Optimal Design of Lower Dimensional Processor Arrays for Uniform Recurrencesy
نویسندگان
چکیده
In this paper we present a parameter-based approach for synthesizing systolic architectures from uniform recurrence equations. The scheme presented is a generalization of the Parameter Method proposed by Li and Wah 1]. The approach synthesizes optimal arrays of any lower dimension from a general uniform recurrence description of the problem. In other previous attempts for mapping uniform recurrences into lower-dimensional arrays 2]]3], optimality of the resulting designs is not guaranteed. As an illustration of the technique, optimal linear arrays for matrix multiplication are given. Due to space limitation, proofs to theorems in this paper are not shown. In a companion paper 4], we present details of the proof of Theorems 1 and 3 and a diierent approach for deening the constraints shown in Theorem 2. A detailed design for solving path-nding problems is also presented there.
منابع مشابه
Optimal Synthesis of Algorithm - Speci c Lower -
Processor arrays are frequently used to deliver high performance in many applications with computationally intensive operations. This paper presents the General Parameter Method (GP-M), a systematic parameter-based approach for synthesizing such algorithm-speciic architec-tures. GPM can synthesize processor arrays of any lower dimension from a uniform-recurrence description of the algorithm. Th...
متن کاملOptimal Synthesis of Algorithm - speci c Lower - DimensionalProcessor
Processor arrays are frequently used to deliver high-performance in many applications with computationally intensive operations. This paper presents the General Parameter Method (GP-M), a systematic parameter-based approach for synthesizing such algorithm-speciic architec-tures. GPM can synthesize processor arrays of any lower dimension from a uniform-recurrence description of the algorithm. Th...
متن کاملSynthesizing Optimal Lower Dimensional Processor Arrays yKumar
Most existing methods for synthesizing sys-tolic architectures can only map n-dimensional recurrences to n ? 1-dimensional arrays. In this paper, we generalize the parameter-based approach of Li and Wah 1] to map n-dimensional uniform recurrences to any k-dimensional processor arrays, where k < n. In our approach, operations of the target array are captured by a set of parameters , and constrai...
متن کاملSynthesizing Optimal Lower Dimensional Processor Arrays y
Most existing methods for synthesizing systolic architectures can only map n-dimensional recurrences to n 1-dimensional arrays. In this paper, we generalize the parameter-based approach of Li and Wah [1] to map n-dimensional uniform recurrences to any k-dimensional processor arrays, where k < n. In our approach, operations of the target array are captured by a set of parameters, and constraints...
متن کاملAn Approach to Checking Link Conflicts in the Mapping of Uniform Dependence Algorithms into Lower Dimensional Processor Arrays
ÐIn this paper, we propose an enumeration method to check link conflicts in the mapping of n-dimensional uniform dependence algorithms with arbitrary convex index sets into k-dimensional processor arrays. Previous methods on checking the link conflicts had to examine either the whole index set or the I/O spaces whose size are O N2n or O Nnÿ1, respectively, where N is the problem size of the n...
متن کامل