Performance evaluation for CC-NUMA multiprocessors using an OLTP workload

Yongwha Chung; Hiecheol Kim; Jin Won Park; Kangwoo Lee

doi:10.1016/S0141-9331(01)00115-6

Performance evaluation for CC-NUMA multiprocessors using an OLTP workload

Yongwha Chung
, Hiecheol Kim
, Jin Won Park
, Kangwoo Lee

Department of Computer Science and Artificial Intelligence

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

1 Scopus citations

Abstract

The CC-NUMA is a promising architecture for multiprocessor computer systems because of its scalability and ease of programming. However, little is known about the collective performance of the cache coherency protocol, the interconnection network, and the I/O subsystem of the CC-NUMA multiprocessor. In this paper, we analyzed the collective performance of various configurations of the CC-NUMA multiprocessor using commercial workload targeted for popular OLTP applications. The simulation results showed that the bottleneck on the ring, the switch-based tree, and the I/O subsystem could be identified and effectively removed by changing the configurations.

Original language	English
Pages (from-to)	221-229
Number of pages	9
Journal	Microprocessors and Microsystems
Volume	25
Issue number	4
DOIs	https://doi.org/10.1016/S0141-9331(01)00115-6
State	Published - 25 Jun 2001

Keywords

CC-NUMA multiprocessor
OLTP workload
Performance evaluation

Access to Document

10.1016/S0141-9331(01)00115-6

Cite this

@article{90f80eb9bc3741a294bb2d96eed13ccc,

title = "Performance evaluation for CC-NUMA multiprocessors using an OLTP workload",

abstract = "The CC-NUMA is a promising architecture for multiprocessor computer systems because of its scalability and ease of programming. However, little is known about the collective performance of the cache coherency protocol, the interconnection network, and the I/O subsystem of the CC-NUMA multiprocessor. In this paper, we analyzed the collective performance of various configurations of the CC-NUMA multiprocessor using commercial workload targeted for popular OLTP applications. The simulation results showed that the bottleneck on the ring, the switch-based tree, and the I/O subsystem could be identified and effectively removed by changing the configurations.",

keywords = "CC-NUMA multiprocessor, OLTP workload, Performance evaluation",

author = "Yongwha Chung and Hiecheol Kim and Park, \{Jin Won\} and Kangwoo Lee",

year = "2001",

month = jun,

day = "25",

doi = "10.1016/S0141-9331(01)00115-6",

language = "English",

volume = "25",

pages = "221--229",

journal = "Microprocessors and Microsystems",

issn = "0141-9331",

publisher = "Elsevier B.V.",

number = "4",

}

TY - JOUR

T1 - Performance evaluation for CC-NUMA multiprocessors using an OLTP workload

AU - Chung, Yongwha

AU - Kim, Hiecheol

AU - Park, Jin Won

AU - Lee, Kangwoo

PY - 2001/6/25

Y1 - 2001/6/25

N2 - The CC-NUMA is a promising architecture for multiprocessor computer systems because of its scalability and ease of programming. However, little is known about the collective performance of the cache coherency protocol, the interconnection network, and the I/O subsystem of the CC-NUMA multiprocessor. In this paper, we analyzed the collective performance of various configurations of the CC-NUMA multiprocessor using commercial workload targeted for popular OLTP applications. The simulation results showed that the bottleneck on the ring, the switch-based tree, and the I/O subsystem could be identified and effectively removed by changing the configurations.

AB - The CC-NUMA is a promising architecture for multiprocessor computer systems because of its scalability and ease of programming. However, little is known about the collective performance of the cache coherency protocol, the interconnection network, and the I/O subsystem of the CC-NUMA multiprocessor. In this paper, we analyzed the collective performance of various configurations of the CC-NUMA multiprocessor using commercial workload targeted for popular OLTP applications. The simulation results showed that the bottleneck on the ring, the switch-based tree, and the I/O subsystem could be identified and effectively removed by changing the configurations.

KW - CC-NUMA multiprocessor

KW - OLTP workload

KW - Performance evaluation

UR - https://www.scopus.com/pages/publications/0035948207

U2 - 10.1016/S0141-9331(01)00115-6

DO - 10.1016/S0141-9331(01)00115-6

M3 - Article

AN - SCOPUS:0035948207

SN - 0141-9331

VL - 25

SP - 221

EP - 229

JO - Microprocessors and Microsystems

JF - Microprocessors and Microsystems

IS - 4

ER -

Performance evaluation for CC-NUMA multiprocessors using an OLTP workload

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this