[Torch Dialect] Add torch.aten.mul.int_float (required to simplify shape calculation of upsample_nearest2d)
#3764
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
zjgarvey
requested changes
Nov 8, 2024
| } | ||
| return atenBinaryFloatOperatorFoldHelper( | ||
| adaptor.getOperands(), | ||
| [](double a, double b) -> double { return a * b; }); |
There was a problem hiding this comment.
I think a is supposed to be an int64_t, so you might need to do something like:
Suggested change
| [](double a, double b) -> double { return a * b; }); | |
| [](int64_t a, double b) -> double { return static_cast<double>(a) * b; }); |
Other helpful options for folding:
you can return the right operand if the left operand is statically 1, or if either operand is zero, the result should be zero even if we don't have all constant operands.
| // CHECK-SAME: %[[RHS:.*]]: !torch.float) -> !torch.float { | ||
| // CHECK-DAG: %[[LHS_I64:.*]] = torch_c.to_i64 %[[LHS]] | ||
| // CHECK-DAG: %[[RHS_F64:.*]] = torch_c.to_f64 %[[RHS]] | ||
| // CHECK: %[[MUL:.*]] = arith.mulf %[[LHS_I64:.*]], [[RHS_F64:.*]] : f64 |
There was a problem hiding this comment.
This is a bit strange, shouldn't there be a cast on LHS_I64 before passing to arith.mulf ?
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Outdated suggestions cannot be applied.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.
As per title. See also PR for
torch.aten.mul.float_int.