The Experts below are selected from a list of 15372 Experts worldwide ranked by ideXlab platform
Sivarama P. Dandamudi - One of the best experts on this subject based on the ideXlab platform.
-
Performance with Synchronization Workloads
Hierarchical Scheduling in Parallel and Cluster Systems, 2003Co-Authors: Sivarama P. DandamudiAbstract:In the last two chapters, we used coarse-grain parallelism to evaluate performance of the hierarchical task queue Organization. This chapter studies its performance under fine-grain parallelism. We use two workload models: lock accessing and barrier synchronization. The lock accessing workload models tasks with a critical section protected by a lock. In barrier synchronization, tasks iterate through a computation phase and a communication phase. Using these two workloads, we study the impact of spinning and blocking synchronization methods on the performance of the hierarchical and distributed Organizations. The Centralized Organization is not considered here because it is not a scalable Organization.
-
HPCN Europe - Buffer Management in Wormhole-Routed Torus Multicomputer Networks
Future Generation Computer Systems, 2000Co-Authors: Kamala Kotapati, Sivarama P. DandamudiAbstract:Abstract This paper focuses on buffer management issues in wormhole-routed torus multicomputer networks. The commonly used buffer Organizations are the Centralized and dedicated buffer Organizations. The results presented in this paper indicate that the dedicated buffer Organization provides better performance than the Centralized Organization under uniform traffic. Under high hot-spot traffic, the Centralized Organization outperforms the dedicated. The hybrid buffer Organization proposed in this paper inherits the merits of the Centralized and distributed Organizations. Our results suggest that the hybrid buffer Organization can be designed to configure dynamically from the dedicated to Centralized depending on the traffic conditions.
-
A Hierarchical Task Queue Organization for
1995Co-Authors: Sivarama P. Dandamudi, Philip S. P. ChengAbstract:There are two basic ways in which waiting ready tasks can be organized: Centralized Organization or dishibuted Organization. In the Centralized Organization, a single central task queue is maintained. In the latter case, each processor has its own private ready queue of tasks. Ideally, a central ready queue global to all processors is desired over the distributed organiza- tion because the Centralized Organization provides perfect load sharing. However, the Centralized Organization is not suitable for large parallel systems because the central task queue could become a system bottleneck. The distributed Organization, on the other hand, creates the load imbalance problem, which results in performance deterioration. While techniques have been proposed to reduce the ill-effects of task queue contention in the Centralized Organization and load imbalance in the distributed Organization these techniques introduce problems of their own. In this paper we propose the use of a hierarchical task queue Organization to incorporate the best features of these two Organizations. Our study into the performance of this hierarchical Organization shows that a properly designed hierarchical Organization provides performance very close to that of the Centralized Organization while eliminating the ready queue contention problem, We also provide an analysis that identifies and provides guidance for de- signing the hierarchical task queue Organization that avoids ready queue access contention. A brief discussion of task scheduling policies is also included.
-
A hierarchical task queue Organization for shared-memory multiprocessor systems
IEEE Transactions on Parallel and Distributed Systems, 1995Co-Authors: Sivarama P. Dandamudi, Philip S. P. ChengAbstract:There are two basic ways in which waiting ready tasks can be organized: Centralized Organization or distributed Organization. In the Centralized Organization, a single central task queue is maintained. In the latter case, private ready queue of tasks. Ideally, a central ready queue global to all processors is desired over the distributed Organization because the Centralized Organization provides perfect load sharing. However, the Centralized Organization is not suitable for large parallel systems because the central task queue could become a system bottleneck. The distributed Organization, on the other hand, creates the load imbalance problem, which results in performance deterioration, while techniques have been proposed to reduce the ill-effects of task queue contention in the Centralized Organization and load imbalance in the distributed Organization these techniques introduce problems of their own. We propose the use of a hierarchical task queue Organization to incorporate the best features of these two Organizations. Our study into the performance of this hierarchical Organization shows that a properly designed hierarchical Organization provides performance very close to that of the Centralized Organization while eliminating the ready queue contention problem, we also provide an analysis that identifies and provides guidance for designing the hierarchical task queue Organization that avoids ready queue access contention. A brief discussion of task scheduling policies is also included. >
-
performance analysis of hierarchical task queue Organization for parallel systems
International Conference on Distributed Computing Systems, 1992Co-Authors: S. P. Cheng, Sivarama P. DandamudiAbstract:A hierarchical task queue Organization that avoids the task queue bottleneck associated with the Centralized Organization and provides performance better than Centralized and distributed Organizations is proposed. A detailed performance analysis shows that the hierarchical Organization is less sensitive to parameters like the branching factor and transfer factor. Therefore, it is suitable for large parallel systems. >
S. P. Cheng - One of the best experts on this subject based on the ideXlab platform.
-
performance analysis of hierarchical task queue Organization for parallel systems
International Conference on Distributed Computing Systems, 1992Co-Authors: S. P. Cheng, Sivarama P. DandamudiAbstract:A hierarchical task queue Organization that avoids the task queue bottleneck associated with the Centralized Organization and provides performance better than Centralized and distributed Organizations is proposed. A detailed performance analysis shows that the hierarchical Organization is less sensitive to parameters like the branching factor and transfer factor. Therefore, it is suitable for large parallel systems. >
-
ICS - Scheduling in parallel systems with a hierarchical Organization of tasks
Proceedings of the 6th international conference on Supercomputing - ICS '92, 1992Co-Authors: S. P. Cheng, Sivarama P. DandamudiAbstract:To exploit multiple processors, a job is usually partitioned into several tasks that can be executed concurrently. These tasks wait for processors in task ready queue(s). There are two basic ways in which waiting ready tasks can be organized: Centralized Organization or distributed Organization. In a Centralized Organization, a single central task queue is maintained. In the latter case, each processor has its own private ready queue of tasks. Ideally, a central ready queue global to all processors is desired over the distributed Organization. However, the Centralized Organization is not suitable for large parallel systems because the global task queue could become a bottleneck. A hierarchical Organization has been proposed to incorporate the good features of these two Organizations. This paper studies the impact of job and task scheduling policies on the performance of the hierarchical Organization.
