Using a "codelet" program execution model for exascale machines

Zuckerman, Stéphane; Suetterlein, Joshua; Knauerhase, Rob; Gao, Guang R.

doi:10.1145/2000417.2000424

Cited by 83 publications

(48 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, there are PXMs which emphasize properties such as the isolation of execution and the explicit declaration of producer-consumer relations like the dataflow program execution models [9]. This paper evaluates an implementation of the codelet model [24], a finegrain PXM inspired by dataflow. We implemented the model using a runtime system, DARTS.…”

Section: Introductionmentioning

confidence: 99%

An Implementation of the Codelet Model

Suettlerlein

Zuckerman

Gao

2013

Euro-Par 2013 Parallel Processing

Self Cite

View full text Add to dashboard Cite

Abstract. Chip architectures are shifting from few, faster, functionally heavy cores to abundant, slower, simpler cores to address pressing physical limitations such as energy consumption and heat expenditure. As architectural trends continue to fluctuate, we propose a novel program execution model, the Codelet model, which is designed for new systems tasked with efficiently managing varying resources. The Codelet model is a fine-grained dataflow inspired model extended to address the cumbersome resources available in new architectures. In the following, we define the Codelet execution model as well as provide an implementation named DARTS. Utilizing DARTS and two predominant kernels, matrix multiplication and the Graph 500's breadth first search, we explore the validity of fine-grain execution as a promising and viable execution model for future and current architectures. We show that our runtime is on par or performs better than AMD's highly-optimized parallel library for matrix multication, outperforming it on average by 1.40× with a speedup up to 4×. Our implementation of the parallel BFS outperforms Graph 500's reference implementation (with or without dynamic scheduling) on average by 1.50× with a speed up of up to 2.38×.

show abstract

Section: Introductionmentioning

confidence: 99%

An Implementation of the Codelet Model

Suettlerlein

Zuckerman

Gao

2013

Euro-Par 2013 Parallel Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…At the same time we plan to use collected and unified knowledge to improve our past techniques on decomposition of complex programs into interconnected kernels, predictive modeling of program behavior, and run-time tuning and adaptation [5,9,17,34,46,54,55,69,82]. Finally, we are extending Collective Mind to assist recent initiatives on reproducible research and new publication models in computer engineering where all experimental results and related research artifacts with all dependencies are continuously shared along with publications to be validated and improved by the community [35].…”

Section: Discussionmentioning

confidence: 99%

Collective Mind: Towards Practical and Collaborative Auto-Tuning

Fursin

Miceli

Lokhmotov

et al. 2014

Scientific Programming

View full text Add to dashboard Cite

Abstract. Empirical auto-tuning and machine learning techniques have been showing high potential to improve execution time, power consumption, code size, reliability and other important metrics of various applications for more than two decades. However, they are still far from widespread production use due to lack of native support for auto-tuning in an ever changing and complex software and hardware stack, large and multi-dimensional optimization spaces, excessively long exploration times, and lack of unified mechanisms for preserving and sharing of optimization knowledge and research material.We present a possible collaborative approach to solve above problems using Collective Mind knowledge management system. In contrast with previous cTuning framework, this modular infrastructure allows to preserve and share through the Internet the whole auto-tuning setups with all related artifacts and their software and hardware dependencies besides just performance data. It also allows to gradually structure, systematize and describe all available research material including tools, benchmarks, data sets, search strategies and machine learning models. Researchers can take advantage of shared components and data with extensible meta-description to quickly and collaboratively validate and improve existing auto-tuning and benchmarking techniques or prototype new ones. The community can now gradually learn and improve complex behavior of all existing computer systems while exposing behavior anomalies or model mispredictions to an interdisciplinary community in a reproducible way for further analysis. We present several practical, collaborative and model-driven auto-tuning scenarios. We also decided to release all material at c-mind.org/repo to set up an example for a collaborative and reproducible research as well as our new publication model in computer engineering where experimental results are continuously shared and validated by the community.

show abstract

“…Turbine tasks are atomically scheduled and execute without pausing or blocking, similar to codelets [28], but with higher granularity. Execution of a Turbine control logic fragment may produce additional control fragments that are redistributed via ADLB.…”

Section: B Turbinementioning

confidence: 99%

Swift/T: Large-Scale Application Composition via Distributed-Memory Dataflow Processing

Wozniak

Armstrong

Wilde

et al. 2013

2013 13th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing

116

View full text Add to dashboard Cite

Abstract-Many scientific applications are conceptually built up from independent component tasks as a parameter study, optimization, or other search. Large batches of these tasks may be executed on high-end computing systems; however, the coordination of the independent processes, their data, and their data dependencies is a significant scalability challenge. Many problems must be addressed, including load balancing, data distribution, notifications, concurrent programming, and linking to existing codes. In this work, we present Swift/T, a programming language and runtime that enables the rapid development of highly concurrent, task-parallel applications. Swift/T is composed of several enabling technologies to address scalability challenges, offers a high-level optimizing compiler for user programming and debugging, and provides tools for binding user code in C/C++/Fortran into a logical script. In this work, we describe the Swift/T solution and present scaling results from the IBM Blue Gene/P and Blue Gene/Q.

show abstract

Using a "codelet" program execution model for exascale machines

Cited by 83 publications

References 11 publications

An Implementation of the Codelet Model

An Implementation of the Codelet Model

Collective Mind: Towards Practical and Collaborative Auto-Tuning

Swift/T: Large-Scale Application Composition via Distributed-Memory Dataflow Processing

Contact Info

Product

Resources

About