It's been 3 days that I'm trying to make hardware event-based sampling work on intel vtune but at this point I cannot really figure out what my problem can be.

I'm running Ubuntu 18.04 on a macbook pro with Intel i7-4870HQ, 2.5Ghz. It's not a virtual machine, it's booted and I'm using rEFInd for selecting the OS at startup. When I run uname -r I get: 5.3.0-51-generic.

I installed vtune as described in the installation page. I also checked the kernel configuration to match for correct hardware event-based sampling and I also set the kptr_restrict to 0.

To open vtune I run sudo ./vtune-gui from /opt/intel/vtune_profiler_2020.1.0.607630/bin64/.

The binary that gets profiled is compiled with gcc and using the -g and -O3 flags.

However when I try running the vtune profiler with hardware event-based sampling I get the warning displayed in the image at the bottom. Before I alsohad the warnings like: cannot locate 'vtssoo.ko', and: cannot locate debugging information for the linux kernel. Now they're gone but I'm not sure if they are solved though.

I think these warnings boil down to the drivers. I run ./insmod-sep -q from /opt/intel/vtune_profiler_2020.1.0.607630/sepdk/src and I get this output:

pax driver is loaded and owned by group "vtune" with file permissions "660".
socperf3 driver is not correctly loaded.
sep5 driver is not correctly loaded.
socwatch driver is loaded.
vtsspp driver is loaded and owned by group "vtune" with file permissions "660".

2 drivers are not loaded correctly. Following the instructions to build the drivers didn't help either and I still get this result.
A colleague of mine has the same setup (same OS  and version) but he's using a lenovo and not macbook pro. In his case after the installation he could already run hardware event-based sampling without warnings and with all the useful information.
I'm starting to think that it might be something with the macbook pro build. What could the problem be? I would really appreciate any help because I really need this feature. Thanks a lot for you effort and time.

Hi all,

I have got a  warning message in vtune profiling.
"amplxe: Warning: Only user space will be profiled due to credentials lack. Consider changing /proc/sys/kernel/perf_event_paranoid file for enabling kernel space profiling."
and current "perf_event_paranoid" is 2.

I would like to use the options including hotspots and hpc-performance in Vtune profiler, Advisor and Tracer.
In the current situation, Are there any methods to use the profiler without changing the "perf_event_paranoid" file?
Because I am not an administrator of whole systems, I can't modify the files.
To ask the administrator, I need solid evidence to modify the file. Is there any document containing the recommended option about "perf_event_paranoid".
Also, In my case, what is the recommended value (0 or 1)?

Thank you in advance.

I have encountered an issue with VTune 2021.1-beta06 on DevCloud where it completes profiling a workload with a specific dataset, but when I try to create reports they are empty. If I run the workload with a different, smaller dataset the reports work fine.

-operating system: Ubuntu 18.04.4 LTS and gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0

Steps to recreate:

1. Download Gromacs: wget http://ftp.gromacs.org/pub/gromacs/gromacs-2020.2.tar.gz

2. Follow the installation steps specified in the following guide (cmake step shown below): http://manual.gromacs.org/2020.2/install-guide/index.html

cmake .. -DGMX_BUILD_OWN_FFTW=ON -DCMAKE_INSTALL_PREFIX= <path to local install dir>   ( e.g. /home/u42144/software/gromacs)

3. Download the dataset then extract: wget https://repository.prace-ri.eu/ueabs/GROMACS/1.2/GROMACS_TestCaseA.tar.gz

4. Run VTune with the workload: vtune -collect hotspots -r v-hotspots -- gmx mdrun -s ion_channel.tpr

5. Create hotspots report: vtune -report hotspots -results-dir v-hotspots

example hotspots report output:

