Exploring Modern FPGA Platforms for Faster Phylogeny Reconstruction with RAxML

Pavlos Malakonakis; Andreas Brokalakis; Nikolaos  Alachiotis; Evripides Sotiriades; Apostolos Dollas

doi:10.1109/BIBE50027.2020.00024

Exploring Modern FPGA Platforms for Faster Phylogeny Reconstruction with RAxML

Pavlos Malakonakis, Andreas Brokalakis, Nikolaos Alachiotis, Evripides Sotiriades, Apostolos Dollas

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

5 Citations (Scopus)

118 Downloads (Pure)

Abstract

The Phylogenetic Likelihood Function (PLF) is one of the cornerstone functions in most phylogenetic inference tools; its execution represents the majority of time required to complete an analysis. This work proposes the acceleration of this function using reconfigurable hardware accelerators, focusing on system-on-chips that integrate Field Programmable Gate Array (FPGA) resources as well as traditional High Performance Computing (HPC) systems that use FPGA-based accelerator cards. Taking into account the specific properties of each platform in order to exploit their processing capabilities, the proposed solutions provide significant performance gains. The measured acceleration of PLF function is up to 8x while the overall time to complete a phylogenetic analysis using the popular RAxML software can be reduced up to 3.2 times (with respect to a pure software implementation on a high-end server processor). Compared to other similar solutions proposed in literature, our systems perform up to 65% faster.

Original language	English
Title of host publication	2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE)
Place of Publication	Piscataway, NJ
Publisher	IEEE
Number of pages	8
ISBN (Electronic)	978-1-7281-9574-2
ISBN (Print)	978-1-7281-9575-9
DOIs	https://doi.org/10.1109/BIBE50027.2020.00024
Publication status	Published - 2020
Event	20th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2020 - Cincinnati, United States Duration: 26 Oct 2020 → 28 Oct 2020 Conference number: 20

Publication series

Name	Proceedings IEEE International Conference on Bioinformatics and Bioengineering (BIBE)
Publisher	IEEE
Volume	2020
ISSN (Print)	2159-5410
ISSN (Electronic)	2471-7819

Conference

Conference	20th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2020
Abbreviated title	BIBE
Country/Territory	United States
City	Cincinnati
Period	26/10/20 → 28/10/20

Keywords

22/2 OA procedure

Access to Document

10.1109/BIBE50027.2020.00024

Malakonakios2020exploringFinal published version, 356 KBLicence: Taverne

Cite this

Malakonakis, P., Brokalakis, A., Alachiotis, N., Sotiriades, E., & Dollas, A. (2020). Exploring Modern FPGA Platforms for Faster Phylogeny Reconstruction with RAxML. In 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE) (Proceedings IEEE International Conference on Bioinformatics and Bioengineering (BIBE); Vol. 2020). IEEE. https://doi.org/10.1109/BIBE50027.2020.00024

@inproceedings{b21795b9cbe74069a5a449eaba49b183,

title = "Exploring Modern FPGA Platforms for Faster Phylogeny Reconstruction with RAxML",

abstract = "The Phylogenetic Likelihood Function (PLF) is one of the cornerstone functions in most phylogenetic inference tools; its execution represents the majority of time required to complete an analysis. This work proposes the acceleration of this function using reconfigurable hardware accelerators, focusing on system-on-chips that integrate Field Programmable Gate Array (FPGA) resources as well as traditional High Performance Computing (HPC) systems that use FPGA-based accelerator cards. Taking into account the specific properties of each platform in order to exploit their processing capabilities, the proposed solutions provide significant performance gains. The measured acceleration of PLF function is up to 8x while the overall time to complete a phylogenetic analysis using the popular RAxML software can be reduced up to 3.2 times (with respect to a pure software implementation on a high-end server processor). Compared to other similar solutions proposed in literature, our systems perform up to 65% faster.",

keywords = "22/2 OA procedure",

author = "Pavlos Malakonakis and Andreas Brokalakis and Nikolaos Alachiotis and Evripides Sotiriades and Apostolos Dollas",

year = "2020",

doi = "10.1109/BIBE50027.2020.00024",

language = "English",

isbn = "978-1-7281-9575-9",

series = "Proceedings IEEE International Conference on Bioinformatics and Bioengineering (BIBE)",

publisher = "IEEE",

booktitle = "2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE)",

address = "United States",

note = "20th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2020, BIBE ; Conference date: 26-10-2020 Through 28-10-2020",

