"DDN has been the primary storage vendor for a number of extreme performance and scale-oriented HPC installations that have stringent uptime and reliability requirements", stated Steve Conway, IDC research vice president, high performance computing and data analysis. "The STAC results indicate that DDN's performance and capability advantages are well-suited to the financial services industry, which has data intensive workloads and challenging uptime and reliability requirements."
The STAC-M3 Benchmark suite is the industry standard for testing solutions that enable high-speed analytics on time series data. The STAC-tested system consisted of Kx Systems kdb+ 3.2 running DDN SFA12KX-40 based EXAScaler platform with Intel Enterprise Edition for Lustre 2.2.
As the STAC results demonstrate, financial services organisations can benefit from DDN's EXAScaler platform as it enables a shared data model, empowers the consolidation of data and massively parallel data queries for market data analytics, and reduces data management costs - all while delivering extremely high performance.
The testing shows that the DDN EXAScaler solution can outperform direct attached SSD-based solutions, and achieve extremely high performance regardless of workload type or size.
The STAC benchmark illustrates why financial services customers in trading firms, hedge funds and investment banks are rapidly moving to DDN Storage. They are able to accelerate their data models to deliver significantly faster results, while simultaneously lowering TCO of the entire data management solution", stated Molly Rector, CMO, executive vice president product management and worldwide marketing, DDN.
Leading global financial institutions test their automated trading and risk management algorithms against years of compiled market data provided by STAC. In this study, two benchmark suites, ANTUCO and KANAGA, were executed. The STAC suite ANTUCO used a limited dataset size of 4.5TB to simulate system performance of a dataset residing mostly on non-volatile media with a broad range of read and write operations. The KANAGA suite analyzed performance on large datasets that range from 33TB to 897TB, with large numbers of concurrent requests.
The DDN EXAScaler high performance storage platform excelled in each aspect of the benchmark testing: