• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.9
• /
• pp.424-433
• /
• 2001

The cyclic debugging approach often fails for message passing parallel programs because they non-deterministic characteristics due to message race conditions. This paper identifies the MPI events that affect non-deterministic executions, and then converts the concurrent execution to the sequential one that is controlled in order to make it equivalent to a reference execution by keeping their orders of events in two executions identical. This paper also presents an efficient algorithm for the causal distributed breakpoint which is initiated by any sequential breakpoint in one process, and restores each process to the earliest state that reflects all events that happened causally before the sequential breakpoint. So a cyclic debugging approach can be used in debugging MPI parallel programs as like as in debugging sequential programming environments.

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.2
• /
• pp.160-168
• /
• 2000

In this paper, we present a performance monitor to trace and evaluate the performance of programs running on networked computers. The performance monitor of the JaNeC is online/batch as well as event/time driven. Since it is implemented with the Java programming language, it provides us with high portability among heterogeneous computer systems, and friendly graphical user interface. This performance monitor consists of various views such as 'Task/Event Filter' and 'TimeLine', 'Task View', 'Task Hoistory', 'Message Passing View', 'Host Cpu View', which allow the user to easily analyze event and time during the program execution.

• The KIPS Transactions:PartA
• /
• v.13A no.6 s.103
• /
• pp.533-540
• /
• 2006

This paper describes the design and implementation of a grid system META (Metacomputing Environment using Test-run of Application) which facilitates the execution of a CFD (Computational Fluid Dynamics) analysis program on distributed environment. The grid system META allows the CFD program developers can access the computing resources distributed over the network just like one computer system. The research issues involved in the grid computing include fault-tolerance, computing resource selection, and user-interface design. In this paper, we exploits an automatic resource selection scheme for executing the parallel SPMD (Single Program Multiple Data) application written in MPI (Message Passing Interface). The proposed resource selection scheme is informed from the network latency time and the elapsed time of the kernel loop attained from test-run. The network latency time highly influences the executional performance when a parallel program is distributed and executed over several systems. The elapsed time of the kernel loop can be used as an estimator of the whole execution time of the CFD Program due to a common characteristic of CFD programs. The kernel loop consumes over 90% of the whole execution time of a CFD program.

• The KIPS Transactions:PartD
• /
• v.11D no.4
• /
• pp.901-906
• /
• 2004

Client- server interaction in a massive multi-player online role-playing game(MMORPG) is usually made via network-message Passing. Since the game contents and elements in such MMORPGs are consistently evolved, messages need to be added, deleted, or modified accordingly. Therefore, game programmers are repeatedly required to write new programs or at least modify existing programs. The XML-based message definition system introduced in this paper facilitates the addition and modification of messages for game interaction ; it not only allows programmers to save a considerable amount of time for modifying existing messages or adding new messages but also relieves them of a serious burden of programming bugs. In addition, this system can be used for general client-server applications.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1994.10a
• /
• pp.32-32
• /
• 1994

In this example, a message passing based multicomputer system with general interdonnedtion network is considered. After multicomputer systems are developed with morm-hole routing network, topologies of interconecting network are not major considertion for process management and resource sharing. Tehre is an independeent operating system kernel oneach node. It communicates with other kernels using message passingmechanism. Based on this architecture, the problem is how mech does performance degradation will occur in the case of processor sharing on multicomputer systems. Processor sharing between application programs is veryimprotant decision on system performance. In almost cases, application programs running on massively parallel computer systems are not so much user-interactive. Thus, the main performance index is system throughput. Each application program has various communication patterns. and the sharing of processors causes serious performance degradation in hte worst case such that one processor is shared by two processes and another processes are waiting the messages from those processes. As a result, considering this problem is improtant since it gives the reason whether the system allows processor sharingor not. Input data has many parameters in this simulation . It contains the number of threads per task , communication patterns between threads, data generation and also defects in random inupt data. Many parallel aplication programs has its specific communication patterns, and there are computation and communication phases. Therefore, this phase informatin cannot be obtained random input data. If we get trace data from some real applications. we can simulate the problem more realistic . On the other hand, simualtion results will be waseteful unless sufficient trace data with varisous communication patterns is gathered. In this project , random input data are used for simulation . Only controllable data are the number of threads of each task and mapping strategy. First, each task runs independently. After that , each task shres one and more processors with other tasks. As more processors are shared , there will be performance degradation . Form this degradation rate , we can know the overhead of processor sharing . Process scheduling policy can affects the results of simulation . For process scheduling, priority queue and FIFO queue are implemented to support round-robin scheduling and priority scheduling.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.4
• /
• pp.192-200
• /
• 2002

