Intel® Parallel Amplifier

Loop Iteration Time using VTune CLI

Hi, I am running an OpenMP code on the Intel Xeon Phi. I want to profile the code using VTune amplifier on Stampede to find out the number of loop iterations and the number of distinct array accesses for each loop. I couldn't find the related events anywhere. I want to use the command line interface of VTune so that I can use VTune GUI installed in my local system to see the results in GUI. Can you kindly help me with the appropriate command ?

Thanks in advance !!!

Regards
Jagannath

Duration parameter of "collect"

Hello,

I am trying to gather some system-wide hardware counters for my application, X seconds after it has started, over a period of Y seconds. I am using the following command line:

amplxe-cl --collect my_custom_conf -target-duration-type=veryshort -duration 30 -no-auto-finalize -no-summary -data-limit=0 -resume-after=20000

and I expect the collection to start after 20s and last for 30s.

I have two questions:

vtune_amplifier_xe_2013 + how to compile

dear all,

I have vtune_amplifier_xe_2013, I used it one year ago to analyze the CPU time in my program. 

I remember that it produce the files: .dump and .xml

I do not remember anymore how to compile the program to get the previous files.

I do not remember the flags that I have to use in ifort.

Someone could help me, please?

I am not able to find the guide anymore. Now I am trying to look inside the  vtune_amplifier_xe_2013 folder.

Thanks

 

Intel VTune can not collect information & cause core dump

Hello,
we are using Intel VTune 2015 for profiling our application which is  running under operating system:2.6.32-504.1.3.el6.x86_64 Red Hat Enterprise Linux Server release 6.6 (Santiago)
CPU: Intel(R) Xeon(R) E5/E7 v2 processor
Frequency          2800004679
Logical CPU Count  4
----------------------------------------------------------------
I started four ngss.elf which is our product.
# ps -ef|grep ngss
root       400 31483  0 07:34 pts/0    00:00:00 ./ngss.elf --iomn 294921

Collecting call counts - possible with MPI?

Hello.  I am attempting to calculate estimated call counts using the command line instructions on this page: https://software.intel.com/en-us/articles/calculating-estimated-call-cou....  OS is RHEL 6.4 with kernel version 2.6.32-358.6.1.el6.x86_64.

Events for measuring branch mispredictions?

I would like to measure the number of branch mispredictions (not specific to indirect/cond/ret etc). Do I understand the following two event counters correctly:

BACLEARS.ANY

​This will tell me exactly how many branch mispredictions occurred? (Probably the event counter I am really looking for)

 

BR_MISP_RETIRED.ALL_BRANCHES_PS

This will tell me how many instructions were executed/retired from a branch which was later determined to be mispredicted?

 

How to do Basic hotshot profile with intel 2015 + VS 2012 + MPI

Hi,

I just bought the Intel studio 2015 cluster edition windows. I need to do Basic hotshot profile with intel 2015 + VS 2012 + MPI for my cfd code. I am using a workstation with 2 cpu (2x12 cores). Using 1 cpu, I managed to the analysis successfully.

I can run my code in parallel using intel's wmpiexec.exe. I can also run my code thru VS 2012 by:

setting the launch command (Configuration Properties - Debugging - Command) to the full path for mpiexec.smpd.exe (eg C:\Program Files (x86)\MPICH2\bin\mpiexec.exe)

"Cannot start collection because the Intel VTune Amplifier XE 2013 failed to create a result directory" when running with MPI

Hi all,

I get this error:

Cannot start collection because the Intel VTune Amplifier XE 2013 failed to create a result directory. Unknown error.

when I run the following amplxe-cl command:

mpiexec -np 3 ~/local/vtune_amplifier_xe_2013_update7/vtune_amplifier_xe_2013/bin64/amplxe-cl -r mpi003 --collect hotspots -- ~/local/MyBuilds/HDGProject/release/install/bin/MyFESolverDP

Подписаться на Intel® Parallel Amplifier