The High Performance Computing (HPC) research group (lead by Prof. Florina M. Ciorba) is seeking a highly talented and motivated PhD student to conduct high quality research, publish in top venues, and pursue a doctoral degree in Computer Science, with a focus on HPC. The position is fully funded (100%) for 4 years in the context of the EU project "DAPHNE: Integrated Data Analysis Pipelines for Large-Scale Data Management, HPC, and Machine Learning".
The DAPHNE project gathers the expertise of 13 distinguished academic and industrial partners from 7 European countries. The goal is to define and build an open and extensible system infrastructure for integrated data analysis pipelines, including data management (DM) and processing, HPC, and machine learning (ML) training and scoring. Although the hardware stacks of clusters and provisioned clouds for DM, HPC, and ML converge rapidly, programming paradigms, cluster resource management, and data formats differ substantially across DM, HPC, and ML software stacks. However, there is a trend toward complex data analysis pipelines that combine these different stacks. In the DAPHNE project, the consortium will systematically investigate the necessary system infrastructure, language abstractions, compilation, and runtime techniques, systems, and tools needed to increase productivity when building such data analysis pipelines, eliminating unnecessary performance bottlenecks.
The topic of this Ph.D. will be on developing and applying hierarchical scheduling solutions for pipelines and workflows originating in mixed DM, HPC, and ML workloads, with emphasis on hierarchical topology-aware task and data placement, non-uniform memory access awareness, and performance optimization in multi-tenant resource sharing scenarios.
We offer you