Global Arrays (GA) is a software system from Pacific Northwest National Laboratory that enables an efficient, portable, and parallel shared memory programming interface to manipulate distributed defense arrays. Using a combination of GA and NumPy, we have reimplemented NumPy as a distributed drop-in replacement called Global Arrays in NumPy (GAiN). Scalability studies will be presented showing the utility of developing serial NumPy codes which can later run on more capable clusters or supercomputers.
Revised: September 27, 2013 |
Published: September 1, 2011
Citation
Daily J.A., and R.R. Lewis. 2011.Using the Global Arrays Toolkit to Reimplement NumPy for Distributed Computation. In Python for Scientific Computing Conference (SciPy 2011), July 11-16, 2011, Austin, Texas. Austin, Texas:Enthought Inc.PNNL-SA-80943.