-
Notifications
You must be signed in to change notification settings - Fork 505
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Implement lowering of torch.aten.renorm #3388
Conversation
3b8c9ef
to
51d098a
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hey, thanks for the PR!
2838f84
to
a319a8f
Compare
a319a8f
to
daf74e5
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This looks good to me.
Before merging, it might be good to get someone's opinion about adding verifiers, since I haven't seen one added in torch-mlir before (perhaps since any torch code which would result in a violation likely throws an error when importing in the first place).
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for this! Below is a review of the verifier
…fferent types for p and maxnorm args
7aacd9b
to
3af823c
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM!
// Arragne reduce_dims tensor (vector), [0, 1, ... , dim-1, dim+1, ... , | ||
// ndim-1] | ||
llvm::SmallVector<Value> reduceDimsVector; | ||
for (u_int64_t i = 0; i < ndim; i++) { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This does not build on MSVC. The portable type name (also used in other parts of this file) is uint64_t
.
torch-mlir\lib\Dialect\Torch\Transforms\DecomposeComplexOps.cpp(2420): error C2065: 'u_int64_t': undeclared identifier
Sent a fix: #3519
Closes nod-ai/SHARK-Turbine/issues/689