}

Malakonakis, P, Brokalakis, A, Alachiotis, N, Sotiriades, E & Dollas, A 2020, Exploring Modern FPGA Platforms for Faster Phylogeny Reconstruction with RAxML. in 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE). Proceedings IEEE International Conference on Bioinformatics and Bioengineering (BIBE), vol. 2020, IEEE, Piscataway, NJ, 20th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2020, Cincinnati, Ohio, United States, 26/10/20. https://doi.org/10.1109/BIBE50027.2020.00024

Exploring Modern FPGA Platforms for Faster Phylogeny Reconstruction with RAxML. / Malakonakis, Pavlos; Brokalakis, Andreas; Alachiotis, Nikolaos et al.
2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE). Piscataway, NJ: IEEE, 2020. (Proceedings IEEE International Conference on Bioinformatics and Bioengineering (BIBE); Vol. 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Exploring Modern FPGA Platforms for Faster Phylogeny Reconstruction with RAxML

AU - Malakonakis, Pavlos

AU - Brokalakis, Andreas

AU - Alachiotis, Nikolaos

AU - Sotiriades, Evripides

AU - Dollas, Apostolos

N1 - Conference code: 20

PY - 2020

Y1 - 2020

N2 - The Phylogenetic Likelihood Function (PLF) is one of the cornerstone functions in most phylogenetic inference tools; its execution represents the majority of time required to complete an analysis. This work proposes the acceleration of this function using reconfigurable hardware accelerators, focusing on system-on-chips that integrate Field Programmable Gate Array (FPGA) resources as well as traditional High Performance Computing (HPC) systems that use FPGA-based accelerator cards. Taking into account the specific properties of each platform in order to exploit their processing capabilities, the proposed solutions provide significant performance gains. The measured acceleration of PLF function is up to 8x while the overall time to complete a phylogenetic analysis using the popular RAxML software can be reduced up to 3.2 times (with respect to a pure software implementation on a high-end server processor). Compared to other similar solutions proposed in literature, our systems perform up to 65% faster.

AB - The Phylogenetic Likelihood Function (PLF) is one of the cornerstone functions in most phylogenetic inference tools; its execution represents the majority of time required to complete an analysis. This work proposes the acceleration of this function using reconfigurable hardware accelerators, focusing on system-on-chips that integrate Field Programmable Gate Array (FPGA) resources as well as traditional High Performance Computing (HPC) systems that use FPGA-based accelerator cards. Taking into account the specific properties of each platform in order to exploit their processing capabilities, the proposed solutions provide significant performance gains. The measured acceleration of PLF function is up to 8x while the overall time to complete a phylogenetic analysis using the popular RAxML software can be reduced up to 3.2 times (with respect to a pure software implementation on a high-end server processor). Compared to other similar solutions proposed in literature, our systems perform up to 65% faster.

KW - 22/2 OA procedure

U2 - 10.1109/BIBE50027.2020.00024

DO - 10.1109/BIBE50027.2020.00024

M3 - Conference contribution

SN - 978-1-7281-9575-9

T3 - Proceedings IEEE International Conference on Bioinformatics and Bioengineering (BIBE)

BT - 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE)

PB - IEEE

CY - Piscataway, NJ

T2 - 20th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2020

Y2 - 26 October 2020 through 28 October 2020

ER -

Malakonakis P, Brokalakis A, Alachiotis N, Sotiriades E, Dollas A. Exploring Modern FPGA Platforms for Faster Phylogeny Reconstruction with RAxML. In 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE). Piscataway, NJ: IEEE. 2020. (Proceedings IEEE International Conference on Bioinformatics and Bioengineering (BIBE)). doi: 10.1109/BIBE50027.2020.00024

Exploring Modern FPGA Platforms for Faster Phylogeny Reconstruction with RAxML

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this