Optical Linear Algebra Processors

Casasent, David P.; Kumar, B. V. K. Vijaya

doi:10.1016/b978-0-12-355760-5.50016-8

Cited by 3 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) Operations of multiplication, inversion and addition in (1) are carried out simultaneously through a decomposition of an augmented matrix A B X--C D I (2) 1. INTRODUCTION Optical linear algebra processors (OLAPs) are single-instruction-multiple-data (SIMD) type parallel computing systems that perform a few operations such as matrix multiplications and matrix decompositions efficiently at a high speed [1]. The OLAPs are not programmable like the digital processors.…”

Section: The Faddeeva Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Performance Of The Faddeeva Algorithm On Optical Processors

1989

View full text Add to dashboard Cite

An optical associative processor realizing the versatile Faddeeva algorithm can be used for several computations such as matrix multiplications, matrix decompositions or inversions, and singular value decompositions just by changing the structure of the data stored. Thus such an optical processor is programmable and efficient. In this paper the realization of this algorithm on various optical structures and their performance are described. For unstable data structures it is necessary to use a preprocessed Faddeeva algorithm on the optical processors for accurate results. The procedure of preprocessing and the performance of the preprocessed Faddeeva algorithm are also described.

show abstract

Section: The Faddeeva Algorithmmentioning

confidence: 99%

“…Optical linear algebra processors (OLAPs) are single-instruction -multiple -data (SIMD) type parallel computing systems that perform a few operations such as matrix multiplications and matrix decompositions efficiently at a high speed [1]. The OLAPs are not programmable like the digital processors.…”

Section: Introductionmentioning

confidence: 99%

Performance Of The Faddeeva Algorithm On Optical Processors

1989

View full text Add to dashboard Cite

show abstract

“…Array multiplication such as vector-matrix and their use in calculating eigenvalues has been suggested using one-and two-dimensional SLMs. [24,25] A system of one-dimensional SLMs designed to perform optically 2-dimensional operations such a s Fourier transforms, matrix-matrix multiplications, and matrix inversion is currently under development. [261 Symbolic substitution was recently suggested as a computing tool using optical implementation.…”

Section: * = Weak P O I N T O F Technoloqy (Odp Applications)mentioning

confidence: 99%