• 대한전자공학회논문지
• /
• 제17권5호
• /
• pp.36-42
• /
• 1980

본 연구에서는, 8085CPU 4대를 사용하여서, 주마이크로프로세서의 버스에 DMA장치를 통하여 종마이크로프로세서에 접속되는 복합마이크로프로세서 시스템을 설계하여서 병렬처리 시킴으로서 처리효율을 높일 수 있었다. 마이크로프로세서의 동작대수와 시스템 Throughput의 관계를 측정한 결과, 이상치의 70∼80퍼센트 정도에 머무는 결과를 얻었다. 자원의 할당이나 일정계획은 주마이크로프로세서가 이루도록 하였고, 마이크로프로세서 사이의 통신 및 공유데이터의 격납은 공유메모리를 사용하도록 하였다. 또한 직렬로 작성된 원시프로그램으로 부터 병렬성을 검출하는 방법을 제시하였다.

• 한국멀티미디어학회논문지
• /
• 제18권11호
• /
• pp.1367-1374
• /
• 2015

In this paper, we propose a model which can prioritize the performance improvement work by analyzing the major risks and their influence, which can cause performance degradation in the system and show an example of a performance improvement using this model. In presentation-tier, as a result of log data analysis before and after the performance improvement of key processes which handle financial transactions, this model brought the CPU utilization and memory enhancement in the performance improvement work of the financial system which was carried out by applying the proposed model. It has been confirmed that the entire end-user can be accommodated. In the web-tier, the available memory increased by 200MB and we were able to improve the server restart(Recycling) that was sustained in the existing system. In the business logic-tier, we have been able to see better figures after performance improvements through the graph which analyzes the log collected with the key performance counters such as CPU%, Batch Requests/sec. In the data-tier, it has been confirmed that CPU usage and standby operation were reduced and the throughput was found to increase.

• 한국컴퓨터정보학회논문지
• /
• 제13권5호
• /
• pp.45-52
• /
• 2008

본 논문에서는 고성능 컴퓨팅 시스템의 성능 향상을 위한 효율적인 동적 작업부하 균등화 정책을 제안한다. 이 정책은 시스템 자원인 CPU와 메모리를 효율적으로 사용하여 고성능 컴퓨팅 시스템의 처리량을 최대화하고, 각 작업의 수행시간을 최소화한다. 또한 이 정책은 수행중인 작업의 메모리 요구량과 각 노드의 부하 상태를 파악하여 작업을 동적으로 할당한다. 이때 작업을 할당받은 노드가 과부하 상태가 되면 다른 노드로 작업을 이주시켜 각 노드의 작업부하를 균등하게 유지함으로써 작업의 대기시간을 줄이고, 각 작업의 수행시간을 단축한다. 본 논문에서는 시뮬레이션을 통하여 제안하는 동적 작업부하 균등화 정책이 기존의 메모리 기반의 작업부하 균등화 정책에 비해 고성능 컴퓨팅 시스템의 성능 향상 면에서 우수함을 보인다.

• 한국멀티미디어학회논문지
• /
• 제18권5호
• /
• pp.620-630
• /
• 2015

This research suggests a load balancing method for a volume rendering system which supports concurrent users. When concurrent users use a volume rendering server system, the computational resources are occupied by a particular user by turns because each process consumes the computational resources as much as possible. In this case, the previous method shows acceptable throughput but the latency is increased for each user. In this research, we suggest a method to improve the latency without performance degradation. Each process makes concessions for taking the resources according to the number of users connected to the system. And we propose a load balancing method in the dynamic situation in which the number of users can vary. Using our methods, we can improve the latency time for each user.

• 한국컴퓨터정보학회논문지
• /
• 제22권4호
• /
• pp.17-24
• /
• 2017

In this paper, we propose an efficient dynamic workload balancing strategy which improves the performance of high-performance computing system. The key idea of this dynamic workload balancing strategy is to minimize execution time of each job and to maximize the system throughput by effectively using system resource such as CPU, memory. Also, this strategy dynamically allocates job by considering demanded memory size of executing job and workload status of each node. If an overload node occurs due to allocated job, the proposed scheme migrates job, executing in overload nodes, to another free nodes and reduces the waiting time and execution time of job by balancing workload of each node. Through simulation, we show that the proposed dynamic workload balancing strategy based on CPU, memory improves the performance of high-performance computing system compared to previous strategies.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권4호
• /
• pp.294-301
• /
• 2016

In this paper, we present methods to efficiently parallelize iterative 3D image reconstruction by exploiting trigeneous devices (three different types of device) at the same time: a CPU, an integrated GPU, and a discrete GPU. We first present a technique that exploits single instruction multiple data (SIMD) architectures in GPUs. Then, we propose a performance estimation model, based on which we can easily find the optimal data partitioning on trigeneous devices. We found that the performance significantly varies by up to 6.23 times, depending on how SIMD units in GPUs are accessed. Then, by using trigeneous devices and the proposed estimation models, we achieve optimal partitioning and throughput, which corresponds to a 9.4% further improvement, compared to discrete GPU-only execution.

• 한국컴퓨터정보학회논문지
• /
• 제21권1호
• /
• pp.147-153
• /
• 2016

In this paper, we propose an efficient dynamic workload balancing strategy which improves the performance of high-performance computing system. The key idea of this dynamic workload balancing strategy is to minimize execution time of each job and to maximize the system throughput by effectively using system resource such as CPU, memory. Also, this strategy dynamically allocates job by considering demanded memory size of executing job and workload status of each node. If an overload node occurs due to allocated job, the proposed scheme migrates job, executing in overload nodes, to another free nodes and reduces the waiting time and execution time of job by balancing workload of each node. Through simulation, we show that the proposed dynamic workload balancing strategy based on CPU, memory improves the performance of high-performance computing system compared to previous strategies.

• 한국컴퓨터정보학회논문지
• /
• 제21권1호
• /
• pp.125-129
• /
• 2016

In this paper, we propose an efficient dynamic workload balancing strategy which improves the performance of high-performance computing system. The key idea of this dynamic workload balancing strategy is to minimize execution time of each job and to maximize the system throughput by effectively using system resource such as CPU, memory. Also, this strategy dynamically allocates job by considering demanded memory size of executing job and workload status of each node. If an overload node occurs due to allocated job, the proposed scheme migrates job, executing in overload nodes, to another free nodes and reduces the waiting time and execution time of job by balancing workload of each node. Through simulation, we show that the proposed dynamic workload balancing strategy based on CPU, memory improves the performance of high-performance computing system compared to previous strategies.

• 한국군사과학기술학회지
• /
• 제10권2호
• /
• pp.115-125
• /
• 2007

The ubiquitous embedded computers are firmly established as the basic electronic component of design that control military systems. Such applications can be found everywhere in the field of military system. A embedded computer is required to redesign when system needs performance upgrade or production-state of processor is NRND or EOL. This paper describes a scheme about impact analysis of designing processor alteration on embedded computer. In this case, hardware architecture and interrupt source of target system must be considered. Also, performance and throughput of that must be analyzed.

• International Journal of Contents
• /
• 제3권1호
• /
• pp.34-38
• /
• 2007

Load redistribution is a critical resource in computer system. In sender-initiated load redistribution algorithms, the sender continues to send unnecessary request messages for load transfer until a receiver is found while the system load is heavy. These unnecessary request messages result in inefficient communications, low CPU utilization, and low system throughput in distributed systems. To solve these problems, we propose a genetic algorithm based approach for improved sender-initiated load redistribution in distributed systems. Compared with the conventional sender-initiated algorithms, the proposed algorithm decreases the response time and task processing time.