[llvm] Re-land [Transform][LoadStoreVectorizer] allow redundant in Chain (PR #168135)

[Drew Kersnar via llvm-commits]

================
@@ -0,0 +1,23 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
+; RUN: opt -mtriple=amdgcn-amd-amdhsa -passes=load-store-vectorizer -S -o - %s | FileCheck %s
+
+define void @test(ptr %ptr) {
+; CHECK-LABEL: define void @test(
+; CHECK-SAME: ptr [[PTR:%.*]]) {
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, ptr [[PTR]], align 4
+; CHECK-NEXT:    [[LD01:%.*]] = extractelement <4 x i32> [[TMP1]], i32 0
+; CHECK-NEXT:    [[LD12:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> poison, <2 x i32> <i32 1, i32 2>
+; CHECK-NEXT:    [[LD23:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> poison, <2 x i32> <i32 2, i32 3>
+; CHECK-NEXT:    [[LD34:%.*]] = extractelement <4 x i32> [[TMP1]], i32 2
+; CHECK-NEXT:    ret void
+;
+  %ld0 = load i32, ptr %ptr, align 4
----------------
dakersnar wrote:

Does this target allow misaligned vectors? Is that why this gets vectorized?

https://github.com/llvm/llvm-project/pull/168135