@TechReport{	  it:2016-010,
  author	= {Afshin Zafari and Elisabeth Larsson and Martin Tillenius},
  title		= {Duct{T}eip: A Task-Based Parallel Programming Framework
		  for Distributed Memory Architectures},
  institution	= {Department of Information Technology, Uppsala University},
  department	= {Division of Scientific Computing},
  year		= {2016},
  number	= {2016-010},
  month		= jun,
  abstract	= {Current high-performance computer systems used for
		  scientific computing typically combine shared memory
		  compute nodes in a distributed memory environment.
		  Extracting high performance from these complex systems
		  requires tailored approaches. Task based parallel
		  programming has been successful both in simplifying the
		  programming and in exploiting the available hardware
		  parallelism. We have previously developed a task library
		  for shared memory systems which performs well compared with
		  other libraries. Here we extend this to distributed memory
		  architectures. We use a hierarchical decomposition of tasks
		  and data in order to accommodate the different levels of
		  hardware. Our experiments on implementing distributed
		  Cholesky factorization show that our framework has low
		  overhead and scales to at least 800 cores. We perform a
		  comparison with related frameworks and show that DuctTeip
		  is highly competitive in its class of frameworks. }
}