Evaluation of DEC`s GIGAswitch for distributed parallel computing

Chen, H; Hutchins, J; Brandt, J

doi:10.2172/10188486

Title: Evaluation of DEC`s GIGAswitch for distributed parallel computing

Full Record
Other Related Research

Abstract

One of Sandia`s research efforts is to reduce the end-to-end communication delay in a parallel-distributed computing environment. GIGAswitch is DEC`s implementation of a gigabit local area network based on switched FDDI technology. Using the GIGAswitch, the authors intend to minimize the medium access latency suffered by shared-medium FDDI technology. Experimental results show that the GIGAswitch adds 16.5 microseconds of switching and bridging delay to an end-to-end communication. Although the added latency causes a 1.8% throughput degradation and a 5% line efficiency degradation, the availability of dedicated bandwidth is much more than what is available to a workstation on a shared medium. For example, ten directly connected workstations each would have a dedicated bandwidth of 95 Mbps, but if they were sharing the FDDI bandwidth, each would have 10% of the total bandwidth, i.e., less than 10 Mbps. In addition, they have found that when there is no output port contention, the switch`s aggregate bandwidth will scale up to multiples of its port bandwidth. However, with output port contention, the throughput and latency performance suffered significantly. Their mathematical and simulation models indicate that the GIGAswitch line efficiency could be as low as 63% when there are nine input ports contending formore »« less

Authors:: Chen, H; Hutchins, J; Brandt, J

Publication Date:: Fri Oct 01 00:00:00 EDT 1993

Research Org.:: Sandia National Lab. (SNL-CA), Livermore, CA (United States)

Sponsoring Org.:: USDOE, Washington, DC (United States)

OSTI Identifier:: 10188486

Report Number(s):: SAND-93-8013
ON: DE94001356; TRN: 93:003610

DOE Contract Number:: AC04-76DR00789

Resource Type:: Technical Report

Resource Relation:: Other Information: PBD: Oct 1993

Country of Publication:: United States

Language:: English

Subject:: 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; COMPUTER NETWORKS; PARALLEL PROCESSING; PERFORMANCE; DEC COMPUTERS; COMPUTERIZED SIMULATION; 990200; MATHEMATICS AND COMPUTERS

Citation Formats


                    Chen, H, Hutchins, J, and Brandt, J. Evaluation of DEC`s GIGAswitch for distributed parallel computing.  United States: N. p., 1993. 
        Web.  doi:10.2172/10188486.

Copy to clipboard


                    Chen, H, Hutchins, J, & Brandt, J. Evaluation of DEC`s GIGAswitch for distributed parallel computing.  United States.  https://doi.org/10.2172/10188486

Copy to clipboard


                    Chen, H, Hutchins, J, and Brandt, J. 1993.  
        "Evaluation of DEC`s GIGAswitch for distributed parallel computing".  United States.  https://doi.org/10.2172/10188486.  https://www.osti.gov/servlets/purl/10188486.

Copy to clipboard


                    
@article{osti_10188486,

  title        = {Evaluation of DEC`s GIGAswitch for distributed parallel computing},

  author       = {Chen, H and Hutchins, J and Brandt, J},

  abstractNote = {One of Sandia`s research efforts is to reduce the end-to-end communication delay in a parallel-distributed computing environment. GIGAswitch is DEC`s implementation of a gigabit local area network based on switched FDDI technology. Using the GIGAswitch, the authors intend to minimize the medium access latency suffered by shared-medium FDDI technology. Experimental results show that the GIGAswitch adds 16.5 microseconds of switching and bridging delay to an end-to-end communication. Although the added latency causes a 1.8% throughput degradation and a 5% line efficiency degradation, the availability of dedicated bandwidth is much more than what is available to a workstation on a shared medium. For example, ten directly connected workstations each would have a dedicated bandwidth of 95 Mbps, but if they were sharing the FDDI bandwidth, each would have 10% of the total bandwidth, i.e., less than 10 Mbps. In addition, they have found that when there is no output port contention, the switch`s aggregate bandwidth will scale up to multiples of its port bandwidth. However, with output port contention, the throughput and latency performance suffered significantly. Their mathematical and simulation models indicate that the GIGAswitch line efficiency could be as low as 63% when there are nine input ports contending for the same output port. The data indicate that the delay introduced by contention at the server workstation is 50 times that introduced by the GIGAswitch. The authors conclude that the GIGAswitch meets the performance requirements of today`s high-end workstations and that the switched FDDI technology provides an alternative that utilizes existing workstation interfaces while increasing the aggregate bandwidth. However, because the speed of workstations is increasing by a factor of 2 every 1.5 years, the switched FDDI technology is only good as an interim solution.},

