Analyzers
Talk to fellow users of Intel Analyzer tools (Intel VTune™ Profiler, Intel Advisor)
Announcements
FPGA community forums and blogs have moved to the Altera Community. Existing Intel Community members can sign in with their current credentials.
5260 Discussions

Using vtune to watch gpu offload in graphic

Hannah_zhen
Novice
1,493 Views

Hi, community:

Recently, I have used vtune to watch gpu offload in WIN10 like:

task.png

However, as I open result generated from ubuntu CLI, some times the task is from level zero api

ze.png

sometimes is from openCL

cl.png

I was wondering whether it can be controlled by myself as I want to watch the time circle about gpu offload with openCL tasks.

 

Is there any solution to control it? Thanks in advance.

Below is my device information :

My running environment is ubuntu22.04 with 6.2.0-36-generic and the processor is i5-1340P.

The vtune version in win10 is 2024.0.0.

0 Kudos
1 Solution
Rahila_T_Intel
Employee
1,461 Views

Hi,

 

Thank you for posting in Intel communities.

 

To select a specific offload device, ONEAPI_DEVICE_SELECTOR environment variables can be used. Using it affects all the device query functions and device selectors. 

To check on the availability of devices for use with SYCL on a running system, simply use the sycl-ls command, e.g.:

 

 

$ sycl-ls

[opencl:acc:0] Intel(R) FPGA Emulation Platform for OpenCL(TM), Intel(R) FPGA Emulation Device 1.2 [2022.13.3.0.16_160000]

[opencl:cpu:1] Intel(R) OpenCL, 11th Gen Intel(R) Core(TM) i7-1185G7 @ 3.00GHz 3.0 [2022.13.3.0.16_160000]

[opencl:gpu:2] Intel(R) OpenCL HD Graphics, Intel(R) Iris(R) Xe Graphics 3.0 [31.0.101.3358]

[ext_oneapi_level_zero:gpu:0] Intel(R) Level-Zero, Intel(R) Iris(R) Xe Graphics 1.3 [1.3.23828]

[host:host:0] SYCL host platform, SYCL host device 1.2 [1.2]

 

 

ONEAPI_DEVICE_SELECTOR environment variable can be used to limit the choice of devices available when the SYCL-using application is run. Useful for limiting devices to a certain type (like GPUs or accelerators) or backends (like Level Zero or OpenCL).

 

The ONEAPI_DEVICE_SELECTOR syntax is shared with OpenMP and also allows sub-devices to be chosen. See https://intel.github.io/llvm-docs/EnvironmentVariables.html#oneapi-device-selector for a full description.

 

To know more about the environment variables that are having effect on DPC++ compiler and runtime please refer the below documents. 

 

Hope this will help in clarifying your query. 

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

 

Thanks

 

View solution in original post

0 Kudos
2 Replies
Rahila_T_Intel
Employee
1,462 Views

Hi,

 

Thank you for posting in Intel communities.

 

To select a specific offload device, ONEAPI_DEVICE_SELECTOR environment variables can be used. Using it affects all the device query functions and device selectors. 

To check on the availability of devices for use with SYCL on a running system, simply use the sycl-ls command, e.g.:

 

 

$ sycl-ls

[opencl:acc:0] Intel(R) FPGA Emulation Platform for OpenCL(TM), Intel(R) FPGA Emulation Device 1.2 [2022.13.3.0.16_160000]

[opencl:cpu:1] Intel(R) OpenCL, 11th Gen Intel(R) Core(TM) i7-1185G7 @ 3.00GHz 3.0 [2022.13.3.0.16_160000]

[opencl:gpu:2] Intel(R) OpenCL HD Graphics, Intel(R) Iris(R) Xe Graphics 3.0 [31.0.101.3358]

[ext_oneapi_level_zero:gpu:0] Intel(R) Level-Zero, Intel(R) Iris(R) Xe Graphics 1.3 [1.3.23828]

[host:host:0] SYCL host platform, SYCL host device 1.2 [1.2]

 

 

ONEAPI_DEVICE_SELECTOR environment variable can be used to limit the choice of devices available when the SYCL-using application is run. Useful for limiting devices to a certain type (like GPUs or accelerators) or backends (like Level Zero or OpenCL).

 

The ONEAPI_DEVICE_SELECTOR syntax is shared with OpenMP and also allows sub-devices to be chosen. See https://intel.github.io/llvm-docs/EnvironmentVariables.html#oneapi-device-selector for a full description.

 

To know more about the environment variables that are having effect on DPC++ compiler and runtime please refer the below documents. 

 

Hope this will help in clarifying your query. 

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

 

Thanks

 

0 Kudos
Rahila_T_Intel
Employee
1,438 Views

Hi,


Thanks for accepting our solution. 

If you need any additional information, please post a new question as this thread will no longer be monitored by Intel.


Thanks


0 Kudos
Reply