Index: lib/Transforms/InstCombine/InstCombineCalls.cpp
===================================================================
--- lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -1452,6 +1452,25 @@
   return maxnum(Src0, Src1);
 }
 
+/// Convert a vector load intrinsic into a simple llvm load instruction.
+/// This is beneficial when the underlying object being addressed comes
+/// from a constant, since we get constant-folding for free.
+static Value *simplifyNeonVld1(const IntrinsicInst &II,
+                               unsigned MemAlign,
+                               InstCombiner::BuilderTy &Builder) {
+  auto *IntrAlign = dyn_cast<ConstantInt>(II.getArgOperand(1));
+
+  if (!IntrAlign)
+    return nullptr;
+
+  unsigned Alignment = IntrAlign->getZExtValue() < MemAlign ?
+                       MemAlign : IntrAlign->getZExtValue();
+
+  auto *BCastInst = Builder.CreateBitCast(II.getArgOperand(0),
+                                          PointerType::get(II.getType(), 0));
+  return Builder.CreateAlignedLoad(BCastInst, Alignment);
+}
+
 // Returns true iff the 2 intrinsics have the same operands, limiting the
 // comparison to the first NumOperands.
 static bool haveSameOperands(const IntrinsicInst &I, const IntrinsicInst &E,
@@ -2968,7 +2987,14 @@
     }
     break;
 
-  case Intrinsic::arm_neon_vld1:
+  case Intrinsic::arm_neon_vld1: {
+    unsigned MemAlign = getKnownAlignment(II->getArgOperand(0),
+                                          DL, II, &AC, &DT);
+    if (Value *V = simplifyNeonVld1(*II, MemAlign, Builder))
+      return replaceInstUsesWith(*II, V);
+    break;
+  }
+
   case Intrinsic::arm_neon_vld2:
   case Intrinsic::arm_neon_vld3:
   case Intrinsic::arm_neon_vld4:
Index: test/Transforms/InstCombine/ARM/vld1.ll
===================================================================
--- /dev/null
+++ test/Transforms/InstCombine/ARM/vld1.ll
@@ -0,0 +1,91 @@
+; RUN: opt < %s -instcombine -S | FileCheck %s
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+
+target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
+target triple = "armv8-arm-none-eabi"
+
+; Turning a vld1 intrinsic into an llvm load is beneficial
+; when the underlying object being addressed comes from a
+; constant, since we get constant-folding for free.
+
+; Bail the optimization if the alignment is not a constant.
+define <2 x i64> @vld1_align(i8* %ptr, i32 %align) {
+; CHECK-NOT: bitcast i8* %ptr to <2 x i64>*
+; CHECK-NOT: load <2 x i64>, <2 x i64>*
+; CHECK: call <2 x i64> @llvm.arm.neon.vld1.v2i64.p0i8
+  %vld1 = call <2 x i64> @llvm.arm.neon.vld1.v2i64.p0i8(i8* %ptr, i32 %align)
+  ret <2 x i64> %vld1
+}
+
+define <8 x i8> @vld1_8x8(i8* %ptr) {
+; CHECK-NOT: call <8 x i8> @llvm.arm.neon.vld1.v8i8.p0i8
+; CHECK: [[bcast:%.*]] = bitcast i8* %ptr to <8 x i8>*
