Compilation of Vector Statements of C[] Language for Architectures with Multilevel Memory Hierarchy

Authors:
A. Ya. Kalinov;A. L. Lastovetsky;I. N. Ledovskikh;M. A. Posypkin
Affiliations:
Institute of System Programming, Russian Academy of Sciences, ul. Bol'shaya Kommunisticheskaya 25, Moscow, 109004 Russia;Institute of System Programming, Russian Academy of Sciences, ul. Bol'shaya Kommunisticheskaya 25, Moscow, 109004 Russia;Institute of System Programming, Russian Academy of Sciences, ul. Bol'shaya Kommunisticheskaya 25, Moscow, 109004 Russia;Institute of System Programming, Russian Academy of Sciences, ul. Bol'shaya Kommunisticheskaya 25, Moscow, 109004 Russia
Venue:
Programming and Computing Software
Year:
2001

Citing 18
Cited 1

The cache performance and optimizations of blocked algorithms

ASPLOS IV Proceedings of the fourth international conference on Architectural support for programming languages and operating systems
Scan primitives for vector computers

Proceedings of the 1990 ACM/IEEE conference on Supercomputing
A data locality optimizing algorithm

PLDI '91 Proceedings of the ACM SIGPLAN 1991 conference on Programming language design and implementation
Improving locality and parallelism in nested loops

Improving locality and parallelism in nested loops
Cache interference phenomena

SIGMETRICS '94 Proceedings of the 1994 ACM SIGMETRICS conference on Measurement and modeling of computer systems
Memory-hierarchy management

Memory-hierarchy management
Tile size selection using cache organization and data layout

PLDI '95 Proceedings of the ACM SIGPLAN 1995 conference on Programming language design and implementation
mpC: a multi-paradigm programming language for massively parallel computers

ACM SIGPLAN Notices
An introduction to STSC's APL compiler

APL '85 Proceedings of the international conference on APL: APL and the future
Cache miss equations: an analytical representation of cache misses

ICS '97 Proceedings of the 11th international conference on Supercomputing
The implementation and evaluation of fusion and contraction in array languages

PLDI '98 Proceedings of the ACM SIGPLAN 1998 conference on Programming language design and implementation
Computer architecture (2nd ed.): a quantitative approach

Computer architecture (2nd ed.): a quantitative approach
New tiling techniques to improve cache temporal locality

Proceedings of the ACM SIGPLAN 1999 conference on Programming language design and implementation
Compiling stencils in high performance Fortran

SC '97 Proceedings of the 1997 ACM/IEEE conference on Supercomputing
Factor-Join: A Unique Approach to Compiling Array Languages for Parallel Machines

LCPC '96 Proceedings of the 9th International Workshop on Languages and Compilers for Parallel Computing
ZPL: An Array Sublanguage

Proceedings of the 6th International Workshop on Languages and Compilers for Parallel Computing
ZPL's WYSIWYG Performance Model

HIPS '98 Proceedings of the High-Level Parallel Programming Models and Supportive Environments
V-nested parallelism in C

PMMP '95 Proceedings of the conference on Programming Models for Massively Parallel Computers

Refined Description of the C[] Language

Programming and Computing Software

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the paper, the use of tiling for compilation of reduction statements in the C[] language is considered. A class of statements is distinguished for which the tiling transformation is proven to be correct and a scheme of their transformation to a sequence of reduction statements of a wide class is given. On the basis of a cache interference model, formulas are obtained that make it possible to accurately compute tiling parameters. It is shown that the code for reduction statements generated by the C[] compiler is comparable with (and, often, even better than) specially designed subroutines in terms of the efficiency.