Function  CPU Time  CPU Time:Effective Time  CPU Time:Effective Time:Idle  CPU Time:Effective Time:Poor  CPU Time:Effective Time:Ok  CPU Time:Effective Time:Ideal  CPU Time:Effective Time:Over  CPU Time:Spin Time  CPU Time:Spin Time:Imbalance or Serial Spinning  CPU Time:Spin Time:Lock Contention  CPU Time:Spin Time:Other  CPU Time:Overhead Time  CPU Time:Overhead Time:Creation  CPU Time:Overhead Time:Scheduling  CPU Time:Overhead Time:Reduction  CPU Time:Overhead Time:Atomics  CPU Time:Overhead Time:Other  Module  Function (Full)  Source File  Start Address
--------  --------  -----------------------  ----------------------------  ----------------------------  --------------------------  -----------------------------  ----------------------------  ------------------  -----------------------------------------------  ----------------------------------  ------------------------  ----------------------  -------------------------------  ---------------------------------  --------------------------------  ------------------------------  ----------------------------  ------  ---------------  -----------  -------------
 

Every one of my captures lead to Vtune being stuck during the Finalizing Result phase.

I see the 'data collection is completed successfully' message and the progress bar gets stuck. There's not specific pattern where it gets stuck, it could be while reading the trace file or a on a dll used by the program. I tried to leaving the process running for hours to see if it would eventually finish, no luck.

To get pass this I usually have to kill VTune from the task manager; re-open VTune and load the capture on which it crashed. At which point the resolution just takes a few seconds and I'm able to see navigate my capture normally.

This happens whether I use Vtune as a stand alone or withing Visual Studio (which i stopped doing since this process usually meant my instance of VS would need to be killed as well).

I'm on Windows 10 1809 (17763.1158)

and using Vtune 2020 (build 605129)

I have been plagued with this behavior for a while and on various versions of Vtune. I have to carefully pick a version from which I can apply the workaround described above, for example, I tried 2020 patch 1 and I'm not able to kill the Vtune instance and resume from it, therefore I had to revert to the version I'm currently using.

Any suggestions would be greatly appreciated. 

Hi,

Earlier I was using Intel VTune profiler on a AMD machine. Though I could use  User Based Sampling for my application but as it was AMD machine, therefore HW sampling was not possible. Now I am using an Intel Machine. And I would really like to use all profiling options finally. 

I am using Intel VTune on my Virtual Machine through Virtual Box. Following are my machine details:

- OS:                  Centos 7

-  uname -r :      3.10.0-1127.e17.x86_64

- virt-what:        virtual box kvm 

- model name:     Intel(R) Core(TM) i7-7500U CPU

While installing Intel VTune Profiler 2020 Update 1, I am getting following two message in Prerequisites ( also attached in this thread):

- The system is running in the virtual environment. Sampling drivers will not be installed.

- Kernel source directory is not found. Unable to build the sampling drivers.

I have also executed the below command but I still get these two messages in my Preequisites installation step: 

sudo yum install kernel-devel-3.10.0-1127.e17.x86_64

Having said that, I could proceed with the installation but I don't want to use user mode sampling only. I would like to have all profiling options. And I think until and unless I don't resolve these two messages in preequisites, I won't be able to use all profiling option.

Also, if you can see in the attached file, the prerequiste steps says  "set  up this parameter in Advanced Options -> Driver Build Options dialog". The question also is. where do I find this option?

I would be really grateful if you can please help me resolving these two messages.

Thanks in advance !!

Greetings:

I am running VTune locally on my Apple laptop, attempting to analyze a remote system which runs Linux. However, due to system configuration and administration requirements within my company, I am unable to configure a remote Linux target via SSH for VTune.

Is there a way to determine the command line flags that the VTune GUI would have tried to run via SSH on the remote system? I would like to log into the remote Linux host and run that exact command manually, then download the resulting data on to my local workstation to analyze the results with the VTune GUI.

Ideally, I'd like to ask VTune on the remote host to attach to a specific PID (and all its child processes/threads), extract all the data that the GUI was expecting with my configuration settings, and then copy the resulting data that was collected to my local workstation.

Is this possible? Is there documentation explaining how to do this and how to import the results? It would be amazing if the VTune GUI had a display somewhere that said "Run this command on the remote host if you can't setup an SSH target: [command]"

Thanks!

