[llvm] [AMDGPU] Improve detection of non-null addrspacecast operands (PR #82311)

[Pierre van Houtryve via llvm-commits]

================
@@ -0,0 +1,279 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
+; RUN: opt -mtriple=amdgcn-- -amdgpu-codegenprepare -S < %s | FileCheck -check-prefix=OPT %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck %s --check-prefixes=ASM,DAGISEL-ASM
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -global-isel -mcpu=gfx900 < %s | FileCheck %s --check-prefixes=ASM,GISEL-ASM
+
----------------
Pierre-vh wrote:

I tried writing one but it's rejected, the intrinsic signature doesn't allow it:
```
Intrinsic has incorrect return type!
ptr @llvm.amdgcn.addrspacecast.nonnull.v4p0.v4p3
```

https://github.com/llvm/llvm-project/pull/82311