Papers by Victor Toporkov
Dependable Computer …, Jan 1, 2011
This work presents slot selection algorithms in economic models for independent job batch schedul... more This work presents slot selection algorithms in economic models for independent job batch scheduling in distributed computing with non-dedicated resources. Existing approaches towards resource co-allocation and multiprocessor job scheduling in economic models of ...
The satisfiability and algorithmic decidability problems are discussed for message passing models... more The satisfiability and algorithmic decidability problems are discussed for message passing models of distributed programs represented as processes communicating through buffers. The satisfiability means that parameters of the buffers are coordinated such that any admissible process histories do not result in appearance of deadlock situations. The decidability problem is reduced to finding the least stable marking on upper semi-lattice of labels of arcs and vertices of the generalized marked net of the distributed program with alternative selections, switches and forks of dataflows. The labels are allowed to be of arbitrary semantic nature. The generalized marked nets represent an algorithmically decidable class of dataflow models of distributed programs.
The usage of b-learning approach on in-service education activities in Turkish education system a... more The usage of b-learning approach on in-service education activities in Turkish education system are getting more and more important these days. Generally, traditional education and computer based education applications are used on in-service education activities. Blended learning (b-learning) combines online learning with face-to-face learning. The goal of blended learning is to provide the most efficient and effective learning experience by combining learning environments. The purpose of this research is to find out the effect of b-learning approach on developing administrators' leadership skills. To identify what the school administrators' educational needs and to know their existing leadership skills, needs assessment questionnaire was applied to 72 school administrators who were selected from 33 primary schools in 11 region of Ankara capital city. According to the descriptive statistical analysis results of questionnaire, in-service training programme was prepared for the development of school administrators' leadership skills. The school administrators were separated into three groups as computer based learning (CBL) (25 participants), blended learning (BL) (23 participants) and traditional learning (TL) (24 participant) groups. These groups were trained separately with these three different learning environments by using the in-service training programme. According to the results of pre-test, post test and achievements score means, it was observed that BL groups' score is the highest when compared to TL and CBL groups. As a result of this research, in terms of achievements and effectiveness, b-learning was found to be the most effective learning environment when compared to the others. Both learners and tutors findings strongly suggest that blended learning is available alternative delivery method for inservice education activities. 1
Parallel Computing …, Jan 1, 2011
In this paper, we present slot selection algorithms for job batch scheduling in distributed compu... more In this paper, we present slot selection algorithms for job batch scheduling in distributed computing with non-dedicated resources. Jobs are parallel applications and these applications are independent. Existing approaches towards resource co-allocation and ...
The report presents cooperation capabilities of CAD Centre at the Technical University "Moscow Po... more The report presents cooperation capabilities of CAD Centre at the Technical University "Moscow Power Engineering Institute" (MPEI) in the area of heterogeneous system design. The problem of system-level synthesis is considered as hardware/ software codesign with result prediction in the early stages of the controled partitioning accounting adjacent effects. This approach avoids apriority restrictions in the system specification, allows the argument choice of candidates for hardware implementation introducing a set of interactive high-level models for an internal representation. The fundamentally new feature of the approach is the possibility to estimate an upper bound of the system implementation complexity.
Dependability of …, Jan 1, 2009
This paper presents the scheduling strategies in distributed computing. The fact that architectur... more This paper presents the scheduling strategies in distributed computing. The fact that architecture of the computational environment is distributed, heterogeneous, and dynamic along with autonomy of processor nodes, makes it much more difficult to manage and assign resources for job execution which fulfils user expectations for quality of service (QoS). The strategies are implemented using a combination of job-flow and application-level techniques of scheduling and resource co-allocation. Strategy is considered as a set of possible job scheduling variants with a coordinated allocation of the tasks to the processor nodes. Applications are regarded as compound jobs with a complex structure containing several tasks. The choice of the specific scheduling depends on the load level of the resource dynamics and is formed as a resource request, which is sent to a local batch-job management system.
Procedia Computer …, Jan 1, 2011
In this paper, we present slot selection algorithms in economic models for independent job batch ... more In this paper, we present slot selection algorithms in economic models for independent job batch scheduling in distributed computing with non-dedicated resources. Existing approaches towards resource co-allocation and multiprocessor job scheduling in economic models of distributed computing are based on search of time-slots in resource occupancy schedules. The sought time-slots must match requirements of necessary span, computational resource properties, and cost. Usually such scheduling methods consider only one suited variant of time-slot set. This paper discloses a scheduling scheme that features multi-variant search. Two algorithms of linear complexity for search of alternative variants are compared. Having several optional resource configurations for each job makes an opportunity to perform an optimization of execution of the whole batch of jobs and to increase overall efficiency of scheduling.
alzaytoonah.edu.jo
This paper presents an integrated approach for scheduling in distributed computing with strategie... more This paper presents an integrated approach for scheduling in distributed computing with strategies as sets of job supporting schedules generated by a critical works method. The strategies are implemented using a combination of job-flow and application-level techniques of scheduling within virtual organizations of Grid. Applications are regarded as compound jobs with a complex structure containing several tasks co-allocated to processor nodes. The choice of the specific schedule depends on the load level of the resource dynamics and is formed as a resource request, which is sent to a local batch-job management system. We propose scheduling framework and compare diverse types of scheduling strategies using simulation studies.
