Algorithm Engineering for Parallel Computation

Bader, David A.; Moret, Bernard M. E.; Sanders, Peter

doi:10.1007/3-540-36383-1_1

Cited by 16 publications

(8 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As is often necessary when engineering parallel algorithms [12], we accept slower single processor performance, so that our code will run faster on the multi-processor machines that are becoming ubiquitous. Further implementation details can be found in Mathuriya et.…”

Section: Resultsmentioning

confidence: 99%

GTfold: Enabling parallel RNA secondary structure prediction on multi-core desktops

et al. 2012

View full text Add to dashboard Cite

BackgroundAccurate and efficient RNA secondary structure prediction remains an important open problem in computational molecular biology. Historically, advances in computing technology have enabled faster and more accurate RNA secondary structure predictions. Previous parallelized prediction programs achieved significant improvements in runtime, but their implementations were not portable from niche high-performance computers or easily accessible to most RNA researchers. With the increasing prevalence of multi-core desktop machines, a new parallel prediction program is needed to take full advantage of today’s computing technology.FindingsWe present here the first implementation of RNA secondary structure prediction by thermodynamic optimization for modern multi-core computers. We show that GTfold predicts secondary structure in less time than UNAfold and RNAfold, without sacrificing accuracy, on machines with four or more cores.ConclusionsGTfold supports advances in RNA structural biology by reducing the timescales for secondary structure prediction. The difference will be particularly valuable to researchers working with lengthy RNA sequences, such as RNA viral genomes.

show abstract

Section: Resultsmentioning

confidence: 99%

GTfold: Enabling parallel RNA secondary structure prediction on multi-core desktops

et al. 2012

View full text Add to dashboard Cite

show abstract

“…However, we use of the term algorithm engineering in a different context to that described in [5], where the process is described as what is required to transform a pencil-and-paper algorithm into a robust, efficient, well tested, and usable implementation. Their definition encompasses a number of low-level issues, such as cache behaviour, and its main focus is experimentation.…”

Section: Concurrent Software Engineering = Concurrency Engineering + mentioning

confidence: 99%

Concurrency engineering

Jesshope

Shafarenko²

2008

2008 13th Asia-Pacific Computer Systems Architecture Conference

View full text Add to dashboard Cite

show abstract

“…Otherwise, the relaxation does not create a cycle. However, since the path to the initial vertex can be long, the cost of edge relaxation becomes O(n) instead of O (1). In order to optimise the overall computational complexity, amortisation is used to pay the cost of checking G p for cycles.…”

Section: Maximal Number Of Accepting Predecessors (Negc)mentioning

confidence: 99%

“…In addition, development of methods, tools, and practises for assessing and refining algorithms through experimentation is unavoidable, extensive use of various techniques for efficient implementation as known from algorithm engineering for parallel computation (see e.g. [1]) underpins the new approach.…”

mentioning

confidence: 99%

Distributed Verification: Exploring the Power of Raw Computing Power

Brim

2007

Formal Methods: Applications and Technology

View full text Add to dashboard Cite

Brute-Force in Distribute VerificationWith the increase in complexity of computer systems, it becomes more important to develop formal methods for ensuring their quality and reliability. Various techniques for automated and semi-automated analysis and verification have been successfully applied to real-life computer systems. However, these techniques are computationally hard and memory intensive in general and their applicability to extremely large systems is limited. The major hampering factor is the state space explosion problem due to which large industrial models cannot be efficiently handled by a single state-of-the-art computer.Much attention has been focused on the development of approaches to battle the state space explosion problem. Many techniques, such as abstraction, state compression, state space reduction, symbolic state representation, etc., are used to reduce the size of the problem to be handled allowing thus a single computer to process larger systems. There are also techniques that purely focus on increasing the amount of available computational power. These are, for example, techniques to fight memory limits with efficient utilisation of an external I/O device [2,19,24,28,32], or techniques that introduce cluster-based algorithms to employ aggregate power of network-interconnected computers.Cluster-based algorithms perform their computation simultaneously on a number of workstations that are allowed to communicate and synchronise themselves by means of message passing. Cluster-based algorithms can thus be characterised as parallel algorithms performing in a distributed memory environment. The algorithms prove their usefulness in verification of large-scale systems. They have been successfully applied to symbolic model checking [22,23], analysis of stochastic [25] and timed [6] systems, equivalence checking [8] and other related problems [7,9,21].The idea of parallel verification appeared already in the very early years of the formal verification era. However, inaccessibility of cheap parallel computers together with negative theoretical complexity results excluded this approach from the main stream in formal verification. The situation changed dramatically during the past several years. Computer progress over the past two decades has measured several orders of magnitude with respect to various physical parameters such as computing power, memory size at all hierarchy levels from caches to disk, power consumption, physical size and cost.

show abstract

Algorithm Engineering for Parallel Computation

Cited by 16 publications

References 42 publications

GTfold: Enabling parallel RNA secondary structure prediction on multi-core desktops

GTfold: Enabling parallel RNA secondary structure prediction on multi-core desktops

Concurrency engineering

Distributed Verification: Exploring the Power of Raw Computing Power

Contact Info

Product

Resources

About