Browsing by Author "Shih, WC"

Now showing 1 - 6 of 6

A hybrid parallel loop scheduling scheme on grid environments
(2005)
Shih, WC
;
Yang, CT
;
Tseng, SS
;
資訊工程學系
;
Department of Computer Science
Effective loop-scheduling can significantly reduce the total execution time of a program on grid environments, especially for loop-intensive applications. This paper describes a two-phased method, named HPLS (Hybrid Parallel Loop Scheduling), to dynamically schedule loop iterations of a program on grid environments. In the first phase, most of the workload is dispatched to each node for execution according to its performance. Then, some well-known self-scheduling scheme is utilized to schedule the remaining workload. Experimental results showed that in most cases our approach could produce more efficient scheduling than previous schemes on our testbed grid. In addition, the results suggest that our approach is suitable for loop scheduling on grid environments.
A hybrid parallel loop scheduling scheme on heterogeneous PC clusters
(2005)
Shih, WC
;
Yang, CT
;
Chen, PI
;
Tseng, SS
;
資訊工程學系
Traditional loop-scheduling schemes are designed for homogeneous computing environments, and are probably not suitable for emerging heterogeneous PC clusters. This paper applies a two-phased method, named HPLS (Hybrid Parallel Loop Scheduling), to heterogeneous PC-cluster environments. The key idea is to distribute most of the workload to each node according to its performance, which is modeled and estimated in advance. Experiments on our testbed PC-cluster showed that, in most cases, our method could reduce the execution time of application programs more than previous schemes could.
A performance-based approach to dynamic workload distribution for master-slave applications on grid environments
(2006)
Shih, WC
;
Yang, CT
;
Tseng, SS
;
資訊工程學系
;
Department of Computer Science
Effective workload distribution techniques can significantly reduce the total completion time of a program on and computing environments. In this paper, we propose a dynamic performance-based workload partition approach for master-slave types of applications on grids. Furthermore, we implement two types of applications and conduct the experimentations on our grid testbed. Experimental results showed that our method could execute more efficiently than traditional schemes.
A performance-based parallel loop self-scheduling on grid computing environments
(2005)
Shih, WC
;
Yang, CT
;
Tseng, SS
;
資訊工程學系
;
Department of Computer Science
Efficient loop scheduling on parallel and distributed systems depends mostly on load balancing, especially on heterogeneous PC-based cluster and grid computing environments. In this paper, a general approach, named Performance-Based Parallel Loop Self-Scheduling (PPLSS), was given to partition workload according to performance of grid nodes. This approach was applied to three types of application programs, which were executed on a testbed grid. Experimental results showed that our approach could execute efficiently for most scheduling parameters when estimation of node performance was accurate.
An efficient network information model using NWS for grid computing environments
(2005)
Yang, CT
;
Shih, PC
;
Chen, SY
;
Shih, WC
;
資訊工程學系
Grid computing technologies enable large-scale aggregation and sharing of resources via wide-area networks focused on sharing computational, data, and other resources to form general-purpose services for users. In this paper, we address network information gathering and focus on providing approximate measurement models for network-related information using Network Weather Service (NWS) for future scheduling and benchmarking. We propose a network measurement model for gathering network-related information including bandwidth, latency, forecasting, error rates, etc., without generating excessive system overhead. We consider inaccuracies in real-world network values in generating approximation values for future use.
Using knowledge-based techniques on loop parallelization for parallelizing compilers
(1997-05-01)
Yang, CT
;
Tseng, SS
;
Chuang, CD
;
Shih, WC
;
資訊工程學系
In this paper we propose a knowledge-based approach for solving data dependence testing and loop scheduling problems. A rule-based system, called the K-Test, is developed by repertory grid and attribute ording table to construct the knowledge base. The K-Test chooses an appropriate testing algorithm according to some features of the input program by using knowledge-based techniques, and then applies the resulting test to detect data dependences for loop parallelization. Another rule-based system, called the KPLS, is also proposed to be able to choose an appropriate scheduling by inferring some features of loops and assign parallel loops on multiprocessors for achieving high speedup. The experimental results show that the graceful speedup obtained by our compiler is obvious.