[Mlir-commits] [mlir] Add arith expansion of f8E8M0 type for extf/trunc ops (PR #140332)

Daniel Hernandez-Juarez llvmlistbot at llvm.org
Sat May 17 00:41:50 PDT 2025


================
@@ -109,6 +109,7 @@ class Type {
   // Convenience predicates.  This is only for floating point types,
   // derived types should use isa/dyn_cast.
   bool isIndex() const;
+  bool isF8E8M0FNU() const;
----------------
dhernandez0 wrote:

all the isF* for small types were recently removed: https://github.com/llvm/llvm-project/pull/123326

https://github.com/llvm/llvm-project/pull/140332


More information about the Mlir-commits mailing list