High Performance Computing (HPC) and Scalable Data Science

The recent advances in supercomputing technologies coupled with data generation technologies, have led to a convergence of High performance computing (HPC) and data science applications. In HPC, the advances in parallel and distributed computing have led to an increased availability of heterogeneous manycore architectures, commodity clusters with Graphic Processing Units (GPUs), and supercomputing platforms that are starting to breach the exascale barrier. Concomitantly, the proliferation of high throughput data generation technologies coupled with scalable algorithms and analytics, intelligent tools for decision making, and efficient methods for large-scale data management and access, have collectively led to scalable data science taking a center-stage in accelerating scientific discovery and engineering innovation.

Researchers at WSU are working at various areas of intersection of HPC and scalable data science, and are at the forefront of developing scalable algorithms, parallel computing solutions, AI and learning frameworks, programming models, large-scale data management, and large-scale applications for data-rich domains in science and engineering.

Key Topics

  • Algorithms:
    Parallel algorithms, graph algorithms, combinatorial scientific computing, machine learning and optimization, scientific data compression
  • Systems:
    Compilers, runtime-systems, manycore architectures and GPUs, large-scale data management and cloud computing
  • Applications:
    Bioinformatics and computational biology, computational epidemiology, biomedical health informatics, molecular plant sciences, spatial geoinformatics