Is that possible to add Float8Type as a derived class of FloatType? In C++, we can add Float8Type as a derived class of FloatType by using class Float8Type : public FloatType. However, in MLIR, we need to determine if Float8Type is FloatType by calling ty.isa<FloatType>, which is hardcoded as i…

Is that possible to extend FloatType (e.g., Float8Type)?

stellaraccident September 14, 2022, 4:20pm 3

1 Like

Topic		Replies	Views
Add FloatType to MLIR Python bindings MLIR	7	292	February 14, 2024
Custom float types MLIR	18	781	March 25, 2024
RFC: Add APFloat and MLIR type support for fp8 (e5m2) LLVM Project	21	3575	March 28, 2025
[RFC] Adding better support for higher precision floating-point MLIR	5	889	January 15, 2021
Add LLVM type support for fp8 data types (F8E4M3 and F8E5M2) LLVM Project llvm	21	3613	March 19, 2024