The paper presents an approach for system-level partitioning of a dataflowdominated functionality... more The paper presents an approach for system-level partitioning of a dataflowdominated functionality based on possibilistic estimations of cost and timing delays. Strong data connectivity causes the necessity of a global dataflow analysis for tightly interactive partitioning and scheduling. A possibilistic graph, data connectivity and complexity measures allow to reduce a scope of the partitioning problem. Cost and performance estimations of a system specification base on a global dataflow analysis with the polynomial complexity. Minimization tasks for given constraints are reduced to the number of the critical path operations.
ubicc.org
In this work, we present slot selection algorithms for job batch scheduling in distributed comput... more In this work, we present slot selection algorithms for job batch scheduling in distributed computing with non-dedicated resources. Jobs are parallel applications and these applications are independent. Existing approaches towards resource coallocation and parallel job scheduling in economic models of distributed computing are based on search of time-slots in resource occupancy schedules. The sought time-slots must match requirements of necessary span, computational resource properties, and cost. Usually such scheduling methods consider only one suited variant of time-slot set. This work discloses a scheduling scheme that features multi-variant search. Two algorithms of linear complexity for search of alternative variants are proposed. Having several optional resource configurations for each job makes an opportunity to perform an optimization of execution of the whole batch of jobs and to increase overall efficiency of scheduling.
… on Computer Systems …, Jan 1, 2010
In this paper, we present an approach to scalable coscheduling in distributed computing for compl... more In this paper, we present an approach to scalable coscheduling in distributed computing for complex sets of interrelated tasks (jobs). The scalability means that schedules are formed for job models with various levels of task granularity, data replication policies, and the processor resource and memory can be upgraded. The necessity of guaranteed job execution at the required quality of service causes taking into account the distributed environment dynamics, namely, changes in the number of jobs for servicing, volumes of computations, possible failures of processor nodes, etc. As a consequence, in the general case, a set of versions of scheduling, or a strategy, is required instead of a single version. We propose a scalable model of scheduling based on multicriteria strategies. The choice of the specific schedule depends on the load level of the resource dynamics and is formed as a resource query which is sent to a local batch-job management system.
International Journal of Critical …, Jan 1, 2010
In this paper, we present an approach to safety scheduling in distributed computing based on stra... more In this paper, we present an approach to safety scheduling in distributed computing based on strategies of resource co-allocation for complex sets of tasks (jobs). The necessity of guaranteed job execution until the time limits requires taking into account the distributed environment dynamics, namely, changes in the number of jobs for servicing, volumes of computations, possible failures of processor nodes, etc. As a consequence, in the general case, a set of versions of scheduling and resource co-allocation, or a strategy, is required instead of a single version. Safety strategies are formed for structurally different job models with various levels of task granularity and data replication policies. We develop and consider scheduling strategies which combine fine-grain and coarse-grain computations, multiple data replicas and constrained data movement. These strategies are evaluated using simulations studies and addressing a variety of metrics.
Parallel Computing Technologies, Jan 1, 2009
This paper presents the scheduling strategies framework for distributed computing. The fact that ... more This paper presents the scheduling strategies framework for distributed computing. The fact that architecture of the computational environment is distributed, heterogeneous, and dynamic along with autonomy of processor nodes, makes it much more difficult to manage ...
… and Communication (UbiCC) Journal. Special Issue …, Jan 1, 2009
This paper presents an integrated approach for scheduling in distributed computing with strategie... more This paper presents an integrated approach for scheduling in distributed computing with strategies as sets of job supporting schedules generated by a critical works method. The strategies are implemented using a combination of job-flow and application-level techniques of scheduling within virtual organizations of Grid. Applications are regarded as compound jobs with a complex structure containing several tasks co-allocated to processor nodes. The choice of the specific schedule depends on the load level of the resource dynamics and is formed as a resource request, which is sent to a local batch-job management system. We propose scheduling framework and compare diverse types of scheduling strategies using simulation studies.
Third International Conference on …, Jan 1, 2008
In this paper, we present an approach to safety scheduling in distributed computing based on stra... more In this paper, we present an approach to safety scheduling in distributed computing based on strategies of resource co-allocation. Safety strategies are formed for structurally different program models with various levels of task granularity and data replication policies. We develop and consider scheduling strategies which combine fine-grain and coarse-grain computations, multiple data replicas, and constrained data movement. These strategies are evaluated using simulations studies and addressing a variety of metrics.
Parallel Computing Technologies, Jan 1, 2007
An approach to generation and optimization of scheduling and resource allocation strategies in sc... more An approach to generation and optimization of scheduling and resource allocation strategies in scalable computing systems is proposed. The approach allows the decomposition of the problem of multicriteria strategy synthesis for the totality of parameterized models of programs with the use of partial and vector quality criteria including, for instance, a cost function and load balancing factors.
Proceedings of the conference on European design …, Jan 1, 1995
The paper presents an approach for performance and complexity analysis of hardware/software imple... more The paper presents an approach for performance and complexity analysis of hardware/software implementations for real-time systems on every stage of the partitioning. There are two main features of the approach. The first one is the rapid performancecomplexity estimations for software based on the set of introduced stochastic characteristics. The second one is the systematic exploration of the codesign space, that enables to determine the partition process direction. These properties allow the renovation of the codesegment candidate list for hardware implementation during the partitioning with internal representation transformations, and the significant design space reduction.
Uploads
Papers by Victor Toporkov