- User Since
- Jan 7 2020, 7:38 AM (106 w, 2 d)
Please fix the commit message though. I just noticed this now.
Pull size checking out of helper.
Tue, Jan 18
Thanks for adding this. I have wanted this a couple of times, too, but never went as far as creating a diff for it.
Mon, Jan 17
Thanks for adding this. Could this rather reuse the logic from verifyAllocLike from the memref operations? It is the same logic but it would need to be exposed to other dialect.
Fri, Jan 14
Thu, Jan 13
Wed, Jan 12
Tue, Jan 11
The arith::minf operation is defined as
There could well be a separate pass that inserts these casts to avoid the behavior in shape reification if that is critical to your use cases. I think it would still be better to fix shape reification to return a static value where possible. After all, if this is valid linalg IR, reification should do as good as it can with it.
Mon, Jan 10
Fri, Jan 7
Combined the two patterns.
Simplified as suggested
Wed, Jan 5
Great find. Thanks for the fix.
Tue, Jan 4
Wed, Dec 22
Can you change the subject to have an additional tag, e.g., [mlir][arith]. That provides a little more context. You could also state that it did fail for vectors before but now it folds them correctly.
Add comments and failure reason.
Dec 21 2021
Thanks. I don't see any reason to disallow this either and was surprised by the error message.
Add tests and fix behaviour for zero case.
Dec 16 2021
Dec 14 2021
It would be nice if we could just pass the data layout as a string.
Dec 8 2021
Dec 1 2021
I assume that would be @nicolasvasilache as I suspect this is a matmul bufferization issue.
Thanks @mehdi_amini ! That is much easier.
Use in-test tag as suggested.
Nov 30 2021
This was recently fixed in https://reviews.llvm.org/D114391. If you rebase, you should pick up that change.
Nov 29 2021
Please sort the headers, otherwise looks good. Thanks!
Nov 25 2021
Thank you for cleaning this up. Just some nits and please address the comments others already had.
Nov 24 2021
Thanks for the clarification.
Nov 22 2021
Just minor nits. Thank you!
Nov 11 2021
Add comment in test
Nov 10 2021
Thanks for the explanation.
Nov 9 2021
Oct 5 2021
Regarding @mehdi_amini comment: I agree that this adds another dimension to the ABI with C but unranked results already have a fairly complex calling convention and I don't think this makes it worse. If there are strong concerns that this will get out of sync, we could hard-wire this to a fixed rank to start with, which would prevent that issue.
Oct 4 2021
@mehdi_amini not sure how to test this. Do the builders do this automatically?
Sep 21 2021
Nice, thanks! I just have a nit about the comment. In case you touch this again anyway.
Sep 14 2021
Looks good to me. Please also wait for @rriddle.
Sep 13 2021
Thanks, just a nit.
Sep 10 2021
clang tidy fix
also support linalg ops with hidden regions like dot.
Note that this is already tested by existing tests that use the math dialect.
Sep 8 2021
This change is not correct in general I believe.
This is adding a specialized pattern that implements the shape reification interface + rewrite based on it. My first hunch was that this should then also be in a pass and not a canonicalization. However, I think control flow is different than compute ops in that regard, so I came to the conclusion that it makes sense to have this as a pattern.
Sep 7 2021
Sep 6 2021
Aug 30 2021
Aug 26 2021
Thanks, makes sense to keep the runtime as self contained as possible. Should this also reflect in cmake somewhere?