At FMS 2019, Xilinx will be showcasing next-generation reconfigurable storage acceleration solutions. Join us at the show for a first-hand look and to connect with Xilinx technology experts.
During Exhibit Hours | Xilinx Booth
The following showcases and demos will be featured throughout the show in the Xilinx booth #313.
Xilinx Booth Demonstrations
Samsung SmartSSD technology to accelerate data analytics
Samsung SmartSSD technology leverages advanced Xilinx programmable hardware and advanced software from Bigstream Solutions Inc to seamlessly accelerate Spark data analytics. The architecture consists of a next-generation FPGA in series with the latest SSD technology from Samsung. Compiler technology from Bigstream is used to bring application-level semantics to the hardware, and execute operations such as filescan, data format processing, filtering and others on the FPGA. This has a three-fold benefit for the user: 1) best-in-class performance, 2) offload of key data processing operations from CPU to the SSD, 3) reduction of traffic on the PCIE bus, which is a shared resource. The seamless (i.e. automatically programmed) allows for in-place upgrade of infrastructure in customer datacenters. The only difference in operation is increased performance of the infrastructure for applications that can leverage it. We believe that moving computation closer to where data is stored is a key advancement that will enable world-class performance of data analytics and machine learning for users across all vertical areas.
Unleash data-driven applications with inline compression/decompression
ScaleFlux Computational Storage Drives incorporating Xilinx FPGAs deliver top-tier performance and TCO savings through utilizing powerful compute engines directly at the data. One such function is inline compression/decompression, which brings two concrete advantages for high transaction workloads like OLTP databases: 1) an immediate 30-50% savings on Flash storage with no CPU resource overhead, 2) overall increase in the transactions per second across mixed workloads. This demo showcases the ScaleFlux CSD 2000 Series executing MySQL benchmarks with superior performance and optimal total cost of ownership (TCO). All this with simple, transparent integration - users can greatly optimize their typical transactional database workloads with no changes to their application.
Hadoop Acceleration using Eideticom’s NoLoad CSP with Xilinx Alveo
Eideticom’s NoLoad® Computational Storage Processor (CSP) with Xilinx Alveo is the ideal solution to accelerate MapReduce workloads. Hadoop MapReduce is the original framework for writing applications that process large amounts of structured and unstructured data stored in the Hadoop Distributed File System (HDFS). The NoLoad CSP with Xilinx Alveo card solution results in significant improvements for Terasort runtimes and accelerates both Compression and Erasure Coding, making it the ideal solution to accelerate MapReduce workloads. The end result is significant improvements in performance and efficiency when compared to a software-only solution.
Pliops + Xilinx Alveo: Accelerating MySQL and multiple high performance databases
Xilinx and Pliops have developed and will demonstrate at FMS 2019 the application of a Pliops Storage Processor using Xilinx Alveo add in card to accelerate MySQL and other high performance databases. With Pliops Storage Processor on the Xilinx Alveo card, MySQL is accelerated to deliver 10X 100% write performance, 4X 70/30 Read/Write mixed workload and reduces SSD storage space required by 50% as compared to a software-only solution. In the case of the space savings, that is over and above what can be accomplished with MySQL software-based compression. MySQL is the most commonly deployed relational database in the world according to 451 Research and is used by leading companies in all industries.
|Xilinx Ecosystem||Booth No.|
|SMART Modular Technologies||627|
Xilinx Conference Participation
Xilinx experts will be participating in the following sessions.
Keynote - FPGAs: The Key to Accelerating High-Speed Storage Systems
With the advent of flash storage and persistent memory, storage is no longer a roadblock to better system performance. Data can already be transferred from SSDs at thousands of times the speed of hard drives. Now NVMe and new technologies such as 3D XPoint are putting further pressure on other system resources with ever-higher data rates. How can processors and networks keep up? With traditional system design – they can’t. Heterogenous architectures and computational storage are becoming the answer to this challenge, with FPGAs leading the charge. This long-proven technology can offload protocol overhead, accelerate storage services such as compression and security, and perform local processing for computational storage. FPGAs are fast, flexible, and capable of handling a wide variety of algorithms and procedures. They can meet today’s challenges and support tomorrow’s emerging applications such as AI/ML, real-time analytics, video and image processing, cybersecurity, and 5G wireless.
Presenter: Salil Raje, Executive Vice President and General Manager, Data Center Group, Xilinx
Date: Wednesday August 7 l 2:40 PM
Location: Mission City Ballroom
Download Presentation File >>
Annual Update on Flash Controllers
Overview of data center trends, applications, flash and storage class memory challenges.
Presenter: David McIntyre, Blockchain Business Lead, Xilinx
Date: Tuesday, August 6 l 3:40 PM
Applications Demanding Accelerated Disaggregated Storage
This session explores the growing trend toward user level networking by cloud providers and how this technology is now being applied to storage and the impact it will have on these emerging applications.
Presenter: Scott Schweitzer, Director, Technology Evangelist, Solarflare
Date: Tuesday, August 6 l 4:55 PM
Accelerating NVMe over TCP for Disaggregated Storage Applications
In this session, we will explore how to accelerate the TCP transport to yield best-in-class performance enabling disaggregated storage to become a reality.
Presenter: Tom Spencer, Senior Director, Product Marketing, Solarflare
Date: Thursday, August 8 l 2:10 PM