Flexible block size for SYEVJ/HEEVJ #859
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
EdDAzevedo
requested review from
jzuniga-amd,
tfalders,
cgmb,
qjojo,
jmachado-amd,
AGonzales-amd and
a team
as code owners
amd-jnovotny
approved these changes
Nov 27, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The kernels (and launch configurations) are modified to accept a block size nb_max that is not equal to BS2=32.
For double_complex type, the nb_max can be set to 22 to allow (2 * nb_max) by (2 * nb_max) "J" rotation matrix and (2 * nb_max) by (nb_max) submatrix of "A" matrix to be stored in LDS cache for use in offd_rotate_kernel(). This can allow allow the (2 * nb_max) by (2 * nb_max) "J" rotation matrix and (2 * nb_max) by (2 * nb_max) submatrix of "A" be stored in LDS shared memory for syevj_offd_kernel().
This reduced block size may improve the performance of HEEVJ for double complex.