• KIPS Transactions on Computer and Communication Systems
• /
• v.2 no.6
• /
• pp.237-244
• /
• 2013

We propose Energy-constrained Multiprocessor Real-Time Scheduling algorithms for (m,k)-firm deadline constrained tasks (EMRTS-MK). Rather than simply saving as much energy as possible, we consider energy as hard constraint under which the system remains functional and delivers an acceptable performance at least during the prescribed mission time. We evaluate EMRTS-MKs in several experiments, which quantitatively show that they achieve the scheduling objectives.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.289-293
• /
• 2000

We propose two new algorithms for parallelism-independent scheduling. The machine code generated from the compiler using these algorithms in its scheduling phase is parallelism-independent code, executable in minimum time regardless of the number of the processors in the parallel computer. Our new algorithms have the following phases: finding the minimum number of processors on which the program can be executed in minimal time, scheduling by an heuristic algorithm for this predefined number of processors, and serialization of the parallel schedule according to the earliest start time of the tasks. At run time tasks are taken from the serialized schedule and assigned to the processor which allows the earliest start time of the task. The order of the tasks decided at compile time is not changed at run time regardless of the number of the available processors which means there is no out-of-order issue and execution. The scheduling is done predominantly at compile time and dynamic scheduling is minimized and diminished to allocation of the tasks to the processors. We evaluate the proposed algorithms by comparing them in terms of schedule length to the CP/MISF algorithm. For performance evaluation we use both randomly generated DAGs (directed acyclic graphs) and DACs representing real applications. From practical point of view, the algorithms we propose can be successfully used for scheduling programs for in-order superscalar processors and shared memory multiprocessor systems. Superscalar processors with any number of functional units can execute the parallelism-independent code in minimum time without necessity for dynamic scheduling and out-of-order issue hardware. This means that the use of our algorithms will lead to reducing the complexity of the hardware of the processors and the run-time overhead related to the dynamic scheduling.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.6
• /
• pp.3046-3070
• /
• 2017

Nowadays, the utilization of multiprocessor environments has been increased due to the increase in time complexity of application programs and decrease in hardware costs. In such architectures during the compilation step, each program is decomposed into the smaller and maybe dependent segments so-called tasks. Precedence constraints, required execution times of the tasks, and communication costs among them are modeled using a directed acyclic graph (DAG) named task-graph. All the tasks in the task-graph must be assigned to a predefined number of processors in such a way that the precedence constraints are preserved, and the program's completion time is minimized, and this is an NP-hard problem from the time-complexity point of view. The results obtained by different approaches are dominated by two major factors; first, which order of tasks should be selected (sequence subproblem), and second, how the selected sequence should be assigned to the processors (assigning subproblem). In this paper, a hybrid proposed approach has been presented, in which two different artificial ant colonies cooperate to solve the multiprocessor task-scheduling problem; one colony to tackle the sequence subproblem, and another to cope with assigning subproblem. The utilization of background knowledge about the problem (different priority measurements of the tasks) has made the proposed approach very robust and efficient. 125 different task-graphs with various shape parameters such as size, communication-to-computation ratio and parallelism have been utilized for a comprehensive evaluation of the proposed approach, and the results show its superiority versus the other conventional methods from the performance point of view.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.3_4
• /
• pp.194-204
• /
• 2003

The performance of a shared memory multiprocessor system is dependent on the system software such as scheduling policy as well as hardware system. Most of existing simulators, however, do not support simulation for multi-programmed environment because they can execute only a single benchmark application at a time. We propose a multi-programmed simulation method on a program-driven simulator, which enables the concurrent executions of multiple parallel workloads contending for limited system resources. Using the proposed method, system developers can measure and analyze detailed effects of resource conflicts among the concurrent applications as well as the effects of scheduling policies on a program-driven simulator. As a result, the proposed multi-programmed simulation provides more accurate and realistic performance projection to design a multiprocessor system.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.630-633
• /
• 2007

클러스터를 이용하여 다수의 작업을 실행시키는 경우에 효율적으로 사용자들이 자원을 사용하기 위해서는 작업 스케줄링이 매우 중요하다. 다양한 스케줄링 방법들이 제안되었으며 그 중 효율적으로 병렬 작업을 스케쥴링하기 위해 제안된 방법으로는 backfilling, co-scheduling, gang scheduling을 들 수 있다. 이러한 연구에서는 이론적인 논의가 많았고, 실제로 구현을 했다고 하더라고 multiprocessor 를 대상으로 backfilling 을 다룬 내용이 대부분이었다. 이 논문은 클러스터상에서의 parallel job scheduling 에 대해 조사하였다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.29 no.11
• /
• pp.611-621
• /
• 2002

