Linear algebra in one-dimensional systolic arrays
G. Papa, J. Šilc
Informatica, 2000, 24(2): 249-257
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 and resources, it is better to use one-dimensional array of processors. This leads to the operation reallocation and causes unequal utilization of processors, but it is much easier to implement since there is only one linear array of processors.
BIBTEX copied to Clipboard