… SuperMicro Portfolio With Optane …
And 2nd gen Intel Xeon scalable rocessors
This is a Press Release edited by StorageNewsletter.com on April 9, 2019 at 2:31 pmSuper Micro Computer, Inc. announced optimized support for Intel Corp.‘s 2nd Generation Xeon Scalable processors on its entire portfolio of X11 servers, storage systems and server building block solutions.
The company has optimized its X11 portfolio to leverage the performance advantages of the 2nd Gen Xeon Scalable processors (formerly codenamed Cascade Lake) and accompanying innovations including Intel Optane DC persistent memory to increase memory capacity and affordability and Intel Deep Learning Boost to enable more efficient AI acceleration. With these company’s Resource-Saving servers, customers can expect better data center performance (35% faster), better TCO (up to 50% reduction) and less impact on the environment.
“At Supermicro, we are strongly committed to providing customers the newest technologies first to help drive leading performance and improved TCO with higher server performance at the same price level,” said Charles Liang, president and CEO, Supermicro. “With the industry’s strongest and broadest product line, our designs deliver world record performance and take full advantage of 2nd Gen Intel Xeon Scalable Processors’ new features such as 10% faster DIMMs, 50% more memory capacity, faster CPU frequency up to 3.8GHz, and Intel Optane DC persistent memory. Furthermore, our all-flash NVMe 1U storage servers support all of the next-generation flash technologies including NF1 and EDSFF form factor SSDs to deliver the highest storage bandwidth, best IO/s performance, NVMe over Fabrics support and ease of maintenance. We already have over a dozen high-profile customers reporting exciting performance gains using these new 2nd Gen Intel Xeon Scalable processors on a variety of applications.“
“Systems with 2nd Gen Intel Xeon Scalable processors and Intel Optane DC persistent memory at their foundation provide the performance, capabilities, and innovations that accelerate application performance across compute, storage and network workloads,” said Lisa Spelman, VP and GM, Xeon processors and data center marketing, Intel. “Supermicro is always quick-to-market with our latest technology, and a leader in delivering ready-to-adopt, workload-optimized Intel Select Solutions, both of which help customers achieve faster time to value.“
Portfolio of over 100 workload optimized systems supporting new processor family includes:
Resource-Saving systems
BigTwin
The firm’s Resource-Saving architecture disaggregates the CPU and memory along with other subsystems, so each resource can be refreshed independently allowing data centers to reduce refresh cycle costs and their impact to the environment by reducing e-waste. Further savings are achieved through shared power and cooling as well as free-air cooling solutions. When viewed over a three to five year refresh cycle, Resource-Saving servers deliver, on average, higher-performing and more-efficient servers at lower costs than traditional rip-and-replace models by allowing data centers to independently optimize adoption of new and improved technologies.
The following Supermicro product lines support Resource-Saving features to not only deliver performance but also superior value: BigTwin with the performance and density in a 2U four-node design with each node supporting 24 DIMMs, six hot-swap NVMe drives and flexible networking capability; 4U FatTwin in a variety of I/O, memory and storage combinations for optimized cloud, HPC and enterprise applications; and SuperBlade systems with two-socket and four-socket Xeon Scalable processor-based blade servers supporting top-bin 205-watt processors, NVMe, 100G EDR IB switch, or 25G/10GbE switches, redundant AC/DC power supplies, and Battery Backup(BBP), making them for enterprise, cloud, and HPC applications.
2U Ultra SuperServers
1U and 2U enterprise systems
The company’s 1U and 2U Ultra SuperServers offer enterprise performance while delivering value, flexibility, scalability and serviceability. Depending on configuration, systems feature dual 2nd Gen Xeon Scalable processors (up to 28 cores, 205W TDP per CPU), 24 DIMMs of DDR4-2933MHz Reg. ECC memory, Optane DC persistent memory, up to 24 hot-swap NVMe (up to 16 million IO/s) or SAS-3/SATA-3 drives, up to eight PCI-E 3.0 expansion slots, dual or quad-port 1G, 10GBase-T, 10G SFP+, or 25GbE SFP28, and redundant 750W/1,000W/1,600W Titanium Level (96%+) digital power supplies.
1U Petascale All-Flash NVMe
1U Petascale All-Flash NVMe storage systems
The firm’s Petascale line of all-flash NVMe 1U storage servers support all of the next-generation flash technologies with up to 52Gb/s data bandwidth out of the box, best IO/s performance, NVMe over Fabrics support and ease of maintenance. With these 1U systems supporting up to 1PB of fast low-latency storage with 32 front hot-swap U.2, EDSFF and NF1 form factor SSDs, the company offers flexibility and choice for high-capacity networked storage applications that require the best latency performance. These systems provide a real time-to-value advantage for data centers running data-intensive workloads.
AI systems
The firm offers a selection of servers optimized for AI, deep learning, and HPC workloads. 2nd Gen Xeon Scalable processors include a range of built-in AI accelerators, such as Intel DL Boost, that take advantage of the growing array of Intel-optimized AI frameworks and tools. Also, with a line of systems from 1U up to 10U supporting a single GPU up to 20 GPUs, Supermicro has specialized systems for the specific AI workload, including optimized system models for high performance of deep learning training and for maximum throughput of Deep Learning Inference.
Multi-processor systems
The company’s 4-socket and 8-socket servers combined with the Optane DC persistent memory offer memory capacity and speed making them for large memory applications like in-memory databases and real-time analytics. With four 2nd Gen Xeon Scalable processors, the 4-socket servers can support up to 112 compute cores and up to 18TB of memory.
Intel select solutions: ready-to-adopt, workload-optimized
Intel Select Solutions are verified hardware and software stacks for specific workloads across compute, storage, and network. Supermicro offers several Iof these solutions for workloads across hybrid cloud, network, and analytics. This year, the company anticipates solutions on the 2nd Gen Xeon Scalable processor, including Intel Select Solution for VMware vSAN V2, Intel Select Solution for SAP HANA TDI, and Intel Select Solution for Hardened Security with Lockheed Martin Corp.