• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04a
• /
• pp.472-474
• /
• 2004

본 논문은 그리드 환경에서 RPC 프로그래밍 메커니즘의 성능향상을 위하여 DAG기반의 Co-scheduling시스템의 구현에 관한 것이다. 제안된 Co-scheduling의 목적은 복수개의 관련된 RPC들의 데이터 입출력 관계를 고려하여 불필요하거나 중복되는 네트워크상의 데이터전송을 제거함으로써 실행시간을 줄이는 것이다. 사용자에 의해 만들어진 작업흐름을 DAG로 구성하여 각 작업에 대한 자원을 탈당 받아 실행기반 시스템을 통해 수행된다. 이 논문에서는 기존 RPC시스템에서의 오버헤드를 지적하고 그것을 극복하기 위한 DAG기반 Co-scheduling을 설명한다. 실험을 통해 구현된 시스템의 성능향상을 확인한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10c
• /
• pp.595-597
• /
• 2004

본 논문은 그리드 환경에서 HPC 프로그래임 메커니즘의 성능향상을 위하며 DAG기반의 Co-scheduling시스템의 신뢰성 향상에 관한 것이다. 제안된 Co-Scheduling의 목적은 복수개의 관련된 RPC들의 데이터 입출력 관계를 고려하여 불필요한 네트워크상의 데이터전송을 제거함으로써 전체 RPC의 실행시간을 줄이는 것이다. 사용자로 부터 요청된 어플리케이션을 DAG로 구성하여 실행기반 시스템을 통해 수행된다. 이 논문에서는 신뢰성 향상을 위한 재시동 프로토콜을 구현하여 결함발생시 전체 작업을 정상적으로 완료하기 위한 메커니즘을 소개하고 재시동 프로토콜의 효율성을 검증한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11a
• /
• pp.189-192
• /
• 2003

이 논문에서는 그리드환경에서 Remote Procedure Call(RPC) 프로그래밍 인터페이스를 위한 메커니즘인 GridRPC 의 성능향상을 위해 DAG 기반의 Co-scheduling API 를 제안한다. 네트워크 상의 통신횟수를 줄임으로써 GridRPC call 의 최적화를 도모하기 위한 프로그래밍 인터페이스와 이를 가능하게 하는 서버구조를 제안한다. DAG 기반의 co-scheduling 은 서버-클라이언트간의 연산에 사용되는 입력값과 출력값들의 흐름을 분석하여 사용자로 하여금 DAG(Directed Acyclic Graph)로 GridRPC call 들을 구성하고 이를 기반으로 GridRPC call 들을 최적화하는 방법이다. 또한, GridRPC가 Client Interface 이기 때문에 생기는 문제점인 서버간의 지원의 문제점을 SOAP 서버의 Wrapping 을 통해 해결한다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.3
• /
• pp.86-95
• /
• 2009

Efficient DAG scheduling is critical for achieving high performance in heterogeneous computing environments. Finding an optimal solution to the problem of scheduling an application modeled by a directed acyclic graph(DAG) onto a set of heterogeneous machines is known to be an NP-complete problem. In this paper we propose a new list scheduling algorithm, called the Heterogeneous Rank-Path Scheduling(HRPS) algorithm, to exploit all of a program's available parallelism in distributed heterogeneous computing system. The primary goal of HRPS is to minimize the schedule length of applications. The performance of the algorithm has been observed by its application to some practical DAGs, and by comparing it with other existing scheduling algorithm such as CPOP, HCPT and FLB in term of the schedule length. The comparison studies show that HRPS significantly outperform CPOP, HCPT and FLB in schedule length.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.7
• /
• pp.2060-2071
• /
• 2000

Scheduling parallel tasks, represented as a Directed Acyclic Graph (DAG) or task graph, on a multiprocessor system has been an important research area in the past decades. List scheduling algorithms assign priorities to a node or an edge in an input DAG, and then generate a schedule according to the assigned priorities. This appear proposes a list scheduling algorithms with effective method of priority assignments. The paper also analyzes the worst case performance and optimality condition for the proposed algorithm. The performance comparison study shows that the proposed algorithms outperforms existing scheduling algorithms especially for input DAGs with high communication overheads. The performance improvement over existing algorithms becomes larger as the input DAG becomes more dense and the level of parallelism in the DAG is increased.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.135-145
• /
• 2010

