[llvm] [AMDGPU] add tests for loop definition of bitconvert (PR #133052)

[Matt Arsenault via llvm-commits]

================
@@ -0,0 +1,68 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+
+; RUN: llc -mtriple=amdgcn  < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -mtriple=amdgcn -mcpu=tonga  < %s | FileCheck -check-prefixes=VI %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx900  < %s | FileCheck -check-prefixes=GFX9 %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1100  < %s | FileCheck -check-prefixes=GFX11 %s
+
+define amdgpu_kernel void @bitcast_i8ptr_v16i8ptr(ptr addrspace(1) %out, ptr addrspace(1) %in) {
----------------
arsenm wrote:

Why "ptr" in the name? There is no pointer cast here. This is also not testing the reverse direction, or all of the interesting type sizes. I think we should be generating all of the cases 

https://github.com/llvm/llvm-project/pull/133052