Today Intel introduced its 3rd Gen Intel® Xeon™ Scalable processors and additions to the software portfolio, which deliver built-in AI acceleration, persistent memory leadership, and trusted Intel architecture to meet the growing data centric needs of our customers. With the introduction of Intel Optane persistent memory series 200, our customers will benefit from increased performance, higher memory bandwidth, improved app performance and optimized thermals.
In my conversations with our customers I hear how they are prioritizing and accelerating business transformation initiatives to gain insights from data faster, reduce infrastructure and operating costs, as well as improve performance. Customers need to move, store and process data quickly and efficiently. DRAM offers fast access, but is limited in capacity, expensive, and volatile. Block storage is large, cheap, and persistent, but slow to access. Intel Optane persistent memory was designed to fill the gaps in the memory and storage hierarchy, bringing large scale memory closer to the CPU.
Customer Benefits
When we introduced PMem last year we expected memory-intensive workloads like AI/analytics, databases, virtualization environments, and content delivery networks would benefit from PMem. Customers using PMem, including Baidu, GPORTAL, Kuaishou Technology, Siemens AG and SoftBank tell us those benefits are materializing; they’re seeing lower operational costs, increased utilization of CPU, faster time to insights, less downtime and better workload performance.
Industry adoption is another area we’re seeing increased traction, including oil & gas, health sciences, manufacturing, education and retail. These join enterprise, cloud and CoSPs and financial services where POC momentum and adoption for PMem are already strong. We have over 350 POC’s underway with over 85% conversion rate to deployments, with more than 50% Fortune 500 companies, five of the top seven cloud service providers, and more than 40 NW CSP and CoSPs.
A Growing Ecosystem
A strong ecosystem is critical to support customers as they embrace new technologies, ours is vibrant and growing. ISV and OS partners are optimizing their software to take advantage of the unique capabilities of PMem. Newcomers like Formulus Black and MemVerge are developing solutions that use APIs to deliver data durability and improved performance without code modification. We’ve seen an increase in solutions supporting business critical infrastructure, from analytics applications like Apache Spark, to hypervisors like VMware ESXi, to in-memory databases like SAP HANA and Aerospike. My last example is the emergence of computing appliances with PMem built in. Oracle Exadata X8M is optimized for database workloads; provides standardized hardware, easily deployed without unique configurations, runs existing applications, and delivers performance improvements.
In closing I want to highlight Intel’s recent win of the Gold Stevie® Award for Achievement in Product Innovation and highlights for the 200 series, which will deliver better performing workloads and faster time to insights.
- Massive memory capacity – up to 4.5TB per socket, designed for larger in-memory datasets and demanding workloads
- Data accessibility – keep larger datasets in memory to support near real-time analysis. Intel Optane persistent memory 200 series delivers an average 25% higher memory bandwidth compared to the first generation1
- Latency – faster access to data stored in memory, where you need it. Unlike conventional DDR memory, Intel Optane persistent memory retains its data even if power is unexpectedly lost, and provides over 225X faster CPU access to persistent data than reading from a mainstream NAND SSD2
- Availability – Deployable now with 3rd Gen Intel Xeon Scalable processors, Intel Optane persistent memory 200 series is targeted for SAP HANA deployments. The 200 series will also be supported with the Ice Lake processor upon its availability.
Visit intel.com/optanepersistentmemory to learn more and follow me on Twitter at @Kristie_L_Mann.
1 Baseline: 1-node, 1x Intel Xeon 8280L 28C @ 2.7GHz processor on Neon City with Single PMem module config (6x32GB DRAM; 1x{128GB,256GB,512GB} Intel Optane PMem 100 Series module at 15W) ucode Rev: 04002F00 running Fedora 29 kernel 5.1.18-200.fc29.x86_64,and MLC ver 3.8 with App-Direct. Source: 2020ww18_CPX_BPS_DI. Tested by Intel, on 27 Apr 2020. New configuration: 1-node, 1x Intel Xeon pre-production CPX6 28C @ 2.9GHz processor on Cooper City with Single PMem module config (6x32GB DRAM; 1x{128GB,256GB,512GB} Intel Optane PMem 200 Series module at 15W), ucode pre-production running Fedora 29 kernel 5.1.18-200.fc29.x86_64,and MLC ver 3.8 with App-Direct. Source: 2020ww18_CPX_BPS_BG. Tested by Intel, on 31 Mar 2020.
2 Intel Optane persistent memory idle read latency of 340 nanoseconds. Intel SSD DC P4610 Series TLC NAND solid state drive idle read latency of 77 microseconds.
Kristie Mann is VP/GM for the IPU Business Unit in Intel’s Network and Edge Group. She focuses on developing the ecosystem for networking infrastructure and storage offload products. She was previously VP Product Management for Optane Products in Intel’s Datacenter and AI Group. Before joining Intel, she was Sr Manager R&D Hardware at HPE, where she was responsible for delivering mechanical hardware and thermal systems development for workstation lines that produced $1.2B of revenue annually. She earned a BSME at Georgia Tech and an MBA at Duke University. She has been a presenter at Tech Field Day, Global Stac Live and SmartNICs Summit and has been interviewed or quoted in many leading technology media such as Blocks & Files, Futurum Research and InfoWorld.