Intel® Trace Analyzer and Collector

Running with Valgrind*

For distributed memory checking (LOCAL:MEMORY:INITIALIZATION) and detecting accesses to memory that is owned by MPI and thus should not be touched by the application (LOCAL:MEMORY:ILLEGAL_ACCESS) it is necessary to run all MPI processes under control of the Valgrind* memory checker (Linux* OS only).

Find Dialog Box

Use the Find dialog box to search for a process or a function.

Open this dialog box through the context menu of the Function Profile and in the context menus of the Function Aggregation and the Process Aggregation dialog boxes.

Filtering

If an event is suppressed by filtering then the effect is as if it were never written to the trace file. This is relatively easy to understand for messages and collective operations.

Caching

Level of Detail

Tracing all available events over time can generate billions of events even for a moderate program runtime of a few minutes and a handful of CPUs. The sheer amount of data is a challenge for any analysis tool that has to cope with this data. This is even worse as in most cases the analysis tool cannot make use of the same system resources as the parallel computer on which the trace was generated.

Windows Menu

Use the menu options in the Windows menu to arrange the open sub-windows as desired. The Windows sub-menu also shows the name and path of the trace file that is presently opened.

Intel® Trace Analyzer

Charts

Charts in Intel® Trace Analyzer are graphical or alphanumerical diagrams that are parameterized with a time interval, a process grouping, a function grouping (see Aggregation) and an optional filter. Together they define the structure in which data is presented and the amount of data to be displayed.

The Charts supported by Intel Trace Analyzer are divided into:

Suscribirse a Intel® Trace Analyzer and Collector