diff --git a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
--- a/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
+++ b/llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp
@@ -724,7 +724,7 @@
     Info.memVT = Intrinsic == Intrinsic::wasm_load32_zero ? MVT::i32 : MVT::i64;
     Info.ptrVal = I.getArgOperand(0);
     Info.offset = 0;
-    Info.align = Info.memVT == MVT::i32 ? Align(4) : Align(8);
+    Info.align = Align(1);
     Info.flags = MachineMemOperand::MOLoad;
     return true;
   case Intrinsic::wasm_load8_lane:
@@ -736,27 +736,22 @@
   case Intrinsic::wasm_store32_lane:
   case Intrinsic::wasm_store64_lane: {
     MVT MemVT;
-    Align MemAlign;
     switch (Intrinsic) {
     case Intrinsic::wasm_load8_lane:
     case Intrinsic::wasm_store8_lane:
       MemVT = MVT::i8;
-      MemAlign = Align(1);
       break;
     case Intrinsic::wasm_load16_lane:
     case Intrinsic::wasm_store16_lane:
       MemVT = MVT::i16;
-      MemAlign = Align(2);
       break;
     case Intrinsic::wasm_load32_lane:
     case Intrinsic::wasm_store32_lane:
       MemVT = MVT::i32;
-      MemAlign = Align(4);
       break;
     case Intrinsic::wasm_load64_lane:
     case Intrinsic::wasm_store64_lane:
       MemVT = MVT::i64;
-      MemAlign = Align(8);
       break;
     default:
       llvm_unreachable("unexpected intrinsic");
@@ -774,7 +769,7 @@
     Info.ptrVal = I.getArgOperand(0);
     Info.memVT = MemVT;
     Info.offset = 0;
-    Info.align = MemAlign;
+    Info.align = Align(1);
     return true;
   }
   default:
diff --git a/llvm/test/CodeGen/WebAssembly/simd-load-lane-offset.ll b/llvm/test/CodeGen/WebAssembly/simd-load-lane-offset.ll
--- a/llvm/test/CodeGen/WebAssembly/simd-load-lane-offset.ll
+++ b/llvm/test/CodeGen/WebAssembly/simd-load-lane-offset.ll
@@ -266,7 +266,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load16_lane 0, 0
+; CHECK-NEXT:    v128.load16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %t = tail call <8 x i16> @llvm.wasm.load16.lane(i16* %p, <8 x i16> %v, i32 0)
   ret <8 x i16> %t
@@ -280,7 +280,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load16_lane 0, 0
+; CHECK-NEXT:    v128.load16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i16* %p to i32
   %r = add nuw i32 %q, 24
@@ -297,7 +297,7 @@
 ; CHECK-NEXT:    i32.const 12
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load16_lane 0, 0
+; CHECK-NEXT:    v128.load16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i16, i16* %p, i32 6
   %t = tail call <8 x i16> @llvm.wasm.load16.lane(i16* %s, <8 x i16> %v, i32 0)
@@ -312,7 +312,7 @@
 ; CHECK-NEXT:    i32.const -12
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load16_lane 0, 0
+; CHECK-NEXT:    v128.load16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i16, i16* %p, i32 -6
   %t = tail call <8 x i16> @llvm.wasm.load16.lane(i16* %s, <8 x i16> %v, i32 0)
@@ -327,7 +327,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load16_lane 0, 0
+; CHECK-NEXT:    v128.load16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i16* %p to i32
   %r = add nsw i32 %q, 24
@@ -344,7 +344,7 @@
 ; CHECK-NEXT:    i32.const 12
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load16_lane 0, 0
+; CHECK-NEXT:    v128.load16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr i16, i16* %p, i32 6
   %t = tail call <8 x i16> @llvm.wasm.load16.lane(i16* %s, <8 x i16> %v, i32 0)
@@ -357,7 +357,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const 42
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.load16_lane 0, 0
+; CHECK-NEXT:    v128.load16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = inttoptr i32 42 to i16*
   %t = tail call <8 x i16> @llvm.wasm.load16.lane(i16* %s, <8 x i16> %v, i32 0)
@@ -371,7 +371,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const gv_i16
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.load16_lane 0, 0
+; CHECK-NEXT:    v128.load16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %t = tail call <8 x i16> @llvm.wasm.load16.lane(i16* @gv_i16, <8 x i16> %v, i32 0)
   ret <8 x i16> %t
@@ -383,7 +383,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 1
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store16_lane 0, 0
