Reduce Costs and Gain IT Efficiencies for Key Workloads Such as SAP HANA with Intel® Optane™ Persistent Memory

Meet customer expectations for high-performance SAP HANA infrastructure that accelerates innovation and time to insight, while simultaneously lowering AWS’ costs.

Enterprise Customers of the Public Cloud Face Three Main Challenges:

Mehr anzeigen Weniger anzeigen

To meet these challenges, many enterprises plan to deploy SAP S/4 HANA. And the good news for AWS is that SAP expects a significant acceleration of cloud growth over the coming years.1

AWS has the opportunity to deliver SAP HANA solutions that meet enterprise customer demands for high-performance data processing and accelerated time to insight, for the lowest possible total cost of ownership (TCO).

One option is to integrate Intel® Optane™ persistent memory (PMem), an innovative memory technology that delivers a unique combination of affordable large capacity and support for data persistence. By integrating it into AWS’ infrastructure you can help customers innovate faster, reduce TCO, and increase IT efficiency.

Here We Examine Some of the Key Benefits:

Benefit

Since customers have the ability to write queries on bigger datasets and combine multiple workloads on the same system, AWS can help them innovate faster with systems that integrate PMem.

Benefit

By increasing memory capacity near the CPU, PMem can help AWS to support more virtual machines (VMs) and more memory per VM for a lower TCO, compared with typical DRAM.

Proof Point

PMem in memory mode expands system memory by up to 33 percent, increasing the number of VMs by up to 36 percent compared to DDR4 DRAM only2, and lowering system hardware costs per VM by up to 30 percent3.

Benefit

By increasing memory density per server and the number of VMs per node, PMem can help AWS reduce its data center footprint by consolidating workloads onto fewer servers, reducing complexity, and simplifying management of SAP HANA workloads.

Proof Point

Based on testing from 2019, implementing a scale-up SAP HANA 2 landscape integrating PMem provided Intel IT with 52 percent more total system memory for a lower cost, compared with a scale-out landscape on a DRAM-only system4. By reducing the overall number of servers needed, Intel IT will have fewer servers to patch, land, power, and connect, resulting in time, as well as cost savings.

Learn More


Discover more benefits of Intel® Optane™ persistent memory.

Explore more resources for AWS from Intel.

Learn more

Notices and Disclaimers

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.

Performance results are based on testing as of dates shown in configurations and may not reflect all publicly available updates. See backup for configuration details. No product or component can be absolutely secure.

Intel does not control or audit third-party data. You should consult other sources to evaluate accuracy.

Intel technologies may require enabled hardware, software or service activation.

Your costs and results may vary.

Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.