The performance of a PC cluster system is limited by the use of traditional communication protocols, such as TCP/IP because these protocols are accompanied with significant software overheads. To overcome the problem, systems based on user-level interface for message passing without intervention of kernel have been developed. The VIA(Virtual Interface Architecture) is one of the representative user-level interfaces which provide low latency and high bandwidth. In this paper, a VIA system is implemented on an SCI(Scalable Coherent Interface) network based PC cluster. The system provides both message-passing and shared-memory programming environments and shows the maximum bandwidth of 84MB/s and the latency of $8{\mu}s$. The system also shows better performance in comparison with other comparable computer systems in carrying out parallel benchmark programs.

• Journal of Internet Computing and Services
• /
• v.6 no.6
• /
• pp.23-34
• /
• 2005

In a large scale parallel computation, failures of some nodes or communication links end up with waste of computing resources, Several fault-tolerant MPI libraries have been proposed so far, but the programs written by using such libraries have a portability problem since fault-tolerant features are not supported by the MPI standard yet, In this paper, we propose an application-level fault-tolerant linear system solver that uses the asynchronous iteration algorithm and the standard MPI functions only, which does not have a portability problem and is more efficient by adopting a simplified recovery mechanism.

• The KIPS Transactions:PartA
• /
• v.11A no.1
• /
• pp.67-74
• /
• 2004

Most of today's parallel numerical schemes use synchronous algorithms, where some processors that have finished their tasks earlier than others must wait at synchronization points for correct computation. Hence overall performance of the system is dependent upon the speed of the slowest processor. In this paper, we det·ise a synchronous/asynchronous hybrid algorithm to accelerate convergence of the solution for finding the dominant eigenpair of a large matrix, by reducing the idle times of faster processors using MPMD programming methodology.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.3
• /
• pp.792-803
• /
• 1999

Most data parallel language compilers are source-to-source translators. Most Compilers of HPF which is recognized as a standard data parallel language convert a parallel program in PHF in a Fortran 77 program inserted message passing primitives. By the way, they currently generate significant amount of ineffective codes in the course of the conversion. Especially, FORALL construct is converted into several DO loops, so loop overhead of these codes is very increased. In this paper, we define and use relation distance vector to keep necessary informations. Then we evaluate and analyze execution time for the codes converted by our method and by PARADIGM method for various array sizes.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10c
• /
• pp.313-315
• /
• 2002

메시지전달 프로그램에서 가장 먼저 발생하는 경합인 최초경합은 다른 경합에 영향을 주므로 반드시 탐지되어야 한다. 기존의 최초경합 탐지기법은 첫 번째 수행에서 각 프로세스에서 처음으로 발생하는 경합의 위치를 탐지하고, 두 번째 수행에서는 그 위치에서 해당 프로세스를 정지하여 경합하는 메시지를 보고한다. 그러나 이 기법은 프로세스를 중단하여 다른 경합에 영향을 주는 메시지의 전송을 단절시키므로 탐지된 경합들간의 영향관계를 알 수 없게 한다. 본 논문에서는 기존 기법의 두 번째 수행이 종료될 때까지 각 프로세스에서 처음으로 발생하는 경합들간의 영향관계를 추적화일에 기록하며, 수행이 종료된 후에 이 정보를 이용하여 경합들간의 영향관계와 상호 영향을 미치는 경합들을 추상적으로 시각화하는 기법을 제안한다. 이 기법은 경합들의 집합을 추상적으로나 구체적으로 시각화함으로써 경합들간의 영향관계를 확장적이고 직관적으로 알수 있게 한다. 따라서 본 기법은 최초경합을 수정함으로써 영향 받은 경합들을 사라지게 한 수 있으므로 메시지전달 프로그램의 효과적인 디버깅을 가능하게 한다.