+; CHECK-NEXT:    v128.store16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   tail call void @llvm.wasm.store16.lane(i16* %p, <8 x i16> %v, i32 0)
   ret void
@@ -397,7 +397,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store16_lane 0, 0
+; CHECK-NEXT:    v128.store16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i16* %p to i32
   %r = add nuw i32 %q, 24
@@ -414,7 +414,7 @@
 ; CHECK-NEXT:    i32.const 12
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store16_lane 0, 0
+; CHECK-NEXT:    v128.store16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i16, i16* %p, i32 6
   tail call void @llvm.wasm.store16.lane(i16* %s, <8 x i16> %v, i32 0)
@@ -429,7 +429,7 @@
 ; CHECK-NEXT:    i32.const -12
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store16_lane 0, 0
+; CHECK-NEXT:    v128.store16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i16, i16* %p, i32 -6
   tail call void @llvm.wasm.store16.lane(i16* %s, <8 x i16> %v, i32 0)
@@ -444,7 +444,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store16_lane 0, 0
+; CHECK-NEXT:    v128.store16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i16* %p to i32
   %r = add nsw i32 %q, 24
@@ -461,7 +461,7 @@
 ; CHECK-NEXT:    i32.const 12
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store16_lane 0, 0
+; CHECK-NEXT:    v128.store16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr i16, i16* %p, i32 6
   tail call void @llvm.wasm.store16.lane(i16* %s, <8 x i16> %v, i32 0)
@@ -474,7 +474,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const 42
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store16_lane 0, 0
+; CHECK-NEXT:    v128.store16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = inttoptr i32 42 to i16*
   tail call void @llvm.wasm.store16.lane(i16* %s, <8 x i16> %v, i32 0)
@@ -487,7 +487,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const gv_i16
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store16_lane 0, 0
+; CHECK-NEXT:    v128.store16_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   tail call void @llvm.wasm.store16.lane(i16* @gv_i16, <8 x i16> %v, i32 0)
   ret void
@@ -503,7 +503,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load32_lane 0, 0
+; CHECK-NEXT:    v128.load32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %t = tail call <4 x i32> @llvm.wasm.load32.lane(i32* %p, <4 x i32> %v, i32 0)
   ret <4 x i32> %t
@@ -517,7 +517,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load32_lane 0, 0
+; CHECK-NEXT:    v128.load32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i32* %p to i32
   %r = add nuw i32 %q, 24
@@ -534,7 +534,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load32_lane 0, 0
+; CHECK-NEXT:    v128.load32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i32, i32* %p, i32 6
   %t = tail call <4 x i32> @llvm.wasm.load32.lane(i32* %s, <4 x i32> %v, i32 0)
@@ -549,7 +549,7 @@
 ; CHECK-NEXT:    i32.const -24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load32_lane 0, 0
+; CHECK-NEXT:    v128.load32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i32, i32* %p, i32 -6
   %t = tail call <4 x i32> @llvm.wasm.load32.lane(i32* %s, <4 x i32> %v, i32 0)
@@ -564,7 +564,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load32_lane 0, 0
+; CHECK-NEXT:    v128.load32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i32* %p to i32
   %r = add nsw i32 %q, 24
@@ -581,7 +581,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load32_lane 0, 0
+; CHECK-NEXT:    v128.load32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr i32, i32* %p, i32 6
   %t = tail call <4 x i32> @llvm.wasm.load32.lane(i32* %s, <4 x i32> %v, i32 0)
@@ -594,7 +594,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const 42
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.load32_lane 0, 0
+; CHECK-NEXT:    v128.load32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = inttoptr i32 42 to i32*
   %t = tail call <4 x i32> @llvm.wasm.load32.lane(i32* %s, <4 x i32> %v, i32 0)
@@ -608,7 +608,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const gv_i32
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.load32_lane 0, 0
