From a3937b231db67c33b4f06e1a5a90a1168487bf21 Mon Sep 17 00:00:00 2001
From: Thomas Lively <tlively@google.com>
Date: Fri, 14 Sep 2018 21:21:42 +0000
Subject: [PATCH] [WebAssembly][NFC] Move SIMD encoding tests to dedicated file

Summary:
This change makes the tests more focused and avoids problematic
interactions between the testing modes and instruction encoding. This
change also allows the other tests to use less verbose output and
stricter checks.

Reviewers: aheejin, dschuff, aardappel

Subscribers: sbc100, jgravelle-google, sunfish, llvm-commits

Differential Revision: https://reviews.llvm.org/D52007

llvm-svn: 342287
---
 llvm/test/CodeGen/WebAssembly/simd-arith.ll       | 372 +++++-----
 llvm/test/CodeGen/WebAssembly/simd-comparisons.ll | 438 +++++------
 llvm/test/CodeGen/WebAssembly/simd-conversions.ll |   6 +-
 llvm/test/CodeGen/WebAssembly/simd-offset.ll      | 846 ++++++++++------------
 llvm/test/CodeGen/WebAssembly/simd.ll             | 430 +++++------
 llvm/test/MC/WebAssembly/simd-encodings.s         | 298 ++++++++
 6 files changed, 1281 insertions(+), 1109 deletions(-)
 create mode 100644 llvm/test/MC/WebAssembly/simd-encodings.s

diff --git a/llvm/test/CodeGen/WebAssembly/simd-arith.ll b/llvm/test/CodeGen/WebAssembly/simd-arith.ll
index 33fd76a..bfbefb1 100644
--- a/llvm/test/CodeGen/WebAssembly/simd-arith.ll
+++ b/llvm/test/CodeGen/WebAssembly/simd-arith.ll
@@ -1,9 +1,9 @@
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -wasm-enable-unimplemented-simd -mattr=+simd128 --show-mc-encoding | FileCheck %s --check-prefixes CHECK,SIMD128
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -wasm-enable-unimplemented-simd -mattr=+simd128 -fast-isel --show-mc-encoding | FileCheck %s --check-prefixes CHECK,SIMD128
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=+simd128 --show-mc-encoding | FileCheck %s --check-prefixes CHECK,SIMD128-VM
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=+simd128 -fast-isel --show-mc-encoding | FileCheck %s --check-prefixes CHECK,SIMD128-VM
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=-simd128 --show-mc-encoding | FileCheck %s --check-prefixes CHECK,NO-SIMD128
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=-simd128 -fast-isel --show-mc-encoding | FileCheck %s --check-prefixes CHECK,NO-SIMD128
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -wasm-enable-unimplemented-simd -mattr=+simd128 | FileCheck %s --check-prefixes CHECK,SIMD128
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -wasm-enable-unimplemented-simd -mattr=+simd128 -fast-isel | FileCheck %s --check-prefixes CHECK,SIMD128
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=+simd128 | FileCheck %s --check-prefixes CHECK,SIMD128-VM
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=+simd128 -fast-isel | FileCheck %s --check-prefixes CHECK,SIMD128-VM
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=-simd128 | FileCheck %s --check-prefixes CHECK,NO-SIMD128
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=-simd128 -fast-isel | FileCheck %s --check-prefixes CHECK,NO-SIMD128
 
 ; Test that basic SIMD128 arithmetic operations assemble as expected.
 
@@ -13,78 +13,78 @@ target triple = "wasm32-unknown-unknown"
 ; ==============================================================================
 ; 16 x i8
 ; ==============================================================================
-; CHECK-LABEL: add_v16i8
+; CHECK-LABEL: add_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.add $push0=, $0, $1 # encoding: [0xfd,0x18]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.add $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @add_v16i8(<16 x i8> %x, <16 x i8> %y) {
   %a = add <16 x i8> %x, %y
   ret <16 x i8> %a
 }
 
-; CHECK-LABEL: sub_v16i8
+; CHECK-LABEL: sub_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.sub $push0=, $0, $1 # encoding: [0xfd,0x1c]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.sub $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @sub_v16i8(<16 x i8> %x, <16 x i8> %y) {
   %a = sub <16 x i8> %x, %y
   ret <16 x i8> %a
 }
 
-; CHECK-LABEL: mul_v16i8
+; CHECK-LABEL: mul_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.mul $push0=, $0, $1 # encoding: [0xfd,0x20]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.mul $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @mul_v16i8(<16 x i8> %x, <16 x i8> %y) {
   %a = mul <16 x i8> %x, %y
   ret <16 x i8> %a
 }
 
