[SME] Utilize predication in fp32 matmul and conv2d schedules #17054
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
11 tasks
lhutton1
force-pushed
the
predicate-sme-fp32-schedules
branch
2 times, most recently
from
398ea16 to
41a1f04
Compare
ekalda
approved these changes
Jun 11, 2024
There was a problem hiding this comment.
Thanks @lhutton1, very nice work! Looks good to me, but I'll let @Anndrey24 to take a look as well...
|
LGTM, too! Seems there's just a small merge conflict that has come up. |
Prior to this commit, the matmul and conv2d schedules required padding of the inputs to some multiple of vscale and a final "unpadding" stage. Instead, we can leverage predicated operations to avoid the the requirement for padding. Both the transpose interleave and outer product fp32 intrinsics are updated to use predication. The `get_active_lane_mask` intrinsic is utilized to generate a variably sized mask of active lanes depending on the global position the tensor intrinsic is operating on. For now this relies on using `offset_of` and `stride` information from the tensor we're predicating an access on. Likely we will want to build on this in the future with a more intuitive API for determining the current tile location. Support for batched conv2d was removed since this causes numerical issues which is suspected to be due to how the current tile is determined (paragraph above). Change-Id: I79620200c9a94e2ca9d7297c4ed2abf87549cc41
Change-Id: Iaddeb046bdecb0352a067174f6e6e4be335e94fd
lhutton1
force-pushed
the
predicate-sme-fp32-schedules
branch
from
41a1f04 to
e755e43
Compare
|
Thanks @lhutton1 and @Anndrey24! |
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Outdated suggestions cannot be applied.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.
Prior to this commit, the matmul and conv2d schedules required padding of the inputs to some multiple of vscale and a final "unpadding" stage.
Instead, we can leverage predicated operations to avoid the the requirement for padding. Both the transpose interleave and outer product fp32 intrinsics are updated to use predication. The
get_active_lane_maskintrinsic is utilized to generate a variably sized mask of active lanes depending on the global position the tensor intrinsic is operating on.For now this relies on using
offset_ofandstrideinformation from the tensor we're predicating an access on. Likely we will want to build on this in the future with a more intuitive API for determining the current tile location.Support for batched conv2d was removed since this causes numerical issues which is suspected to be due to how the current tile is determined (paragraph above).
Note: this should not be merged until after #17048cc @ekalda @Anndrey24