Hi,

In order to learn how Vtune works, I am trying to analyze assembly commands’ running time of the pre-build "matrix.exe". I have several problems:

• By performing memory access analysis I receive running times of matrix.exe’s functions but cannot see some of the function’s name (e.g some of the matrix.exe functions appear as func@0X1400345 while other functions appear with their actual name “init”, “multipy”, etc..)
• By performing hotspots analysis, the output indeed contains all the functions names. However, now all the running times are ‘0’ or “unknown”

I would like to know what I am doing wrong and how to fix it.

Another question - I want to demonstrate Vtune's capabilities to my colleagues and having problem to analyze my original C++ exe files. I would like to know where I can find existing files just like "matrix.exe" that by performing the analysis on them I will probably receive reasonable and informative results.

Thanks!

Steps to reproduce - 

compile the following program:

#include <iostream>

int main() {
    std::cout << "Hello World"<< std::endl;
    return 0;
}

with

clang++-9 hello_world.cpp --stdlib=libc++  -g -O2 -o hello_world.exe

Attempting to profile with VTune results in the following error

Source/pin/elfio/img_elf.cpp: ProcessSectionHeaders: 809: unknown section type 0x6fff4c04 for sec[124,.deplibs] in /usr/lib/x86_64-linux-gnu    /libc++.so.1

# Product Version

Intel VTune Profile 2020 Update 1

Product Build 607630

# System info:

Collection and Platform Info
    Application Command Line:    /home/andrew/projects/fuel3d/work/hello_world.exe 
    Operating System:    5.3.0-53-generic NAME="Ubuntu"

VERSION="18.04.4 LTS (Bionic Beaver)"
ID=ubuntu
ID_LIKE=debian
PRETTY_NAME="Ubuntu 18.04.4 LTS"
VERSION_ID="18.04"

    CPU
        Name:    Intel(R) microarchitecture code named Coffeelake
        Frequency:    3.6 GHz 
        Logical CPU Count:    16
 

I have vTune 2020 update 1 and I'm having problems trying to do a hotspot trace. I can't open a case. When I login and click the dashboard access the "My Support" it wants you to select the product and I searched through all the links and can't find vTune. Also searched for vtune on the support page and there's nothing.

Hi,

I have installed VTune Profiler recently to profile an OpenCL project on VS2019. I need some help with how can I profile my code with VTune. 

I could not find anything helpful yet. If I can get some document that discusses the step-by-step procedure starting from the welcome page, it would be very helpful for a newbie like me.

Thanks,

Gaurav.

Hi,

I have been able to build the sampling drivers and signed them for use with secure boot. However, `insmod-q` returns the following:

pax driver is loaded and owned by group "vtune" with file permissions "660".
socperf3 driver is loaded and owned by group "vtune" with file permissions "660".
sep5 driver is loaded and owned by group "vtune" with file permissions "660".
socwatch driver is not loaded.
vtsspp driver is not loaded.

No further information is provided. How do I load the socwatch and vtsspp drivers? I am unable to get callstack information without loading these drivers.

Regards,

Andrew.

Hi,

I ran the latest version of Platform Profiler and uploaded the result file to the platform profiler webpage (localhost:6543).

In Memory view, I can see the 'DRAM Write Queue Latency' graph in 'Socket 0 - Latency'.

The graph shows the DRAM write queue latency over the elapsed time, but the data is too coarse to check the tail latency. I think the sampling rate of measurement is too low.

So, how can I check the all latency information about memory accesses? Is there any way to measure it using Vtune Profiler or Platform Profiler or other tools?

Especially, I am interested in write tail latency of Optane DCPMM. I found the 'Persistent Memory Write Queue Latency' graph in the result of Platform Profiler, but the Platform Profiler only shows me the sampled data. I want all data measured by hardware performance counters.

This picture is an example graph showed by platform profiler. But the sampling rate of the graph is too low.

Best regards,

Minjae Kim

I am running vtune 2020.1 with `vtune -R top-down -column="CPU Time:Self","Module" -report-out result.csv -format csv -csv-delimiter comma -q -r /path/to/r001hs` and noticed I couldn't read the resulting csv file with https://github.com/brendangregg/FlameGraph. Upon inspection of the csv file, I noticed the first lines are:

war:Column filter is ON.
Function Stack,CPU Time:Self,Module
Total,0.0,[Unknown]
 clone,0.0,libc.so.6
  start_thread,0.0,libpthread.so.0
   func@0xbd6d0,0.0,libstdc++.so.6
 

...

