[Mlir-commits] [mlir] [mlir][gpu] Add pass for emulating unsupported types. (PR #138087)

Krzysztof Drewniak llvmlistbot at llvm.org
Thu May 1 07:53:25 PDT 2025


krzysz00 wrote:

High-level question: why is this in GPU?

Shouldn't the translation from bf16 to i16 either be a pass over on Arith or part of the SPIR-V lowering? See also, when going to LLVM, we replace all the 8-bit float types with i8

https://github.com/llvm/llvm-project/pull/138087


More information about the Mlir-commits mailing list