Intel® Trace-Analyzer und -Collector

Multithreaded Tracing

To trace multithreaded applications, just link and run as described above. Additional threads will be registered automatically as soon as they call Intel® Trace Collector through MPI wrapper functions or the API. Within each process every thread will have a unique number starting with zero for the master thread.

Tracing of Distributed Applications

Processes in non-MPI applications or systems are created and communicate using non-standard and varying methods. The communication may be slow or unsuitable for Intel® Trace Collector communication patterns. Therefore a special version of the Intel® Trace Collector library was developed that neither relies on MPI nor on the application's communication, but rather implements its own communication layer using TCP/IP.

Defining Groups of Processes

Intel® Trace Collector makes it possible to define an arbitrary, recursive group structure over the processes of an MPI application, and Intel® Trace Analyzer is able to display profiling and communication statistics for these groups. Thus, a user can start with the top-level groups and walk down the hierarchy, unfolding interesting groups into ever more detail until he arrives at the level of processes or threads.

Intel® Trace-Analyzer und -Collector abonnieren