilities that enable users to generate insightful analyses and reports based on sales and distribution data. These reports provide valuable insights into sales performance, customer trends, inventory management, and revenue generation.

 

Overall, SAP SD plays a vital role in streamlining sales and distribution operations, enhancing efficiency, and enabling informed decision-making within organizations leveraging SAP ERP software. The SAP-SD 2-Tier benchmark evaluates hardware performance by measuring database performance in SAP Application Performance Standard units (SAPS). SAPS is a hardware-independent unit that quantifies system performance within the SAP environment. SAPS are derived from the Sales and Distribution (SD) benchmark and reflect the system's capacity to handle SAP workloads. During SAP benchmark testing, vendors use their standard methodology to determine the system's capacity to support SD users. Each module within the benchmark carries a weightage that converts users into a Normalized SD (NSD) number.  SAPS is calculated from the NSD. SAPS results from the SAP SD benchmark help SAP customers size their SAP systems and plan their infrastructure footprint. This benchmark enables customers to conduct Proof-of-Concepts (POCs), anticipate future growth, and compare platforms to select the optimal hardware configuration for their SAP solution.

 

On Bare Metal

The compute-intensive nature of the SAP SD workload make 4th Gen AMD EPYC processors (9004 series) an optimal choice for deploying SAP applications on bare metal servers. These processors maximize performance by harnessing significant improvements in Instructions per Cycle (IPC), faster memory access, increased L3 cache sizes, and higher core density compared to prior-generation AMD EPYC processors.

Figure 1 demonstrates the performance improvements attained with "top of stack" processor SKUs throughout the four generations of general-purpose AMD EPYC processors. Additionally, it highlights the consistent outperformance of 2nd Gen AMD EPYC processors and newer generations compared to corresponding generations of Intel® Xeon® processors. Notably, 4th Gen AMD EPYC processors exceed the performance of 5th Gen Intel® Xeon® processors by 53%.[2]

 

fig_1.jpg

Figure 1: Generational and competitive SAP SD 2-Tier performance uplifts on 2P bare-metal systems (click image for larger view)

 

In the Cloud

Looking to deploy SAP in the cloud? AMD EPYC processors offer comprehensive support here as well. The left side of Figure 2 illustrates significant performance enhancements across 2nd, 3rd, and 4th Gen AMD EPYC processors on Microsoft Azure and Amazon EC2 cloud instances. The right side of Figure 2 shows how an Amazon EC2 m7a.48xlarge instance powered by 4th Gen AMD EPYC processors outperforms a comparable Amazon EC2 m7i.48xlarge instance powered by Intel Xeon Platinum 8488C processors.[3]

 

raghu_nambiar_2-1712589789272.jpeg

Figure 2: Generational SAP SD 2-Tier performance on cloud instances (click image for larger view)

 

Comparing SAP-SD Performance with SPEC CPU® 2017 (Curiosity Analysis)

Many individuals strive to relate how the SPEC CPU® 2017 benchmark is truly representative of real world enterprise applications. The SPEC CPU® 2017 benchmark holds significant industry prominence because its performance measurements thoroughly stress a system's processor, memory subsystem, and compiler. These measurements enable users to compare the performance of various systems effectively. SPEC CPU 2017 comprises four suites: SPECspeed® 2017 Integer, SPECspeed® 2017 Floating Point, SPECrate® 2017 Integer, and SPECrate® 2017 Floating Point. SPECspeed metrics assess the time taken to complete a workload, while SPECrate metrics gauge the amount of work accomplished per unit of time.

Among these metrics, SPECrate 2017 Integer demonstrates a strong correlation with the SAP-SD 2-Tier Benchmark Users metric, as depicted in Figure 3. This correlation is particularly valuable for SAP SD 2-Tier sizing because it allows deriving reliable SAP-SD 2-Tier Benchmark Users estimates based on the SPECrate 2017 Integer metric results published for every EPYC SKU.[4]

 

raghu_nambiar_1-1712589789265.jpeg

 Figure 3: SPECrate® 2017_int-base performance tracks with SAP SD 2-Tier performance (click image for larger view)

 

Conclusion

The performance prowess of AMD EPYC processors shines through in the SAP SD benchmark results, whether deployed on bare metal or in cloud environments. Equipped with 4th Gen AMD EPYC processors, these systems boast cutting-edge features, including "Zen 4" cores fabricated on 5nm process technology,  support up to 12 channels of DDR5 memory with speeds reaching up to 4800GHz and up to 128 (1P) or 160 (2P) lanes of PCIe® Gen5, doubling the transfer rate of PCIe Gen4. AMD actively collaborates with independent software vendors (ISVs) to drive software optimizations that leverage the unique AMD EPYC architecture, unlocking superior performance compared to other x86 platforms. Guidance on optimal CPU tuning practices for AMD EPYC processors is readily available via the AMD Documentation Hub, housing an extensive library of AMD EPYC Tuning Guides.

References

  1. GD-204: “Technical Computing” or “Technical Computing Workloads” as defined by AMD can include: electronic design automation, computational fluid dynamics, finite element analysis, seismic tomography, weather forecasting, quantum mechanics, climate research, molecular modeling, or similar workloads.
  2. For Figure 1:
  3. For Figure2:
  4. For Figure 3:
  5. GD-183: AMD Infinity Guard features vary by EPYC™ Processor generations. Infinity Guard security features must be enabled by server OEMs and/or Cloud Service Providers to operate. Check with your OEM or provider to confirm support of these features. Learn more about Infinity Guard at https://www.amd.com/en/technologies/infinity-guard.
About the Author
Raghu Nambiar currently holds the position of Corporate Vice President at AMD, where he leads a global engineering team dedicated to shaping the software and solutions strategy for the company's datacenter business. Before joining AMD, Raghu served as the Chief Technology Officer at Cisco UCS, instrumental in driving its transformation into a leading datacenter compute platform. During his tenure at Hewlett Packard, Raghu made significant contributions as an architect, pioneering several groundbreaking solutions. He is the holder of ten patents, with several more pending approval, and has made extensive academic contributions, including publishing over 75 peer-reviewed papers and 20 books in the LNCS series. Additionally, Raghu has taken on leadership roles in various industry standards committees. Raghu holds dual Master's degrees from the University of Massachusetts and Goa University, complemented by completing an advanced management program at Stanford University.