Parameter Estimation for a Generalized Parallel Loop Scheduling Algorithm

2019 ◽  
pp. 155-172
Keyword(s):  
Parameter Estimation ◽  
Scheduling Algorithm ◽  
Loop Scheduling ◽  
Parallel Loop

Using program visualization for tuning parallel-loop scheduling

1997 ◽  
Vol 5 (1) ◽  
pp. 26-40
Author(s):  
S.F. Hummel ◽  
D. Kimelman ◽  
E. Schonberg ◽  
M. Tennenhouse ◽  
D. Zernik
Keyword(s):  
Loop Scheduling ◽  
Program Visualization ◽  
Parallel Loop

Power-Aware Parallel Loop Scheduling Method for Heterogeneous System

2011 ◽  
Vol 22 (9) ◽  
pp. 2222-2234 ◽  
Author(s):  
Gui-Bin WANG ◽  
Xue-Jun YANG ◽  
Xin-Hai XU ◽  
Yi-Song LIN ◽  
Xin LI
Keyword(s):  
Heterogeneous System ◽  
Loop Scheduling ◽  
Parallel Loop ◽  
Scheduling Method

A LOOP-BASED SCHEDULING ALGORITHM FOR HARDWARE DESCRIPTION LANGUAGES

1994 ◽  
Vol 04 (03) ◽  
pp. 351-364 ◽  
Author(s):  
MAHER RAHMOUNI ◽  
KEVIN O’BRIEN ◽  
AHMED A. JERRAYA
Keyword(s):  
High Performance ◽  
Scheduling Algorithm ◽  
Control Flow ◽  
Control Flow Graph ◽  
Hardware Description Languages ◽  
Loop Scheduling ◽  
Flow Graph ◽  
Loop Feedback ◽  
Hardware Description ◽  
Description Languages

This paper presents Dynamic Loop Scheduling (DLS), a loop-based algorithm that can efficiently schedule large, control-flow dominated designs. It compares favourably with results produced for traditional path-based approaches and at the same time requires much less overhead to implement. The high-performance of DLS is due mainly to the inclusion of loop feedback edges in the control-flow graph and the interruption of the path generation on the fly. The latter eliminates the generation of false paths thereby avoiding the path explosion problem.

PARALLEL LOOP SCHEDULING APPROACHES FOR DISTRIBUTED AND SHARED MEMORY SYSTEMS

2005 ◽  
Vol 15 (01n02) ◽  
pp. 131-152 ◽  
Author(s):  
JOSE AGUILAR ◽  
ERNST LEISS
Keyword(s):  
Shared Memory ◽  
Memory Systems ◽  
Communication Overhead ◽  
Scheduling Problem ◽  
Loop Scheduling ◽  
Parallel Loop ◽  
Chunk Size ◽  
Synchronization Overhead ◽  
Scheduling Models

In this paper, we propose different approaches for the parallel loop scheduling problem on distributed as well as shared memory systems. Specifically, we propose adaptive loop scheduling models in order to achieve load balancing, low runtime scheduling, low synchronization overhead and low communication overhead. Our models are based on an adaptive determination of the chunk size and an exploitation of the processor affinity property, and consider different situations (central or local queues, and dynamic or static loop partition).

Sign in / Sign up

Export Citation Format

Share Document