International Workshop on Visual Analytics in Supercomputing and Performance Engineering (VASPE ‘19)
– cancelled –
Unfortunately, we have received too few submissions. We therefore decided to cancel this year’s edition of VASPE. – We’ll try again next year. So, please, check back …
The Original Scope
Both high performance computing (HPC) and performance engineering (PE) experts are facing the challenge of analyzing, comparing, visualizing, and reasoning about ever increasing volumes of performance-related data. While HPC typically deals with massively parallel simulation codes being executed on supercomputers, PE focuses on distributed, reliable software systems.
Due to the scale of performance-related data and the open-ended nature of analyzing it, visualization (VIS) and data analytics are often the only feasible tools to comprehend, debug, and improve the performance behavior of systems and/or codes. This is becoming ever more important, since the scale of performance-related data keeps rapidly growing. However the research communities in HPC, PE, and VIS are mostly disjunct.
VASPE ‘19 aims at gathering experts from (i) the HPC community, (ii) the PE community, and (iii) the VIS community in order to breed cross-community algorithms, techniques, and systems for analyzing and visualizing performance-related data.
Topics include, but are not limited to:
- Scalable displays of performance data
- Data models to enable scalable visualization
- Graph representation of unstructured performance data
- Presentation of high-dimensional data
- Visual correlations between multiple data source
- Human-Computer Interfaces for exploring performance data
- Multi-scale representations of performance data for visual exploration
- Data analytics of historical performance data
- Machine learning or statistical techniques for data exploration