Parallelization of tree-to-TLV serialization

Makoto Nakayama; Kenichi Yamazaki; Satoshi Tanaka; Hironori Kasahara

doi:10.1109/PCCC.2014.7017059

Parallelization of tree-to-TLV serialization

Makoto Nakayama, Kenichi Yamazaki, Satoshi Tanaka, Hironori Kasahara

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

A serializer/deserializer (SerDe) is necessary to serialize a data object into a byte array and to deserialize in reverse direction. A SerDe that is used worldwide and runs quickly is the Protocol Buffer (ProtoBuf), which serializes a tree-structured data object into the Type-Length-Value (TLV) format. Acceleration of SerDe processing is beneficial because SerDes are used in various fields. This paper proposes a new method that accelerates the tree-to-TLV serialization through 2-way parallel processing called "parallelized serialization" and "parallelization with streaming". Experimental results show that parallelized serialization with 4 worker threads achieves a 1.97 fold shorter serialization time than when using a single worker thread, and the combination of 2-way parallel processing achieves a 2.11 fold shorter output time than that for ProtoBuf when 4 worker threads, File Output Stream and trees of 10,080 container nodes are used.

本文言語	English
ホスト出版物のタイトル	2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014
出版社	Institute of Electrical and Electronics Engineers Inc.
巻	2014-January
ISBN（電子版）	9781479975754
DOI	https://doi.org/10.1109/PCCC.2014.7017059
出版ステータス	Published - 2015 1月 20
イベント	33rd IEEE International Performance Computing and Communications Conference, IPCCC 2014 - Austin, United States 継続期間: 2014 12月 5 → 2014 12月 7

Other

Other	33rd IEEE International Performance Computing and Communications Conference, IPCCC 2014
国/地域	United States
City	Austin
Period	14/12/5 → 14/12/7

ASJC Scopus subject areas

ソフトウェア
計算理論と計算数学
コンピュータネットワークおよび通信

文献へのアクセス

10.1109/PCCC.2014.7017059

他のファイルとリンク

引用スタイル

Nakayama, M, Yamazaki, K, Tanaka, S & Kasahara, H 2015, Parallelization of tree-to-TLV serialization. in 2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014. vol. 2014-January, 7017059, Institute of Electrical and Electronics Engineers Inc., 33rd IEEE International Performance Computing and Communications Conference, IPCCC 2014, Austin, United States, 14/12/5. https://doi.org/10.1109/PCCC.2014.7017059

@inproceedings{0e7b41b3dbb74e43bf437f818c3e895e,

title = "Parallelization of tree-to-TLV serialization",

abstract = "A serializer/deserializer (SerDe) is necessary to serialize a data object into a byte array and to deserialize in reverse direction. A SerDe that is used worldwide and runs quickly is the Protocol Buffer (ProtoBuf), which serializes a tree-structured data object into the Type-Length-Value (TLV) format. Acceleration of SerDe processing is beneficial because SerDes are used in various fields. This paper proposes a new method that accelerates the tree-to-TLV serialization through 2-way parallel processing called {"}parallelized serialization{"} and {"}parallelization with streaming{"}. Experimental results show that parallelized serialization with 4 worker threads achieves a 1.97 fold shorter serialization time than when using a single worker thread, and the combination of 2-way parallel processing achieves a 2.11 fold shorter output time than that for ProtoBuf when 4 worker threads, File Output Stream and trees of 10,080 container nodes are used.",

keywords = "Multi-Core, Parallel Processing, Serialization",

author = "Makoto Nakayama and Kenichi Yamazaki and Satoshi Tanaka and Hironori Kasahara",

year = "2015",

month = jan,

day = "20",

doi = "10.1109/PCCC.2014.7017059",

language = "English",

volume = "2014-January",

booktitle = "2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "33rd IEEE International Performance Computing and Communications Conference, IPCCC 2014 ; Conference date: 05-12-2014 Through 07-12-2014",

}

TY - GEN

T1 - Parallelization of tree-to-TLV serialization

AU - Nakayama, Makoto

AU - Yamazaki, Kenichi

AU - Tanaka, Satoshi

AU - Kasahara, Hironori

PY - 2015/1/20

Y1 - 2015/1/20

N2 - A serializer/deserializer (SerDe) is necessary to serialize a data object into a byte array and to deserialize in reverse direction. A SerDe that is used worldwide and runs quickly is the Protocol Buffer (ProtoBuf), which serializes a tree-structured data object into the Type-Length-Value (TLV) format. Acceleration of SerDe processing is beneficial because SerDes are used in various fields. This paper proposes a new method that accelerates the tree-to-TLV serialization through 2-way parallel processing called "parallelized serialization" and "parallelization with streaming". Experimental results show that parallelized serialization with 4 worker threads achieves a 1.97 fold shorter serialization time than when using a single worker thread, and the combination of 2-way parallel processing achieves a 2.11 fold shorter output time than that for ProtoBuf when 4 worker threads, File Output Stream and trees of 10,080 container nodes are used.

AB - A serializer/deserializer (SerDe) is necessary to serialize a data object into a byte array and to deserialize in reverse direction. A SerDe that is used worldwide and runs quickly is the Protocol Buffer (ProtoBuf), which serializes a tree-structured data object into the Type-Length-Value (TLV) format. Acceleration of SerDe processing is beneficial because SerDes are used in various fields. This paper proposes a new method that accelerates the tree-to-TLV serialization through 2-way parallel processing called "parallelized serialization" and "parallelization with streaming". Experimental results show that parallelized serialization with 4 worker threads achieves a 1.97 fold shorter serialization time than when using a single worker thread, and the combination of 2-way parallel processing achieves a 2.11 fold shorter output time than that for ProtoBuf when 4 worker threads, File Output Stream and trees of 10,080 container nodes are used.

KW - Multi-Core

KW - Parallel Processing

KW - Serialization

UR - http://www.scopus.com/inward/record.url?scp=84983121041&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983121041&partnerID=8YFLogxK

U2 - 10.1109/PCCC.2014.7017059

DO - 10.1109/PCCC.2014.7017059

M3 - Conference contribution

AN - SCOPUS:84983121041

VL - 2014-January

BT - 2014 IEEE 33rd International Performance Computing and Communications Conference, IPCCC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 33rd IEEE International Performance Computing and Communications Conference, IPCCC 2014

Y2 - 5 December 2014 through 7 December 2014

ER -

Parallelization of tree-to-TLV serialization

抄録

Other

ASJC Scopus subject areas

文献へのアクセス

他のファイルとリンク

フィンガープリント

引用スタイル