[Mlir-commits] [mlir] [mlir][spirv] Add 8-bit float type emulation (PR #148811)
Krzysztof Drewniak
llvmlistbot at llvm.org
Tue Jul 22 08:13:21 PDT 2025
================
@@ -39,6 +39,10 @@ struct SPIRVConversionOptions {
/// The number of bits to store a boolean value.
unsigned boolNumBits{8};
+ /// Whether to emulate unsupported floats with integer types of same bit
+ /// width.
+ bool emulateUnsupportedFloatTypes{true};
----------------
krzysz00 wrote:
I think the theory is that you'll generally want to do software emulation of the small floats earlier?
https://github.com/llvm/llvm-project/pull/148811
More information about the Mlir-commits
mailing list