  doi          = {10.2172/10188486},

  url          = {https://www.osti.gov/biblio/10188486},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {Fri Oct 01 00:00:00 EDT 1993},

  month        = {Fri Oct 01 00:00:00 EDT 1993}

}

Copy to clipboard

Technical Report:

View Technical Report (1.59 MB)

https://doi.org/10.2172/10188486

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

The APS control system network upgrade.

Conference Sidorowicz, K; Leibfritz, D; McDowell, W

When it was installed,the Advanced Photon Source (APS) control system network was at the state-of-the-art. Different aspects of the system have been reported at previous meetings [1,2]. As loads on the controls network have increased due to newer and faster workstations and front-end computers, we have found performance of the system declining and have implemented an upgraded network. There have been dramatic advances in networking hardware in the last several years. The upgraded APS controls network replaces the original FDDI backbone and shared Ethernet hubs with redundant gigabit uplinks and fully switched 10/100 Ethernet switches with backplane fabrics in excessmore »« less
Full Text Available
Data Processing and Analysis Systems for JT-60U

Journal Article Matsuda, T; Totsuka, T; Tsugita, T; ... - Fusion Science and Technology

The JT-60U data processing system is a large computer complex gradually modernized by utilizing progressive computer and network technology. A main computer using state-of-the-art CMOS technology can handle {approx}550 MB of data per discharge. A gigabit ethernet switch with FDDI ports has been introduced to cope with the increase of handling data. Workstation systems with VMEbus serial highway drivers for CAMAC have been developed and used to replace many minicomputer systems. VMEbus-based fast data acquisition systems have also been developed to enlarge and replace a minicomputer system for mass data.The JT-60U data analysis system is composed of a JT-60U databasemore »« less
QsNetII : Defining High-Performance Network Design

Journal Article Beecroft, Jon; Addison, David; Hewson, David; ... - IEEE Micro, 25(4):34 - 47

Cluster computers—parallel computers built from commodity processors—are becoming the predominant supercomputer architecture because of their combined scalable performance and attractive price. As of June 2005, 61 percent of the world’s top-500 supercomputers were clusters (http://www.top500.org). This is a significant paradigm shift from a few decades ago, when supercomputers were special purpose, like the Cray vector machines, and designers built them from expensive, custom components. Clusters that use commodity processors still require high-performance, low-latency networks, if their applications are fine-grained, or if the cluster has many processors. Clusters can use commodity networks, such as Gigabit Ethernet, but these fall short inmore »« less
https://doi.org/10.1109/MM.2005.75
Research in models for massively parallel computing

Conference Morse, N

Workstation-Based Supercomputing: Supercomputing in the DoE has been traditionally performed on von Neumann vector pipeline machines. In the past few years, a belief has developed that advances in supercomputing capability in the future must come from massively parallel architectures. When considering such architectures, many questions remain which are active areas of research. Examples of research subjects for massively parallel computing paradigms are communication structures, memory structures, node processor architectures, latency hiding, algorithm development, switching schemes, communication bandwidth and support software. Gigabit Networks: A problem which has existed in computing since networks were invented is that the quality of service receivedmore »« less
Configurable Crossbar Switch for Deterministic, Low-latency Inter-blade Communications in a MicroTCA Platform

Program Document Karamooz, Saeed; Breeding, John; Justice, T

As MicroTCA expands into applications beyond the telecommunications industry from which it originated, it faces new challenges in the area of inter-blade communications. The ability to achieve deterministic, low-latency communications between blades is critical to realizing a scalable architecture. In the past, legacy bus architectures accomplished inter-blade communications using dedicated parallel buses across the backplane. Because of limited fabric resources on its backplane, MicroTCA uses the carrier hub (MCH) for this purpose. Unfortunately, MCH products from commercial vendors are limited to standard bus protocols such as PCI Express, Serial Rapid IO and 10/40GbE. While these protocols have exceptional throughput capability,more »« less
Full Text Available

Similar Records