Optimizing Reduction Computations In a Distributed Environment

Kurç, Tahsin; Lee, Feng; Agrawal, Gagan; Çatalyürek, Ümit V.; Ferreira, Renato; Saltz, Joel

doi:10.1145/1048935.1050160

Cited by 6 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our experience with the filter-stream programming model, most applications are bottleneck free, and the number of active internal tasks are higher than the available processors [8,11,17,35,40,43]. Thus, the proposed approach to exploit heterogeneous resources consists of allocating multiple tasks concurrently to processors where they will perform the best, as detailed in Sect.…”

Section: Motivating Applicationmentioning

confidence: 99%

Optimizing dataflow applications on heterogeneous environments

et al. 2011

Self Cite

View full text Add to dashboard Cite

The increases in multi-core processor parallelism and in the flexibility of many-core accelerator processors, such as GPUs, have turned traditional SMP systems into hierarchical, heterogeneous computing environments. Fully exploiting these improvements in parallel system design remains an open problem. Moreover, most of the current tools for the development of parallel applications for hierarchical systems concentrate on the use of only a single processor type (e.g., accelerators) and do not coordinate several heterogeneous processors. Here, we show that making use of all of the heterogeneous computing resources can significantly improve application performance. Our approach, which consists of optimizing applications at run-time by efficiently coordinating application task execution on all available processing units is evaluated in the context of replicated dataflow applications. The proposed techniques were developed and implemented in an integrated run-time system targeting both intra-and inter-node parallelism. The experimental results with a real-world complex biomedical application show that our approach nearly doubles the performance of the GPU-only implementation on a distributed heterogeneous accelerator cluster.

show abstract

Section: Motivating Applicationmentioning

confidence: 99%

Optimizing dataflow applications on heterogeneous environments

et al. 2011

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although more complex hybrid solutions to the decomposition of the input and output data can be developed [12], their performance is typically close to that of the outputpartitioned scheme when the output size is large. Also since the input-partitioned and output-partitioned parallelization schemes represent the extremes of the SAR image formation pipeline design space and constitutes a good base cases for comparisons, in this work we only develop and present these two parallelization schemes.…”

Section: Figure 4 Sar Imaging Input Partitioningmentioning

confidence: 99%

Investigating the use of GPU-accelerated nodes for SAR image formation

Hartley

Fasih

Berdanier

et al. 2009

2009 IEEE International Conference on Cluster Computing and Workshops

View full text Add to dashboard Cite

The computation of an electromagnetic reflectivity image from a set of radar returns is a computationally intensive process. Therefore, the use of high performance computing is required to form images from radar signals in a short time frame. This paper explores the use of distributed memory cluster computers and accelerator technologies such as GPUs for radar signal analysis applications, particularly backprojection image formation. We obtain good results with the use of GPUs and compare their performance in terms of execution time with distributed memory cluster computers. When using a configuration with 4 GPUaccelerated nodes, we achieve speedups up to 3.45x for different input and output data size combinations.

show abstract

“…Our work is distinct in considering a higher-level language and virtual view of the datasets. Kurc et al have examined different runtime strategies for supporting reductions in a distributed environment [6]. We focus on supporting a high-level language, but currently have implemented only a single strategy.…”

Section: Related Workmentioning

confidence: 99%

Supporting SQL-3 Aggregations on Grid-Based Data Repositories

Weng¹,

Agrawal²,

Çatalyürek

et al. 2005

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. There is an increasing trends towards distributed and shared repositories for storing scientific datasets. Developing applications that retrieve and process data from such repositories involves a number of challenges. First, these data repositories store data in complex, low-level layouts, which should be abstracted from application developers. Second, as data repositories are shared resources, part of the computations on the data must be performed at a different set of machines than the ones hosting the data. Third, because of the volume of data and the amount of computations involved, parallel configurations need to be used for both hosting the data and the processing on the retrieved data. In this paper, we describe a system for executing SQL-3 queries over scientific data stored as flatfiles. A relational table-based virtual view is supported on these flat-file datasets. The class of queries we consider involve data retrieval using Select and Where clauses, and processing with user-defined aggregate functions and group-bys. We use a middleware system STORM for providing much of the low-level functionality. Our compiler analyzes the SQL-3 queries and generates many of the functions required by this middleware. Our experimental results show good scalability with respect to the number of nodes as well as the dataset size.

show abstract

Optimizing Reduction Computations In a Distributed Environment

Cited by 6 publications

References 27 publications

Optimizing dataflow applications on heterogeneous environments

Optimizing dataflow applications on heterogeneous environments

Investigating the use of GPU-accelerated nodes for SAR image formation

Supporting SQL-3 Aggregations on Grid-Based Data Repositories

Contact Info

Product

Resources

About