In-memory computing has become essential to power applications and analytic solutions that capture, process, and analyze enormous sizes of diverse data in real time. Yet many organizations are struggling to find hardware configurations that satisfy their need for affordable, real-time data processing.
SAP has always made it our mission to democratize in-memory computing for businesses of any size and to address a wide variety of scenarios. To make this a reality we continue to deliver new innovative technology. But this requires a consistent commitment to co-innovate with a large ecosystem of partners to make in-memory computing more efficient, accessible, and cost-effective.
SAP has always made it its mission
to democratize in-memory computing
SAP has joined forces with Google and Intel to deliver real-time data processing for vastly larger amounts of data at a lower TCO. Now, companies can leverage their growing data volumes to impact business outcomes.
The support for Intel® Optane™ DC persistent memory that we introduced in SAP HANA 2.0 SPS 03 will play a key role allowing us to deliver this added value to customers. The unique in-memory architecture of SAP HANA allowed us to easily optimize the platform for the most efficient use of persistent memory.
Our close partnership with Google is allowing us to take the next step of announcing plans to bring this powerful hardware innovation to the Google Cloud Platform when Intel Optane DC persistent memory becomes available later this year. Since Intel’s persistent memory modules each support capacities of 512 GB (4x greater than traditional 128 GB DDR4 DIMM sizes), we will be able to offer end customers Google Compute Engine VMs fueled by future Intel Xeon Scalable processors with significantly larger memory availability than possible in the past, broadening the range of use cases our customers can implement on the Google Cloud Platform.
Is Persistent Memory Right for Your Business?
The upcoming Intel Optane DC persistent memory combines the best features of both dynamic random-access memory (DRAM) and disk-based storage, enabling fast access for larger amounts of data and the ability to preserve data even after a system shutdown.
Persistent memory will deliver less latency when delivering data to each CPU core’s registers compared to solid-state drives (SSDs), accelerating access to your warm data. Furthermore, systems that combine DRAM and persistent memory will deliver a higher overall memory capacity and a lower cost per GB, compared to those with DRAM only. This will allow you to keep more data in memory with a lower overall TCO.
And, the advantages of using persistent memory do not stop here. For example, as detailed in Chris Hallenbeck’s blog, an internal benchmark of a 6TB SAP HANA installation using Intel Optane DC persistent memory has shown a 12.5 times improvement in SAP HANA startup time. This is possible because the data remains available in memory after a shutdown and does not need to be reloaded from SSDs. With shorter downtime, you can instantly improve the reliability of your data-driven operations and ensure continuous data access, further lowering the total cost of ownership (TCO) of your SAP HANA landscape.
If you believe your SAP S/4HANA installation, SAP Business Warehouse, or custom applications built on SAP HANA could benefit from in-memory access to larger amounts of data and faster startup-times, you should give a serious look at the upcoming Google Compute Engine VMs with Intel Optane DC persistent memory.
How to Get Started?
Google Cloud instances with Intel Optane DC Persistent Memory for SAP HANA will be available later this year aligned with Intel’s delivery of this new memory technology. To learn more, please fill out this form.
To learn more about leveraging persistent memory in SAP HANA landscapes and SAP’s partnership with Google and Intel visit:
- The SAP HANA in-memory database page on sap.com
- SAP and Google Cloud
- Intel and Google Cloud Platform