An Inspector-Executor Algorithm for Irregular Assignment Parallelization

A loop with irregular assignment computations contains loop-carried output data dependences that can only be detected at run-time. In this paper, a load-balanced method based on the inspector-executor model is proposed to parallelize this loop pattern. The basic idea lies in splitting the iteration space of the sequential loop into sets of conflict-free iterations that can be executed concurrently on different processors. As will be demonstrated, this method outperforms existing techniques. Irregular access patterns with different load-balancing and reusability properties are considered in the experiments.

[1]  Juan Touriño,et al.  A GSA-based compiler infrastructure to extract parallelism from complex loops , 2003, ICS '03.

[2]  David A. Padua,et al.  On the Automatic Parallelization of Sparse and Irregular Fortran Programs , 1998, LCR.

[3]  Lawrence Rauchwerger,et al.  The LRPD test: speculative run-time parallelization of loops with privatization and reduction parallelization , 1995, PLDI '95.

[4]  Vivek Sarkar,et al.  Array SSA form and its use in parallelization , 1998, POPL '98.

[5]  Youcef Saad,et al.  A Basic Tool Kit for Sparse Matrix Computations , 1990 .

[6]  Openmp: a Proposed Industry Standard Api for Shared Memory Programming , 2022 .

[7]  Francisco F. Rivera,et al.  Exploiting locality in the run-time parallelization of irregular loops , 2002, Proceedings International Conference on Parallel Processing.

[8]  Michael F. P. O'Boyle,et al.  A Compiler Strategy for Shared Virtual Memories , 1996 .

[9]  Juan Touriño,et al.  Irregular Assignment Computations on cc-NUMA Multiprocessors , 2002, ISHPC.

[10]  Cheng-Zhong Xu,et al.  Time Stamp Algorithms for Runtime Parallelization of DOACROSS Loops with Dynamic Dependences , 2001, IEEE Trans. Parallel Distributed Syst..

[11]  S. Turek,et al.  FEATFLOW - Finite element software for the incompressible Navier-Stokes equations - User Manual Rele , 1998 .

[12]  Emilio L. Zapata,et al.  Balanced, Locality-Based Parallel Irregular Reductions , 2001, LCPC.

[13]  Chau-Wen Tseng,et al.  Efficient compiler and run-time support for parallel irregular reductions , 2000, Parallel Comput..