For real-time systems, multiprocessor support is indispensable to handle the large number of requests. Existing real-time on-line scheduling algorithms such as Earliest Deadline First Algorithm (EDF) and Least Laxity Algorithm (LLA) may not be suitable for scheduling real-time tasks in multiprocessor systems. Although EDF has low context switching overhead, it suffers from "multiple processor anomalies." LLA has been shown as suboptimal, but has the potential for higher context switching overhead. Earliest Deadline Zero Laxity (EDZL) solved somewhat the problems of those algorithms, however is suboptimal for only two processors. Another algorithm EDA2 shows very good performance in overload phase, however, is not suboptimal for muitiprocessors. We propose two on-line scheduling algorithms, Earliest Deadline/Least Laxity (ED/LL) and ED2/LL. ED/LL is suboptimal for multiprocessors, and has low context switching overhead and low deadline miss rate in normal load phase. However, ED/LL is ineffective when the system is overloaded. To solve this problem, ED2/LL uses ED/LL or EDZL in normal load phase and uses EDA2 in overload phase. Experimental results show that ED2/LL achieves good performance in overload phase as wet] as in normal load phase.oad phase.

• Journal of Electrical Engineering and information Science
• /
• v.2 no.3
• /
• pp.105-112
• /
• 1997

The performance of a shared memory multiprocessor system is very sensitive to process scheduling. w can enhance the performance of a whole system as well as of an individual process by taking the multiprocessor characteristics into account in the design of the process scheduler. In this paper, we proposed a general purpose scheduler for a shared memory multiprocessor, called the Two-Level Multi-Scan (TLMS) process scheduler, that considers the processor affinity loosely and decreases the interference among multiple processors greatly. The TLMS scheduler is composed of a local scheduler at each processor and a semi-global scheduler that balances the load among processors. In particular, the semi-global scheduler tries to minimize priority inversion, which is an important factor of the system performance. The TLMS scheduler also tries to reduce the number of resources to be shared and improves the processor utilization. to meet these requirements, th semi-global scheduler interacts with the operation of the local scheduler when a need arises, thus the name is loose processor-affinity. We also show that the proposed scheduling technique can be extended for other types of resources making it a general purpose resource management queue.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.430-433
• /
• 1999

Woo[8]proposed dual-token based fault-tolerant scheduling algorithm in multiprocessor environment for resolving the problem of old systems that have a central dispatcher processor. However, this algorithm does not present token allocation algorithm in detail when central dispatcher processor has failed. In this paper, we propose a fault detection algorithm and processor selection algorithm for token allocation when central dispatcher processor has failed.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.21 no.1
• /
• pp.147-161
• /
• 1996

Generally the Multiprocessor Scheduling (MPS) problem is difficult to solve because of the precedence of the tasks, and it takes a lot of time to obtain its optimal solution. Though Genetic Algorithm (GA) does not guarantee the optimal solution, it is practical and effective to solve the MPS problem in a reasonable time. The algorithm developed in this research consists of a improved GA and GP/MISF (Critical Path/Most Immediate Successors First). An efficient genetic operator is derived to make GA more efficient. It runs parallel CP/MISF with GA to complement the faults of GA. The solution by the developed algorithm is compared with that of CP/MISF, and the better is taken as a final solution. As a result of comparative analysis by using numerical examples, although this algorithm does not guarantee the optimal solution, it can obtain an approximate solution that is much closer to the optimal solution than the existing GA's.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1995.09a
• /
• pp.220-229
• /
• 1995

Generally the Multiprocessor Scheduling(MPS) problem is difficult to solve because of the precedence of the tasks, and it takes a lot of time to obtain its optimal solution. Though Genetic Algorithm(GA) does not guarantee the optimal solution, it is practical and effective to solve the MPS problem in a reasonable time. The algorithm developed in this research consists of a improved GA and CP/MISF(Critical Path/Most Immediate Successors First). A new genetic operator is derived to make GA more efficient. It runs parallel CP/MISF with Ga to complement the faults of GA. The solution by the developed algorithm is compared with that of CP/MISF, and the better is taken as a final solution. As a result of comparative analysis by using numerical examples, although this algorithm does not guarantee the optimal solution, it can obtain an approximate solution that is much closer to the optimal solution than the existing GA's.