This paper presents a series of experiments for evaluating the influence of the interaction between Network Interfaces (NIs) and host computer systems on the performance of a messaging system based on Myrinet. Major points of interest are the data transfer between user buffers and NI local memory and the synchronization between host systems and NIs. The paper provides a taxonomy of various transfer modes and synchronization schemes, describes experiments for their performance evaluation, and analyzes the results on a specific platform as well as between different platforms. Furthermore, this paper points out the affects of the reviewed data transfer modes and synchronization schemes on the overall performance of Myrinet based message-passin...
iAbstract Much of a computer’s communication performance is determined by how well it inter-acts wit...
This paper presents a high-fidelity, event-driven model for performance analysis of various applicat...
Contact chongcsucdavisedu The goal of this paper is to gain insight into the relative performance o...
This paper surveys the design issues for user-level network interface protocols for modern high-spee...
The performance of parallel and distributed applications running on network of workstation resources...
Both the Infiniband and the virtual interface architecture (VIA) aim at providing effective cluster ...
Clusters of workstations are a popular platform for high-performance computing. For many parallel ap...
We describe the design and implementation of MPI-NP, a Myrinet communication system tailored to sup...
This paper compares the performance of Myrinet and Eth-ernet as a communication substrate for MPI li...
This paper describes an implementation of the Message Passing Interface (MPI) on the Portals 3.0 dat...
Both the Infiniband and the virtual interface architecture (VIA) aim at providing effective cluster ...
We systematically evaluate the performance of five implementations of a single, user-level communica...
We have implemented a system called MPI-NP II, which is an MPI specific messaging system for the My...
User-level network interfaces allow applications direct access to the network without operating syst...
This paper provides experimental data and analysis to quantify both the peak and sustained performan...
iAbstract Much of a computer’s communication performance is determined by how well it inter-acts wit...
This paper presents a high-fidelity, event-driven model for performance analysis of various applicat...
Contact chongcsucdavisedu The goal of this paper is to gain insight into the relative performance o...
This paper surveys the design issues for user-level network interface protocols for modern high-spee...
The performance of parallel and distributed applications running on network of workstation resources...
Both the Infiniband and the virtual interface architecture (VIA) aim at providing effective cluster ...
Clusters of workstations are a popular platform for high-performance computing. For many parallel ap...
We describe the design and implementation of MPI-NP, a Myrinet communication system tailored to sup...
This paper compares the performance of Myrinet and Eth-ernet as a communication substrate for MPI li...
This paper describes an implementation of the Message Passing Interface (MPI) on the Portals 3.0 dat...
Both the Infiniband and the virtual interface architecture (VIA) aim at providing effective cluster ...
We systematically evaluate the performance of five implementations of a single, user-level communica...
We have implemented a system called MPI-NP II, which is an MPI specific messaging system for the My...
User-level network interfaces allow applications direct access to the network without operating syst...
This paper provides experimental data and analysis to quantify both the peak and sustained performan...
iAbstract Much of a computer’s communication performance is determined by how well it inter-acts wit...
This paper presents a high-fidelity, event-driven model for performance analysis of various applicat...
Contact chongcsucdavisedu The goal of this paper is to gain insight into the relative performance o...