Produkt- und Leistungsinformationen

1 https://www.sapinsideronline.com/blogs/cloud-continues-to-lead-sap-growth-sap-sets-aggressive-5-year-outlook/
2 Baseline Config (DRAM Only): Nodes: 1; Sockets: 2; CPU: Cascade Lake B08272L; Cores/socket, Threads/socket: 26, 52; HT: ON; Turbo: ON; BKC version: WW42'18; Intel® Optane™ persistent memory FW version: 5253; System DDR Mem Config: slots/cap/run-speed; 24 slots/32 GB/2666 MT/s; Total Memory/Node (DDR, Intel® Optane™ persistent memory) 768 GB, 0; Storage – boot: 1x Samsung PM963 M.2 960 GB; Storage application drives: 7 x Samsung PM963 M.2 960 GB, 4x Intel® SSDs S4600 (1.92 TB); Network: Intel X520SR2 (10 Gb); PCH LBG QS/PRQ-T-B2; OS: Windows Server 2019 RS5-17763; Workload & version: OLTP Cloud Benchmark. Intel® Optane™ persistent memory & DRAM Config: Nodes: 1; Sockets: 2; CPU: Cascade Lake B08272L; Cores/socket, Threads/socket: 26, 52; HT: ON; Turbo: ON; BKC version: WW42'18; Intel® Optane™ persistent memory FW version: 5253; System DDR Mem Config: slots/cap/run-speed; 12 slots/16 GB/2666 MT/s; System Intel® Optane™ persistent memory Config: slots/cap/run-speed: 8 slots/128 GB/2666 MT/s; Total Memory/Node (DDR, Intel® Optane™ persistent memory) 192 GB, 1 TB; Storage – boot: 1x Samsung PM963 M.2 960 GB; Storage application drives: 7 x Samsung PM963 M.2 960 GB, 4x Intel® SSDs S4600 (1.92 TB); Network: Intel X520SR2 (10 Gb); PCH LBG QS/PRQ-T-B2; OS: Windows Server 2019 RS5-17763; Workload & version: OLTP Cloud Benchmark. Running 4 vCPUs per VM, 32 GB memory per VM.
3Baseline Config (DRAM Only): # of systems: 1; Memory Sub System Per Socket: DRAM – 284 GB (12x32 GB); CPU SKU|# per system: 3276 (CLX, Plat, 28core)|2; Storage Description|Total Storage Cost: # of HDD/SDDs|$7,200; SW License Description|Cost per System: SW Cost (per/core or per system)|$0; Relevant Value Metric:22.00; CPU Cost: 2x8276 (CLX, Plat 28core): $17,348; Memory subsystem: Total Capacity (DRAM only): 768 GB (384 GB/ Socket): $8,993; Storage: #of HDD/SDDs: $7,200; RBOM: Chassis; PSUs; Bootdrive, etc: $1,300; SW Costs: $0; Total System Cost: $34,931. Intel® Optane™ persistent memory & DRAM Config: # of systems: 1; Memory Sub System Per Socket: 2 GB (4x128 GB DCPMM+6x16 GB DRAM, 2-2-1, Memory Mode; CPU SKU|# per system: 3276 (CLX, Plat, 28core)|2; Storage Description|Total Storage Cost: # of HDD/SDDs|$7,200; SW License Description|Cost per System: SW Cost (per/core or per system)|$0; Relevant Value Metric:22.00; CPU Cost: 2x8276 (CLX, Plat 28core): $17,348; Memory subsystem: Total Capacity (Intel® Optane™ persistent memory+DRAM): 1024 GB (512 GB/ Socket): $7,306; Storage: #of HDD/SDDs: $7,200; RBOM: Chassis; PSUs; Bootdrive, etc: $1,300; SW Costs: $0; Total System Cost: $33,244.
4 52% more data capacity at same or lower cost: Pricing guidance as of March 15, 2019. Intel does not guarantee any costs or cost reduction. Results have been estimated by Intel IT as of 3/4/2019 using internal Intel analysis or architecture simulation or modeling, and provided to you for informational purposes. Any differences in your system hardware, software or configuration may affect your actual results. Cost reduction scenarios described are intended as examples of how a given Intel- based product, in the specified circumstances and configurations, may affect future costs and provide cost savings. Circumstances will vary. Intel does not guarantee any costs or cost reduction. Scale-up configuration: 8-node SAP HANA® 2 landscape. Per node: 8-socket 2nd Generation Intel® Xeon® Platinum 8276M processors. Memory capacity per socket: 6 x 128 GB DDR4 2,133 MHz. and 6 x128 GB Intel® Optane™ DC persistent memory. Estimated total cost is $2,369,496. Estimated cost per server is $296,187 (CPU=$93,776; memory=$119,808; storage=$45,000; other=$37,603). Scale-out configuration: 21-node SAP HANA® 2 landscape. Per node: 4-socket 2nd Generation Intel® Xeon® Platinum 8276 processor. Memory capacity per socket: 12 x 64 GB DDR4 2, 133 MHz. Estimated total cost is $2,834,433. Estimated cost per server is $134,973 (CPU=$34,876; memory=$33,994; storage=$21,000; other=$45,103).