[MLIR] [NFC] Use APFloat semantics to get floating type width #107372
Conversation
This file contains hidden or 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
|
@llvm/pr-subscribers-mlir-core @llvm/pr-subscribers-mlir Author: Sergey Kozub (sergey-kozub) ChangesAs suggested in the comments of #105573 Full diff: https://github.com/llvm/llvm-project/pull/107372.diff 1 Files Affected:
diff --git a/mlir/lib/IR/BuiltinTypes.cpp b/mlir/lib/IR/BuiltinTypes.cpp
index 16b53efa55fb80..58f83333b00c20 100644
--- a/mlir/lib/IR/BuiltinTypes.cpp
+++ b/mlir/lib/IR/BuiltinTypes.cpp
@@ -91,21 +91,9 @@ IntegerType IntegerType::scaleElementBitwidth(unsigned scale) {
//===----------------------------------------------------------------------===//
unsigned FloatType::getWidth() {
- if (llvm::isa<Float8E5M2Type, Float8E4M3Type, Float8E4M3FNType,
- Float8E5M2FNUZType, Float8E4M3FNUZType, Float8E4M3B11FNUZType,
- Float8E3M4Type>(*this))
- return 8;
- if (llvm::isa<Float16Type, BFloat16Type>(*this))
- return 16;
- if (llvm::isa<Float32Type, FloatTF32Type>(*this))
+ if (llvm::isa<FloatTF32Type>(*this))
return 32;
- if (llvm::isa<Float64Type>(*this))
- return 64;
- if (llvm::isa<Float80Type>(*this))
- return 80;
- if (llvm::isa<Float128Type>(*this))
- return 128;
- llvm_unreachable("unexpected float type");
+ return getFloatSemantics().sizeInBits;
}
/// Returns the floating semantics for the given type.
|
sergey-kozub
force-pushed
the
mlir-float-getwidth
branch
from
7102cae to
ad2cce9
Compare
apivovarov
reviewed
Sep 9, 2024
| if (llvm::isa<Float16Type, BFloat16Type>(*this)) | ||
| return 16; | ||
| if (llvm::isa<Float32Type, FloatTF32Type>(*this)) | ||
| if (llvm::isa<FloatTF32Type>(*this)) | ||
| return 32; |
There was a problem hiding this comment.
There was a problem hiding this comment.
Added the comment, thanks!
There was a problem hiding this comment.
Seems fine I think, this is NFC right? (please edit the PR title)
There was a problem hiding this comment.
Yeah, I don't have a problem with this either
sergey-kozub
force-pushed
the
mlir-float-getwidth
branch
from
ad2cce9 to
bb4556d
Compare
apivovarov
approved these changes
Sep 9, 2024
dcaballe
approved these changes
Sep 10, 2024
sergey-kozub
changed the title
matthias-springer
added a commit
that referenced
this pull request
Nov 20, 2024
TF32 is a variant of F32 that is truncated to 19 bits. There used to be
special handling in `FloatType::getWidth()` so that TF32 was treated as
a 32-bit float in some places. (Some places use `FloatType::getWidth`,
others directly query the `APFloat` semantics.) This caused problems
because `FloatType::getWidth` did not agree with the underlying
`APFloat` semantics.
In particular, creating an elements attr / array attr with `tf32`
element type crashed. E.g.:
```
"foo"() {attr = dense<4.0> : tensor<tf32>} : () -> ()
mlir-opt: llvm-project/llvm/lib/Support/APFloat.cpp:4108: void llvm::detail::IEEEFloat::initFromAPInt(const fltSemantics *, const APInt &): Assertion `api.getBitWidth() == Sem->sizeInBits' failed.
PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace.
```
```
"foo"() {f32attr = array<tf32: 1024.>} : () -> ()
mlir-opt: llvm-project/mlir/lib/AsmParser/AttributeParser.cpp:847: void (anonymous namespace)::DenseArrayElementParser::append(const APInt &): Assertion `data.getBitWidth() % 8 == 0' failed.
PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace.
```
It is unclear why the special handling for TF32 is needed. For
reference: #107372
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 suggested in the comments of #105573