Community
cancel
Showing results for 
Search instead for 
Did you mean: 
Highlighted
Beginner
61 Views

New 24.20.100.6094 Win10 driver performance regression from .6025

My suite of kernels compiled (to binaries) with the .6094 driver on Win10/x64 take almost twice the amount of time to execute as those compiled with .6025.

Compiling on .6025 and executing on .6094 shows no regression.

Compiling on .6094 and executing on .6094 or .6025 shows the huge performance drop.

Inspection of the .6094 produced assembly shows long sequences of MOV operations that I believe are unnecessary. 

I wish there was a better way to report performance regressions (and reproducers) than here or the GitHub issues page (which is very quiet).

-ASM

0 Kudos
5 Replies
Highlighted
Beginner
61 Views

The .6136 driver is also spilling a LOT of registers on kernels that compile without any spills on .6025.

I'm using __attribute__((intel_reqd_sub_group_size(8))) so there should be plenty of registers.

0 Kudos
Highlighted
Beginner
61 Views

Today's new driver (.6194) exhibits the same regression. 

As noted above, .6025 works perfectly.

All kernels listed here are decorated with a reqd_subroup_size(8).

Let me know who I can send the kernels to.

spillage.png

0 Kudos
Highlighted
Employee
61 Views

Here is a link for Graphics Compiler project

https://github.com/intel/intel-graphics-compiler

Compiler development team is monitoring it, so publishing an issue there may help.

0 Kudos
Highlighted
Beginner
61 Views

Done, thanks!

0 Kudos
Highlighted
61 Views

Hi AllanM,

Thanks for the detail. If your reproducer source is privileged, it can be submitted confidentially through the Intel Service Center. I can route it to the devs from there. For OpenCL, I recommend marking it as Media Server Studio/Media SDK related or Intel System Studio related.

https://software.intel.com/en-us/support/priority-support

 

Thank you

-MichaelC

0 Kudos