[llvm] [AMDGPU] Extend promotion of alloca to vectors (PR #127973)

[Matt Arsenault via llvm-commits]

================
@@ -0,0 +1,292 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -passes=amdgpu-promote-alloca -disable-promote-alloca-to-lds=1 < %s | FileCheck %s
+
+define amdgpu_kernel void @i32_2d_load_store(ptr %out) {
----------------
arsenm wrote:

Test some pointer elements, FP elements, and sub-32-bit elements 

https://github.com/llvm/llvm-project/pull/127973