Improving MPI-HMMER's scalability with parallel I/O

Walters, John Paul; Darole, Rohan; Chaudhary, Vipin

doi:10.1109/ipdps.2009.5161074

Cited by 13 publications

(11 citation statements)

References 12 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This increase in number of events led to the increase in overhead seen in Table 2. For example, the number of events sent by Gromacs [10] when it is solving a large problem using 128 cores is around two millions, which is more than twice as larger as the number of events sent by MPIHMMER [11] for solving a large problem. The larger number of events sent by Gromacs led to an almost 0.2% increase in the overhead imposed by PROMON .…”

Section: Monitoring Overheadmentioning

confidence: 99%

Monitoring HPC applications in the production environment

Sharifi

Aaziz

Cook

2015

Proceedings of the 2nd Workshop on Parallel Programming for Analytics Applications

View full text Add to dashboard Cite

The advancement of HPC systems brings with it a need for more introspection into the run-time environment and performance of longrunning applications. Software and hardware fault tolerance, scaling performance issues, soft error effect on computations, and even large-scale computational progress will require more capable runtime monitoring of applications during production runs. Current HPC toolsets, however, are geared towards heavyweight program introspection during the development, debugging, and optimization phases of software development, and are not suitable for production monitoring. To this end this work has developed PROMON, a framework for the production monitoring of HPC applications. PROMON is part of a vision for automatic monitoring of HPC applications without requiring developers or users to do significant work to support it. This paper presents PROMON, motivates its purpose, and shows that production monitoring can be performed efficiently.

show abstract

Section: Monitoring Overheadmentioning

confidence: 99%

Monitoring HPC applications in the production environment

Sharifi

Aaziz

Cook

2015

Proceedings of the 2nd Workshop on Parallel Programming for Analytics Applications

View full text Add to dashboard Cite

show abstract

“…This “Disk Wall” problem will become worse along with the exponential growth of database sizes. Walters et al [ 12 ] studied the I/O problems in HMMER and enhanced its MPI implementation (called MPI-HMMER) using parallel I/O and a parallel file system. In this new version (called PIO-HMMER), the database distribution mechanism was modified so that the master node, instead of directly reading data and sending them to slave nodes, only distributes sequence indexes (each containing sequence offsets and lengths) to slave nodes and slave nodes read from the database in parallel.…”

Section: Software Accelerated Hmmermentioning

confidence: 99%

Modern Computational Techniques for the HMMER Sequence Analysis

Meng

2013

ISRN Bioinformatics

View full text Add to dashboard Cite

This paper focuses on the latest research and critical reviews on modern computing architectures, software and hardware accelerated algorithms for bioinformatics data analysis with an emphasis on one of the most important sequence analysis applications—hidden Markov models (HMM). We show the detailed performance comparison of sequence analysis tools on various computing platforms recently developed in the bioinformatics society. The characteristics of the sequence analysis, such as data and compute-intensive natures, make it very attractive to optimize and parallelize by using both traditional software approach and innovated hardware acceleration technologies.

show abstract

“…There has been a great deal of work on optimizing HMMER 2 for traditional parallel computers [13]- [16]. J. P. Walters and etc.…”

Section: Algorithm 1: Pseudo-code Of Hmmsearchmentioning

confidence: 99%

A Speculative HMMER Search Implementation on GPU

Han

et al. 2012

2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops &Amp; PhD Forum

View full text Add to dashboard Cite

Due to the exponentially growing bioinformatics databases and rapidly popular of GPU for general purpose computing, it is promising to employ GPU techniques to accelerate the sequence search process. Hmmsearch from HMMER bioinformatics software package is a wildly used software tool for sensitive profile HMM (Hidden Markov Model) searches of biological sequence databases. In this paper, we implement a speculative hmmsearch implementation on NVIDIA Fermi GPU and apply various optimizations to it. We test the enhancements in our GPU implementation in order to demonstrate the effectiveness of optimization strategies. Result shows that our speculative hmmsearch implementation achieves up to 6.5x speedup over previous fast single-threaded SSE implementation.

show abstract

Improving MPI-HMMER's scalability with parallel I/O

Cited by 13 publications

References 12 publications

Monitoring HPC applications in the production environment

Monitoring HPC applications in the production environment

Modern Computational Techniques for the HMMER Sequence Analysis

A Speculative HMMER Search Implementation on GPU

Contact Info

Product

Resources

About