[AIE2] Add AIE2 vector intrinsics #99
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
ValentijnvdBeek
added
vectorization
ValentijnvdBeek
requested review from
abhinay-anubola,
abnikant,
andcarminati,
gbossu,
khallouh,
konstantinschwarz,
martien-de-jong,
SagarMaheshwari99 and
stephenneuendorffer
as code owners
ValentijnvdBeek
force-pushed
the
vvandebe.shufflevector.pattern.optimization
branch
from
e160d1c to
07244e7
Compare
This implements the simple legalization that lowers G_SHUFFLE_VECTOR into extracts of the elements based on the mask and then combining them using a G_BUILD_VECTOR. Our architecture has a VSHUFFLE instruction which could be used to implement some patterns more efficiently.
… CONCAT_VECTOR We check for iterative shift masks which corresponds to the CONCAT_VECTOR instruction.
…hunks of a vector
… of two vectors together
ValentijnvdBeek
force-pushed
the
vvandebe.shufflevector.pattern.optimization
branch
from
07244e7 to
4836f6a
Compare
ValentijnvdBeek
force-pushed
the
vvandebe.shufflevector.add.intrinsics
branch
from
3a34679 to
d1411d4
Compare
ValentijnvdBeek
force-pushed
the
vvandebe.shufflevector.pattern.optimization
branch
5 times, most recently
from
b49d34c to
f855c29
Compare
ValentijnvdBeek
force-pushed
the
vvandebe.shufflevector.pattern.optimization
branch
2 times, most recently
from
4d6af83 to
13cc82a
Compare
ValentijnvdBeek
force-pushed
the
vvandebe.shufflevector.pattern.optimization
branch
2 times, most recently
from
c38562a to
ebe6489
Compare
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Outdated suggestions cannot be applied.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.
Updates the C header to use the new intrinsics based on Shuffle Vector. A lot of these cases are optimized by #41, however there are a couple of variants that still generate a very slow implementation. Specifically,
extractandinsertare covered for a normative case, but not for all possible variants. Especially, the intrinsics generate cases for256_1024and128_512, which have more cases than the combiner can deal with.It also adds a test for C intrinsics, however this it does this at the LLVM IR level. The code balks at the idea of generating to assembly, so maybe there is an intermediate that we can target instead.