DDN Delivers STAC-M3 World Records with Flexible Appliances that Accelerate Data Analytics
DDN’s EXAScaler Appliances Deliver Record Breaking Performance for Financial Services in a Compact Footprint
DDN, premier provider of Artificial Intelligence (AI) and Data Management software and hardware solutions enabling Intelligent Infrastructure, announced it had established new performance records on the STAC-M3 Benchmark with just two DDN A3I AI400X appliances.
Quickly following a recent report rating DDN number-one by its customers for technical execution, future purchases, innovation, and operational roadmap, DDN now proves its leadership in Financial Analytics. The results of the tests, audited by independent third party STAC, clearly demonstrate why DDN is the smart choice for scalable production financial services workloads, as well as other industries like automotive and manufacturing companies who use Kx kdb+ for data-intensive analytics. DDN’s EXAScaler appliances are end-to-end parallel and are capable of scaling indefinitely, bringing simplicity and flexibility to customers in finance.
The STAC-M3 benchmark specifications are maintained by the STAC Benchmark Council, which consists of over 500 financial institutions and vendor organizations, whose purpose is to discuss technical challenges and solutions in financial services and to develop technology benchmark standards that are useful to financial organizations. User firms include the largest global banks, brokerage houses, exchanges, hedge funds, proprietary trading shops, and other market participants.
DDN outperformed all publicly disclosed results in all year-high bid throughput benchmarks. The tested system performed faster than a solution using NFS-based NAS and four database nodes in 14 out of 17 benchmarks in the STAC-M3 Antuco suite, including a 9.4x speedup in the National Best Bid and Offer (NBBO) operation.
The DDN AI400X appliances each deliver in two Rack Units theoretical peak performance of 48GB/s of throughput and 3M 4k random read 4k IOPs, with a fully end-to-end parallel architecture. These results, along with the comprehensive set of STAC-M3 benchmarks audited by STAC, clearly show why DDN’s EXAScaler appliances are optimal for data-intensive workloads and offer faster time to insight based on easy configurability and management, no matter the scale of the challenge.
DDN designs platforms to reach key performance metrics with the most efficient, manageable and cost-effective systems on the market. The DDN appliances recently introduced a new capability to expand with either high performance flash or cost-effective spinning drives, further improving customer flexibility.
“Delivering the highest value, efficiency and customer satisfaction in our intelligent data storage solutions is what we thrive on at DDN, and we’ve had overwhelming support from thousands of our customers in use cases such as AI and analytics, web and cloud, enterprise at scale, as well as government and research,” said Kurt Kuckein, vice president, marketing, DDN. “These STAC results reinforce our leadership position in delivering the right data solutions for the most challenging data-intensive applications.”
The benchmark configuration was a Kx kdb+ 3.6 database system distributed across 15 servers, each with one Intel Xeon Gold 6138 CPU 2.0GHz and a Mellanox SB7790 36-port Non-blocking Managed EDR 100Gb/sec InfiniBand switch connected to two DDN A3I AI400X appliances. STAC-M3 is the industry standard for testing solutions that enable high-speed analytics on time series data, such as tick database stacks. STAC audited the results from two STAC-M3 benchmark suites: Antuco and Kanaga. The baseline suite, Antuco, uses a limited dataset size with constraints to simulate performance against a full-size dataset residing mostly on non-volatile media. It tests a wide range of compute-bound and storage-bound operations to probe the strengths and weaknesses of each stack. The scaling suite, Kanaga, uses a subset of Antuco queries without constraints against a significantly larger data set.