A framework for adaptive execution in grids

Huedo, Eduardo; Montero, Rubén; Llorente, Ignacio

doi:10.1002/spe.584

Cited by 239 publications

(163 citation statements)

References 31 publications

Supporting

Mentioning

158

Contrasting

Unclassified

Order By: Relevance

“…Job co-scheduling for High-end computing (HEC) systems often use a single job submission portal [18,20]. But such approaches using a centralized resource manager do not scale.…”

Section: Related Workmentioning

confidence: 99%

Distributed Job Allocation for Large-Scale Manycores

Ramachandran

Mueller

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

As today's manycore processors already feature over 64 cores and as tomorrow's are slated to contain 1000s, it is important to design operating system techniques that can efficiently cope with this scale of resource coordination. The current state-of-the-art in manycore processor architectures has evolved from traditional bus-based architectures over rings to mesh-based Network-on-Chip (NoC) interconnects. This implies an increasing potential for scalable message passing. However, contemporary operating systems heavily rely on single system images with shared memory constructs that may not scale well to large core counts. To address these challenges, we devise a distributed message passing only system comprised of so-called "pico-kernels" per core. They are controlled by dedicated "micro-kernels" topologically centered within a set of cores that cooperatively comprise the overall operating system in a peer-to-peer fashion.Such a system promotes rethinking and redesigning of various operating system services focusing on scalability as the primary design constraint. We consider the challenges of distributed allocation of jobs, each comprised of a set of tasks to be mapped to disjoint cores. A naive solution performing fragmented allocations may quickly escalate to deadlocks, where jobs hold and wait for cores in circular dependencies. To tackle these challenges, we propose a deadlock free distributed job allocation protocol. We have devised two policies for avoiding deadlocks, namely active cancellation and sequencer-based atomic broadcast. The protocol and the two policies have been implemented and evaluated on a Tilera TilePro64 processor with 64 cores on a single socket. Results show that for sparse job allocations active cancellation provides less job allocation overhead while for denser job allocations the sequencer-based atomic broadcast provides less overhead.

show abstract

“…Job co-scheduling for High-end computing (HEC) systems often use a single job submission portal [18,20]. But such approaches using a centralized resource manager do not scale.…”

Section: Related Workmentioning

confidence: 99%

Distributed Job Allocation for Large-Scale Manycores

Ramachandran

Mueller

2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The deployment of the virtual workspaces is managed by the GridWay 4 meta-scheduling system [10]. GridWay allows unattended, reliable, and efficient execution of jobs on heterogeneous and dynamic Grids.…”

Section: Virtual Workpace Schedulingmentioning

confidence: 99%

Management of Virtual Machines on Globus Grids Using GridWay

Montero

Huedo

Montero

et al. 2007

2007 IEEE International Parallel and Distributed Processing Symposium

View full text Add to dashboard Cite

Virtual machines are a promising technology to overcome some of the problems found in current Grid infrastructures, like heterogeneity, performance partitioning or application isolation. In this work, we present an straightforward deployment of virtual machines in Globus Grids. This solution is based on standard services and does not require additional middleware to be installed. Also, we assess the suitability of this deployment in the execution of a high throughput scientific application, the XMM-Newton Scientific Analysis System.

show abstract

“…We have designed a software layer [2], based upon the Globus Toolkit 2.4 [3] and results from the GridWay project [4]. Basic scheduling support has been added to allocate tasks to nodes on the grid.…”

Section: Globus Toolkit Developmentsmentioning

confidence: 99%

Grid Computing Based Simulations of the Electrical Activity of the Heart

Alonso

Hernández

Moltó

2004

Computational Science - ICCS 2004

View full text Add to dashboard Cite

Abstract. Simulation of the electrical activity of the heart by modelization of the action potential propagation is a computational and memory intensive process. In addition many studies, such as the investigation of the ischemia phenomenon, require the execution of lots of parametric simulations, what increases the computational problem by several orders of magnitude. This paper presents the integration of a parallel simulator for the action potential propagation on cardiac tissues into a Grid infrastructure under the Globus Toolkit and InnerGrid middlewares.

show abstract

A framework for adaptive execution in grids

Cited by 239 publications

References 31 publications

Distributed Job Allocation for Large-Scale Manycores

Distributed Job Allocation for Large-Scale Manycores

Management of Virtual Machines on Globus Grids Using GridWay

Grid Computing Based Simulations of the Electrical Activity of the Heart

Contact Info

Product

Resources

About