COMP Superscalar: Bringing GRID Superscalar and GCM Together

Tejedor, Enric; Badía, Rosa M.

doi:10.1109/ccgrid.2008.104

Cited by 35 publications

(25 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By flattening access to disparate, homogeneous resources, grid technologies should yield an abundance of raw computational power that should be irresistible to anyone desiring high performance computing. While grid projects such as Cui et al (2007), Natrajan et al (2004), Tejedor and Badia (2008), and Rubio-Solar et al (2008) each enjoy success in their own goals, no single implementation has dominated. Though all aim for generality, all have features that are tuned to their own application domains, and are not generic enough for each other's purposes.…”

Section: Grid-inspiredmentioning

confidence: 99%

“…Though all aim for generality, all have features that are tuned to their own application domains, and are not generic enough for each other's purposes. All target large-scale computation, but only one maintains an interface simple enough for lightweight tasks from casual users (Tejedor and Badia 2008). The few that are aware of data locality require specialized tools to construct tasks.…”

Section: Grid-inspiredmentioning

confidence: 99%

“…Because the system re-interprets the script, it can ensure that only safe programs are referenced and only permissible files are read, and that program outputs are safely mapped to isolated areas. It is worth noting that (Tejedor and Badia 2008) provides similarly simple computational service, but requires tasks to be specified in a custom Perl-like language (Wall et al 2000).…”

Section: Usage Modelmentioning

confidence: 99%

See 2 more Smart Citations

Efficient clustered server-side data analysis workflows using SWAMP

2009

View full text Add to dashboard Cite

Technology continues to enable scientists to set new records in data collection and production, intensifying a need for large scale tools to efficiently process and analyze the growing mountain of data. To complement growth in the number of data centers and the volume of data they store, we introduce our Script Workflow Analysis for MultiProcessing (SWAMP) system. Our system provides safe server-side processing capabilities that allow scientists to reuse familiar desktop-based analysis methods represented in shellscripts. Built-in script compilation isolates file accesses and generates workflows, while a cluster-capable execution engine partitions and executes the resulting workflow. Benchmarks illustrate up to 20X performance gains, as well as the importance of I/O considerations which make other computation systems less effective at geoscience data reduction.

show abstract

Section: Grid-inspiredmentioning

confidence: 99%

Section: Grid-inspiredmentioning

confidence: 99%

Section: Usage Modelmentioning

confidence: 99%

See 1 more Smart Citation

Efficient clustered server-side data analysis workflows using SWAMP

2009

View full text Add to dashboard Cite

show abstract

“…The proposed scheduler has been designed to be applied to the COMP Superscalar (COMPSs) framework [9,10]. It provides an infrastructure-agnostic task-based programming model, which facilitates the development of parallel applications in distributed computing platforms.…”

Section: Introductionmentioning

confidence: 99%

Dynamic energy-aware scheduling for parallel task-based application in cloud computing

Juarez

Ejarque

Badía

2018

Future Generation Computer Systems

Self Cite

183

View full text Add to dashboard Cite

h i g h l i g h t s• Energy-aware run-time scheduler for task-based applications.• Model for estimating the application Energy consumption.• Methodology to automatically generate the required power consumption profile.• Multi-heuristic resource allocation algorithm to get solutions in polynomial time.• Energy saving/performance trade-off evaluation for different scenarios. a r t i c l e i n f o b s t r a c tGreen Computing is a recent trend in computer science, which tries to reduce the energy consumption and carbon footprint produced by computers on distributed platforms such as clusters, grids, and clouds. Traditional scheduling solutions attempt to minimize processing times without taking into account the energetic cost. One of the methods for reducing energy consumption is providing scheduling policies in order to allocate tasks on specific resources that impact over the processing times and energy consumption. In this paper, we propose a real-time dynamic scheduling system to execute efficiently taskbased applications on distributed computing platforms in order to minimize the energy consumption. Scheduling tasks on multiprocessors is a well known NP-hard problem and optimal solution of these problems is not feasible, we present a polynomial-time algorithm that combines a set of heuristic rules and a resource allocation technique in order to get good solutions on an affordable time scale. The proposed algorithm minimizes a multi-objective function which combines the energy-consumption and execution time according to the energy-performance importance factor provided by the resource provider or user, also taking into account sequence-dependent setup times between tasks, setup times and down times for virtual machines (VM) and energy profiles for different architectures. A prototype implementation of the scheduler has been tested with different kinds of DAG generated at random as well as on real task-based COMPSs applications. We have tested the system with different size instances and importance factors, and we have evaluated which combination provides a better solution and energy savings. Moreover, we have also evaluated the introduced overhead by measuring the time for getting the scheduling solutions for a different number of tasks, kinds of DAG, and resources, concluding that our method is suitable for run-time scheduling.

show abstract

“…Each StarSs member targets a particular architecture [6] [4] [5]; nevertheless, all share the same philosophy: the user is only required to select a set of methods of a sequential application that will run as parallel tasks on the available resources. For each method parameter, its direction (input, output or in-out) needs to be specified; this information is used by StarSs to discover, at execution time, the data dependencies between tasks.…”

Section: Introductionmentioning

confidence: 99%

ClusterSs

Tejedor

Farreras

Grove

et al. 2011

Proceedings of the 20th International Symposium on High Performance Distributed Computing

Self Cite

View full text Add to dashboard Cite

Programming for large-scale, multicore-based architectures requires adequate tools that offer ease of programming while not hindering application performance. StarSs is a family of parallel programming models based on automatic function level parallelism that targets productivity. StarSs deploys a data-flow model: it analyses dependencies between tasks and manages their execution, exploiting their concurrency as much as possible.We introduce Cluster Superscalar (ClusterSs), a new StarSs member designed to execute on clusters of SMPs. ClusterSs tasks are asynchronously created and assigned to the available resources with the support of the IBM APGAS runtime, which provides an efficient and portable communication layer based on one-sided communication.This short paper gives an overview of the ClusterSs design on top of APGAS, as well as the conclusions of a productivity study; in this study, ClusterSs was compared to the IBM X10 language, both in terms of programmability and performance. A technical report is available with the details.

show abstract

COMP Superscalar: Bringing GRID Superscalar and GCM Together

Cited by 35 publications

References 16 publications

Efficient clustered server-side data analysis workflows using SWAMP

Efficient clustered server-side data analysis workflows using SWAMP

Dynamic energy-aware scheduling for parallel task-based application in cloud computing

ClusterSs

Contact Info

Product

Resources

About