DE-ZFP: An FPGA implementation of a modified ZFP compression/decompression algorithm

Mahmoud Habboush; Aiman H. El-Maleh; Muhammad E.S. Elrabaa; Saleh AlSaleh

doi:10.1016/j.micpro.2022.104453

DE-ZFP: An FPGA implementation of a modified ZFP compression/decompression algorithm

Mahmoud Habboush, Aiman H. El-Maleh^*, Muhammad E.S. Elrabaa, Saleh AlSaleh

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

3 Scopus citations

Abstract

In this work, we present DE-ZFP: a hardware implementation of modified ZFP compression and decompression algorithms on a Field Programmable Gate Array (FPGA). It can be used to accelerate applications running on a host CPU that generates large volumes of floating point data. The proposed design uses dictionary-based encoding (DE) in lieu of ZFP's original embedded encoding to maximize hardware performance. Furthermore, the block encoder logic was optimized such that the loss of compression efficiency due to DE remains within 4%–13% of the original ZFP software implementation, with up to 19x improvement in throughput.

Original language	English
Article number	104453
Journal	Microprocessors and Microsystems
Volume	90
DOIs	https://doi.org/10.1016/j.micpro.2022.104453
State	Published - Apr 2022

Bibliographical note

Funding Information:
This research was funded by KFUPM under project No. DF191015 .

Funding Information:
This research was funded by KFUPM under project No. DF191015.This work is supported by King Fahd University of Petroleum & Minerals under project No. DF191015. The authors acknowledge the help of Dr. Peter Lindstrom. Hurricane Isabel data produced by the Weather Research and Forecast model, courtesy of NCAR and the U.S. National Science Foundation. Data collection is a courtesy of DOE NNSA ECP project and the ECP CODAR project.

Funding Information:
This work is supported by King Fahd University of Petroleum & Minerals under project No. DF191015. The authors acknowledge the help of Dr. Peter Lindstrom. Hurricane Isabel data produced by the Weather Research and Forecast model, courtesy of NCAR and the U.S. National Science Foundation. Data collection is a courtesy of DOE NNSA ECP project and the ECP CODAR project.

Publisher Copyright:
© 2022 Elsevier B.V.

Keywords

FPGA acceleration
Hardware implementation
Lossy compression

ASJC Scopus subject areas

Software
Hardware and Architecture
Computer Networks and Communications
Artificial Intelligence

Access to Document

10.1016/j.micpro.2022.104453

Cite this

@article{b4781a13f50d4449aec2a9e1ec21699b,

title = "DE-ZFP: An FPGA implementation of a modified ZFP compression/decompression algorithm",

abstract = "In this work, we present DE-ZFP: a hardware implementation of modified ZFP compression and decompression algorithms on a Field Programmable Gate Array (FPGA). It can be used to accelerate applications running on a host CPU that generates large volumes of floating point data. The proposed design uses dictionary-based encoding (DE) in lieu of ZFP's original embedded encoding to maximize hardware performance. Furthermore, the block encoder logic was optimized such that the loss of compression efficiency due to DE remains within 4%–13% of the original ZFP software implementation, with up to 19x improvement in throughput.",

keywords = "FPGA acceleration, Hardware implementation, Lossy compression",

author = "Mahmoud Habboush and El-Maleh, {Aiman H.} and Elrabaa, {Muhammad E.S.} and Saleh AlSaleh",

note = "Funding Information: This research was funded by KFUPM under project No. DF191015 . Funding Information: This research was funded by KFUPM under project No. DF191015.This work is supported by King Fahd University of Petroleum & Minerals under project No. DF191015. The authors acknowledge the help of Dr. Peter Lindstrom. Hurricane Isabel data produced by the Weather Research and Forecast model, courtesy of NCAR and the U.S. National Science Foundation. Data collection is a courtesy of DOE NNSA ECP project and the ECP CODAR project. Funding Information: This work is supported by King Fahd University of Petroleum & Minerals under project No. DF191015. The authors acknowledge the help of Dr. Peter Lindstrom. Hurricane Isabel data produced by the Weather Research and Forecast model, courtesy of NCAR and the U.S. National Science Foundation. Data collection is a courtesy of DOE NNSA ECP project and the ECP CODAR project. Publisher Copyright: {\textcopyright} 2022 Elsevier B.V.",

year = "2022",

month = apr,

doi = "10.1016/j.micpro.2022.104453",

language = "English",

volume = "90",

journal = "Microprocessors and Microsystems",

issn = "0141-9331",

publisher = "Elsevier",

}

TY - JOUR

T1 - DE-ZFP

T2 - An FPGA implementation of a modified ZFP compression/decompression algorithm

AU - Habboush, Mahmoud

AU - El-Maleh, Aiman H.

AU - Elrabaa, Muhammad E.S.

AU - AlSaleh, Saleh

N1 - Funding Information: This research was funded by KFUPM under project No. DF191015 . Funding Information: This research was funded by KFUPM under project No. DF191015.This work is supported by King Fahd University of Petroleum & Minerals under project No. DF191015. The authors acknowledge the help of Dr. Peter Lindstrom. Hurricane Isabel data produced by the Weather Research and Forecast model, courtesy of NCAR and the U.S. National Science Foundation. Data collection is a courtesy of DOE NNSA ECP project and the ECP CODAR project. Funding Information: This work is supported by King Fahd University of Petroleum & Minerals under project No. DF191015. The authors acknowledge the help of Dr. Peter Lindstrom. Hurricane Isabel data produced by the Weather Research and Forecast model, courtesy of NCAR and the U.S. National Science Foundation. Data collection is a courtesy of DOE NNSA ECP project and the ECP CODAR project. Publisher Copyright: © 2022 Elsevier B.V.

PY - 2022/4

Y1 - 2022/4

N2 - In this work, we present DE-ZFP: a hardware implementation of modified ZFP compression and decompression algorithms on a Field Programmable Gate Array (FPGA). It can be used to accelerate applications running on a host CPU that generates large volumes of floating point data. The proposed design uses dictionary-based encoding (DE) in lieu of ZFP's original embedded encoding to maximize hardware performance. Furthermore, the block encoder logic was optimized such that the loss of compression efficiency due to DE remains within 4%–13% of the original ZFP software implementation, with up to 19x improvement in throughput.

AB - In this work, we present DE-ZFP: a hardware implementation of modified ZFP compression and decompression algorithms on a Field Programmable Gate Array (FPGA). It can be used to accelerate applications running on a host CPU that generates large volumes of floating point data. The proposed design uses dictionary-based encoding (DE) in lieu of ZFP's original embedded encoding to maximize hardware performance. Furthermore, the block encoder logic was optimized such that the loss of compression efficiency due to DE remains within 4%–13% of the original ZFP software implementation, with up to 19x improvement in throughput.

KW - FPGA acceleration

KW - Hardware implementation

KW - Lossy compression

UR - http://www.scopus.com/inward/record.url?scp=85123883948&partnerID=8YFLogxK

U2 - 10.1016/j.micpro.2022.104453

DO - 10.1016/j.micpro.2022.104453

M3 - Article

AN - SCOPUS:85123883948

SN - 0141-9331

VL - 90

JO - Microprocessors and Microsystems

JF - Microprocessors and Microsystems

M1 - 104453

ER -

DE-ZFP: An FPGA implementation of a modified ZFP compression/decompression algorithm

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this