Title :
A loop allocation policy for DOACROSS loops
Author :
Lim, J.T. ; Hurson, A.R. ; Kavi, K. ; Lee, B.
Author_Institution :
Dept. of Electr. & Comput. Eng., Pennsylvania State Univ., University Park, PA, USA
Abstract :
The dataflow model of computation, in general, and its recent direction to combine dataflow processing with control-flow processing, in particular, provide attractive alternatives to satisfy the computational demands of new applications, without experiencing the shortcomings of the traditional concurrent systems. This should motivate researchers to analyze the applicability of familiar concepts, such as scheduling and load balancing, within this new architectural framework. Effective execution of loop iterations as a means to improve performance and hardware utilization has received a great deal of attention in the past. In this paper we address the problem of scheduling/allocation of DOACROSS loops in a multithreaded dataflow environment. An extension to the staggered scheme-Cyclic staggered scheme-which produces a more balanced distribution of iterations among processors is introduced and its performance improvement in a dataflow and control-flow environment is simulated and analyzed
Keywords :
data flow computing; parallel programming; performance evaluation; processor scheduling; resource allocation; synchronisation; Cyclic staggered scheme; DOACROSS loops; architectural framework; concurrent systems; control-flow processing; dataflow model of computation; dataflow processing; hardware utilization; load balancing; loop allocation policy; loop iterations; multithreaded dataflow environment; performance; performance improvement; scheduling; Computational modeling; Concurrent computing; Delay; Hardware; Job shop scheduling; Parallel processing; Process control; Processor scheduling; Switches; Yarn;
Conference_Titel :
Parallel and Distributed Processing, 1996., Eighth IEEE Symposium on
Conference_Location :
New Orleans, LA
Print_ISBN :
0-8186-7683-3
DOI :
10.1109/SPDP.1996.570340
