Quantifying Intrinsic Parallelism Using Linear Algebra for Algorithm/Architecture Coexploration

Lee, Gwo Giun; Lin, He-Yuan; Chen, Chun-Fu; Huang, Tai Yin

doi:10.1109/tpds.2011.230

Cited by 14 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To map algorithm onto architecture, these metrics provide a systematic manner to explore the design space for the multidimensional video signals. A systematic quantification of parallelism has been demonstrated in our previous work [3] already. This method quantified the parallelism across various data granularities based on the spectral theory on dataflow graphs.…”

Section: Introductionmentioning

confidence: 80%

Algorithmic complexity analysis on data transfer rate and data storage for multidimensional signal processing

Lee

Chen

Lin

2013

SiPS 2013 Proceedings

Self Cite

View full text Add to dashboard Cite

Algorithmic complexity, such as data storage size and data transfer rate, is dramatically increased in multidimensional signal processing, including visual computing exploiting temporal and spatial information to achieve better visual quality. This paper present a systematic method, which is a new paradigm of designing on the complex multidimensional signal and is called as algorithm/architecture co-exploration, to efficiently quantify the algorithmic complexity, including data storage and data transfer rate, whose characteristics are independent from platforms. By exploring design space based on the dataflow with different executing orders and various data granularities, the trade-off between data storage size and data transfer rate is made by a systematic manner and hence the algorithm could be smoothly mapped onto architecture. Case studies reveal that our framework can effectively characterize the complexity of algorithms, and that the extracted complexity can facilitate design space exploration at various data granularities.

show abstract

Section: Introductionmentioning

confidence: 80%

Algorithmic complexity analysis on data transfer rate and data storage for multidimensional signal processing

Lee

Chen

Lin

2013

SiPS 2013 Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…We will use the dependency matrix to develop our method. [9] introduce a linear algebra approach to systematically quantify the degree of parallelism embedded in DFGs; furthermore, a multi-grain concept has been introduced, too. Lee's method uses Laplacian matrix to quantify the number of operation sets could be computed in parallel; moreover, the null space spanned by the dependency matrix is also capable of quantifying the degree of parallelism.…”

Section: A Data Flow Modelmentioning

confidence: 99%

“…... We could apply the methodology developed by our previous work [9] to quantify degree of parallelism at multi-grain granularity according to various level of data dependency. When data granularity is larger than one task, it is hard to exploit the degree of parallelism due to the fact all tasks are connected sequentially; in contrast, when we narrow down data granularity into one task, the parallelization possibility of CME is increased.…”

Section: B Mapping Mc-fruc Onto Ibm Cell Be Via Compleixty Metrics Qmentioning

confidence: 99%

Mapping visual signal processing onto multi-core platform via algorithm/architecture co-exploration

Chen

Lee

et al. 2014

2014 IEEE Workshop on Signal Processing Systems (SiPS)

Self Cite

View full text Add to dashboard Cite

Degree of parallelism and data communication should be investigated to achieve high performance for mapping algorithm onto multi-core platform since multi-core platform would concurrently process multiple tasks and lots of data would be transferred between storages and processors. This paper proposes a method to resolve the burden of increase on data transfer rate in parallel processing via the analysis on the dependency matrix of data flow graph. The proposed method does not bias any multi-core platform since it just considers the intrinsic characteristics of algorithm, i.e., data flow graph. This paper utilizes dependency matrix, which conveys the causality of data transfer, for quantifying data transfer rate and corresponding storage requirement; as a consequence, a feasible mapping result, which has smaller data transfer rate and acceptable storage requirement, was exploited. Furthermore, in conjunction with degree of parallelism quantification, this paper presents a comprehensive exploration on design space for mapping algorithm onto multi-core platform through dependency matrix. IBM Cell Broadband Engine is selected to be the targeted multi-core platform in this paper. Experimental results show that when six cores are used, our result can speedup 5.75x on average as compared to single-core case; in addition, by integrating the proposed method on data transfer analysis, about 46% cycles of data transfer could be saved and overall performance could be further increased to 7.51x on average in comparison with the scenario of single-core without data reuse.

show abstract

“…Современная параллельная обработка данных требует от формальных инструментов, предназначенных для описания организации вычислений, особых характеристик, которыми традиционные алгоритмы не обладают [1][2][3][4][5][6][7][8][9][10][11]. Такие формальные инструменты должны быть адаптивными и в них должна быть заложена возможность оптимизации вычислений.…”

Section: Introductionunclassified

An optimization approach to the development of parallel algorithms for digital signal processing operations

Klimova¹

2022

DREAM

View full text Add to dashboard Cite

The paper studies the optimization possibilities of an approach which made it possible to develop a formal tool, i.e. a model of computation organization for digital signal processing (DSP) operations and operations structurally similar to them. The resulting formal tool describes the inter-nal parameterized structure of operations and generates adaptive algorithms that can adjust to dif-ferent conditions of parallel computation. The developed approach to the construction of such algo-rithms endows them with extended functionality, which ensures the implementation of the follow-ing capabilities: changes in the parameters of algorithm structures; synthesis of their variety; opti-mization of variants of computation organization. Due to the variety of this functionality, several directions are identified for implementing this optimization. A general description of the optimiza-tion approach to the reasonable choice of the best variant of computation organization under the given conditions of their implementation is given. We consider a scheme of actions aimed at com-putation optimization and enabling you to develop various classes of parameterized parallel algo-rithms within the framework of the approach proposed.

show abstract

Quantifying Intrinsic Parallelism Using Linear Algebra for Algorithm/Architecture Coexploration

Cited by 14 publications

References 22 publications

Algorithmic complexity analysis on data transfer rate and data storage for multidimensional signal processing

Algorithmic complexity analysis on data transfer rate and data storage for multidimensional signal processing

Mapping visual signal processing onto multi-core platform via algorithm/architecture co-exploration

An optimization approach to the development of parallel algorithms for digital signal processing operations

Contact Info

Product

Resources

About