Parallel Processing Research Laboratory

Queen's University, Kingston, Ontario
What the facility does

Parallel and distributed processing, high-performance networking, high-performance computing, power-aware computing

Area(s) of Expertise

The Parallel Processing Research Laboratory at Queen’s University conducts research in various innovative techniques that could be effectively used at different layers to enhance the performance and scalability of parallel and distributed computing systems and to minimize their power/energy consumption. Our research, in part, is focused on improving the performance and scalability of networking and communication subsystems, messaging layers and runtime systems for high-performance clusters, high-end systems, and data centres. Research is ongoing in optimizing the Message Passing Interface (MPI) and hybrid parallel programming paradigms (including multi-threaded languages, PGAS, CUDA/OpenCL, etc.) and their communication runtime systems for future-generation computing systems. The lab is also active in several areas related to high-performance networking technologies, such as InfiniBand, iWARP Ethernet and other RDMA-enabled interconnects to support efficient execution and development of parallel and distributed applications. The lab also carries out work at the application level.  In addition, with the increasing amount of power/energy consumption in high-performance computing and data centres, our research is exploring novel ideas to reduce power consumption and improve energy efficiency with little or no impact on performance. The lab is actively collaborating with academia and industry to realize the aforementioned objectives.

Research Services

Parallel and distributed processing, network-based high-performance computing, cluster computing and data centres, interconnection networks and communication subsystems, messaging layers, system software, communication runtime, collective communications, parallel programming paradigms, power-aware/ high-performance computing, accelerator-based (GPUs/ Xeon Phi) hybrid scalable systems, workload characterization, benchmarking and performance evaluation

Sectors of Application
  • Aerospace and satellites
  • Automotive
  • Defence and security industries
  • Energy (renewable and fossil)
  • Financial services and insurance
  • Information and communication technologies and media
  • Life sciences, pharmaceuticals and medical equipment

Specialized lab


A number of high-performance clusters, consisting of:

High-end rack-mount servers


High-performance networks and switches, including InfiniBand, iWARP Ethernet, Myrinet, Quadrics, 10G Ethernet, Fujitsu


High-performance accelerators from NVIDIA and Intel Xeon Phi

  • Argonne National Laboratory
  • University of Illinois at Urbana-Champaign
  • University of New Mexico
  • Sandia National Laboratories
  • Platform Computing