-; CHECK-LABEL: and_v16i8
+; CHECK-LABEL: and_v16i8:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.and $push0=, $0, $1 # encoding: [0xfd,0x3b]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.and $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @and_v16i8(<16 x i8> %x, <16 x i8> %y) {
   %a = and <16 x i8> %x, %y
   ret <16 x i8> %a
 }
 
-; CHECK-LABEL: or_v16i8
+; CHECK-LABEL: or_v16i8:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.or $push0=, $0, $1 # encoding: [0xfd,0x3c]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.or $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @or_v16i8(<16 x i8> %x, <16 x i8> %y) {
   %a = or <16 x i8> %x, %y
   ret <16 x i8> %a
 }
 
-; CHECK-LABEL: xor_v16i8
+; CHECK-LABEL: xor_v16i8:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.xor $push0=, $0, $1 # encoding: [0xfd,0x3d]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.xor $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @xor_v16i8(<16 x i8> %x, <16 x i8> %y) {
   %a = xor <16 x i8> %x, %y
   ret <16 x i8> %a
 }
 
-; CHECK-LABEL: not_v16i8
+; CHECK-LABEL: not_v16i8:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.not $push0=, $0 # encoding: [0xfd,0x3e]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.not $push0=, $0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @not_v16i8(<16 x i8> %x) {
   %a = xor <16 x i8> %x, <i8 -1, i8 -1, i8 -1, i8 -1,
                           i8 -1, i8 -1, i8 -1, i8 -1,
@@ -96,78 +96,78 @@ define <16 x i8> @not_v16i8(<16 x i8> %x) {
 ; ==============================================================================
 ; 8 x i16
 ; ==============================================================================
-; CHECK-LABEL: add_v8i16
+; CHECK-LABEL: add_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.add $push0=, $0, $1 # encoding: [0xfd,0x19]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.add $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @add_v8i16(<8 x i16> %x, <8 x i16> %y) {
   %a = add <8 x i16> %x, %y
   ret <8 x i16> %a
 }
 
-; CHECK-LABEL: sub_v8i16
+; CHECK-LABEL: sub_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.sub $push0=, $0, $1 # encoding: [0xfd,0x1d]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.sub $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @sub_v8i16(<8 x i16> %x, <8 x i16> %y) {
   %a = sub <8 x i16> %x, %y
   ret <8 x i16> %a
 }
 
-; CHECK-LABEL: mul_v8i16
+; CHECK-LABEL: mul_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.mul $push0=, $0, $1 # encoding: [0xfd,0x21]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.mul $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @mul_v8i16(<8 x i16> %x, <8 x i16> %y) {
   %a = mul <8 x i16> %x, %y
   ret <8 x i16> %a
 }
 
-; CHECK-LABEL: and_v8i16
+; CHECK-LABEL: and_v8i16:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.and $push0=, $0, $1 # encoding: [0xfd,0x3b]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.and $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @and_v8i16(<8 x i16> %x, <8 x i16> %y) {
   %a = and <8 x i16> %x, %y
   ret <8 x i16> %a
 }
 
-; CHECK-LABEL: or_v8i16
+; CHECK-LABEL: or_v8i16:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.or $push0=, $0, $1 # encoding: [0xfd,0x3c]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.or $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @or_v8i16(<8 x i16> %x, <8 x i16> %y) {
   %a = or <8 x i16> %x, %y
   ret <8 x i16> %a
 }
 
-; CHECK-LABEL: xor_v8i16
+; CHECK-LABEL: xor_v8i16:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.xor $push0=, $0, $1 # encoding: [0xfd,0x3d]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.xor $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @xor_v8i16(<8 x i16> %x, <8 x i16> %y) {
   %a = xor <8 x i16> %x, %y
   ret <8 x i16> %a
 }
 
-; CHECK-LABEL: not_v8i16
+; CHECK-LABEL: not_v8i16:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.not $push0=, $0 # encoding: [0xfd,0x3e]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.not $push0=, $0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @not_v8i16(<8 x i16> %x) {
   %a = xor <8 x i16> %x, <i16 -1, i16 -1, i16 -1, i16 -1,
                           i16 -1, i16 -1, i16 -1, i16 -1>
@@ -177,78 +177,78 @@ define <8 x i16> @not_v8i16(<8 x i16> %x) {
 ; ==============================================================================
 ; 4 x i32
 ; ==============================================================================
-; CHECK-LABEL: add_v4i32
+; CHECK-LABEL: add_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.add $push0=, $0, $1 # encoding: [0xfd,0x1a]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.add $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @add_v4i32(<4 x i32> %x, <4 x i32> %y) {
   %a = add <4 x i32> %x, %y
   ret <4 x i32> %a
 }
 
