by Yijun Yu, Erik H. D'holl
http://wwwmath.uni-muenster.de/math/u/guidow/wsvl2000/Papers/YuDHollander.ps
Add To MetaCart
Abstract:
A 3D-iteration space visualizer (ISV) is presented to analyze the parallelism in loops and to find loop transformations which enhance the parallelism. Using automatic program instrumentation, the iteration space dependency graph (ISDG) is constructed, which shows the exact data dependencies of arbitrarily nested loops. Various graphical operations such as rotation, zooming, clipping, coloring and filtering, permit a detailed examination of the dependence relations. Furthermore an animated dataflow execution shows the maximal parallelism and the parallel loops are indicated automatically by an embedded data dependence analysis. In addition, the user may discover and indicate additional parallelism for which a suitable unimodular loop transformation is calculated and verified. The ISV has been applied to parallelize algorithmic kernel programs, a CFD (Computational Fluid Dynamics) simulation code, the detection of statement level parallelism and loop variable privatization.The applications show that the visualizer is a versatile and easy to use tool for the high performance application programmer.
Citations
|
172
|
Unimodular transformations of double loops
– Banerjee
- 1990
|
|
92
|
Maximizing parallelism and minimizing synchronization with affine partitions”, Parallel Computing 24
– Lim
- 1998
|
|
77
|
The Range Test: A Dependence Test for Symbolic, Non-linear Expressions
– Blume, Eigenmann
- 1994
|
|
72
|
Array Privatization for Parallel Execution of Loops
– Li
- 1992
|
|
71
|
The Omega Library Interface Guide
– Kelly, Maslov, et al.
- 1996
|
|
58
|
Nonlinear array dependence analysis
– Wonnacott, Pugh
- 1995
|
|
48
|
Non-unimodular transformations of nested loops
– Ramanujam
- 1992
|
|
25
|
Minimizing communication while preserving parallelism
– Kelly, Pugh
- 1996
|
|
24
|
Partitioning and labeling of loops by unimodular transformations
– D'Hollander
- 1992
|
|
23
|
Static and Dynamic Evaluation of Data Dependence Analysis
– Petersen, Padua
- 1993
|
|
22
|
An affine Partitioning Algorithm to Maximize Parallelism and Minimize Communication
– Lim, Cheong, et al.
- 1999
|
|
18
|
Experiences using the ParaScope Editor: an interactive parallel programming tool
– Hall, Harvey, et al.
- 1993
|
|
18
|
Unimodular transformations of non-perfectly nested loops
– Xue
- 1997
|
|
14
|
Nonlinear and Symbolic Data Dependence Testing
– Blume, Eigenmann
- 1998
|
|
14
|
The fortran parallel transformer and its programming environment
– D’Hollander, Zhang, et al.
- 1998
|
|
10
|
SUIF: A parallelizing and optimizing research compiler
– WILSON, FRENCH, et al.
- 1994
|
|
7
|
The Banerjee-Wolfe and GCD tests on exact data dependence information
– Psarris
- 1996
|
|
5
|
Partitioning loops with variable dependence distances
– Yu, D’Hollander
- 2000
|
|
4
|
NaraView: An interactive 3D visualization system for parallelization of programs
– Sasakura, Joe, et al.
- 1999
|
|
3
|
A 3D-java tool to visualize loop-carried dependences, Parallel Computing: Fundamentals
– Yu
- 1999
|
|
2
|
Fluid flow and thermal analysis during mould filling and solidification of castings
– Xu
- 1993
|
|
1
|
Unimodular transformations of double loops. InAdvances inLanguages andCompilers for Parallel Computing
– Banerjee
- 1990
|
|
1
|
Nonlinear and symbolic data dependence testing. IEEETransactions onParallel andDistributed Systems
– Blume, Eigenmann
- 1998
|
|
1
|
Experiences using the ParaScope Editor: an interactive parallel programming tool
– Roth
- 1993
|
|
1
|
Anafnepartitioning algorithm to maximize parallelism and minimize communication
– Lim, Lam
|
|
1
|
Static anddynamic evaluationof datadependence analysis techniques:. IEEETransactions onParallel andDistributedSystems
– Padua
- 1996
|
|
1
|
Fluidow andthermal analysis during mouldlling and solidication of castings
– Xu
- 1993
|
|
1
|
A3D-javatool to visualize loop-carrieddependences. InParallel Computing: Fundamentals &Applications
– Yu
- 2000
|
