Title :
Resource Optimization of a Parallel Computer for Multiple Vector Processing
Author :
Hwang, Kai ; Ni, Lionel M.
Author_Institution :
School of Electrical Engineering, Purdue University
Abstract :
Performance optimization of a shared-resource parallel computer is studied in this correspondence. Such a parallel computer contains multiple control units (CU´s) sharing a resource pool of processing elements (PE´s) and operating with multiple single-instruction-multiple-data (MSIMD) streams. A formal queueing model is proposed for MSIMD machines used in multiple array processing. Analytic results are obtained to evaluate the performance of MSIMD computers. Systematic procedures are given to optimize the size of PE resource pool and to determine the sufficient job queue size for a given vector workload distribution.
Keywords :
M/M/k/l queueing system; multiple SIMD (MSIMD) computer; multiprocessor architecture; parallel vector processing; performance optimization; Algorithm design and analysis; Computer architecture; Concurrent computing; Data analysis; Data flow computing; Flow graphs; High level languages; Magnetic heads; Parallel architectures; Tree graphs; M/M/k/l queueing system; multiple SIMD (MSIMD) computer; multiprocessor architecture; parallel vector processing; performance optimization;
Journal_Title :
Computers, IEEE Transactions on
DOI :
10.1109/TC.1980.1675683
