[Joint Matrix] Enable different accumulator and output types in spirv. Add tests to cover bfloat16 and half floating-point sizes. #17502
Conversation
This file contains hidden or 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
dkhaldi
reviewed
Mar 18, 2025
ggojska
force-pushed
the
commonhpp_reference_calculation_change
branch
from
f5e46ba to
3a5de5a
Compare
ggojska
force-pushed
the
commonhpp_reference_calculation_change
branch
from
3a5de5a to
c5be2c5
Compare
This comment was marked as outdated.
This comment was marked as outdated.
Sorry, something went wrong.
ggojska
force-pushed
the
commonhpp_reference_calculation_change
branch
from
c5be2c5 to
29c35ac
Compare
ggojska
force-pushed
the
commonhpp_reference_calculation_change
branch
from
29c35ac to
8116625
Compare
ggojska
force-pushed
the
commonhpp_reference_calculation_change
branch
from
8116625 to
fc7eaf7
Compare
MrSidims
reviewed
Jun 26, 2025
| @@ -54,7 +54,7 @@ | |||
| // tests to match the required format and in that case you should just update | |||
| // (i.e. reduce) the number and the list below. | |||
| // | |||
| // NUMBER-OF-UNSUPPORTED-WITHOUT-INFO: 248 | |||
| // NUMBER-OF-UNSUPPORTED-WITHOUT-INFO: 249 | |||
There was a problem hiding this comment.
nit: Can we add sycl/test-e2e/Matrix/joint_matrix_half.cpp to the unsupported tests below?
There was a problem hiding this comment.
sycl/test-e2e/Matrix/joint_matrix_half.cpp There is patch https://github.com/intel-innersource/drivers.gpu.unified/pull/195521 where support for half and bfloat16 accumulator/output is added to IGC. Do we want to mark it as unsupported untill it is merged or just xfail?
There was a problem hiding this comment.
Well, may be leaving as is is fine, @KornevNikita WDYT?
There was a problem hiding this comment.
I posted a suggestion below.
Co-authored-by: Nikita Kornev <nikita.kornev@intel.com>
Add JIRA trackers
Add JIRA trackers
Remove tests from unsupported without info check file
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.
Updated matrix_compare and matrix_multiply_ref functions to better match bfloat16 calculations on device.