Analyzers
Talk to fellow users of Intel Analyzer tools (Intel VTune™ Profiler, Intel Advisor)
4974 Discussions

Request to add my account in video group

vaidya__miheer
2,112 Views

Hi I was trying gpu profiling on devcloud and I am getting incomplete profiler results.

I stumbled across https://www.intel.com/content/www/us/en/develop/documentation/vtune-help/top/installation/set-up-system-for-gpu-analysis.html .

Can you add me to the "video" group so I can do gpu profiling using vtune on devcloud?

Labels (1)
0 Kudos
10 Replies
JaideepK_Intel
Moderator
2,098 Views

Hi,

 

Thank you for posting in Intel Communities.

As you are trying on Devcloud There is no separate video group available in Devcloud. I ran GPU offload analysis on Devcloud and it works fine. Let me share the steps I followed for vector-add sample.

 

Connect to the Devcloud:

 

ssh devcloud

 

Currently you are in login node then connect to compute node :

 

qsub -I -l nodes=1:gpu:ppn=2 -d .

 

or

 

qsub -I -l nodes=1:dual_gpu:ppn=2 -d .

 

 

Download the samples.

 

git clone https://github.com/oneapi-src/oneAPI-samples.git

 

 

Go to the vector-add sample

 

cd oneAPI-samples/DirectProgramming/DPC++/DenseLinearAlgebra/vector-add/src

 

 

In this directory you can find 2 samples with following names: vector-add-buffers.cpp, vector-add-usm.cpp you can select any one of them.

 

Now we need to build an executable file:

 

dpcpp ./vector-add-buffers.cpp -o vector-add-buffer

 

Now an executable is created with name vector-add-buffer, with help of this we can profile on Vtune.

 

GPU offload analysis:

 

vtune -collect gpu-offload ./vector-add-buffer

 

You can find a logs in same directory (eg:r000go)

 

In Devcloud wouldn't be possible to add a specific user to any group as the permissions would remain the same for all users.

 

Thanks,

Jaideep

 

vaidya__miheer
2,080 Views

Hi Jaideep, I am trying to run https://www.intel.com/content/www/us/en/develop/documentation/vtune-help/top/analyze-performance/accelerators-group/gpu-compute-media-hotspots-analysis.html#gpu-compute-media-hotspots-analysis_CODE-LEVEL

I got below command line from vtune:

vtune -collect-with runsa -knob enable-stack-collection=true -knob useEventBasedCounts=true -knob "gpu-profiling-mode=0:0:2.0|instcount" -knob "gpu-counters-mode=0:0:2.0|global-local-accesses" -knob enable-gpu-usage=true -knob collectMemObjects=true -knob analyzeDgfxBandwidth=true  -knob collectPStateData=falsevtune -collect-with runsa -knob enable-stack-collection=true -knob useEventBasedCounts=true -knob "gpu-profiling-mode=0:0:2.0|instcount" -knob "gpu-counters-mode=0:0:2.0|global-local-accesses" -knob enable-gpu-usage=true -knob collectMemObjects=true -knob analyzeDgfxBandwidth=true -knob collectPStateData=false ./gemm-run-gpu.out

I get error:

vtune: Error: Events for detailed GPU utilization analysis cannot be collected due to a lack of credentials. Make sure you have read/write access to debugFS. You may either run the analysis with root privileges (recommended) or follow the configuration instructions provided in the Linux and Android Kernel Analysis help to
pic.

 Maybe it's not possible to do this analysis on devcloud?

0 Kudos
SergeyD_Intel
Employee
1,923 Views

Hello Vaidya,

 

Given message should be considered as "Info", not as "Error".  The point is that option enable-gpu-usage requires access to debugFS.

So, VTune work as designed, however I agree that message should improved.

Is it possible to disable this option?

Maybe I can help to configure analysis for collecting data whish is needed to you?

