Reducing the Number of Processors Elements in Systolic Arrays for Matrix Multiplication using Linear Transformation Matrix
نویسندگان
چکیده
Abstract: Besides different definitions, in this work is given the so called transformation matrix, which maps the given index space in another index space. Transformation used in this new index space reduces the number of processing elements in the array. We illustrate all possible instances of transformation matrices and we show the importance of using the transformation matrix by comparing the number of processing elements of the array where we use it with another array where this transformation is not used. For this purpose also is given a mathematical explanation. The comparison is made using the matrices of size N=4.
منابع مشابه
Reducing the Number of Processors Elements in Systolic Arrays for Matrix Multiplication
Author is discussing a problems of determining parameters suitable systolic arrays for implementation regular 3-nested loop algorithms. Author shows that if the characteristics of so called adaptable algorithms to the projection direction are used we have the best results. This characteristics can be space (number of processor elements,chip area, input-output elements, ...), time(flow period of...
متن کاملSome Characteristics of Systolic Arrays
In this paper is investigated a possible optimization of some linear algebra problems which can be solved by parallel processing using the special arrays called systolic arrays. In this paper are used some special types of transformations for the designing of these arrays. We show the characteristics of these arrays. The main focus is on discussing the advantages of these arrays in parallel com...
متن کاملFilomat 17 (2003), 135–141 Matrix Multiplication on Bidirectional Linear Systolic Arrays
This paper addresses the problem of rectangular matrix multiplication on bidirectional linear systolic arrays (SAs). We analyze all bidirectional linear SAs in terms of efficiency. We conclude that the efficiency depends on the relation between the loop boundaries in the systolic algorithm (i.e. matrix dimensions). We point out which SA is the best choice depending on the relation between matri...
متن کاملLinear Algebra in One-Dimensional Systolic Arrays
Frequently used problems of linear algebra, such as the solution of linear systems, triangular decomposition and matrix multiplication, are computationally extensive. To increase the speed, those problems should be solved with systolic structures, where many processors are used concurrently to compute the result. Since two-dimensional array of processors is very consumptive, considering space a...
متن کاملDetermining the Number of Processing Elements in Systolic Arrays
In this paper we determine the minimal number of processing in the 2D systolic implementation for one class of nested loop algorithms. The number of processing elements is derived depending on the projection direction and size of loops. Obtained results are illustrated on matrix multiplication algorithm.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2008