llvm-project

cbc8f650 - [HLSL][DirectX] Fix `dot2add` DXIL operation to use float overload (#152781)

[HLSL][DirectX] Fix `dot2add` DXIL operation to use float overload (#152781) Fixes #152585. The `dot2add` DXILOpFunction should be `dx.op.dot2AddHalf.f32` (i.e. it has [a single overload that's a float](https://github.com/microsoft/DirectXShaderCompiler/blob/main/utils/hct/hctdb.py#L3960), rather than no overloads). It was also being defined for too low of a DXIL version - [dxc says SM6.4](https://github.com/microsoft/DirectXShaderCompiler/blob/main/utils/hct/hctdb.py#L740).