The increasing availability of smart devices and sensors has been producing large data volumes in the form of streams, which need to be processed in real-time to extract actionable intelligence. In this context, there is a continuous demand for High-Performance Data Stream Processing Systems to cover a wide spectrum of applications with high socio-economic impact, like systems for healthcare, emergency management, surveillance, intelligent transportation, and many others.
High-volume data streams can be efficiently handled through the adoption of novel high-performance solutions targeting today’s highly parallel hardware. This comprises multicore platforms and heterogeneous systems equipped with GPU and FPGA co-processors. The capacity of these heterogeneous computing platforms has grown remarkably over the years, offering tens of thousands of heterogeneous cores and multiple terabytes of aggregated RAM that is reaching computing, memory and storage capacity of a large warehouse-scale cluster of just few years ago.
The Auto-DaSP 2021 workshop aims at collecting scientific contributions from the community working in the Data Stream Processing (DSP) domain at different levels, both experts in streaming algorithms and applications and researchers working on stream processing frameworks and support tools. The focus is on parallel and autonomic models and practical implementations of DSP applications on parallel hardware and distributed systems, performance management and optimizations with runtime in parallel/distributed environments.
The expected outcome has a twofold nature: stimulating scientific questions on the interrelations among the three core parts of the workshop, i.e. autonomic computing, high-performance, and data stream processing; cross-fertilizing the parallel/distributed computing and performance engineering domains with the DSP research area. A partial list of topics of this workshop is as follows:
- Performance characterization and modeling of streaming applications and systems
- Highly parallel models for streaming applications
- Streaming parallel patterns
- Strategies for dynamic operator and query placement
- Autonomic solutions for load management, elasticity, and reconfiguration
- Integration of elasticity and fault tolerance in stream processing systems
- Stream processing on heterogeneous and reconfigurable hardware
- Streaming state management
- Techniques to deal with out-of-order data streams
- Benchmarking of parallel/distributed stream processing systems
- Energy- and power-aware management of stream processing systems
- Applications and use cases in various domains including Smart Cities, Internet of Things, Finance, Social Media, and Healthcare
Journal Special Issue
The Program Chairs of the workshop are in the process of finding a special issue in a top-ranked journal. The authors of a selection of the accepted papers will be invited to extend their work for a journal submission. Further details will be announced soon.
Submissions are made via Easychair and must be in the standard ACM format for conference proceedings. Papers length is between 6 and 10 pages double column including figures, tables, and references.