@TechReport{	  it:2012-017,
  author	= {Xin He and Marcus Holm and Maya Neytcheva},
  title		= {Efficiently Parallel Implementation of the Inverse
		  {S}herman-{M}orrison Algorithm},
  institution	= {Department of Information Technology, Uppsala University},
  department	= {Division of Scientific Computing},
  year		= {2012},
  number	= {2012-017},
  month		= aug,
  abstract	= {We contribute two parallel strategies to compute the exact
		  and approximate inverse of a dense matrix, based on the
		  so-called inverse Sherman-Morrison algorithm and
		  demonstrate their efficiencies on multicore CPU and
		  GPU-equipped computers. Our methods are shown to be much
		  better than a common matrix inverse method, yielding up to
		  12 times faster performance. A comparison of the
		  performance of the CPU and GPU versions is made and
		  analyzed with the aid of a performance model.}
}