Programmability and portability for exascale: Top down programming methodology and tools with StarSs

Subotic, Vladimir; Brinkmann, Steffen; Marjanovic, Vladimir; Badía, Rosa M.; Gracia, José; Niethammer, Christoph; Ayguadé, Eduard; Labarta, Jesús; Valero, Mateo

doi:10.1016/j.jocs.2013.01.008

Cited by 15 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Open Community Runtime (OCR) [124] is proposed as a runtime system for high-level exascale programming models, although recent development has been scarce. StarSs [168] is a programming model that enables programmers to parallelize existing sequential application using code annotations. Legion [90] is a scalable data-centric framework for programming distributed platforms.…”

Section: Alternative Programming Models Several Alternative Programmmentioning

confidence: 99%

The Landscape of Exascale Research

et al. 2020

View full text Add to dashboard Cite

The next generation of supercomputers will break the exascale barrier. Soon we will have systems capable of at least one quintillion (billion billion) floating-point operations per second (10 18 FLOPS). Tremendous amounts of work have been invested into identifying and overcoming the challenges of the exascale era. In this work, we present an overview of these efforts and provide insight into the important trends, developments, and exciting research opportunities in exascale computing. We use a three-stage approach in which we (1) discuss various exascale landmark studies, (2) use data-driven techniques to analyze the large collection of related literature, and (3) discuss eight research areas in depth based on influential articles. Overall, we observe that great advancements have been made in tackling the two primary exascale challenges: energy efficiency and fault tolerance. However, as we look forward, we still foresee two major concerns: the lack of suitable programming tools and the growing gap between processor performance and data bandwidth (i.e., memory, storage, networks). Although we will certainly reach exascale soon, without additional research, these issues could potentially limit the applicability of exascale computing.

show abstract

Section: Alternative Programming Models Several Alternative Programmmentioning

confidence: 99%

The Landscape of Exascale Research

et al. 2020

View full text Add to dashboard Cite

show abstract

“…OmpSs [41] is a task based programming model developed at the Barcelona Supercomputing Center that aims to address the needs of portability and programmability for both homogeneous and heterogeneous machines. The name originates from a combination of the OpenMP and the Star SuperScalar [16] programming model names. A runtime implementation of OmpSs is provided through the Nanos++ [39] runtime system research tool which provides user-level threads, synchronization support, and heterogeneity support and through the Mercurium compiler [38] for handling clauses and directives.…”

Section: Ompssmentioning

confidence: 99%

A Survey: Runtime Software Systems for High Performance Computing

2017

JSFI

View full text Add to dashboard Cite

High Performance Computing system design and operation are challenged by requirements for significant advances in efficiency, scalability, productivity, and portability at the end of Moore's Law with approaching nano-scale technology. Conventional practices employ message-passing programming interfaces; sometimes combining thread-based shared memory interfaces such as OpenMP. These methods they are principally coarse grained and statically scheduled. Yet, performance for many real-world applications yield efficiencies of less than 10% even though some benchmarks achieve 80% efficiency or better (e.g., HPL). To address these challenges, strategies employing runtime software systems are being pursued to exploit information about the status of the application and the system hardware operation throughout the execution to guide task scheduling and resource management for dynamic adaptive control. Runtimes provide adaptive means to reduce the effects of starvation, latency, overhead, and contention. Many share common properties such as multi-tasking either preemptive or non-preemptive, message-driven computation such as active messages, sophisticated fine-grain synchronization such as dataflow and future constructs, global name or address spaces, and control policies for optimizing task scheduling to address the uncertainty of asynchrony. This survey will identify key parameters and properties of modern and experimental runtime systems actively employed today and provide a detailed description, summary, and comparison within a shared space of dimensions. It is not the intent of this paper to determine which is better or worse but rather to provide sufficient detail to permit the reader to select among them according to individual need.

show abstract

“…However they are most often simply the inputs and outputs of functions. There are also tools for the automation of the annotations [39]. One can find example implementation of fork-join tasks in OpenMP 3.0 [12] and dataflow tasks in OmpSs [14], OpenMP 4.0 [30] and Intel TBB [2].…”

Section: A Error Classification and Failure Modelmentioning

confidence: 99%

A Runtime Heuristic to Selectively Replicate Tasks for Application-Specific Reliability Targets

Subaşi

Yalcin

Zyulkyarov

et al. 2016

2016 IEEE International Conference on Cluster Computing (CLUSTER)

Self Cite

View full text Add to dashboard Cite

Abstract-In this paper we propose a runtime-based selective task replication technique for task-parallel high performance computing applications. Our selective task replication technique is automatic and does not require modification/recompilation of OS, compiler or application code. Our heuristic, we call App FIT, selects tasks to replicate such that the specified reliability target for an application is achieved. In our experimental evaluation, we show that App FIT selective replication heuristic is low-overhead and highly scalable. In addition, results indicate that complete task replication is overkill for achieving reliability targets. We show that with App FIT, we can tolerate pessimistic exascale error rates with only 53% of the tasks being replicated.

show abstract

Programmability and portability for exascale: Top down programming methodology and tools with StarSs

Cited by 15 publications

References 4 publications

The Landscape of Exascale Research

The Landscape of Exascale Research

A Survey: Runtime Software Systems for High Performance Computing

A Runtime Heuristic to Selectively Replicate Tasks for Application-Specific Reliability Targets

Contact Info

Product

Resources

About