Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Implementation of MPICH on Top of MP_Lite

Thesis/Dissertation ·
DOI:https://doi.org/10.2172/803737· OSTI ID:803737
 [1]
  1. Iowa State Univ., Ames, IA (United States)

The goal of this thesis is to develop a new Channel Interface device for the MPICH Implementation of the MPI (Message Passing Interface) standard using MP_Lite. MP_Lite is a lightweight message-passing library that is not a full MPI implementation, but offers high performance MPICH (Message Passing Interface CHameleon) is a full implementation of the MPI standard that has the p4 library as the underlying communication device for TCP/IP networks. By integrating MP_Lite as a Channel Interface device in MPICH, a parallel programmer can utilize the full MPI implementation of MPICH as well as the high bandwidth offered by MP_Lite. There are several layers in the MPICH library where one can tie a new device. The Channel Interface is the lowest layer that requires very few functions to add a new device. By attaching MP_Lite to MPICH at the lowest level, the Channel Interface, almost all of the performance of the MP_Lite library can be delivered to the applications using MPICH. MP_Lite can be implemented either as a blocking or a non-blocking Channel Interface device. The performance was measured on two separate test clusters, the PC and the Alpha miniclusters, having Gigabit Ethernet connections. The PC cluster has two 1.8 GHz Pentium 4 PCs and the Alpha cluster has two 500 MHz Compaq DS20 workstations. Different network interface cards like Netgear, TrendNet and SysKonnect Gigabit Ethernet cards were used for the measurements. Both the blocking and non-blocking MPICH-MP_Lite Channel Interface devices perform close to raw TCP, whereas a performance loss of 25-30% is seen in the MPICH-p4 Channel Interface device for larger messages. The superior performance offered by the MPICH-MP_Lite device compared to the MPICH-p4 device can be easily seen on the SysKonnect cards using jumbo frames. The throughput curve also improves considerably by increasing the Eager/Rendezvous threshold.

Research Organization:
Ames Lab., Ames, IA (United States)
Sponsoring Organization:
USDOE Office of Science (SC)
DOE Contract Number:
W-7405-ENG-82
OSTI ID:
803737
Report Number(s):
IS--T 2206
Country of Publication:
United States
Language:
English

Similar Records

Installation guide to mpich, a portable implementation of MPI
Technical Report · Mon Jul 01 00:00:00 EDT 1996 · OSTI ID:378911

Implementation of MP_Lite for the VI Architecture
Thesis/Dissertation · Sun Dec 31 23:00:00 EST 2000 · OSTI ID:803356

Users guide for mpich, a portable implementation of MPI
Technical Report · Mon Jul 01 00:00:00 EDT 1996 · OSTI ID:378910