Interrupt-less parallel I/O processing based on the continuation-based multiThreading model

Masaaki Izumi; Mitsuhiro Aono; Satoshi Amamiya; Takanori Matsuzaki; Shigeru Kusakabe; Hideo Taniguchi; Ryuzo Hasegawa; Makoto Amamiya

Interrupt-less parallel I/O processing based on the continuation-based multiThreading model

Masaaki Izumi, Mitsuhiro Aono, Satoshi Amamiya, Takanori Matsuzaki, Shigeru Kusakabe, Hideo Taniguchi, Ryuzo Hasegawa, Makoto Amamiya

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

Abstract

We propose the Fuco architecture based on dataflow computing model. The goal of this architecture is fusion of communication and execution. The multiple thread execution model of the architecture takes the continuation-based multithreading model that manages dependency among fine-grain "uninterruptible" threads. In this paper, the continuation-based multithreading model constructs more resourceful parallel I/O processing cooperated with by processor and operating system. Our model is different from the conventional I/O processing model that handles "interrupt." We illustrate the continuation-based parallel I/O processing model.

Original language	English
Pages (from-to)	41-47
Number of pages	7
Journal	Research Reports on Information Science and Electrical Engineering of Kyushu University
Volume	12
Issue number	1
Publication status	Published - Mar 2007
Externally published	Yes

Keywords

Chip multiprocessor
Fine-grain multithreading
Fuce architecture
Interrupt-less
Parallel I/O processing

ASJC Scopus subject areas

Computer Science(all)
Electrical and Electronic Engineering

Cite this

@article{1f32258981054b838cb9af435344a2f9,

title = "Interrupt-less parallel I/O processing based on the continuation-based multiThreading model",

abstract = "We propose the Fuco architecture based on dataflow computing model. The goal of this architecture is fusion of communication and execution. The multiple thread execution model of the architecture takes the continuation-based multithreading model that manages dependency among fine-grain {"}uninterruptible{"} threads. In this paper, the continuation-based multithreading model constructs more resourceful parallel I/O processing cooperated with by processor and operating system. Our model is different from the conventional I/O processing model that handles {"}interrupt.{"} We illustrate the continuation-based parallel I/O processing model.",

keywords = "Chip multiprocessor, Fine-grain multithreading, Fuce architecture, Interrupt-less, Parallel I/O processing",

author = "Masaaki Izumi and Mitsuhiro Aono and Satoshi Amamiya and Takanori Matsuzaki and Shigeru Kusakabe and Hideo Taniguchi and Ryuzo Hasegawa and Makoto Amamiya",

year = "2007",

month = mar,

language = "English",

volume = "12",

pages = "41--47",

journal = "Research Reports on Information Science and Electrical Engineering of Kyushu University",

issn = "1342-3819",

publisher = "Kyushu University, Faculty of Science",

number = "1",

}

TY - JOUR

T1 - Interrupt-less parallel I/O processing based on the continuation-based multiThreading model

AU - Izumi, Masaaki

AU - Aono, Mitsuhiro

AU - Amamiya, Satoshi

AU - Matsuzaki, Takanori

AU - Kusakabe, Shigeru

AU - Taniguchi, Hideo

AU - Hasegawa, Ryuzo

AU - Amamiya, Makoto

PY - 2007/3

Y1 - 2007/3

N2 - We propose the Fuco architecture based on dataflow computing model. The goal of this architecture is fusion of communication and execution. The multiple thread execution model of the architecture takes the continuation-based multithreading model that manages dependency among fine-grain "uninterruptible" threads. In this paper, the continuation-based multithreading model constructs more resourceful parallel I/O processing cooperated with by processor and operating system. Our model is different from the conventional I/O processing model that handles "interrupt." We illustrate the continuation-based parallel I/O processing model.

AB - We propose the Fuco architecture based on dataflow computing model. The goal of this architecture is fusion of communication and execution. The multiple thread execution model of the architecture takes the continuation-based multithreading model that manages dependency among fine-grain "uninterruptible" threads. In this paper, the continuation-based multithreading model constructs more resourceful parallel I/O processing cooperated with by processor and operating system. Our model is different from the conventional I/O processing model that handles "interrupt." We illustrate the continuation-based parallel I/O processing model.

KW - Chip multiprocessor

KW - Fine-grain multithreading

KW - Fuce architecture

KW - Interrupt-less

KW - Parallel I/O processing

UR - http://www.scopus.com/inward/record.url?scp=34548051796&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548051796&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:34548051796

SN - 1342-3819

VL - 12

SP - 41

EP - 47

JO - Research Reports on Information Science and Electrical Engineering of Kyushu University

JF - Research Reports on Information Science and Electrical Engineering of Kyushu University

IS - 1

ER -

Interrupt-less parallel I/O processing based on the continuation-based multiThreading model

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this