Static tiling for heterogeneous computing platforms

Boulet, Pierre; Dongarra, Jack; Robert, Yves; Vivien, Frédéric

doi:10.1016/s0167-8191(99)00012-5

Cited by 24 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results reported below in table 2 show significant gains in performance. Note however that work is under study to use theoretical results from [BDRV99] so as to find the optimal number of emulated processes. New experiments are currently undertaken to evaluate the extra gain that can be obtained with this method.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Source Code Transformations Strategies to Load-Balance Grid Applications

David¹,

Genaud²,

Giersch³

et al. 2002

Grid Computing — GRID 2002

View full text Add to dashboard Cite

We present load-balancing strategies to improve performances of parallel MPI applications running in a Grid environment. We analyze the data distribution constraints found in two scientific codes and propose adapted code transformations to load-balance computations. We present the general framework for our load-balancing techniques. We then describe these techniques as well as their application to our examples. Experimental results confirm that adapted source code transformations can improve Grid application performances.

show abstract

Section: Resultsmentioning

confidence: 99%

“…The algorithm outlined here has been exposed in [BDRV99] where it is fully explained. We only exhibit the principles of the algorithm in the following.…”

Section: B1 Minimizing Algorithmmentioning

confidence: 99%

Source Code Transformations Strategies to Load-Balance Grid Applications

David¹,

Genaud²,

Giersch³

et al. 2002

Grid Computing — GRID 2002

View full text Add to dashboard Cite

show abstract

“…Under fluid schedule S fluid , each application A k is devoted a share k of the resource such that P n k¼1 k 1. From S fluid , we build an atomic model schedule S 1D using a 1D load-balancing algorithm [18]: at any time step, if n k is the number of tasks of application A k already scheduled, the next task to be scheduled is the one minimizing ðn k þ1ÞÂt k k . We can prove that under schedule S 1D , a task T does not terminate later than under S fluid .…”

Section: Basic Schedule Transformationsmentioning

confidence: 99%

“…2. We apply the 1D load-balancing algorithm [18] to S may have a makespan smaller that M (if the resource was not totally used in the original schedule S fluid ). In this case, our method automatically introduces idle time in the 1D schedule, to avoid to start a task too early.…”

Section: Basic Schedule Transformationsmentioning

confidence: 99%

Scheduling Concurrent Bag-of-Tasks Applications on Heterogeneous Platforms

Benoît

Marchal

Pineau

et al. 2010

IEEE Trans. Comput.

View full text Add to dashboard Cite

Abstract-Scheduling problems are already difficult on traditional parallel machines, and they become extremely challenging on heterogeneous clusters. In this paper, we deal with the problem of scheduling multiple applications, made of collections of independent and identical tasks, on a heterogeneous master-worker platform. The applications are submitted online, which means that there is no a priori (static) knowledge of the workload distribution at the beginning of the execution. The objective is to minimize the maximum stretch, i.e., the maximum ratio between the actual time an application has spent in the system and the time this application would have spent if executed alone. On the theoretical side, we design an optimal algorithm for the offline version of the problem (when all release dates and application characteristics are known beforehand). We also introduce a heuristic for the general case of online applications. On the practical side, we have conducted extensive simulations and MPI experiments, showing that we are able to deal with very large problem instances in a few seconds. Also, the solution that we compute totally outperforms classical heuristics from the literature, thereby fully assessing the usefulness of our approach.

show abstract

“…Ohta et al determine the optimal tile size by minimizing the theoretical execution time [16]. Boulet et al [3] and Chen et al [4] extend tiling based on execution time to heterogeneous computing. Desprez et al in [7] determine the processor idle time in two dimensional tiling for various tile shapes.…”

mentioning

confidence: 99%

An optimal scheduling scheme for tiling in distributed systems

Kyriakopoulos

Chronopoulos

2007

2007 IEEE International Conference on Cluster Computing

View full text Add to dashboard Cite

Abstract-There exist several scheduling schemes for parallelizing loops without dependences for shared and distributed memory systems. However, efficiently parallelizing loops with dependences is a more complicated task. This becomes even more difficult when the loops are executed on a distributed memory cluster where communication and synchronization can be a bottleneck. The problem lies in the processor idle time which occurs during the beginning and final stages of the execution. In this paper we propose a new scheduling scheme that minimizes the processor idle time and thus it enhances load balancing and performance. The new scheme is applied to two-dimensional iteration spaces with dependences. The proposed scheduling scheme follows a tiled wavefront pattern in which the tile size gradually decreases in all dimensions. We have tested the proposed scheme on a dedicated and homogeneous cluster of workstations and we verified that it significantly improves execution times over scheduling using traditional tiling.

show abstract

Static tiling for heterogeneous computing platforms

Cited by 24 publications

References 20 publications

Source Code Transformations Strategies to Load-Balance Grid Applications

Source Code Transformations Strategies to Load-Balance Grid Applications

Scheduling Concurrent Bag-of-Tasks Applications on Heterogeneous Platforms

An optimal scheduling scheme for tiling in distributed systems

Contact Info

Product

Resources

About