Compilation of out-of-core data parallel programs for distributed memory machines

Authors:
Rajeev Thakur;Rajesh Bordawekar;Alok Choudhary
Affiliations:
Dept. of Electrical and Computer Eng. and Northeast Parallel Architectures Center, Syracuse University, Syracuse, NY;Dept. of Electrical and Computer Eng. and Northeast Parallel Architectures Center, Syracuse University, Syracuse, NY;Dept. of Electrical and Computer Eng. and Northeast Parallel Architectures Center, Syracuse University, Syracuse, NY
Venue:
ACM SIGARCH Computer Architecture News - Special issue on input/output in parallel computer systems
Year:
1994

Citing 5
Cited 6

Supercompilers for parallel and vector computers

Supercompilers for parallel and vector computers
High-performance I/O for massively parallel computers: problems and prospects

Computer
Compiler and runtime support for out-of-core HPF programs

ICS '94 Proceedings of the 8th international conference on Supercomputing
Optimizing Supercompilers for Supercomputers

Optimizing Supercompilers for Supercomputers
Compiling Communication-Efficient Programs for Massively Parallel Machines

IEEE Transactions on Parallel and Distributed Systems

Synthesizing Efficient Out-of-Core Programs for Block Recursive Algorithms Using Block-Cyclic Data Distributions

IEEE Transactions on Parallel and Distributed Systems
A General Interprocedural Framework for Placement of Split-Phase Large Latency Operations

IEEE Transactions on Parallel and Distributed Systems
I/O Granularity Transformations

LCPC '98 Proceedings of the 11th International Workshop on Languages and Compilers for Parallel Computing
Disk Resident Arrays: An Array-Oriented I/O Library for Out-Of-Core Computations

FRONTIERS '96 Proceedings of the 6th Symposium on the Frontiers of Massively Parallel Computation
Compiler and middleware support for scalable data mining

LCPC'01 Proceedings of the 14th international conference on Languages and compilers for parallel computing
Reducing seek overhead with application-directed prefetching

USENIX'09 Proceedings of the 2009 conference on USENIX Annual technical conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

We are developing a compiler and runtime support system called PASSION (Parallel And Scalable Software for Input-Output), to translate out-of-core programs written in a data parallel language like HPF to message passing node programs with explicit parallel I/O. This paper describes the basic model of the compiler and the various steps involved in the compilation. We also discuss the runtime routines used by the compiler for I/O and communication. The working of the compiler is illustrated using the example of an out-of-core Laplace equation solver, with performance results on the Intel Touchstone Delta.