SWAMP: Smith-Waterman using associative massive parallelism

Steinfadt, Shannon Irene; Baker, Johnnie W.

doi:10.1109/ipdps.2008.4536468

Cited by 5 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many algorithms have been designed for the ASC model and software projects for AP platform (often using the ASC language) in order to demonstrate the versatility of the ASC model and the AP system. These include graph algorithms [67,44,42], convex hull [68,69,70,71], string matching [72,73], sequence alignment [74,75], NPComplete [76,77], databases [78,79], parallel compilers [80,81,82], supporting functional and logic-based languages [83,84,85], and supporting expert system languages [86,87,88]. In [39], Batcher lists fast Fourier transforming, sonar post-processing, string search, file processing, air traffic control, image processing, data management, position locating and reporting, bulk filtering, and radar processing as STARAN applications, and for the first five of these, provides a comparison of the STARAN's performance with several other systems.…”

Section: Observations and Consequences Of The Preceding Resultsmentioning

confidence: 99%

Comparisons of air traffic control implementations on an associative processor with a MIMD and consequences for parallel computing

Yuan¹,

Baker²,

Meilander³

2013

Journal of Parallel and Distributed Computing

Self Cite

View full text Add to dashboard Cite

This paper has two complementary focuses. The first is the system design and algorithmic development for air traffic control (ATC) using an associative SIMD processor (AP). The second is the comparison of this implementation with a multiprocessor implementation and the implications of these comparisons. This paper demonstrates how one application, ATC, can more easily, more simply, and more efficiently be implemented on an AP than is generally possible on other types of traditional hardware. The AP implementation of ATC will take advantage of its deterministic hardware to use static scheduling. The software will be dramatically smaller and cheaper to create and maintain. Likewise, a large AP system will be considerably simpler and cheaper than the MIMD hardware currently used. While APs were used for ATC-type applications earlier, these are no longer available. We use a ClearSpeed CSX600 accelerator to emulate the AP solutions of ATC on an ATC prototype consisting of eight data-intensive ATC real-time tasks. Its performance is compared with an 8-core multiprocessor (MP) using OpenMP. Our extensive experiments show that the AP implementation meets all deadlines while the MP will regularly miss a large number of deadlines. The AP code will be similar in size to sequential code for the same tasks and will avoid all of the additional support software needed with an MP to handle dynamic scheduling, load balancing, shared resource management, race conditions, * Corresponding author Email addresses: myuan@cs.kent.edu (Man(Mike) Yuan), jbaker@cs.kent.edu (Johnnie W. Baker), wllcm@att.net (Will C. Meilander) 1 This is the first author footnote. Preprint submitted to Journal of Parallel and Distributed Computing August 15, 2012false sharing, etc. At this point, essentially only MIMD systems are built. Many of the advantages of using an AP to solve an ATC problem would carry over to other applications. AP solutions for a wide variety of applications will be cited in this paper. Applications that involve a high degree of data parallelism such as database management, text processing, image processing, graph processing, bioinformatics, weather modeling, managing UAS (Unmanned Aircraft Systems or drones) etc, are good candidates for AP solutions. This raises the issue of whether we should routinely consider using non-multiprocessor hardware like the AP for applications where substantially simpler software solutions will normally exist. It also raises the question of whether the use of both AP and MIMD hardware in the same system could provide more versatility and efficiency. Either the AP or MIMD could serve as the primary system but could hand off jobs it could not handle efficiently to the other system.

show abstract

Section: Observations and Consequences Of The Preceding Resultsmentioning

confidence: 99%

Comparisons of air traffic control implementations on an associative processor with a MIMD and consequences for parallel computing

Yuan¹,

Baker²,

Meilander³

2013

Journal of Parallel and Distributed Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…An example of the sequential Smith-Waterman matrix. The dependencies of cell (3,2) are shown with arrows. While the calculated C values for the entire matrix are given, the shaded anti-diagonal (where all i+j values are equal) shows one logical parallel step since they can be computed in lockstep simultaneously.…”

Section: A Smith-waterman Local Sequence Alignmentmentioning

confidence: 99%

“…Smith-Waterman using Associative Massive Parallelism, or SWAMP, has been implemented as an associative parallel local sequence alignment algorithm [2] using the ASC programming language, compiler, and simulator. The SWAMP algorithm finds the best local alignment in O(m+n) time using m+1 processing elements versus O(m*n) sequential time.…”

Section: B Swamp and Swamp+mentioning

confidence: 99%

“…SWAMP+ is a suite of innovative extensions [3] based on the underlying SWAMP algorithm. It will find the single top scoring local alignment in parallel, providing the same output as SWAMP or even the Smith-Waterman algorithm.…”

Section: B Swamp and Swamp+mentioning

confidence: 99%

“…Instead, a single run can return multiple results in an automated fashion not available with standard Smith-Waterman implementations. This group of algorithms, known as SWAMP [1][2] and SWAMP+ [3] are Smith-Waterman using Associative Massive Parallelism. They are computationally intensive, parallel algorithms based on the proven and widely used SmithWaterman algorithm but with innovative extensions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Parallel Approaches for SWAMP Sequence Alignment

Steinfadt

Schaffer

2009

2009 Ohio Collaborative Conference on Bioinformatics

Self Cite

View full text Add to dashboard Cite

This document is a summary and overview of several approaches to implement the local sequence alignment algorithms known as SWAMP and SWAMP+ on commercially available hardware. Using a Smith-Waterman style of alignment, these parallel algorithms have several innovative extensions that take advantage of the ASC associative computing model while maintaining speed, accuracy, and producing a richer set of results in an automated way that is not currently available.We consider four different hardware architectures for the realization of the ASC model. These are the ClearSpeed CSX processor, NVIDIA GPGPU graphics processors, IBM Cell Processors, and FPGAs.

show abstract

Fine-grained parallel implementations for SWAMP+ Smith–Waterman alignment

Steinfadt

2013

Parallel Computing

View full text Add to dashboard Cite

SWAMP: Smith-Waterman using associative massive parallelism

Abstract: Abstract

Cited by 5 publications

References 12 publications

Comparisons of air traffic control implementations on an associative processor with a MIMD and consequences for parallel computing

Comparisons of air traffic control implementations on an associative processor with a MIMD and consequences for parallel computing

Parallel Approaches for SWAMP Sequence Alignment

Fine-grained parallel implementations for SWAMP+ Smith–Waterman alignment

Contact Info

Product

Resources

About