-; CHECK-LABEL: sub_v4i32
+; CHECK-LABEL: sub_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.sub $push0=, $0, $1 # encoding: [0xfd,0x1e]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.sub $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @sub_v4i32(<4 x i32> %x, <4 x i32> %y) {
   %a = sub <4 x i32> %x, %y
   ret <4 x i32> %a
 }
 
-; CHECK-LABEL: mul_v4i32
+; CHECK-LABEL: mul_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.mul $push0=, $0, $1 # encoding: [0xfd,0x22]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.mul $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @mul_v4i32(<4 x i32> %x, <4 x i32> %y) {
   %a = mul <4 x i32> %x, %y
   ret <4 x i32> %a
 }
 
-; CHECK-LABEL: and_v4i32
+; CHECK-LABEL: and_v4i32:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.and $push0=, $0, $1 # encoding: [0xfd,0x3b]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.and $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @and_v4i32(<4 x i32> %x, <4 x i32> %y) {
   %a = and <4 x i32> %x, %y
   ret <4 x i32> %a
 }
 
-; CHECK-LABEL: or_v4i32
+; CHECK-LABEL: or_v4i32:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.or $push0=, $0, $1 # encoding: [0xfd,0x3c]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.or $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @or_v4i32(<4 x i32> %x, <4 x i32> %y) {
   %a = or <4 x i32> %x, %y
   ret <4 x i32> %a
 }
 
-; CHECK-LABEL: xor_v4i32
+; CHECK-LABEL: xor_v4i32:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.xor $push0=, $0, $1 # encoding: [0xfd,0x3d]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.xor $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @xor_v4i32(<4 x i32> %x, <4 x i32> %y) {
   %a = xor <4 x i32> %x, %y
   ret <4 x i32> %a
 }
 
-; CHECK-LABEL: not_v4i32
+; CHECK-LABEL: not_v4i32:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.not $push0=, $0 # encoding: [0xfd,0x3e]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.not $push0=, $0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @not_v4i32(<4 x i32> %x) {
   %a = xor <4 x i32> %x, <i32 -1, i32 -1, i32 -1, i32 -1>
   ret <4 x i32> %a
@@ -257,32 +257,32 @@ define <4 x i32> @not_v4i32(<4 x i32> %x) {
 ; ==============================================================================
 ; 2 x i64
 ; ==============================================================================
-; CHECK-LABEL: add_v2i64
+; CHECK-LABEL: add_v2i64:
 ; NO-SIMD128-NOT: i64x2
 ; SIMD128-VM-NOT: i64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i64x2.add $push0=, $0, $1 # encoding: [0xfd,0x1b]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i64x2.add $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i64> @add_v2i64(<2 x i64> %x, <2 x i64> %y) {
   %a = add <2 x i64> %x, %y
   ret <2 x i64> %a
 }
 
-; CHECK-LABEL: sub_v2i64
+; CHECK-LABEL: sub_v2i64:
 ; NO-SIMD128-NOT: i64x2
 ; SIMD128-VM-NOT: i64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i64x2.sub $push0=, $0, $1 # encoding: [0xfd,0x1f]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i64x2.sub $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i64> @sub_v2i64(<2 x i64> %x, <2 x i64> %y) {
   %a = sub <2 x i64> %x, %y
   ret <2 x i64> %a
 }
 
 ; v2i64.mul is not in spec
-; CHECK-LABEL: mul_v2i64
+; CHECK-LABEL: mul_v2i64:
 ; NO-SIMD128-NOT: i64x2
 ; SIMD128-VM-NOT: i64x2
 ; SIMD128-NOT: i64x2.mul
@@ -293,49 +293,49 @@ define <2 x i64> @mul_v2i64(<2 x i64> %x, <2 x i64> %y) {
   ret <2 x i64> %a
 }
 
-; CHECK-LABEL: and_v2i64
+; CHECK-LABEL: and_v2i64:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.and $push0=, $0, $1 # encoding: [0xfd,0x3b]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.and $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i64> @and_v2i64(<2 x i64> %x, <2 x i64> %y) {
   %a = and <2 x i64> %x, %y
   ret <2 x i64> %a
 }
 
