Outside any module

[Rafał]

Hi,

I have a problem with correctly grouping data into modules during process profiling. I use the command:

vtune -collect uarch-exploration -result-dir 'my-dir' -target-process my-process.exe  

I receive profiling data where most of the data is assigned to [Outside any module]. I use Process/Module/Function grouping.

The profiler collects data correctly as the results are similar to previous test runs. The problem has been occurring for 2 days.

I conducted a test on another process using these modules, and in this run, the data is grouped correctly. I updated vtune, reviewed other posts, and couldn’t find an answer to the problem. The test was performed on a Windows 11 platform, CPU Intel® microarchitecture code named Alderlake-S. I also used older modules for my test to rule out that their update is causing the problem.

Can I ask for help in finding the cause of the lack of data division between application modules?

Thank you

[yuzhang3_intel]

Did you try the VTune 2024.2.1 release? Is the same issue also observed on this release?

[Rafał]

I updated vtune to version 2024.2.1 (build 628577). Now I have another problem:

vtune-self-checker.bat
Intel(R) VTune(TM) Profiler Self Check Utility
Copyright (C) 2009 Intel Corporation. All rights reserved.
Build Number: 628577

HW event-based analysis (counting mode)
Example of analysis types: Performance Snapshot
    Collection: Fail
vtune: Error: VTune cannot detect local machine configuration.
vtune: Error: VTune cannot detect local machine configuration.

Instrumentation based analysis check
Example of analysis types: Hotspots and Threading with user-mode sampling
    Collection: Fail
vtune: Error: VTune cannot detect local machine configuration.
vtune: Error: VTune cannot detect local machine configuration.

HW event-based analysis check
Example of analysis types: Hotspots with HW event-based sampling, HPC Performance Characterization, etc.
    Collection: Fail
vtune: Error: VTune cannot detect local machine configuration.
vtune: Error: VTune cannot detect local machine configuration.

HW event-based analysis check
Example of analysis types: Microarchitecture Exploration
    Collection: Fail
vtune: Error: VTune cannot detect local machine configuration.
vtune: Error: VTune cannot detect local machine configuration.

HW event-based analysis with uncore events
Example of analysis types: Memory Access
    Collection: Fail
vtune: Error: VTune cannot detect local machine configuration.
vtune: Error: VTune cannot detect local machine configuration.

HW event-based analysis with stacks
Example of analysis types: Hotspots with HW event-based sampling and call stacks
    Collection: Fail
vtune: Error: VTune cannot detect local machine configuration.
vtune: Error: VTune cannot detect local machine configuration.

HW event-based analysis with context switches
Example of analysis types: Threading with HW event-based sampling
    Collection: Fail
vtune: Error: VTune cannot detect local machine configuration.
vtune: Error: VTune cannot detect local machine configuration.

Checking DPC++ application as prerequisite for GPU analyses: Fail
Unable to run DPC++ application on GPU connected to this system. If you are using an Intel GPU and want to verify profiling support for DPC++ applications, check these requirements:
* Install Intel(R) GPU driver.
* Install Intel(R) Level Zero GPU runtime.
* Install Intel(R) oneAPI DPC++ Runtime and set the environment.

The check observed a product failure on your system.
Review errors in the output above to fix a problem or contact Intel technical support.

The following analyses have failed on the system:
* Performance Snapshot
* Hotspots and Threading with user-mode sampling
* Hotspots with HW event-based sampling, HPC Performance Characterization, etc.
* Microarchitecture Exploration
* Memory Access
* Hotspots with HW event-based sampling and call stacks
* Threading with HW event-based sampling
* GPU Compute/Media Hotspots (characterization mode)
* GPU Compute/Media Hotspots (source analysis mode)

sep -version
Sampling Enabling Product Version: 5.48 Beta built on Jul 29 2024 12:31:32
SEP Driver Version: 5.48 Beta (public)
PAX Driver Version: 1.0
Platform type: 145
CPU name: Intel(R) microarchitecture code named Alderlake-S
PMU: alderlake
Driver configs: Maskable Interrupt, OFFCORE OFF (by OS security), REGISTER CHECK ON
Virtualization platform: Host VM on Hyper-V with VBS enabled
Copyright(C) 2007 Intel Corporation. All rights reserved.



amplxe-sepreg.exe -i
Warning, socperf3 driver is already installed and will be re-used... skipping
Installing and starting sepdrv5...
OK
Installing and starting sepdal...
OK
Installing and starting vtss...
OK

[yuzhang3_intel]

It looks like there is an environmental issue. A similar issue was discussed and resolved in the forum before. You can refer to the following post.

https://community.intel.com/t5/Analyzers/VTune-cannot-detect-local-machine-configuration/m-p/1625731#M25198

[Rafał]

I reviewed the thread before starting my own. Compared to that thread, a few things don’t match up:

• Windows Defender is permanently disabled, and I use a different antivirus.
• I have a 12th generation processor, not a 9th, but I updated the drivers as suggested.
• I also ran the commands mentioned in the thread.
• Finally, I reinstalled version 2024.0 because that version works.

The problem is still the incorrect grouping of data into modules. While running the commands mentioned in the thread, I found that VTSS isn’t working. Could this be causing the issue?

