|Martin Hirzel (IBM TJ Watson)
|Fast Streaming Analytics Made Easy
|Tuesday, 27.9.2016, 16:15
|S2|02 Room C120, Hochschulstr. 10, 64283 Darmstadt
Real-world systems in all areas of society and commerce are producing real-time data streams. Analyzing these streams online as they are being produced enables immediate insights and actions while reducing storage requirements. However, such streaming analytics are challenging to implement, because they must handle high-speed data efficiently. This talk describes three projects that address this challenge. First, our catalog of streaming optimizations educates developers in writing fast streaming systems and applications. Second, our SPL language allows library writers to implement streaming operators as compiler extensions. And third, META offers a unified rule-based programming model both for online event processing and for batch analytics in the same system. This talk describes our research innovations as well as productization experiences.
is a research staff member and the manager of the Advanced Cognitive Engineering research group at the IBM T.J. Watson Research Center. Martin received his Vordiplom from TU Darmstadt in 1998 and his PhD from CU Boulder in 2004; his thesis adviser was Amer Diwan. At IBM, Martin works on tools and languages for streaming and cognitive systems. Martin is an ACM Distinguished Scientist. Martin Hirzel