Regular Partitioning for Synthesizing Xed-size Systolic Arrays
نویسنده
چکیده
Extending the projection method for the synthesis of systolic arrays , we present a procedure for the design of xed-size systolic arrays using a technique called "locally sequential globally parallel" (LSGP) partitioning. Our main result, which gives a necessary and suucient condition to characterize the boxes in which cells can be merged without connict, is the key to the procedure presented here.
منابع مشابه
Regular partitioning for synthesizing fixed-size systolic arrays
Extending the projection method for the synthesis of systolic arrays , we present a procedure for the design of xed-size systolic arrays using a technique called "locally sequential globally parallel" (LSGP) partitioning. Our main result, which gives a necessary and suucient condition to characterize the boxes in which cells can be merged without connict, is the key to the procedure presented h...
متن کاملReconngurability and Reliability of Systolic/wavefront Arrays
In this paper we study fault-tolerant redundant structures for maintaining reliable arrays. In particular we assume the desired array (application graph) is embedded in a certain class of regular, bounded-degree graphs called dynamic graphs. We deene the degree of reconngurability DR, and DR with distance DR d , of a redundant graph. When DR (respectively DR d) is independent of the size of the...
متن کاملTwo Cycle-Related Problems of Regular Data Flow Graphs: Complexity and Heuristics
1 Abstract1 A regular data flow graph (RDFG) is a graph with a highly regular structure that enables its description to be exponentially smaller than the description size for an ordinary graph. Such graphs arise when certain regular iterative algorithms (like matrix multiplication or convolution) are modeled using dependence graphs. These graphs can be implemented either on systolic arrays, or ...
متن کاملDesign of Space-Optimal Regular Arrays for Algorithms with Linear Schedules
The problem of designing space-optimal 2D regular arrays for N x N x N cubical mesh algorithms with linear schedule ai + bj + ck, 1 I a I b 5 c, and N = nc, is studied. Three novel nonlinear processor allocation methods, each of which works by combining a partitioning technique (gcd-partition) with different nonlinear processor allocation procedures (traces), are proposed to handle different ca...
متن کاملOn the synthesis of regular VLSI architectures for the 1 - D discretewavelet transform
A methodology for synthesizing parallel computational structures has been applied to the Discrete Wavelet Transform algorithm. It is based on linear space-time mapping with constraint driven localization. The data dependence analysis, localization of global variables, and space-time mapping is presented, as well as one realization of a 3-octave systolic array. The DWT algorithm may not be descr...
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 1991