[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtins & Codegen support for v_cvt_scale_fp4<->f32 for gfx950 (PR #117743)

[Shilei Tian via llvm-branch-commits]

================
@@ -14,8 +14,6 @@ typedef __bf16 __attribute__((ext_vector_type(2))) bfloat2;
 typedef float __attribute__((ext_vector_type(16))) float16;
 typedef half __attribute__((ext_vector_type(2))) half2;
 typedef float __attribute__((ext_vector_type(2))) float2;
-typedef half __attribute__((ext_vector_type(2))) half2;
----------------
shiltian wrote:

no sure why they were removed

https://github.com/llvm/llvm-project/pull/117743