+; CHECK: load <8 x i8>, <8 x i8>* [[bcast]], align 8
+  %vld1 = call <8 x i8> @llvm.arm.neon.vld1.v8i8.p0i8(i8* %ptr, i32 8)
+  ret <8 x i8> %vld1
+}
+
+define <4 x i16> @vld1_4x16(i8* %ptr) {
+; CHECK-NOT: call <4 x i16> @llvm.arm.neon.vld1.v4i16.p0i8
+; CHECK: [[bcast:%.*]] = bitcast i8* %ptr to <4 x i16>*
+; CHECK: load <4 x i16>, <4 x i16>* [[bcast]], align 16
+  %vld1 = call <4 x i16> @llvm.arm.neon.vld1.v4i16.p0i8(i8* %ptr, i32 16)
+  ret <4 x i16> %vld1
+}
+
+define <2 x i32> @vld1_2x32(i8* %ptr) {
+; CHECK-NOT: call <2 x i32> @llvm.arm.neon.vld1.v2i32.p0i8
+; CHECK: [[bcast:%.*]] = bitcast i8* %ptr to <2 x i32>*
+; CHECK: load <2 x i32>, <2 x i32>* [[bcast]], align 32
+  %vld1 = call <2 x i32> @llvm.arm.neon.vld1.v2i32.p0i8(i8* %ptr, i32 32)
+  ret <2 x i32> %vld1
+}
+
+define <1 x i64> @vld1_1x64(i8* %ptr) {
+; CHECK-NOT: call <1 x i64> @llvm.arm.neon.vld1.v1i64.p0i8
+; CHECK: [[bcast:%.*]] = bitcast i8* %ptr to <1 x i64>*
+; CHECK: load <1 x i64>, <1 x i64>* [[bcast]], align 64
+  %vld1 = call <1 x i64> @llvm.arm.neon.vld1.v1i64.p0i8(i8* %ptr, i32 64)
+  ret <1 x i64> %vld1
+}
+
+define <8 x i16> @vld1_8x16(i8* %ptr) {
+; CHECK-NOT: call <8 x i16> @llvm.arm.neon.vld1.v8i16.p0i8
+; CHECK: [[bcast:%.*]] = bitcast i8* %ptr to <8 x i16>*
+; CHECK: load <8 x i16>, <8 x i16>* [[bcast]], align 16
+  %vld1 = call <8 x i16> @llvm.arm.neon.vld1.v8i16.p0i8(i8* %ptr, i32 16)
+  ret <8 x i16> %vld1
+}
+
+define <16 x i8> @vld1_16x8(i8* %ptr) {
+; CHECK-NOT: call <16 x i8> @llvm.arm.neon.vld1.v16i8.p0i8
+; CHECK: [[bcast:%.*]] = bitcast i8* %ptr to <16 x i8>*
+; CHECK: load <16 x i8>, <16 x i8>* [[bcast]], align 8
+  %vld1 = call <16 x i8> @llvm.arm.neon.vld1.v16i8.p0i8(i8* %ptr, i32 8)
+  ret <16 x i8> %vld1
+}
+
+define <4 x i32> @vld1_4x32(i8* %ptr) {
+; CHECK-NOT: call <4 x i32> @llvm.arm.neon.vld1.v4i32.p0i8
+; CHECK: [[bcast:%.*]] = bitcast i8* %ptr to <4 x i32>*
+; CHECK: load <4 x i32>, <4 x i32>* [[bcast]], align 32
+  %vld1 = call <4 x i32> @llvm.arm.neon.vld1.v4i32.p0i8(i8* %ptr, i32 32)
+  ret <4 x i32> %vld1
+}
+
+define <2 x i64> @vld1_2x64(i8* %ptr) {
+; CHECK-NOT: call <2 x i64> @llvm.arm.neon.vld1.v2i64.p0i8
+; CHECK: [[bcast:%.*]] = bitcast i8* %ptr to <2 x i64>*
+; CHECK: load <2 x i64>, <2 x i64>* [[bcast]], align 64
+  %vld1 = call <2 x i64> @llvm.arm.neon.vld1.v2i64.p0i8(i8* %ptr, i32 64)
+  ret <2 x i64> %vld1
+}
+
+declare <8 x i8> @llvm.arm.neon.vld1.v8i8.p0i8(i8*, i32)
+declare <4 x i16> @llvm.arm.neon.vld1.v4i16.p0i8(i8*, i32)
+declare <2 x i32> @llvm.arm.neon.vld1.v2i32.p0i8(i8*, i32)
+declare <1 x i64> @llvm.arm.neon.vld1.v1i64.p0i8(i8*, i32)
+declare <8 x i16> @llvm.arm.neon.vld1.v8i16.p0i8(i8*, i32)
+declare <16 x i8> @llvm.arm.neon.vld1.v16i8.p0i8(i8*, i32)
+declare <4 x i32> @llvm.arm.neon.vld1.v4i32.p0i8(i8*, i32)
+declare <2 x i64> @llvm.arm.neon.vld1.v2i64.p0i8(i8*, i32)