Capital Markets firms – whether big universal banks, focused hedge funds, algo traders or quants all have something in common.The need for high-performance access to data.Whether that is to make a trading decision, execute a trade to get the most competitive price, or to ensure compliance, speed matters. As the availability and quantity of data ever increases, so does the need to offer the highest performance possible.
To ensure that firms can take advantage of the new data intensive and latency sensitive applications, a modern IT architecture that can handle the most demanding storage workloads is needed.This is where HPE and WekaIO can help with their record breaking performance and scalability.
High performance access to data is key
Today HPE and WekaIO announced record breaking performance on the STAC-M3 benchmark. The STAC-M3 benchmark specifications are maintained by the STAC Benchmark Council whose purpose is to discuss technical challenges and solutions in financial services and to develop technology benchmark standards that are useful to financial organizations. The STAC Benchmark Council focuses on areas where new technology has great potential to solve strategic problems—that is, where innovations intersect important business workloads. These workloads are classified into 3 categories: Fast data workloads that are event-driven, latency and throughput intensive found primarily in automated high-frequency trading; Big data workloads that are data-bound such as tick analytics, backtesting (trading algorithm validation), fraud detection, predictive processing, and operational risk and compliance; and Big compute workloads that are computationally intense such as derivatives pricing, market and credit risk management.
As part of the benchmark test, the Weka File System (WekaFS™) on HPE ProLiant XL170r Gen 10 servers in an Apollo r2800 chassis delivered record-breaking performance at scale for the STAC-M3 “Tick Analytics” Benchmarks - breaking 12 STAC-M3 world records for mean query-response times and 5 world records for throughput. These results affirm that an integrated storage solution from Weka and HPE is the ideal choice for algorithmic trading and quantitative analysis workloads common in financial services. More technical detail on the records set, and the technical set-up, can be found in this blog by WekaIO.
HPE have validated the Weka software defined storage solution, including a specific “AI Data Node” offering that can deliver rich capabilities for high-performance data analytics (HPDA), artificial intelligence and deep learning use cases.WekaFS software scales to meet the demanding IOPS and throughput requirements for high-performance data processing delivering an integrated flash-based parallel file system on HPE servers that can significantly accelerate compute-intensive workloads. The result of the integrated solution is a low latency, throughput-optimized environment providing industry-leading performance, scale, and value. Whether you are a big universal bank, a hedge fund or a algo trader, it is perfect to help deliver high-velocity analytics!
Both HPE and Weka are presenting at the STAC Summit Virtual Conference this week.Please go to www.STACresearch.com/spring2020 to register, and make sure you catch both Barbara Murphy from WekaIO for “WekaFS for Financial Analytics”, and Dr Joe Landman from HPE for “Making your analytics more agile”.
Chris is a Chief Technologist for HPE, focused on the Financial Services industry. Before joining HPE, Chris has worked at both a Global Systems Integrator, as well as at a Global Bank in a variety of senior architectural roles.