diff --git a/llvm/test/Transforms/PhaseOrdering/X86/vec-load-combine.ll b/llvm/test/Transforms/PhaseOrdering/X86/vec-load-combine.ll
new file mode 100644
index 00000000000000..1ed72290f2dfac
--- /dev/null
+++ b/llvm/test/Transforms/PhaseOrdering/X86/vec-load-combine.ll
@@ -0,0 +1,72 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -passes="default<O3>" -S            < %s | FileCheck %s --check-prefix=SSE
+; RUN: opt -passes="default<O3>" -S -mattr=avx < %s | FileCheck %s --check-prefix=AVX
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64--"
+
+%union.ElementWiseAccess = type { <4 x float> }
+
+$getAt = comdat any
+
+define dso_local noundef <4 x float> @ConvertVectors_ByRef(ptr noundef nonnull align 16 dereferenceable(16) %0) #0 {
+; SSE-LABEL: @ConvertVectors_ByRef(
+; SSE-NEXT:    [[TMP2:%.*]] = load <4 x float>, ptr [[TMP0:%.*]], align 16
+; SSE-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [4 x float], ptr [[TMP0]], i64 0, i64 1
+; SSE-NEXT:    [[TMP4:%.*]] = load <2 x float>, ptr [[TMP3]], align 4
+; SSE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
+; SSE-NEXT:    [[TMP6:%.*]] = shufflevector <4 x float> [[TMP2]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 4, i32 5, i32 undef>
+; SSE-NEXT:    [[TMP7:%.*]] = shufflevector <4 x float> [[TMP6]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 2, i32 5>
+; SSE-NEXT:    ret <4 x float> [[TMP7]]
+;
+; AVX-LABEL: @ConvertVectors_ByRef(
+; AVX-NEXT:    [[TMP2:%.*]] = load <4 x float>, ptr [[TMP0:%.*]], align 16
+; AVX-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [4 x float], ptr [[TMP0]], i64 0, i64 2
+; AVX-NEXT:    [[TMP4:%.*]] = load float, ptr [[TMP3]], align 8
+; AVX-NEXT:    [[TMP5:%.*]] = insertelement <4 x float> [[TMP2]], float [[TMP4]], i64 2
+; AVX-NEXT:    [[TMP6:%.*]] = insertelement <4 x float> [[TMP5]], float [[TMP4]], i64 3
+; AVX-NEXT:    ret <4 x float> [[TMP6]]
+;
+  %2 = alloca ptr, align 8
+  %3 = alloca <4 x float>, align 16
+  store ptr %0, ptr %2, align 8
+  %4 = load ptr, ptr %2, align 8
+  %5 = call noundef nonnull align 16 dereferenceable(16) ptr @castToElementWiseAccess_ByRef(ptr noundef nonnull align 16 dereferenceable(16) %4)
+  %6 = call noundef float @getAt(ptr noundef nonnull align 16 dereferenceable(16) %5, i32 noundef 0)
+  %7 = insertelement <4 x float> undef, float %6, i32 0
+  %8 = load ptr, ptr %2, align 8
+  %9 = call noundef nonnull align 16 dereferenceable(16) ptr @castToElementWiseAccess_ByRef(ptr noundef nonnull align 16 dereferenceable(16) %8)
+  %10 = call noundef float @getAt(ptr noundef nonnull align 16 dereferenceable(16) %9, i32 noundef 1)
+  %11 = insertelement <4 x float> %7, float %10, i32 1
+  %12 = load ptr, ptr %2, align 8
+  %13 = call noundef nonnull align 16 dereferenceable(16) ptr @castToElementWiseAccess_ByRef(ptr noundef nonnull align 16 dereferenceable(16) %12)
+  %14 = call noundef float @getAt(ptr noundef nonnull align 16 dereferenceable(16) %13, i32 noundef 2)
+  %15 = insertelement <4 x float> %11, float %14, i32 2
+  %16 = load ptr, ptr %2, align 8
+  %17 = call noundef nonnull align 16 dereferenceable(16) ptr @castToElementWiseAccess_ByRef(ptr noundef nonnull align 16 dereferenceable(16) %16)
+  %18 = call noundef float @getAt(ptr noundef nonnull align 16 dereferenceable(16) %17, i32 noundef 2)
+  %19 = insertelement <4 x float> %15, float %18, i32 3
+  store <4 x float> %19, ptr %3, align 16
+  %20 = load <4 x float>, ptr %3, align 16
+  ret <4 x float> %20
+}
+
+define internal noundef nonnull align 16 dereferenceable(16) ptr @castToElementWiseAccess_ByRef(ptr noundef nonnull align 16 dereferenceable(16) %0) #1 {
+  %2 = alloca ptr, align 8
+  store ptr %0, ptr %2, align 8
+  %3 = load ptr, ptr %2, align 8
+  ret ptr %3
+}
+
+define linkonce_odr dso_local noundef float @getAt(ptr noundef nonnull align 16 dereferenceable(16) %0, i32 noundef %1) #1 comdat align 2 {
+  %3 = alloca ptr, align 8
+  %4 = alloca i32, align 4
+  store ptr %0, ptr %3, align 8
+  store i32 %1, ptr %4, align 4
+  %5 = load ptr, ptr %3, align 8
+  %6 = load i32, ptr %4, align 4
+  %7 = sext i32 %6 to i64
+  %8 = getelementptr inbounds [4 x float], ptr %5, i64 0, i64 %7
+  %9 = load float, ptr %8, align 4
+  ret float %9
+}