Escali 4.4 manual SMC network devices

Page 24

Section: 2.2 SMC network devices

Figure 2-1:illustrates how applications started with mpimon have their communication system established by a system of daemons on the nodes. This process uses TCP/IP communication over the networking Ethernet, whereas optional high performance interconnects are used for communication between processes.

Parameter control is performed by mpimon to check as many of the specified options and parameters as possible. The user program names are checked for validity, and the nodes are contacted (using sockets) to ensure they are responding and that mpid is running.

Via mpid mpimon establishes contact with the nodes and transfers basic information to enable mpid to start the submonitor mpisubmon on each node. Each submonitor establishes a connection to mpimon for exchange of control information between each mpisubmon and mpimon to enable mpisubmon to start the specified userprograms (MPI-processes).

As mpisubmon starts all the MPI-processes to be executed they MPI_Init(). Once inside here the user processes wait for all the mpisubmons inovolved to coordinate via mpimon. Once all processes are ready mpimon will return a “start running” message to the processes. They will then return from MPI_Init() and start executing the user code.

Stopping MPI application programs is requested by the user processes as they enter the MPI_Finalize() call. The local mpisubmon will signal mpimon and wait for mpimon to return a “all stopped message”. This comes when all processes are waiting in MPI_Finalize(). As the user processes return from the MPI_Finalize() they release their resources and terminates. Then the local mpisubmon terminates and eventuall mpimon terinates.

2.2 SMC network devices

Figure 2-2:Scali MPI Connect relies on DAT to interface to a number of interconnects

Beginning with SSP 4.0.0 and SMC 4.0.0 the Scali MPI offers generic support for interconnects. This does not yet mean that every interconnect is supported out of the box, since SMC still requires a driver for each interconnect. But from SMC's point of view, a driver is just a

Scali MPI Connect Release 4.4 Users Guide

12

Image 24
Contents Scali MPI ConnectTM Users Guide Acknowledgement Copyright 1999-2005 Scali AS. All rights reservedScali Bronze Software Certificate Maintenance II Software License Terms CommencementGrant of License Support License ManagerSub-license and distribution Export RequirementsSCALI’s Obligations LICENSEE’s ObligationsTitle to Intellectual Property Rights TransferWarranty of Title and Substantial Performance Compliance with LicensesLimitation on Remedies and Liabilities Scali MPI Connect Release 4.4 Users Guide ViiProprietary Information MiscellaneousGoverning Law Scali MPI Connect Release 4.4 Users Guide Table of contents Profiling with Scali MPI Connect Appendix a Example MPI code Scali MPI Connect Release 4.4 Users Guide Chapter Scali MPI Connect product contextScali mailing lists SMC FAQ SMC release documents Problem reportsSupport Platforms supportedHow to read this guide Acronyms and abbreviationsLicensing FeedbackNIC Terms and conventions Typographic conventionsGUI style font Typographic conventions Description of Scali MPI Connect Scali MPI Connect componentsSMC network devices Direct Access Transport DAT Network devicesShared Memory Device Ethernet DevicesUsing detctl Using detstat3.2 DET Myrinet Infiniband4.1 GM 5.1 IBCommunication protocols on DAT-devices 6 SCIChannel buffer Inlining protocol Eagerbuffering protocolTransporter protocol MPI-2 Features Support for other interconnectsZerocopy protocol Scali MPI Connect Release 4.4 Users Guide MPI-2 Features Setting up a Scali MPI Connect environment Compiling and linkingScali MPI Connect environment variables RunningCompiler support Linker flagsRunning Scali MPI Connect programs Naming conventionsMpimon monitor program Basic usageIdentity of parallel processes Controlling options to mpimon Standard inputStandard output Program specHow to provide options to mpimon Network optionsMpirun wrapper script Mpirun usageRunning with tcp error detection Tfdr Suspending and resuming jobsRunning with dynamic interconnect failover capabilities Part partDebugging and profiling Debugging with a sequential debuggerUsing built-in segment protect violation handler Built-in-tools for debuggingAssistance for external profiling Debugging with Etnus TotalviewControlling communication resources Communication resources on DAT-devicesChannelinlinethreshold size to set threshold for inlining Using MPIIsend, MPIIrecv Using MPIBsendGood programming practice with SMC Matching MPIRecv with MPIProbeError and warning messages User interface errors and warningsFatal errors Unsafe MPI programsMpimon options Giving numeric values to mpimon PrefixPostfix Scali MPI Connect Release 4.4 Users Guide Profiling with Scali MPI Connect ExampleUsing Scali MPI Connect built-in trace TracingAbsRank MPIcallcommNamerankcall-dependant-parameters where +relSecs S eTime whereFeatures ExampleUsing Scali MPI Connect built-in timing TimingMPIcallDcallsDtimeDfreq TcallsTtimeTfreq Using the scanalyze Commrank recv from fromworldFromcommonFieldsCommrank send to toworldTocommonFields where Count!avrLen!zroLen!inline!eager!transporter! whereFor timing Using SMCs built-in CPU-usage functionality This produces the following reportScali MPI Connect Release 4.4 Users Guide Tuning communication resources Automatic buffer managementHow to optimize MPI performance BenchmarkingCaching the application program on the nodes First iteration is very slowCollective operations Memory consumption increase after warm-upFinding the best algorithm Appendix a Programs in the ScaMPItst packageImage contrast enhancement Scali MPI Connect Release 4.4 Users Guide File format OriginalWhen things do not work troubleshooting Why does not my program start to run?Appendix B Why can I not start mpid? Why does my program terminate abnormally?General problems Per node installation of Scali MPI Connect Appendix CInstall Scali MPI Connect for TCP/IP Install Scali MPI Connect for Direct EthernetInstall Scali MPI Connect for Myrinet ExampleInstall Scali MPI Connect for Infiniband Install Scali MPI Connect for SCIInstall and configure SCI management software License optionsUninstalling SMC Troubleshooting Network providersScali kernel drivers Troubleshooting 3rdparty DAT providers Troubleshooting the GM providerScali MPI Connect Release 4.4 Users Guide Appendix D Bracket expansion and grouping Bracket expansionGrouping Scali MPI Connect Release 4.4 Users Guide Appendix E Related documentationScali MPI Connect Release 4.4 Users Guide List of figures Scali MPI Connect Release 4.4 Users Guide Index Transporter protocolSSP