profiling opencl benchmarks

[RamyaSri01]

Hi,

Can anyone help me to execute OpenCL benchmarks on intel integrated UHD 620 graphics and profile them to get timeseries data of low level counters like memory bandwidth, IPC, cache statistics? 

currently, I am thinking to use system analyzer tool to profile while executing OpenCL benchmarks on gpu in the backend. Can you please confirm whether it works or not ? 

It will be helpful if you provide any related documentation also.

Thanks and regards

RamyaSri

[Pamela_H_Intel]

I am going to move this question to the Graphics Forum.

Graphics Performance Analyzers help find bottlenecks in games and other real time rendering applications. So for you or your friends who create games or just want to take a look under the hood, run your exe through GPA. 🙂

[Pamela_H_Intel]

Hello RamyaSri,

GPA's System Analyzer supports Direct3D, OpenGL and Vulkan, but not OpenCL . . . though you can view hardware metrics as you run your application.

System Analyzer does live analysis and you can change metrics sets while running your application. But, still, GPA is strong in deep rendering profiling, and light CPU profiling, but not so much in deep CPU profiling, hence the reason we don't support OpenCL.

Pamela

[RamyaSri01]

Hi, Pamela

Thank you for the information. 

Is there any profiler which supports openCL applications. We can also run openCL programs GPU right. And also I am trying to run rodinia openCL benchmarks  on Intel discrete GPU.  So, can you please  provide information about why can't we profile openCL using system analyzer?

Thank you

G Ramya Sri