PS C:\Program Files (x86)\Intel\oneAPI\vtune\2024.0\bin64>  amplxe-sepreg.exe -i
Warning, socperf3 driver is already installed and will be re-used... skipping
Installing and starting sepdrv5...
OK
Installing and starting sepdal...
OK
Installing and starting vtss...
FAILED
Reason: Unsupported Windows version; error code: 50
PS C:\Program Files (x86)\Intel\oneAPI\vtune\2024.0\bin64> amplxe-sepreg.exe -s
Checking sepdrv5 driver path...OK
Checking sepdrv5 service...
Driver status: the sepdrv5 service is running
Checking sepdal driver path...OK
Checking sepdal service...
Driver status: the sepdal service is running
Checking socperf3 driver path...OK
Checking socperf3 service...
Driver status: the socperf3 service is running
Checking vtss driver path...OK
Checking vtss service...FAILED

[yuzhang3_intel]

Did you install the 2024.2.1 release?  and your Windows version is 23H2?

[Rafał]

Yes, I had version 2024.2.1 of the system installed (10.0.22631 Build 22631), but I reverted to version 2024.0.0 because it works correctly for me, but it doesn’t group data.

[yuzhang3_intel]

Please check if your VTune driver is ready?  Using one simple example to verify if the same issue is observed first. Thanks.

[Rafał]

Everything seems to be fine with the drivers.

PS C:\Program Files (x86)\Intel\oneAPI\vtune\2024.0\bin64> .\vtune-self-checker.bat
Intel(R) VTune(TM) Profiler Self Check Utility
Copyright (C) 2009 Intel Corporation. All rights reserved.
Build Number: 626834

HW event-based analysis (counting mode) (Intel driver)
Example of analysis types: Performance Snapshot
    Collection: Ok
vtune: Warning: You are going to run an analysis via Remote Desktop. For successful data collection in this mode, make sure your application can run properly via Remote Desktop. If the application fails to run, consider using VNC, local host collection, or any other reliable solution.
    Finalization: Ok...
vtune: Warning: You are going to run an analysis via Remote Desktop. For successful data collection in this mode, make sure your application can run properly via Remote Desktop. If the application fails to run, consider using VNC, local host collection, or any other reliable solution.

    Report: Ok

Instrumentation based analysis check
Example of analysis types: Hotspots and Threading with user-mode sampling
    Collection: Ok
    Finalization: Ok...
    Report: Ok

HW event-based analysis check (Intel driver)
Example of analysis types: Hotspots with HW event-based sampling, HPC Performance Characterization, etc.
    Collection: Ok
    Finalization: Ok...
    Report: Ok

HW event-based analysis check (Intel driver)
Example of analysis types: Microarchitecture Exploration
    Collection: Ok
    Finalization: Ok...
vtune: Warning: The result contains a lot of raw data. Finalization may take a long time to complete.

    Report: Ok

HW event-based analysis with uncore events (Intel driver)
Example of analysis types: Memory Access
    Collection: Ok
    Finalization: Ok...
vtune: Warning: The result contains a lot of raw data. Finalization may take a long time to complete.

    Report: Ok

HW event-based analysis with stacks (Intel driver)
Example of analysis types: Hotspots with HW event-based sampling and call stacks
    Collection: Ok
vtune: Warning: Stack flow analysis on this platform is limited to the hardware LBR-based stack type that has a depth limitation.
    Finalization: Ok...
vtune: Warning: The result contains a lot of raw data. Finalization may take a long time to complete.

    Report: Ok

HW event-based analysis with context switches (Intel driver)
Example of analysis types: Threading with HW event-based sampling
    Collection: Ok
    Finalization: Ok...
    Report: Ok

Checking DPC++ application as prerequisite for GPU analyses: Fail
Unable to run DPC++ application on GPU connected to this system. If you are using an Intel GPU and want to verify profiling support for DPC++ applications, check these requirements:
* Install Intel(R) GPU driver.
* Install Intel(R) Level Zero GPU runtime.
* Install Intel(R) oneAPI DPC++ Runtime and set the environment.

The system is ready to be used for performance analysis with Intel VTune Profiler.
Review warnings in the output above to find product limitations, if any.

The system is ready for the following analyses:
* Performance Snapshot
* Hotspots and Threading with user-mode sampling
* Hotspots with HW event-based sampling, HPC Performance Characterization, etc.
* Microarchitecture Exploration
* Memory Access
* Hotspots with HW event-based sampling and call stacks
* Threading with HW event-based sampling

The following analyses have failed on the system:
* GPU Compute/Media Hotspots (characterization mode)
* GPU Compute/Media Hotspots (source analysis mode)

 

I don't understand what I should do, can you write more on this: "Using one simple example to verify if the same issue is observed first."

[yuzhang3_intel]

I mean you can profile one matrix sample to see if the issue is observed.

C:\Users\yuzhang3\Downloads>vtune -collect hotspots -- "c:\Users\yuzhang3\OneDrive - Intel Corporation\Documents\VTune\Samples\matrix\matrix.exe"

[Rafał]

It looks like the problems with the anonymous modules were caused by changes to the profiled application. At the moment I can't tell what those changes are, but when I profile an older version of the app I still get correctly grouped data.

[yuzhang3_intel]

Since the application is changed, all symbols/source and binary specified in VTune are matched when you profile it, right?