Skip to content

Upcast gradually when computing variance #4283

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.

Sign up for GitHub

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

Merged
merged 1 commit into from
Aug 6, 2025
+9 −3
Merged

Upcast gradually when computing variance #4283

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 9 additions & 3 deletions lib/Dialect/Torch/Transforms/DecomposeComplexOps.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9322,9 +9322,15 @@ static LogicalResult calculateVariance(OpTy op, PatternRewriter &rewriter,
op, "support floating-point type input only");
}

// Upcasting the input tensor to `F64` dtype for higher precision during the
// computation of the result.
if (inputTensorTy.getDtype().getIntOrFloatBitWidth() != 64) {
// Upcasting the input tensor to a double-bitwidth dtype for higher precision
// during the computation of the result.
unsigned bitwidth = inputTensorTy.getDtype().getIntOrFloatBitWidth();
if (bitwidth != 64) {
Type targetTy = rewriter.getF64Type();
if (bitwidth == 8)
targetTy = rewriter.getBF16Type();
else if (bitwidth == 16)
targetTy = rewriter.getF32Type();
self = convertTensorToDtype(rewriter, loc, self, rewriter.getF64Type());
Comment on lines +9325 to 9334
Copy link
Collaborator

Choose a reason for hiding this comment

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

Don't you need to replace rewriter.getF64Type() with the targetTy here?

inputTensorTy = cast<BaseTensorType>(self.getType());
}
Expand Down
Loading