Enabling more affordable or bigger memory solutions for data centers.
Transparently Integrate SSDs Into the Memory Subsystem
Intel® Memory Drive Technology is a revolutionary software that extends system memory transparently. A great option for legacy platforms, the Intel® Optane™ Solid State Drive (SSD) is paired with Intel® Memory Drive Technology to transparently integrate the SSD into the memory subsystem. Without any further changes, the software makes the SSD appear like DRAM to the OS and applications. For 2nd Gen Intel® Xeon® Scalable platforms, Intel® Optane™ persistent memory is the best solution to increase memory capacity and persistence, and is optimized for in-memory databases like SAP HANA.
The combination of cost-efficiency and increased capacity means enterprises can break through today’s memory limits, enabling new possibilities—like accessing higher-capacity, in-memory datasets to deliver better, faster analytics insight. As an example, cloud providers can reduce capital cost for memory when enabled to oversubscribe workloads with greater overall capacity. Or, high-performance computing centers can increase large memory datasets to improve research and scientific results, and test new simulations quickly and cost-efficiently.
Deliver more aﬀordable memory pools by displacing a portion of DRAM. By pairing the DRAM with the high-performing non-volatile memory of the Intel® Optane™ SSD, data centers can more cost-eﬀectively execute workloads that require high-end memory configurations with much lower DRAM capacity installed, saving on both Capex, and Opex costs.
Grow your memory footprint beyond the DRAM capacity. Together, the DRAM and the Intel® Optane™ SSD emulate a single volatile memory pool. Intel® Memory Drive Technology intelligently determines where data should be located in the pool to maximize performance, enabling servers to deliver performance across many workloads— even when DRAM is only supplying one-third to one-tenth of the memory pool capacity.
Extending memory configurations that allow containers and virtual machines to utilize more operating system memory on Linux. This can improve workload density opportunities.
Spark* is the most popular Data Processing Engine for analytics. It comes with a rich set of libraries to process traditional structured datasets, unstructured/streaming data and complex analytics for machine learning and AI.