Intel® VTune™ Amplifier
Use this configuration to specify an application (a binary or a script) to analyze with the Intel® VTune™ Amplifier on the remote Linux* system via SSH connection.
To access the configuration, open the Analysis Target window, choose the remote Linux (SSH) target system on the left, select the Launch Application target type from the drop-down menu on the right, and in the via SSH field specify the username, hostname, and port (if required) for your remote Linux machine as username@hostname[:port].
Make sure to prepare your target Linux system for analysis:
Set up a password-less SSH access to the target using RSA keys.
Build the drivers on the host (if required), copy them to the target system and install the drivers.
To build the sampling driver as RPM using build services as Open Build Service (OBS), use the sepdk.spec file located at <install_dir>/sepdk/src the directory.
Install the VTune Amplifier target package with data collectors on the target Linux system.
If you choose to install the target package to a non-default location, make sure to specify the correct path either with the VTune Amplifier installation directory on the remote system option in the Analysis Target tab (GUI) or with the -target-install-dir option (CLI).
|
Use This |
To Do This |
|---|---|
|
Application field |
Specify a full path to the application to analyze, which can be a binary file or script. |
|
Application parameters field |
Specify input parameters for your application. Click the Modify button to choose a file or a folder as an input. |
|
Managed code profiling mode menu |
Select a profiling mode for managed code. Managed mode attributes data to managed source and only collects managed portion. Native mode collects everything but does not attribute data to managed source. Mixed mode collects everything and attributes data to managed source where appropriate. |
|
Automatically resume collection after (sec) |
Specify the time that should elapse before the data collection is resumed. When this options is used, the collection starts in the paused mode automatically. |
|
Automatically stop collection after (sec) |
Set the duration of data collection in seconds starting from the target run. This is useful if you want to exclude some post-processing activities from the analysis results. |
Use the Advanced section to provide more details on your target configuration.
|
Use This |
To Do This |
|---|---|
|
VTune Amplifier installation directory on the remote system |
Specify a path to VTune Amplifier on the remote system. If the default location is used, this path is automatically supplied. |
|
Temporary directory on the remote system |
Specify a path to the /tmp directory on the remote system where performance results are temporarily stored. |
|
Analyze child processes check box |
Collect data on processes launched by the target process. Use this option when profiling an application with the script. |
|
Modify button |
Click the Modify button to open the Per-process Configuration dialog box and specify child processes to analyze. For example, if your target application calls shell or makes processes, you can choose to exclude them from analysis and focus only on the processes you develop. This option is not applicable to hardware event-based analysis types. |
|
Duration time estimate menu |
Estimate the application duration time. This value affects the size of collected data. For long running targets, sampling interval is increased to reduce the result size. For hardware event-based sampling analysis types, the VTune Amplifier uses this estimate to apply a multiplier to the configured sample after value. |
|
Allow multiple runs check box |
Enable multiple runs to achieve more precise results for hardware event-based collections. When disabled, the collector multiplexes events running a single collection, which lowers result precision. |
|
Analyze system-wide check box |
Enable analyzing all processes running on the system. When disabled, only the target process is analyzed. This option is applicable to hardware event-based sampling analysis types only. |
|
Collection data limit, MB spin box |
Limit the amount of the raw data to be collected. Use this option to start analyzing the beginning of the target execution when the amount of collected data is very large and takes long to process. Outcome: VTune Amplifier suspends data collection when the specified limit is reached.
NoteThe size of data stored in the result directory may not exactly match the specified limit due to the following reasons:
|
|
Slow frames threshold, frames/s |
Specify a threshold to separate Slow and Good frames. Frame rates lower than this threshold are marked as Slow. This threshold needs to be smaller than the Fast frames threshold. |
|
Fast frames threshold, frames/s |
Specify a threshold to separate Good and Fast frames. Frame rates higher than this threshold are marked as Fast. This threshold needs to be larger than the Slow frames threshold. |
|
CPU mask |
Specify CPU(s) to collect data on (for example: 2-8,10,12-14). This option is applicable to hardware event-based analysis types only. |
|
Custom collector |
Provide a command line for launching an external collection tool, if any. You can later import the custom collection data (time intervals and counters) in a CSV format to a VTune Amplifier result. Click the Modify button to add a path to your external collector. |
|
Analyze KVM guest OS check box |
Enable KVM guest system profiling. For proper kernel symbol resolution, make sure to specify:
|
|
Trace MPI check box |
Configure collectors to trace MPI code and determine MPI rank IDs in case of a non-Intel MPI library implementation. |
|
Result location options |
Select where you want to store your result file. By default, the result is stored in the project directory. |