-
ICDCS - Performance analysis of hierarchical task queue Organization for parallel systems
[1992] Proceedings of the 12th International Conference on Distributed Computing Systems, 1Co-Authors: S. P. Cheng, Sivarama P. DandamudiAbstract:A hierarchical task queue Organization that avoids the task queue bottleneck associated with the Centralized Organization and provides performance better than Centralized and distributed Organizations is proposed. A detailed performance analysis shows that the hierarchical Organization is less sensitive to parameters like the branching factor and transfer factor. Therefore, it is suitable for large parallel systems. >
Philip S. P. Cheng - One of the best experts on this subject based on the ideXlab platform.
-
A Hierarchical Task Queue Organization for
1995Co-Authors: Sivarama P. Dandamudi, Philip S. P. ChengAbstract:There are two basic ways in which waiting ready tasks can be organized: Centralized Organization or dishibuted Organization. In the Centralized Organization, a single central task queue is maintained. In the latter case, each processor has its own private ready queue of tasks. Ideally, a central ready queue global to all processors is desired over the distributed organiza- tion because the Centralized Organization provides perfect load sharing. However, the Centralized Organization is not suitable for large parallel systems because the central task queue could become a system bottleneck. The distributed Organization, on the other hand, creates the load imbalance problem, which results in performance deterioration. While techniques have been proposed to reduce the ill-effects of task queue contention in the Centralized Organization and load imbalance in the distributed Organization these techniques introduce problems of their own. In this paper we propose the use of a hierarchical task queue Organization to incorporate the best features of these two Organizations. Our study into the performance of this hierarchical Organization shows that a properly designed hierarchical Organization provides performance very close to that of the Centralized Organization while eliminating the ready queue contention problem, We also provide an analysis that identifies and provides guidance for de- signing the hierarchical task queue Organization that avoids ready queue access contention. A brief discussion of task scheduling policies is also included.
-
A hierarchical task queue Organization for shared-memory multiprocessor systems
IEEE Transactions on Parallel and Distributed Systems, 1995Co-Authors: Sivarama P. Dandamudi, Philip S. P. ChengAbstract:There are two basic ways in which waiting ready tasks can be organized: Centralized Organization or distributed Organization. In the Centralized Organization, a single central task queue is maintained. In the latter case, private ready queue of tasks. Ideally, a central ready queue global to all processors is desired over the distributed Organization because the Centralized Organization provides perfect load sharing. However, the Centralized Organization is not suitable for large parallel systems because the central task queue could become a system bottleneck. The distributed Organization, on the other hand, creates the load imbalance problem, which results in performance deterioration, while techniques have been proposed to reduce the ill-effects of task queue contention in the Centralized Organization and load imbalance in the distributed Organization these techniques introduce problems of their own. We propose the use of a hierarchical task queue Organization to incorporate the best features of these two Organizations. Our study into the performance of this hierarchical Organization shows that a properly designed hierarchical Organization provides performance very close to that of the Centralized Organization while eliminating the ready queue contention problem, we also provide an analysis that identifies and provides guidance for designing the hierarchical task queue Organization that avoids ready queue access contention. A brief discussion of task scheduling policies is also included. >
Jesus Gomezgardenes - One of the best experts on this subject based on the ideXlab platform.
-
from modular to Centralized Organization of synchronization in functional areas of the cat cerebral cortex
PLOS ONE, 2010Co-Authors: Jesus Gomezgardenes, Gorka Zamoralopez, Yamir Moreno, Alex ArenasAbstract:Recent studies have pointed out the importance of transient synchronization between widely distributed neural assemblies to understand conscious perception. These neural assemblies form intricate networks of neurons and synapses whose detailed map for mammals is still unknown and far from our experimental capabilities. Only in a few cases, for example the C. elegans, we know the complete mapping of the neuronal tissue or its mesoscopic level of description provided by cortical areas. Here we study the process of transient and global synchronization using a simple model of phase-coupled oscillators assigned to cortical areas in the cerebral cat cortex. Our results highlight the impact of the topological connectivity in the developing of synchronization, revealing a transition in the synchronization Organization that goes from a modular deCentralized coherence to a Centralized synchronized regime controlled by a few cortical areas forming a Rich-Club connectivity pattern.
Alex Arenas - One of the best experts on this subject based on the ideXlab platform.
-
from modular to Centralized Organization of synchronization in functional areas of the cat cerebral cortex
PLOS ONE, 2010Co-Authors: Jesus Gomezgardenes, Gorka Zamoralopez, Yamir Moreno, Alex ArenasAbstract:Recent studies have pointed out the importance of transient synchronization between widely distributed neural assemblies to understand conscious perception. These neural assemblies form intricate networks of neurons and synapses whose detailed map for mammals is still unknown and far from our experimental capabilities. Only in a few cases, for example the C. elegans, we know the complete mapping of the neuronal tissue or its mesoscopic level of description provided by cortical areas. Here we study the process of transient and global synchronization using a simple model of phase-coupled oscillators assigned to cortical areas in the cerebral cat cortex. Our results highlight the impact of the topological connectivity in the developing of synchronization, revealing a transition in the synchronization Organization that goes from a modular deCentralized coherence to a Centralized synchronized regime controlled by a few cortical areas forming a Rich-Club connectivity pattern.