 

Best regards,

Sergey

vaidya__miheer
1,849 Views

Hello Sergey,

Maybe I can help to configure analysis for collecting data whish is needed to you?

That would be awesome. I am trying to get the values of gpu metrics: https://www.intel.com/content/www/us/en/develop/documentation/vtune-help/top/reference/gpu-metrics-reference.html using vtune when I run my kernel (as I change the design of kernel). In particular I am trying to look at:

1. Local memory accesses (or utilized bandwidth) to verify if the kernel is spilling or not

2. Shared memory accesses and bank conflicts (https://www.intel.com/content/www/us/en/develop/documentation/iocl-opg/top/optimizing-opencl-usage-with-intel-processor-graphics/memory-access-considerations/recommendations/local-memory.html)

3. Dram accesses (or utilized bandwidth)

----

Is it possible to disable this option?

I am not sure which option you are referring here.

----

Thanking you,

+miheer

0 Kudos
SergeyD_Intel
Employee
1,810 Views

For getting GPU Memory and DRAM memory bandwidth, you could run predefined GPU Hotspot analysis:

         vtune -collect gpu-hotspots -knob collect-memory-bandwidth=true

 

The same in GUI:

SergeyD_Intel_0-1638810970549.png

Result:

SergeyD_Intel_1-1638811685034.png

 

But unfortunately, only few hosts could measure SLM traffic.

Could you specify CPU and GPU on your system?

 

By the way, you could use vtune-backend server for remote access with UI

 

___________


Is it possible to disable this option?

I am not sure which option you are referring here.


I mean this option:

vtune -collect-with runsa -knob enable-stack-collection=true -knob useEventBasedCounts=true -knob "gpu-profiling-mode=0:0:2.0|instcount" -knob "gpu-counters-mode=0:0:2.0|global-local-accesses" -knob enable-gpu-usage=true -knob collectMemObjects=true -knob analyzeDgfxBandwidth=true -knob collectPStateData=falsevtune -collect-with runsa -knob enable-stack-collection=true -knob useEventBasedCounts=true -knob "gpu-profiling-mode=0:0:2.0|instcount" -knob "gpu-counters-mode=0:0:2.0|global-local-accesses" -knob enable-gpu-usage=true -knob collectMemObjects=true -knob analyzeDgfxBandwidth=true -knob collectPStateData=false ./gemm-run-gpu.out

 

Best regards,

Sergey

vaidya__miheer
1,770 Views

Hello Sergey,

I am on using Intel(R) Xeon(R) E-2176G looking at gen9 gpus on (s001-n157).

0 Kudos
vaidya__miheer
1,548 Views

Hello Sergey,

I don't see the tab "GPU Compute/Media Hotspots (preview)" in the available options as shown in your screenshot (and I guess because of that I don't see the graph which you have posted in earlier reply). Which vtune version are you using?

 

Intel(R) oneAPI VTune(TM) Profiler 2022.0.0 (build 621730) Command Line Tool (/glob/development-tools/versions/oneapi/2022.1.1/oneapi/vtune/2022.0.0/bin64/vtune).

vaidya__miheer_0-1640214908539.png

 

0 Kudos
SergeyD_Intel
Employee
1,512 Views

Hello!

You use correct version of VTune. GPU Hotspots viewpoint could be hidden in a case, when some of important data were not collected. It could be result of incorrect system configuration, or bug on VTune side.

Could you attach result for proper analysis and log of .../bin64/vtune-self-checker ?

 

Best regards,

Sergey

0 Kudos
JaideepK_Intel
Moderator
2,067 Views

Hi,

 

Thank you for sharing the command. We were able to reproduce the same issue and informed to Development team as well. We are working on this and we will get back to you soon.

 

Thanks,

Jaideep

 

0 Kudos
JaideepK_Intel
Moderator
1,310 Views

Hi,


We have not heard back from you. This thread will no longer be monitored by Intel. If you need further assistance, please post a new question.


Thanks,

Jaideep


0 Kudos
Reply