[Mlir-commits] [mlir] [MLIR][XeVM] Add truncf and mma_mx op. (PR #180055)

[Sang Ik Lee]

silee2 wrote:

FYI, default LLVM type converter converts small float (8bits and smaller) to integer types.
https://github.com/llvm/llvm-project/blob/main/mlir/lib/Conversion/LLVMCommon/TypeConverter.cpp#L295
Of course, conversion pass to LLVM intrinsic wrapper dialects can customize the behavior but need to do it in way that is still compatible regular LLVM dialect. 

https://github.com/llvm/llvm-project/pull/180055