Intel® Inspector XE

Are these false positives?

I am running Inspector on a C++ application using OpenMP for parallel threading on Linux (Redhat 6).  In the "Locate Deadlocks and Data Races" tool, it reported a few correct data races, mostly on some counters that don't affect the output.  However, it also reported numerous data races under one ID in the Summary section that all appear to be in local stack variables allocated internally by the various threads.  They don't appear to be able to overlap in any way.  Is anyone aware of any issues with false positives similar to this?
 

Some of my Inspector settings were:

Cross stack access

Hi all,

I'm using OpenMP to parallelize a portion of my code, in a way that one subroutine is fine-grained parallelized, and other two subroutines are being called from the main program as a coarse grained parallelization.

Attached is an Intel Inspector screen shot which tells me that I do not have data race, but at least one of my threads access the stack of other thread, i.e., cross stack access.

How it can be resolved ?

Thank you,

Jack. 

Object size Memory Leak

Hi there,

in Intel Inspector the Object size column gives the amount of bytes for, e.g., a memory leak. If a memory leak occurred let's say 10 times (code locations), to what exactly refes the object size? To the total amount of memory leakage from all occurrences or to each of the 10 occurrences?

Thanks for a quick answer

Cheers

Intel Xeon Phi Intel Inspector analisys

Hi. I have problem with analysis my aplication on Intel Xeon Phi. After analisys in result list i havent full information about problem. I use Intel Inspector xe 2015.

First: I compile program on host, with flags: icc -g -O0 -mmic ... -o main.cpp main.out

Second: After compilation I copy program to Intel Xeon Phi: scp ./main.out mic0:/tmp

Third: I create project. As Aplication i type ssh, as Aplication Parameters i type: mic0 '/tmp/matrix.out'

Memory growth: "unknown" results

Hi,

the memory growth analysis would be very useful to find growth-related problems in our software. I have tested it several times now, but the result was always the same: I got 1 memory growth problem found, and this was reported as "Unknown", so it just tells me nothing about the underlying problem(s) (see screenshot).

In which cases does the tool report "unknown"? (Perhaps this helps me finding out what is going wrong...)

What I did:

  • new project

No complaint about use of uninitialized variables in simple Fortran test cases?

Hi

I'm trying to use Inspector on the simple examples in the Polyhedron test suite (http://www.polyhedron.com/wp-content/uploads/2014/04/win32_diagnose_src.zip), but I don't get the error reports I expect.  Am I doing something wrong?

Taking UIN7 as an example, it's compiled from the command line using

ifort uin7.for      /debug:full /Od /libs:dll /threads /dbglibs

Internal error, application exitcode -1

Greetings,

First of all, sorry for double-post, but it seems my post got lost after submitting.

I have application compiled with ICC 14.0 Update 4 (since ICC 15 has bug/internal error).

Both inspector XE 2013 and XE 2015 displays similar results in bot MSVC 2013 IDE and ran as a standalone application.

I have Haswell, Win 8.1 Pro x64, target app x64, 16 GiB RAM.

Here is copy-paste of log saying actually nothing except of "internal error". NB: sensitive informations, particulary full paths were obfuscated by upper-case "XXX" without quotes:

No complaint about use of uninitialized variables in simple Fortran test cases?

Hi

I'm trying to use Inspector on the simple examples in the Polyhedron test suite (http://www.polyhedron.com/wp-content/uploads/2014/04/win32_diagnose_src.zip), but I don't get the error reports I expect.  Am I doing something wrong?

Taking UIN7 as an example, it's compiled from the command line using

ifort uin7.for      /debug:full /Od /libs:dll /threads /dbglibs

MPI

Hi,

I am trying to run:

mpirun -np 2 inspxe-cl --result-dir insp_results -collect mi1 -- myApp

but i get the following error:

Fatal error: Cannot start collection because the Intel Inspector XE 2013 failed to create a result directory. Unknown error

This message comes only once, if I start 3 jobs 2 times, 4 jobs 3 times, etc.

inspector create only one directory insp_results, so without numbers.

What is going wrong?

best regards,

Jaap

Subscribe to Intel® Inspector XE