DAPPER 2018 - International Workshop on Data Analytics and Parallel Performance (DAPPER)

Optimizing high performance computing (HPC)/data centers, and applications running at these centers presents a unique set of challenges, and an opportunity to automate complex optimization tasks. The use of machine learning and statistical techniques to model and characterize performance data is gaining traction in the parallel community. The International Workshop on Data Analytics and Parallel Performance provides a forum for sharing academic and industrial research work focused on applying data analytics to performance analysis, debugging and optimization/tuning of parallel software and systems.
Workshop Topics
Authors are invited to submit novel research as well as ongoing work pertaining to:
Deep learning, neural networks
Supervised/unsupervised machine learning
Classification, regression, clustering
Dimensionality reduction
Data-driven modeling
applied to
Performance analysis
Debugging, performance debugging
Performance optimization, auto-tuning
of/for
Parallel benchmarks, proxy applications, and production codes
Scientific workflows
HPC workloads/Full system
HPC/Data center facilities