[SLP] Added testcase for PR47623

Author: davidbolvansky

llvm/test/Transforms/SLPVectorizer/X86/pr47623.ll

@@ -0,0 +1,37 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+sse2     | FileCheck %s --check-prefixes=CHECK,SSE
+; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+avx      | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
+; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+avx2     | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
+; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+avx512f  | FileCheck %s --check-prefixes=CHECK,AVX,AVX512,AVX512F
+; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX,AVX512,AVX512VL
+
+
+@b = global [8 x i32] zeroinitializer, align 16
+@a = global [8 x i32] zeroinitializer, align 16
+
+define void @foo() {
+; CHECK-LABEL: @foo(
+; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @b, i64 0, i64 0), align 16
+; CHECK-NEXT:    store i32 [[TMP1]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 0), align 16
+; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @b, i64 0, i64 2), align 8
+; CHECK-NEXT:    store i32 [[TMP2]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 1), align 4
+; CHECK-NEXT:    store i32 [[TMP1]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 2), align 8
+; CHECK-NEXT:    store i32 [[TMP2]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 3), align 4
+; CHECK-NEXT:    store i32 [[TMP1]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 4), align 16
+; CHECK-NEXT:    store i32 [[TMP2]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 5), align 4
+; CHECK-NEXT:    store i32 [[TMP1]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 6), align 8
+; CHECK-NEXT:    store i32 [[TMP2]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 7), align 4
+; CHECK-NEXT:    ret void
+;
+  %1 = load i32, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @b, i64 0, i64 0), align 16
+  store i32 %1, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 0), align 16
+  %2 = load i32, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @b, i64 0, i64 2), align 8
+  store i32 %2, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 1), align 4
+  store i32 %1, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 2), align 8
+  store i32 %2, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 3), align 4
+  store i32 %1, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 4), align 16
+  store i32 %2, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 5), align 4
+  store i32 %1, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 6), align 8
+  store i32 %2, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 7), align 4
+  ret void
+}