Efficient Directed Acyclic Graph(DAG) scheduling is critical for achieving high performance in Distributed Heterogeneous computing System(DHCS). In this paper, we present a new high-performance scheduling algorithm, called the LCFT(Levelized Critical First Task) algorithm, for DHCS. The LCFT algorithm is a list-based scheduling that uses a new attribute to efficiently select tasks for scheduling in DHCS. The complexity of LCFT is $O(\upsilon+e)(p+log\;\upsilon)$. The performance of the algorithm has been observed by its application to some practical DAGs, and by comparing it with other existing scheduling algorithms such as PETS, HPS, HCPT and GCA in terms of the schedule length and SpeedUp. The comparison studies show that LCFT significantly outperforms PETS, HPS, HCPT and GCA in schedule length, SpeedUp.

• Journal of Korean Institute of Industrial Engineers
• /
• v.24 no.4
• /
• pp.591-600
• /
• 1998

The scheduling of parallel computing systems consists of two procedures, the assignment of tasks to each available processor and the ordering of tasks in each processor. The assignment procedure is same with a clustering. The clustering is classified into linear or nonlinear according to the precedence relationship of the tasks in each cluster. The parallel computing system can be modeled with a Directed Acyclic Graph(DAG). By the granularity theory, DAG is categorized into Coarse Grain Type(CDAG) and Fine Grain Type(FDAG). We suggest the linear clustering method for the scheduling of CDAG using the genetic algorithm. The method utilizes a properly that the optimal schedule of a CDAG is one of linear clustering. We present the computational comparisons between the suggested method for CDAG and an existing method for the general DAG including CDAG and FDAG.

• The KIPS Transactions:PartA
• /
• v.13A no.2 s.99
• /
• pp.163-170
• /
• 2006

Most scheduling problems including DAG(Directed Acyclic Graph)-based are known to be NP-complete, so many heuristic-based scheduling algorithms have been researched. HEFT and CPOP are such algorithms which have been devised to be effective in heterogeneous environment. We proposed, in the previous research, three scheduling algorithms which are effective in realistic global heterogeneous environment: CPOC, eCPOPC and eCPOP. In this paper, the heuristics which are used in the above five algorithms will be systematically analyzed. Those algorithms will be also studied experimentally using various benchmarks. Experimental results show that the eCPOC generates better schedules than any other algorithms and the heuristics which are used in the proposed algorithms are effective in the global heterogeneous environment.

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.2
• /
• pp.76-89
• /
• 2010

The performance of Distributed Heterogeneous Computing System depends on the algorithm which schedules input DAG graph. Among various scheduling algorithms, list scheduling algorithm provides superior performance with low complexity. List scheduling consists of task prioritizing phase and processor allocation phase, but most studies only focus on task prioritizing phase. In this paper, we propose LIP policy which has the same complexity with traditional allocation policies but has superior performance. The performance of LIP has been observed by applying them to task prioritizing phase of traditional list scheduling algorithms, HCPT, HEFT, GCA, and PETS. The results show that LIP has better performance than insertion-based policy and non-insertion-based policy, which are traditional processor allocation policies.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.4
• /
• pp.71-81
• /
• 2010

In grid system, Task scheduling based on list scheduling models has showed low complexity and high efficiency in fully connected processor set environment. However, earlier schemes did not consider sufficiently the communication cost among tasks and the composition process of lightpath for communication in optical gird environment. In this thesis, we propose LSOG (Leveling Selection in Optical Grid) which sets task priority after forming a hierarchical directed acyclic graph (DAG) that is optimized in optical grid environment. To determine priorities of task assignment in the same level, proposed algorithm executes the task with biggest communication cost between itself and its predecessor. Then, it considers the shortest route for communication between tasks. This process improves communication cost in scheduling process through optimizing link resource usage in optical grid environment. We compared LSOG algorithm with conventional ELSA (Extended List Scheduling Algorithm) and SCP (Scheduled Critical Path) algorithm. We could see the enhancement in overall scheduling performance through increment in CCR value and smoothing network environment.