+; CHECK-NEXT:    v128.load32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %t = tail call <4 x i32> @llvm.wasm.load32.lane(i32* @gv_i32, <4 x i32> %v, i32 0)
   ret <4 x i32> %t
@@ -620,7 +620,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 1
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store32_lane 0, 0
+; CHECK-NEXT:    v128.store32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   tail call void @llvm.wasm.store32.lane(i32* %p, <4 x i32> %v, i32 0)
   ret void
@@ -634,7 +634,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store32_lane 0, 0
+; CHECK-NEXT:    v128.store32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i32* %p to i32
   %r = add nuw i32 %q, 24
@@ -651,7 +651,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store32_lane 0, 0
+; CHECK-NEXT:    v128.store32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i32, i32* %p, i32 6
   tail call void @llvm.wasm.store32.lane(i32* %s, <4 x i32> %v, i32 0)
@@ -666,7 +666,7 @@
 ; CHECK-NEXT:    i32.const -24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store32_lane 0, 0
+; CHECK-NEXT:    v128.store32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i32, i32* %p, i32 -6
   tail call void @llvm.wasm.store32.lane(i32* %s, <4 x i32> %v, i32 0)
@@ -681,7 +681,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store32_lane 0, 0
+; CHECK-NEXT:    v128.store32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i32* %p to i32
   %r = add nsw i32 %q, 24
@@ -698,7 +698,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store32_lane 0, 0
+; CHECK-NEXT:    v128.store32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr i32, i32* %p, i32 6
   tail call void @llvm.wasm.store32.lane(i32* %s, <4 x i32> %v, i32 0)
@@ -711,7 +711,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const 42
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store32_lane 0, 0
+; CHECK-NEXT:    v128.store32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = inttoptr i32 42 to i32*
   tail call void @llvm.wasm.store32.lane(i32* %s, <4 x i32> %v, i32 0)
@@ -724,7 +724,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const gv_i32
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store32_lane 0, 0
+; CHECK-NEXT:    v128.store32_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   tail call void @llvm.wasm.store32.lane(i32* @gv_i32, <4 x i32> %v, i32 0)
   ret void
@@ -740,7 +740,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load64_lane 0, 0
+; CHECK-NEXT:    v128.load64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %t = tail call <2 x i64> @llvm.wasm.load64.lane(i64* %p, <2 x i64> %v, i32 0)
   ret <2 x i64> %t
@@ -754,7 +754,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load64_lane 0, 0
+; CHECK-NEXT:    v128.load64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i64* %p to i32
   %r = add nuw i32 %q, 24
@@ -771,7 +771,7 @@
 ; CHECK-NEXT:    i32.const 48
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load64_lane 0, 0
+; CHECK-NEXT:    v128.load64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i64, i64* %p, i32 6
   %t = tail call <2 x i64> @llvm.wasm.load64.lane(i64* %s, <2 x i64> %v, i32 0)
@@ -786,7 +786,7 @@
 ; CHECK-NEXT:    i32.const -48
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load64_lane 0, 0
+; CHECK-NEXT:    v128.load64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i64, i64* %p, i32 -6
   %t = tail call <2 x i64> @llvm.wasm.load64.lane(i64* %s, <2 x i64> %v, i32 0)
@@ -801,7 +801,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load64_lane 0, 0
+; CHECK-NEXT:    v128.load64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i64* %p to i32
   %r = add nsw i32 %q, 24
@@ -818,7 +818,7 @@
 ; CHECK-NEXT:    i32.const 48
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 1
-; CHECK-NEXT:    v128.load64_lane 0, 0
+; CHECK-NEXT:    v128.load64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr i64, i64* %p, i32 6
   %t = tail call <2 x i64> @llvm.wasm.load64.lane(i64* %s, <2 x i64> %v, i32 0)
@@ -831,7 +831,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const 42
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.load64_lane 0, 0
