vtune self-check fails on GPU Compute/Media Hotspots

[Chuyuezh]

Hi,

I'm running vtune on

OS: ubuntu22.04
vtune: 2023.1.0
CPU: Intel i7-12700H
GPU: Intel iris Xe Gen12

When running vtune-self-checker.sh:

root@ubuntu2204:/opt/intel/oneapi/vtune/latest/bin64# ./vtune-self-checker.sh
Intel(R) VTune(TM) Profiler Self Check Utility
Copyright (C) 2009 Intel Corporation. All rights reserved.
Build Number: 625246

HW event-based analysis (counting mode) (Intel driver)
Example of analysis types: Performance Snapshot
    Collection: Ok
    Finalization: Ok...
    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...
vtune: Warning: Cannot locate debugging information for the Linux kernel. Source-level analysis will not be possible. Function-level analysis will be limited to kernel symbol tables. See the Enabling Linux Kernel Analysis topic in the product online help for instructions.

    Report: Ok

HW event-based analysis check (Intel driver)
Example of analysis types: Microarchitecture Exploration
    Collection: Ok
    Finalization: Ok...
vtune: Warning: Cannot locate debugging information for the Linux kernel. Source-level analysis will not be possible. Function-level analysis will be limited to kernel symbol tables. See the Enabling Linux Kernel Analysis topic in the product online help for instructions.

    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.

vtune: Warning: Cannot locate debugging information for the Linux kernel. Source-level analysis will not be possible. Function-level analysis will be limited to kernel symbol tables. See the Enabling Linux Kernel Analysis topic in the product online help for instructions.

    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
    Finalization: Ok...
vtune: Warning: Cannot locate debugging information for the Linux kernel. Source-level analysis will not be possible. Function-level analysis will be limited to kernel symbol tables. See the Enabling Linux Kernel Analysis topic in the product online help for instructions.

    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...
vtune: Warning: Cannot locate debugging information for the Linux kernel. Source-level analysis will not be possible. Function-level analysis will be limited to kernel symbol tables. See the Enabling Linux Kernel Analysis topic in the product online help for instructions.

    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)

Log location: /tmp/vtune-tmp-root/self-checker-2023.06.08_16.19.44/log.txt

Drivers are already loaded properly:

root@ubuntu2204:/opt/intel/oneapi/vtune/latest/sepdk/src# ./insmod-sep -q
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".

socwatch2_15 driver is loaded and owned by group "vtune" with file permissions "660".

vtsspp driver is loaded and owned by group "vtune" with file permissions "660".

When running vtune-gui:

root@ubuntu2204:/opt/intel/oneapi/vtune/latest/bin64# ./vtune-gui
[36953:0608/163730.647467:ERROR:gpu_memory_buffer_support_x11.cc(44)] dri3 extension not supported.
[36925:0608/163731.099072:ERROR:cert_verify_proc_builtin.cc(670)] CertVerifyProcBuiltin for 127.0.0.1 failed:
----- Certificate i=0 (CN=ubuntu2204) -----
ERROR: No matching issuer found

No error message on vtune-gui analysis configuration:

The analyzing process always stuck in finalizing result:

Could you please help me fix this issue? I know there are similar posts. But those solutions cannot solve my issue. Thanks in advance.

[DiyaN_Intel]

Hi,

Thank you for posting in Intel communities.

We were able to reproduce the issue from our end.

In order to access GPU we need to upgrade the kernel version.

In this link ,  please give all the commands one by one to install all the necessary packages and reboot the system.

After upgrading you can check that the kernel version is updated to 5.19.0-41-generic

The next step is to build and install Intel(R) Metrics Discovery Application Programming Interface.

Please follow all the steps mentioned in this link

Then when you can run the self-checker script file to find out that there is no failed analysis as everything is installed properly in the system and then you will be able to open the vtune-gui and do the necessary analysis.

If you face any issues, please get back to us.

If this resolves your issue, make sure to accept this as a solution. This would help others with similar issues. Thank you!

Regards,

Diya

[Chuyuezh]

Hi Diya,

Thanks a lot for your solution. I had trouble in upgrading the kernel version, and I'm reinstalling ubuntu. I will get back to you later.

Best,

Chuyue

[Chuyuezh]

Hi Diya,

I have updated the kernel to 5.19.0-41-generic.

But GPU Compute/Media Hotspots still cannot work.

Other than that, ./insmod-sep -q shows that drivers are not loaded after reboot, which might be the problem. Before I install metrics-discovery and reboot, drivers are loaded. Attached please find the log.

[DiyaN_Intel]

Hi,

Good day to you.

We can see from the logs that you are using Vtune 2023.0.0, can you update it to the latest one (2023.1.0).

We can also see from the logs that the drivers are not installed properly, could you please load the drivers and run the self-checker logs once again?

If you face any issues, please get back to us.

If this resolves your issue, make sure to accept this as a solution. This would help others with similar issues. Thank you!

Regards,

Diya

[DiyaN_Intel]

Hi, 

Good day to you.

We have not heard back from you.

Is your issue resolved with the above solution?

If this resolves your issue, make sure to accept this as a solution. 

This would help others with similar issues. Thank you!

Thanks and Regards, 

Diya

[Chuyuezh]

Hi Diya,

I was out of office last week. Sorry for the late reply.

Thanks for your suggestion. I loaded the drivers:

root@ubuntu2204:/opt/intel/oneapi/vtune/2023.0.0/sepdk/src# ./insmod-sep -q
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 loaded and owned by group "vtune" with file permissions "660".

vtsspp driver is loaded and owned by group "vtune" with file permissions "660".

 But  GPU Compute/Media Hotspots is still not working. Please check log0626.txt attached.

I have used the VTune 2023.1.0 version before, and the results were the same as 2023.0.0. So I downgraded afterwards.

Looking forward to your reply. 

Thanks,

Chuyue

[DiyaN_Intel]

Hi, 

Can you please try one more thing and show us the result of what you are getting?

Please give the below command and let us know what output you are getting and share the screenshot. This will help us to debug further.

sycl-ls

Thanks and Regards,

Diya

[Chuyuezh]

Hi,

I run sycl-ls and it shows no GPU device detected. How to get it fixed?

Thanks a lot.

Chuyue

[DiyaN_Intel]

Hi,

Good day to you.

Based on our discussion about creating a priority ticket if needed, I am going ahead and closing this case for now.

Please feel free to contact us further if you need any assistance from our side.

Thanks & Regards,

Diya