Streams: una librería de habilitación de paralelismo mixto de tareas en cascada y datos para el lenguaje de programación ZPL

Streams is a library for pipelined parallelism designed for the data-parallel programming language ZPL. The combination ZPL/Streams enables mixed parallelism: data and pipelining, which is useful for the Synthetic Aperture Radar processing and video processing. We discuss the usage of the library in ZPL programs and we compare the performance between ZPL and ZPL/Streams for a FFT2D application. We show that the library achieves a substantial increase of throughput for the FFT2D for small and intermediated-sized frames. These results are consistent with typical applications in SAR processing and video processing.

[1]  Demetrio Rey,et al.  Extending the capabilities of zpl to improve the performance of pipelined applications , 2004 .

[2]  Fernando Gustavo Tinetti,et al.  Parallel programming: techniques and applications using networked workstations and parallel computers. Barry Wilkinson, C. Michael Allen , 2000 .

[3]  Demetrio Rey,et al.  Porting the parallel array programming language ZPL to an embedded multicomputing system , 2002, APL.

[4]  Thomas H. Einstein.  Mercury Computer Systems' modular heterogeneous RACE(R) multicomputer , 1997, Proceedings Sixth Heterogeneous Computing Workshop (HCW'97).

[5]  Peter A. Dinda,et al.  The CMU task parallel program suite , 1994 .

[6]  Bradford L. Chamberlain,et al.  ZPL's WYSIWYG performance model , 1998, Proceedings Third International Workshop on High-Level Parallel Programming Models and Supportive Environments.

[7]  Steven G. Johnson,et al.  The Design and Implementation of FFTW3 , 2005, Proceedings of the IEEE.

[8]  Bradford L. Chamberlain,et al.  The design and implementation of a region-based parallel programming language , 2001 .

[9]  Matthew Haines,et al.  Approaches for integrating task and data parallelism , 1998, IEEE Concurr..

[10]  Prithviraj Banerjee,et al.  Optimizations for Efficient Array Redistribution on Distributed Memory Multicomputers , 1996, J. Parallel Distributed Comput..

[11]  Lawrence Snyder,et al.  The design and development of ZPL , 2007, HOPL.

[12]  Bradford L. Chamberlain,et al.  ZPL: A Machine Independent Programming Language for Parallel Computers , 2000, IEEE Trans. Software Eng..

[13]  Jaspal Subhlok,et al.  Optimal Use of Mixed Task and Data Parallelism for Pipelined Computations , 2000, J. Parallel Distributed Comput..