+; CHECK-NEXT:    v128.load64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = inttoptr i32 42 to i64*
   %t = tail call <2 x i64> @llvm.wasm.load64.lane(i64* %s, <2 x i64> %v, i32 0)
@@ -845,7 +845,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const gv_i64
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.load64_lane 0, 0
+; CHECK-NEXT:    v128.load64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %t = tail call <2 x i64> @llvm.wasm.load64.lane(i64* @gv_i64, <2 x i64> %v, i32 0)
   ret <2 x i64> %t
@@ -857,7 +857,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 1
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store64_lane 0, 0
+; CHECK-NEXT:    v128.store64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   tail call void @llvm.wasm.store64.lane(i64* %p, <2 x i64> %v, i32 0)
   ret void
@@ -871,7 +871,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store64_lane 0, 0
+; CHECK-NEXT:    v128.store64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i64* %p to i32
   %r = add nuw i32 %q, 24
@@ -888,7 +888,7 @@
 ; CHECK-NEXT:    i32.const 48
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store64_lane 0, 0
+; CHECK-NEXT:    v128.store64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i64, i64* %p, i32 6
   tail call void @llvm.wasm.store64.lane(i64* %s, <2 x i64> %v, i32 0)
@@ -903,7 +903,7 @@
 ; CHECK-NEXT:    i32.const -48
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store64_lane 0, 0
+; CHECK-NEXT:    v128.store64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i64, i64* %p, i32 -6
   tail call void @llvm.wasm.store64.lane(i64* %s, <2 x i64> %v, i32 0)
@@ -918,7 +918,7 @@
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store64_lane 0, 0
+; CHECK-NEXT:    v128.store64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i64* %p to i32
   %r = add nsw i32 %q, 24
@@ -935,7 +935,7 @@
 ; CHECK-NEXT:    i32.const 48
 ; CHECK-NEXT:    i32.add
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store64_lane 0, 0
+; CHECK-NEXT:    v128.store64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr i64, i64* %p, i32 6
   tail call void @llvm.wasm.store64.lane(i64* %s, <2 x i64> %v, i32 0)
@@ -948,7 +948,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const 42
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store64_lane 0, 0
+; CHECK-NEXT:    v128.store64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   %s = inttoptr i32 42 to i64*
   tail call void @llvm.wasm.store64.lane(i64* %s, <2 x i64> %v, i32 0)
@@ -961,7 +961,7 @@
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const gv_i64
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.store64_lane 0, 0
+; CHECK-NEXT:    v128.store64_lane 0:p2align=0, 0
 ; CHECK-NEXT:    # fallthrough-return
   tail call void @llvm.wasm.store64.lane(i64* @gv_i64, <2 x i64> %v, i32 0)
   ret void
diff --git a/llvm/test/CodeGen/WebAssembly/simd-load-zero-offset.ll b/llvm/test/CodeGen/WebAssembly/simd-load-zero-offset.ll
--- a/llvm/test/CodeGen/WebAssembly/simd-load-zero-offset.ll
+++ b/llvm/test/CodeGen/WebAssembly/simd-load-zero-offset.ll
@@ -18,7 +18,7 @@
 ; CHECK:         .functype load_zero_i32_no_offset (i32) -> (v128)
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.load32_zero 0
+; CHECK-NEXT:    v128.load32_zero 0:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %v = tail call <4 x i32> @llvm.wasm.load32.zero(i32* %p)
   ret <4 x i32> %v
@@ -29,7 +29,7 @@
 ; CHECK:         .functype load_zero_i32_with_folded_offset (i32) -> (v128)
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.load32_zero 24
+; CHECK-NEXT:    v128.load32_zero 24:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i32* %p to i32
   %r = add nuw i32 %q, 24
@@ -43,7 +43,7 @@
 ; CHECK:         .functype load_zero_i32_with_folded_gep_offset (i32) -> (v128)
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.load32_zero 24
+; CHECK-NEXT:    v128.load32_zero 24:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i32, i32* %p, i32 6
   %t = tail call <4 x i32> @llvm.wasm.load32.zero(i32* %s)
@@ -57,7 +57,7 @@
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    i32.const -24
 ; CHECK-NEXT:    i32.add
