Generalizing matrix multiplication for efficient computations on modern computers

Authors:
Stanislav G. Sedukhin;Marcin Paprzycki
Affiliations:
The University of Aizu, Aizuwakamatsu City, Fukushima, Japan;Systems Research Institute Polish Academy of Sciences, Warsaw, Poland
Venue:
PPAM'11 Proceedings of the 9th international conference on Parallel Processing and Applied Mathematics - Volume Part I
Year:
2011

Citing 12
Cited 0

Transitive closure and related semiring properties via eliminants

Theoretical Computer Science
An extended set of FORTRAN basic linear algebra subprograms

ACM Transactions on Mathematical Software (TOMS)
A set of level 3 basic linear algebra subprograms

ACM Transactions on Mathematical Software (TOMS)
Design of the IBM RISC System/6000 floating-point execution unit

IBM Journal of Research and Development
Using Strassen's algorithm to accelerate the solution of linear systems

The Journal of Supercomputing
Basic Linear Algebra Subprograms for Fortran Usage

ACM Transactions on Mathematical Software (TOMS)
The CRAY-1 computer system

Communications of the ACM - Special issue on computer architecture
MPI: The Complete Reference

MPI: The Complete Reference
The fused multiply-add instruction leads to algorithms for extended-precision floating point: applications to java and high-performance computing

CASCON '99 Proceedings of the 1999 conference of the Centre for Advanced Studies on Collaborative research
Combining building blocks for parallel multi-level matrix multiplication

Parallel Computing
Overview of the Blue Gene/L system architecture

IBM Journal of Research and Development
Orbital Algorithms and Unified Array Processor for Computing 2D Separable Transforms

ICPPW '10 Proceedings of the 2010 39th International Conference on Parallel Processing Workshops

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recent advances in computing allow taking new look at matrix multiplication, where the key ideas are: decreasing interest in recursion, development of processors with thousands (potentially millions) of processing units, and influences from the Algebraic Path Problems. In this context, we propose a generalized matrix-matrix multiply-add (MMA) operation and illustrate its usability. Furthermore, we elaborate the interrelation between this generalization and the BLAS standard.