J. Shirako, K. Nagasawa, K. Ishizaka, M. Obata, and H. Kasahara (Japan)
Parallel Processing, Automatic parallelizing compiler, Multi grain parallel processing, Program restructuring
This paper proposes a selective procedure inlining scheme to improve a multi-grain parallelism, which hierarchically exploits the coarse grain task parallelism among loops, sub routines and basic blocks and near fine grain parallelism among statements inside a basic block in addition to the loop parallelism. Using the proposed scheme, the par allelism among different layers(nested levels) can be ex ploited. In the evaluation using 103.su2cor, 107.mgrid and 125.turb3d in SPEC95FP benchmarks on 16 way IBM pSeries690 SMP server, the multi-grain parallel process ing with the proposed scheme gave us 3.65 to 5.34 times speedups against IBM XL Fortran compiler and 1.03 to 1.47 times speedups against conventional multi-grain par allelization.
Important Links:
Go Back