-; CHECK-NEXT:    v128.load32_zero 0
+; CHECK-NEXT:    v128.load32_zero 0:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i32, i32* %p, i32 -6
   %t = tail call <4 x i32> @llvm.wasm.load32.zero(i32* %s)
@@ -71,7 +71,7 @@
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
-; CHECK-NEXT:    v128.load32_zero 0
+; CHECK-NEXT:    v128.load32_zero 0:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i32* %p to i32
   %r = add nsw i32 %q, 24
@@ -87,7 +87,7 @@
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
-; CHECK-NEXT:    v128.load32_zero 0
+; CHECK-NEXT:    v128.load32_zero 0:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr i32, i32* %p, i32 6
   %t = tail call <4 x i32> @llvm.wasm.load32.zero(i32* %s)
@@ -99,7 +99,7 @@
 ; CHECK:         .functype load_zero_i32_from_numeric_address () -> (v128)
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const 0
-; CHECK-NEXT:    v128.load32_zero 42
+; CHECK-NEXT:    v128.load32_zero 42:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %s = inttoptr i32 42 to i32*
   %t = tail call <4 x i32> @llvm.wasm.load32.zero(i32* %s)
@@ -112,7 +112,7 @@
 ; CHECK:         .functype load_zero_i32_from_global_address () -> (v128)
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const 0
-; CHECK-NEXT:    v128.load32_zero gv_i32
+; CHECK-NEXT:    v128.load32_zero gv_i32:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %t = tail call <4 x i32> @llvm.wasm.load32.zero(i32* @gv_i32)
   ret <4 x i32> %t
@@ -127,7 +127,7 @@
 ; CHECK:         .functype load_zero_i64_no_offset (i32) -> (v128)
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.load64_zero 0
+; CHECK-NEXT:    v128.load64_zero 0:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %v = tail call <2 x i64> @llvm.wasm.load64.zero(i64* %p)
   ret <2 x i64> %v
@@ -138,7 +138,7 @@
 ; CHECK:         .functype load_zero_i64_with_folded_offset (i32) -> (v128)
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.load64_zero 24
+; CHECK-NEXT:    v128.load64_zero 24:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i64* %p to i32
   %r = add nuw i32 %q, 24
@@ -152,7 +152,7 @@
 ; CHECK:         .functype load_zero_i64_with_folded_gep_offset (i32) -> (v128)
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    local.get 0
-; CHECK-NEXT:    v128.load64_zero 48
+; CHECK-NEXT:    v128.load64_zero 48:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i64, i64* %p, i64 6
   %t = tail call <2 x i64> @llvm.wasm.load64.zero(i64* %s)
@@ -166,7 +166,7 @@
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    i32.const -48
 ; CHECK-NEXT:    i32.add
-; CHECK-NEXT:    v128.load64_zero 0
+; CHECK-NEXT:    v128.load64_zero 0:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr inbounds i64, i64* %p, i64 -6
   %t = tail call <2 x i64> @llvm.wasm.load64.zero(i64* %s)
@@ -180,7 +180,7 @@
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    i32.const 24
 ; CHECK-NEXT:    i32.add
-; CHECK-NEXT:    v128.load64_zero 0
+; CHECK-NEXT:    v128.load64_zero 0:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %q = ptrtoint i64* %p to i32
   %r = add nsw i32 %q, 24
@@ -196,7 +196,7 @@
 ; CHECK-NEXT:    local.get 0
 ; CHECK-NEXT:    i32.const 48
 ; CHECK-NEXT:    i32.add
-; CHECK-NEXT:    v128.load64_zero 0
+; CHECK-NEXT:    v128.load64_zero 0:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %s = getelementptr i64, i64* %p, i64 6
   %t = tail call <2 x i64> @llvm.wasm.load64.zero(i64* %s)
@@ -208,7 +208,7 @@
 ; CHECK:         .functype load_zero_i64_from_numeric_address () -> (v128)
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const 0
-; CHECK-NEXT:    v128.load64_zero 42
+; CHECK-NEXT:    v128.load64_zero 42:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %s = inttoptr i32 42 to i64*
   %t = tail call <2 x i64> @llvm.wasm.load64.zero(i64* %s)
@@ -221,7 +221,7 @@
 ; CHECK:         .functype load_zero_i64_from_global_address () -> (v128)
 ; CHECK-NEXT:  # %bb.0:
 ; CHECK-NEXT:    i32.const 0
-; CHECK-NEXT:    v128.load64_zero gv_i64
+; CHECK-NEXT:    v128.load64_zero gv_i64:p2align=0
 ; CHECK-NEXT:    # fallthrough-return
   %t = tail call <2 x i64> @llvm.wasm.load64.zero(i64* @gv_i64)
   ret <2 x i64> %t