[clang] [llvm] AMDGPU: Builtins & Codegen support for v_cvt_scalef32_pk_f32_{fp8|bf8} for gfx950 (PR #117741)

[Matt Arsenault via cfe-commits]

================
@@ -14,8 +14,10 @@ typedef unsigned int uint;
 typedef unsigned int uint2 __attribute__((ext_vector_type(2)));
 typedef half __attribute__((ext_vector_type(2))) half2;
 typedef short __attribute__((ext_vector_type(2))) short2;
+typedef float __attribute__((ext_vector_type(2))) float2;
 
-void test(global uint* out, global uint2* out_v2u32, uint a, uint b, global half2* out_v2f16, global float* out_f32, float scale, global short2* out_v2i16, float src0, float src1) {
+void test(global uint* out, global uint2* out_v2u32, uint a, uint b, global half2* out_v2f16, global float* out_f32, float scale, global short2* out_v2i16, float src0, float src1,
+          global float2* out_v2f32) {
----------------
arsenm wrote:

I am not touching any formatting, this is what's in the branch. clang-format ignores tests 

https://github.com/llvm/llvm-project/pull/117741