Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data.

Paul Dietrich

dblp:88/1992 · DBLP profile ↗
← Back
2ranked-venue papers
2as first author
0since 2021 · last 1996
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Systems, architecture and hardware · 1 · 1 first-authorComputer networks · 1 · 1 first-author

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Computer architecture, parallel and distributed computing, and storage systems
2 papers
Performance modeling and evaluation · 52% Interconnection networks and networks-on-chip · 48%

Topics — the 6 heaviest of 7, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Performance modeling and evaluation
delay analysis
0.021996
Request Resubmission in a Blocking, Circuit-Switched, Interconnection Network · IEEE Trans. Computers 1996
Delay Analysis of a Circuit-Switched Interconnection Network With Non-Uniform Traffic · INFOCOM 1994
Interconnection networks and networks-on-chip › switching network
multistage interconnection network
0.021996
Request Resubmission in a Blocking, Circuit-Switched, Interconnection Network · IEEE Trans. Computers 1996
Delay Analysis of a Circuit-Switched Interconnection Network With Non-Uniform Traffic · INFOCOM 1994
Interconnection networks and networks-on-chip › switching network › multistage interconnection network
delta network
0.011996
Request Resubmission in a Blocking, Circuit-Switched, Interconnection Network · IEEE Trans. Computers 1996
Performance modeling and evaluation
queueing models
0.011996
Request Resubmission in a Blocking, Circuit-Switched, Interconnection Network · IEEE Trans. Computers 1996
Performance modeling and evaluation
queueing analysis
0.011994
Delay Analysis of a Circuit-Switched Interconnection Network With Non-Uniform Traffic · INFOCOM 1994
Interconnection networks and networks-on-chip › switching network
self-routing network
0.011996
Request Resubmission in a Blocking, Circuit-Switched, Interconnection Network · IEEE Trans. Computers 1996

Methods — techniques the papers use, named apart from their topics

simulation · 0.0dominant system analysis · 0.0recursive expression · 0.0
YearPublicationVenuePosition
1996 Request Resubmission in a Blocking, Circuit-Switched, Interconnection Network
abstract
In this paper, we study the delay performance of a circuit switched, self-routing Delta network. A gated hold protocol that retains partial path information is used to guarantee service of all requests. A novel technique that involves the construction of an easier to analyze dominant system is presented. A recursive expression for the probability mass function of the cycle time in the dominant system is derived. Comparison of the dominant system analysis with simulation of the actual system shows that the dominant system accurately predicts performance for low network loads. As network loads increase, the dominant system becomes worse at predicting behavior of the actual system. These results also help develop insight into how to trade off higher delay variability for increased throughput.
Paul Dietrich, Ramesh R. Rao
IEEE Trans. Computers1
1994 Delay Analysis of a Circuit-Switched Interconnection Network With Non-Uniform Traffic
abstract
The authors analyze a circuit-switched, blocking, multi-stage interconnection network (MIN) with arbitrary independent input distributions and arbitrary switch routing probabilities. The network uses a gated-hold strategy which retains partial path information. By formulating a dominant system, they derive a recursive expression for the mean time to process a batch of requests given a particular input distribution and a set of switch routing probabilities. This system is compared to a simulation of a non-blocking switch implementing a similar gated strategy. Results indicate that this method yields tight bounds for small networks with arbitrary input distributions and switch routing probabilities. For networks with uniform input and output distributions this bound is closer than one introduced in a previous work examining the same protocol.>
Paul Dietrich, Ramesh R. Rao
INFOCOM1