VTune: Difference between revisions

Revision as of 16:04, 4 June 2021

Intel® VTune™ Profiler is a performance analysis tool for serial and multithreaded applications. Use VTune Profiler:

to determine the most time-consuming (hot) functions in your application
to discover on very fine-grained level which section of code (loop, source code line or even data field) do not effectively utilize available processor time
to analyse communication behavior that affects threaded performance
for accurate analysis with low overhead
for serial and multithreaded applications
- MPI (MPT, OpenMPI)
- OpenMP, Intel® oneAPI Threading Building Blocks, native threads
Languages:
- C/C++/C#, Fortran, Python and others

(Formerly Intel® VTune™ Performance Analyzer with Intel® Thread Profiler)


Developer:	Intel
Platforms:
Category:	Performance Analyzer
License:	Commercial
Website:	Intel® VTune™ Amplifier XE homepage

Load the necessary module. For example:

module load compiler/intel 
module load performance/vtune # set up VTune environment
module load mpi/impi          # if MPI needed

Compilation example:

ifort -g -O2 prog.f90

Analyzing MPI applications:

 mpirun –n4 amplxe-cl -c hotspots –r my_result -- path_to_my_app

Load the necessary module. For example:

module swap PrgEnv-cray PrgEnv-intel # set up MPI environment too 
module load performance/vtune        # set up VTune environment

Compilation example:

ftn -dynamic -g -O2 prog.f90

Analyzing MPI applications:

 aprun –n4 amplxe-cl -c hotspots –r myResult-@@@{at} -- path_to_my_app

@@ Line 1: / Line 1: @@
 {{Infobox software
-| description = Intel® '''VTune™ Amplifier XE''' is Intel's newest performance profiling tool and builds on the success of Intel® VTune™ Performance Analyzer. It includes all the capabilities of Intel® Parallel Amplifier plus a number of advanced capabilities for developers who need even greater performance optimization.
+| description = Intel® '''VTune™ Profiler ''' is a performance analysis tool for serial and multithreaded applications. Use VTune Profiler:
+* to determine the most time-consuming (hot) functions in your application
+* to discover on very fine-grained level which section of code (loop, source code line or even data field) do not effectively utilize available processor time
+* to analyse communication behavior that affects threaded performance
+* for accurate analysis with low overhead
+* for serial and multithreaded applications
+**	MPI (MPT, OpenMPI)
+**	OpenMP, Intel® oneAPI Threading Building Blocks, native threads
+*	Languages:
+**	C/C++/C#, Fortran, Python and others
 (Formerly Intel® VTune™ Performance Analyzer with Intel® Thread Profiler)
 | logo = [[Image:intel-logo.png]]