The Classification, Fusion, and Parallelization of Array Language Primitives

Authors:
D. C. R. Ju;C. L. Wu;P. Carini
Affiliations:
-;-;-
Venue:
IEEE Transactions on Parallel and Distributed Systems
Year:
1994

Citing 11
Cited 2

Data parallel algorithms

Communications of the ACM - Special issue on parallelism
Advanced compiler optimizations for supercomputers

Communications of the ACM - Special issue on parallelism
An APL compiler

An APL compiler
Architecture and Applications of the Connection Machine

Computer
Exploitation of APL data parallelism on a shared-memory MIMD machine

PPOPP '91 Proceedings of the third ACM SIGPLAN symposium on Principles and practice of parallel programming
Size and access inference for data-parallel programs

PLDI '91 Proceedings of the ACM SIGPLAN 1991 conference on Programming language design and implementation
Parallel expression in the APL2 language

IBM Systems Journal
Compilation and delayed evaluation in APL

POPL '78 Proceedings of the 5th ACM SIGACT-SIGPLAN symposium on Principles of programming languages
Optimizing Supercompilers for Supercomputers

Optimizing Supercompilers for Supercomputers
Parallelism in random access machines

STOC '78 Proceedings of the tenth annual ACM symposium on Theory of computing
A programming language

A programming language

Fast greedy weighted fusion

Proceedings of the 14th international conference on Supercomputing
Fast Greedy Weighted Fusion

International Journal of Parallel Programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a classification scheme for array language primitives that quantifies the variation in parallelism and data locality that results from the fusion of any two primitives. We also present an algorithm based on this scheme that efficiently determines when it is beneficial to fuse any two primitives. Experimental results show that five LINPACK routines report 50% performance improvement from the fusion of array operators.