This User and Reference Guide provides you with the description of the features of the Intel® Trace Collector. This information is provided in the two main sections:
void VT_traceoff (void)
Turns off tracing for the thread if it was enabled, does nothing otherwise.
Generally, every View is split into two sections: Timelines and Profiles. Use the Layout menu to organize the Charts.
The Layout choices are available when there are two or more charts open.
The following entries are available in the Layout menu:
In the Comparison mode (see Comparison of two Trace Files), the Filtering dialog has an additional label and a combo box that enables you to apply the chosen filter expression to the other trace file shown in the View.
STF-PROCS-PER-FILE <number of processes>
In addition to or instead of combining trace data per node, the number of processes per file can be limited. This helps to restrict the amount of data that has to be loaded when analyzing a sub-set of the processes.
Intel® Trace Collector can save the trace data in the single-file STF format. This format is selected by specifying the LOGFILE-FORMAT STFSINGLE configuration option, and it causes all the component files of an STF trace to be combined into one file with the extension .single.stf. The logical structure is preserved. The drawback of the single-file STF format is that no I/O parallelism can be exploited when writing the tracefile.
Aggregation reduces the amount of data by aggregating events into thread groups and into function groups.
The following aggregation types are discussed in this topic:
int VT_getthrank (int * thrank)
Gets thread index within a process.
Can be assigned either automatically by Intel® Trace Collector, or manually with VT_registerthread().
In addition to the menu entries and shortcuts, there are two more ways to navigate the time interval in Intel® Trace Analyzer:
Use the scroll bar found below the timelines
Use the mouse to zoom into a time interval
Similar to the keystrokes, these operations manipulate the zoom stack.
Intel® Trace Collector can gather and store statistics about the function calls and their communication. These statistics are gathered even if no trace data is collected, so it is a good starting point for trying to understand an unknown application that might produce an unmanageable trace.
To collect this light-weight statistics for your application, set the following environment variables before tracing: