[llvm] [AMDGPU] Enable vectorization of i8 values. (PR #134934)

[Matt Arsenault via llvm-commits]

================
@@ -0,0 +1,377 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a < %s | FileCheck %s --check-prefixes=GFX90A
+
+
+define void @loads_i1(i32 %arg) {
----------------
arsenm wrote:

Can precommit this test 

https://github.com/llvm/llvm-project/pull/134934