[llvm] [AMDGPU] Allocate i1 argument to SGPRs (PR #72461)

[Jun Wang via llvm-commits]

jwanggit86 wrote:

> I believe we also need more tests for i1 vectors and arrays, with and without inreg / signext / zeroext

@arsenm In the following case where the func returns "zeroext i1",
```
define zeroext i1 @i1_zeroext_func_void() {
  %val = load i1, ptr addrspace(1) undef
  ret i1 %val
}
```
because of the zeroext, the return type is updated to i32 and return val allocated to a VGPR. However, on the caller side, the return val is still obtained from a SGPR. How do you want the behavior to be, using VGPR or SGPR?


https://github.com/llvm/llvm-project/pull/72461