Multilayered array computing

Kak, Subhash

doi:10.1016/0020-0255(88)90010-2

Cited by 16 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We propose that instead of using the exact form of the DHT matrix and converting it into corresponding integers for numbers modulo an appropriate prime, we should merely consider the form of the matrix with its alternate zeros and non-zeros. Incidentally, this structure was the motivation to seek multilayered and unusual arrays for matrix multiplication [19], [20].…”

Section: Number Theoretic Dht (Nht)mentioning

confidence: 99%

The Number Theoretic Hilbert Transform

Kak

2014

Circuits Syst Signal Process

View full text Add to dashboard Cite

This paper presents a general expression for a number-theoretic Hilbert transform (NHT). The transformations preserve the circulant nature of the discrete Hilbert transform (DHT) matrix together with alternating values in each row being zero and non-zero. Specific examples for 4-point, 6-point, and 8-point NHT are provided. The NHT transformation can be used as a primitive to create cryptographically useful scrambling transformations.

show abstract

Section: Number Theoretic Dht (Nht)mentioning

confidence: 99%

The Number Theoretic Hilbert Transform

Kak

2014

Circuits Syst Signal Process

View full text Add to dashboard Cite

show abstract

“…The mesh architecture [1], [2] (Figure 1) was proposed to speed up the computation for multiplying two n×n matrices using distributed computing nodes. In Figure 1, we have the mesh array for multiplying two 4×4 matrices which takes 7 steps, whereas the standard systolic array [3] (Figure 2) requires the same number of steps to multiply two 3×3 matrices.…”

Section: Introductionmentioning

confidence: 99%

A two-layered mesh array for matrix multiplication

Kak

1988

Parallel Computing

Self Cite

View full text Add to dashboard Cite

“…However, Kung's use of a systolic array in his paper 14 and his book 15 in one case was in fact the same as the engagement array, but he called it the concept of a systolic wave front. Varman et al 16 studied the performance of a systolic linear array with and without local memory, and Tsay et al 17 analyzed the performance of a cylindrical array 18 and a two-layer mesh array 19 for matrix multiplication. Interested readers are referred to their papers in Refs.…”

mentioning

confidence: 99%

Modified engagement method for matrix operation

Zhou

Liu

et al. 1995

Appl. Opt.

View full text Add to dashboard Cite

We describe a modified engagement method for matrix operation based on a two-dimensional crossed-ring interconnection network. Our method incorporates fewer steps than that reported by Bocker et al. 3Appl. Opt. 22, 804 1198324, and its performance is found to be the most efficient 1minimum steps2 in comparison with other systolic and@or engagement methods for matrix operation. Thus, it may be helpful for other optical and electronic implementations of matrix operations. One compact optoelectronic integrity approach for implementing the modified engagement method is briefly described.r 1995 Optical Society of America Matrix operation is one of the basic operations in scientific computing, so how to calculate it effectively is always an interesting subject. In electronics, there are a number of non-von Neumann architectures proposed for parallel matrix operations. 1 A systolic array with fixed, regular, and local interconnections is one of the prominent practical solutions that can be used efficiently for parallel matrix operation because of advanced VLSI technology. In optics, more freedom with interconnections is possible.

show abstract

Multilayered array computing

Cited by 16 publications

References 7 publications

The Number Theoretic Hilbert Transform

The Number Theoretic Hilbert Transform

A two-layered mesh array for matrix multiplication

Modified engagement method for matrix operation

Contact Info

Product

Resources

About