What I don't expect to find in a csv file is that first line `war: Column filter is ON.`. Removing that line, I can process the csv file successfully.

Should that warning really be in the csv file instead of being printed to stderr? Also, is this new behaviour (I was under the impression I was using vtune -r as per the instructions in FlameGraph and that FlameGraph was meant to handle vtune output). Sorry that this thread doesn't touch vtune exclusively but is on the interoperability with external software.

Hi,

I just switched to using vtune after some experience with advisor. Advisor has a snapshot feature that packs all sources and binaries together with results into an *.advixeexpz file. This is convenient when editing, recompiling, and rerunning code because one is still able to look at old benchmarks as reference and navigate through the old source and assembly. And one can copy these files conveniently from a server where a profile is created to a local computer to investigate the results. I didn't see a similar feature in the VTune documentation but might have missed it.

Is there a similar snapshot feature in VTune?

Thanks,

Paul

Hey all,

i use the Amplifier on a daily basis in a software company with a hugh code base.
I am talking about real world problems here, not the 10 class project.
So the number of dlls is quite high and the depth of the callstacks is also in the hundreds.

In the 2015 Amplifier version the TopDownView would expand to the selected DLLs or function selected in the BottomUp view.
Also you could do a expand all in the TopDownView.

This functionality seems to have been removed in the newer versions or am i just not finding them?

Expanding the TopDownView is 200 clicks minimum now, depending on the path and using arrow keys.
So developers which dont use it on a daily basis might be ok with this but for my team it is unbearable.

So while the rest of the company uses the newer 2019 version we still use the 2015 version.
Is there any chance of these features coming back?
I would also like to have more features like this, e.g. it would be great if i could let the TopDownView expand automatically until 10% or a 1sec or some value i set.

Also is it possible to run the Amplifier 2015 with newer licences ?
Because the company is discussing how many and what new licences to buy and i dont want to be screwed.

Thanks for any reply, maybe there is a soltion to this which i have not found yet...

Been playing with seeing what I can do with dpc++/GPU and VTune.  I've installed (ubuntu 18.04.4) OneAPI beta6 and that looks to give me VTune 2021.1-beta06. My question is that I don't seem to be seeing the features shown in the cookbook at https://software.intel.com/content/www/us/en/develop/documentation/vtune... (which says it's version 2020?).  I think I've got everything setup but I only get "GPU Utilization" and "GPU Frequency" menu items.  (Sorry I don't know how to include an image.)  I have not yet bitten the bullet to recompile the i915 driver nor rebuild a new linux kernel and am hoping that's not necessary.

So do I need to build a kernel to be able to get the extra GPU stuff?  Should I be using something other than the OneAPI beta6 version of VTune?

The performance counters mem_load_l3_miss_retired.remote_dram and mem_load_l3_miss_retired.local_dram giving wrong numbers when the processes are making accesses to shared memory. 

Hi,

Earlier I have used Intel VTune profiler on a server which had graphical interface. Now I am using a bare metal server with no Graphical Interface (no GUI). I would like to download the tar file of Intel VTune profiler. I am struggling with the exact command to download the tar file. I have tried following:

wget http://registrationcenter-download.intel.com/vtune_profiler_2020_update1...

But it does not work....

Can someone please help me with it. I am using Ubuntu

Hi,

I have a question. I am using a Ubuntu server with no graphical desktop environment. I would like to install Intel VTune Profiler on it. Can I use GUI of Intel VTune Profiler on a server with no graphical desktop environment?

Thanks

BR
Bobby

I am trying to use vtune to profile a Fortran console app using Intel Parallel Studio XE 2019.  Apparently hotspot analysis (only memory) is supported from the API Gui.  In trying to use the vtune profiler directly it will not run my app because it can't find associated DLLs becuase the compiler update environment is not established.  I can open a compiler environment window and run my app using amplex-cl to gather the data - but how do I establish the enviroment when invoked from the Intel Vtune AMplifier GUI?