Intel® VTune™ Amplifier provides a mechanism to analyze code parallelism and power consumption using the hardware event-based sampling with the stack collection enabled. As soon as you created a VTune Amplifier project and specified your analysis target, follow these steps to enable the collection and analyze the data:
Before running an analysis with the Intel® VTune™ Amplifier, you have to create a project, which is a container for an analysis target and analysis type configuration and data collection results.
Use this configuration to specify an analysis target activated from the host system and running on the Intel Xeon Phi coprocessor, for example: an offload application, OpenCL™ program, MPI rank, script, and so on. This target type is available for the Intel® VTune™ Amplifier XE only.
Performance analysis on Android* systems is supported by the Intel® VTune™ Amplifier for Systems, part of the Intel® System Studio.
For accurate module resolution and source analysis of your Android* application, make sure to specify search paths for binary and source files when configuring performance analysis:
If required, edit a list of hardware events monitored by the Intel® VTune™ Amplifier for your processor by modifying an existing or creating a new hardware event-based sampling analysis configuration.