Skip to content

Radix sort one-sweep#117

Merged
KaoCC merged 11 commits intomainfrom
feature/ORO-0-radix-sort-one-sweep
Mar 24, 2025
Merged

Radix sort one-sweep#117
KaoCC merged 11 commits intomainfrom
feature/ORO-0-radix-sort-one-sweep

Conversation

@meistdan
Copy link
Copy Markdown
Collaborator

@meistdan meistdan commented Feb 19, 2025

Porting the code from the previous repo/PR: amdadvtech#87

@meistdan meistdan marked this pull request as draft February 19, 2025 00:32
@meistdan meistdan requested review from KaoCC and removed request for KaoCC February 19, 2025 00:33
}
}
int maxBlocksPerMP = 0;
oroError e = oroOccupancyMaxActiveBlocksPerMultiprocessor( &maxBlocksPerMP, oroFunctions[Kernel::SORT_GHISTOGRAM], GHISTOGRAM_THREADS_PER_BLOCK, 0 );
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think I forgot to fix it to oroModuleOccupancyMaxActiveBlocksPerMultiprocessor
based on #96

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What is the fix? Just changing oroOccupancyMaxActiveBlocksPerMultiprocessor --> oroModuleOccupancyMaxActiveBlocksPerMultiprocessor?

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes. "module" is for driver api

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

oroOccupancyMaxActiveBlocksPerMultiprocessor always fails

@AtsushiYoshimura0302
Copy link
Copy Markdown
Contributor

I checked behavior on RX 7900 XTX and RTX 4090 and worked well :)

@meistdan meistdan requested review from RichardGe and removed request for RichardGe February 19, 2025 02:14
@meistdan meistdan marked this pull request as ready for review March 24, 2025 04:54
@meistdan meistdan requested a review from KaoCC March 24, 2025 04:59
@KaoCC
Copy link
Copy Markdown
Collaborator

KaoCC commented Mar 24, 2025

I've tested on AMD Radeon RX 9070 XT. Works great !

KaoCC added 4 commits March 24, 2025 14:27
Signed-off-by: Chih-Chen Kao <chihchen.kao@amd.com>
… radix sort

Signed-off-by: Chih-Chen Kao <chihchen.kao@amd.com>
Signed-off-by: Chih-Chen Kao <chihchen.kao@amd.com>
Signed-off-by: Chih-Chen Kao <chihchen.kao@amd.com>
@KaoCC KaoCC merged commit adb8668 into main Mar 24, 2025
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants