Skip to content
This repository was archived by the owner on Apr 23, 2021. It is now read-only.

Conversation

bondhugula
Copy link
Contributor

The check in isValidSymbol, as far as a DimOp result went, checked if
the dim op was on a top-level memref. However, any alloc'ed, view, or
subview memref would be fine as long as the corresponding dimension of
that memref is either a static one or was in turn created using a valid
symbol in the case of dynamic dimensions.

Reported-by: Jose Gomez

Signed-off-by: Uday Bondhugula uday@polymagelabs.com

Copy link

@nicolasvasilache nicolasvasilache left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for your contribution!

@nicolasvasilache
Copy link

Blocked by #254, fix is in flight.

@nicolasvasilache
Copy link

Fix has landed, please rebase and I'll push it internally (may be some delay this is the first time I try this part of the flow).

The check in isValidSymbol, as far as a DimOp result went, checked if
the dim op was on a top-level memref. However, any alloc'ed, view, or
subview memref would be fine as long as the corresponding dimension of
that memref is either a static one or was in turn created using a valid
symbol in the case of dynamic dimensions.

Reported-by: Jose Gomez

Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>
@bondhugula
Copy link
Contributor Author

Anything more here? The build is failing due to an issue unrelated to this PR.

tensorflow-copybara pushed a commit to tensorflow/tensorflow that referenced this pull request Nov 23, 2019
The check in isValidSymbol, as far as a DimOp result went, checked if
the dim op was on a top-level memref. However, any alloc'ed, view, or
subview memref would be fine as long as the corresponding dimension of
that memref is either a static one or was in turn created using a valid
symbol in the case of dynamic dimensions.

Reported-by: Jose Gomez

Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>

Closes #252

COPYBARA_INTEGRATE_REVIEW=tensorflow/mlir#252 from bondhugula:symbol 7b57dc394df9375e651f497231c6e4525a32a662
PiperOrigin-RevId: 282097114
Change-Id: I100a84c736e880044ba6faf5734e4cbbdf5b3256
joker-eph pushed a commit to joker-eph/llvm-project-with-mlir that referenced this pull request Nov 23, 2019
The check in isValidSymbol, as far as a DimOp result went, checked if
the dim op was on a top-level memref. However, any alloc'ed, view, or
subview memref would be fine as long as the corresponding dimension of
that memref is either a static one or was in turn created using a valid
symbol in the case of dynamic dimensions.

Reported-by: Jose Gomez

Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>

Closes #252

COPYBARA_INTEGRATE_REVIEW=tensorflow/mlir#252 from bondhugula:symbol 7b57dc394df9375e651f497231c6e4525a32a662
PiperOrigin-RevId: 282097114
@bondhugula bondhugula deleted the symbol branch December 9, 2019 03:01
swift-ci pushed a commit to swiftlang/llvm-project that referenced this pull request Dec 24, 2019
The check in isValidSymbol, as far as a DimOp result went, checked if
the dim op was on a top-level memref. However, any alloc'ed, view, or
subview memref would be fine as long as the corresponding dimension of
that memref is either a static one or was in turn created using a valid
symbol in the case of dynamic dimensions.

Reported-by: Jose Gomez

Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>

Closes tensorflow/mlir#252

COPYBARA_INTEGRATE_REVIEW=tensorflow/mlir#252 from bondhugula:symbol 7b57dc394df9375e651f497231c6e4525a32a662
PiperOrigin-RevId: 282097114
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants