Analysis and enhancement of pipelining the protocol overheads for a high throughput

Hyun Wook Jin, Hyuck Yoo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper investigates the protocol overhead pipelining between the host and network interface card (NIC). Existing researches into the protocol overhead pipelining assume that protocol overheads in the host and NIC can be naturally pipelined. Our architecture-aware investigation, however, finds a new fact that the host and NIC compete against each other to access the host memory, system bus, and I/O bus, so that the overhead pipelining is seriously hindered, which leads to a sub-optimal performance. We suggest several methods to avoid such competitions for the hardware resources and implement a pipelining UDP named π-UDP on Myrinet. As a result, π-UDP achieves over 97% of the theoretical maximum throughput of Myrinet.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications
EditorsH.R. Arabnia, Y. Mun, H.R. Arabnia, Y. Mun
Pages935-941
Number of pages7
Volume2
Publication statusPublished - 2003 Dec 1
EventProceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications - Las Vegas, NV, United States
Duration: 2003 Jun 232003 Jun 26

Other

OtherProceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications
CountryUnited States
CityLas Vegas, NV
Period03/6/2303/6/26

Keywords

  • Gigabit LAN
  • Myrinet
  • Overhead pipelining
  • UDP/IP

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Analysis and enhancement of pipelining the protocol overheads for a high throughput'. Together they form a unique fingerprint.

  • Cite this

    Jin, H. W., & Yoo, H. (2003). Analysis and enhancement of pipelining the protocol overheads for a high throughput. In H. R. Arabnia, Y. Mun, H. R. Arabnia, & Y. Mun (Eds.), Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications (Vol. 2, pp. 935-941)