ANNOUNCEMENT:

   MPICL, a port of the PICL tracing logic to MPI, is now
available from http://www.epm.ornl.gov/picl . Using MPICL, MPI
programs written in C or Fortran can produce profile data or
ParaGraph-readable detailed trace data on communication and
user-defined events.

   MPICL uses the MPI profiling interface to intercept calls to MPI 
routines, sample the system clock, save event-specific information, 
and then call the underlying MPI routine. To enable this data
collection requires the addition of three subroutine calls to
the source code. To instrument user-defined events or to control more 
precisely what data is collected requires additional modifications.
If the MPI_PCONTROL interface is used to call the MPICL commands, 
the MPICL commands will be treated as "no-ops" when the
instrumentation library is not linked in. Thus a single version of the
source code can be used for both performance evaluation and production.

   MPICL is an extension to the Portable Instrumented Communication
Library (PICL), a software package that provided a portable
message-passing interface in the days before the MPI standard. This
release also represents an update to the PICL library.
While an MPI user need know nothing about PICL message-passing, this
does mean that MPICL can be used to collect performance data for
non-MPI programs. But information on communication events is collected
only if MPI or PICL message-passing commands are used, or if the user
instruments the message-passing layer using MPICL instrumentation
commands.

DISCLAIMER:

   MPICL was developed by P. H. Worley at Oak Ridge National
Laboratory and has been used by the author for a variety of
performance evaluation studies since its initial incarnation in 1997.
However, MPICL IS RESEARCH SOFTWARE WITHOUT ANY GUARANTEE OR WARRANTY
THAT IT IS GOOD FOR ANYTHING OR SAFE TO USE. It is being made
available at this time to coordinate with the release of the new
MPI-aware version of ParaGraph. Please notify and acknowledge the
author in any research or publications utilizing MPICL, or any part of
the code. Suggestions, bug reports, and (especially) new ports are
also appreciated. 

PORTS:

   At the current time, the MPI instrumentation layer has been used
successfully on the HP/Convex Exemplar, IBM SP, Intel Paragon,
SGI/Cray Origin 2000, SGI/Cray T3E, and on a network of workstations
using MPICH and LAM. MPICL is easily ported to any standards-compliant
version of MPI. The machine dependent code primarily deals with the Fortran/C
interface and, optionally, the use of a higher resolution system clock.

   The underlying PICL library works on a much larger set of machines
and communication libraries, many of which are obsolete:

MPL:    IBM SP-1, SP-2

MPI:    IBM SP-2, Intel Paragon, SGI Origin, Cray T3D, Cray T3E,
        network of workstations using MPICH

NX/2:   mpsim hypercube simulator, Intel iPSC/2, iPSC/860, DELTA,
        Paragon/OSF, and Paragon/SUNMOS

VERTEX: nCUBE/2, nCUBE/2S

PVM:    network of workstations, Cray T3D, Cray T3E

Note that the non-MPICL aspects of PICL are not exercised very often,
and some of these implementations may no longer work perfectly.

FOR MORE INFORMATION:

  Contact Pat Worley at worleyph@ornl.gov or (423) 574-3128.