-; CHECK-LABEL: or_v2i64
+; CHECK-LABEL: or_v2i64:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.or $push0=, $0, $1 # encoding: [0xfd,0x3c]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.or $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i64> @or_v2i64(<2 x i64> %x, <2 x i64> %y) {
   %a = or <2 x i64> %x, %y
   ret <2 x i64> %a
 }
 
-; CHECK-LABEL: xor_v2i64
+; CHECK-LABEL: xor_v2i64:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.xor $push0=, $0, $1 # encoding: [0xfd,0x3d]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.xor $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i64> @xor_v2i64(<2 x i64> %x, <2 x i64> %y) {
   %a = xor <2 x i64> %x, %y
   ret <2 x i64> %a
 }
 
-; CHECK-LABEL: not_v2i64
+; CHECK-LABEL: not_v2i64:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.not $push0=, $0 # encoding: [0xfd,0x3e]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.not $push0=, $0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i64> @not_v2i64(<2 x i64> %x) {
   %a = xor <2 x i64> %x, <i64 -1, i64 -1>
   ret <2 x i64> %a
@@ -344,45 +344,45 @@ define <2 x i64> @not_v2i64(<2 x i64> %x) {
 ; ==============================================================================
 ; 4 x float
 ; ==============================================================================
-; CHECK-LABEL: add_v4f32
+; CHECK-LABEL: add_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.add $push0=, $0, $1 # encoding: [0xfd,0x7a]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.add $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x float> @add_v4f32(<4 x float> %x, <4 x float> %y) {
   %a = fadd <4 x float> %x, %y
   ret <4 x float> %a
 }
 
-; CHECK-LABEL: sub_v4f32
+; CHECK-LABEL: sub_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.sub $push0=, $0, $1 # encoding: [0xfd,0x7c]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.sub $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x float> @sub_v4f32(<4 x float> %x, <4 x float> %y) {
   %a = fsub <4 x float> %x, %y
   ret <4 x float> %a
 }
 
-; CHECK-LABEL: div_v4f32
+; CHECK-LABEL: div_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.div $push0=, $0, $1 # encoding: [0xfd,0x7e]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.div $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x float> @div_v4f32(<4 x float> %x, <4 x float> %y) {
   %a = fdiv <4 x float> %x, %y
   ret <4 x float> %a
 }
 
-; CHECK-LABEL: mul_v4f32
+; CHECK-LABEL: mul_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.mul $push0=, $0, $1 # encoding: [0xfd,0x80]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.mul $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x float> @mul_v4f32(<4 x float> %x, <4 x float> %y) {
   %a = fmul <4 x float> %x, %y
   ret <4 x float> %a
@@ -391,49 +391,49 @@ define <4 x float> @mul_v4f32(<4 x float> %x, <4 x float> %y) {
 ; ==============================================================================
 ; 2 x double
 ; ==============================================================================
-; CHECK-LABEL: add_v2f64
+; CHECK-LABEL: add_v2f64:
 ; NO-SIMD128-NOT: f64x2
-; SIMD129-VM-NOT: f62x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.add $push0=, $0, $1 # encoding: [0xfd,0x7b]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-VM-NOT: f62x2
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.add $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x double> @add_v2f64(<2 x double> %x, <2 x double> %y) {
   %a = fadd <2 x double> %x, %y
   ret <2 x double> %a
 }
 
-; CHECK-LABEL: sub_v2f64
+; CHECK-LABEL: sub_v2f64:
 ; NO-SIMD128-NOT: f64x2
-; SIMD129-VM-NOT: f62x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.sub $push0=, $0, $1 # encoding: [0xfd,0x7d]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-VM-NOT: f62x2
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.sub $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x double> @sub_v2f64(<2 x double> %x, <2 x double> %y) {
   %a = fsub <2 x double> %x, %y
   ret <2 x double> %a
 }
 
-; CHECK-LABEL: div_v2f64
+; CHECK-LABEL: div_v2f64:
 ; NO-SIMD128-NOT: f64x2
-; SIMD129-VM-NOT: f62x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.div $push0=, $0, $1 # encoding: [0xfd,0x7f]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-VM-NOT: f62x2
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.div $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x double> @div_v2f64(<2 x double> %x, <2 x double> %y) {
   %a = fdiv <2 x double> %x, %y
   ret <2 x double> %a
 }
 
-; CHECK-LABEL: mul_v2f64
+; CHECK-LABEL: mul_v2f64:
 ; NO-SIMD128-NOT: f64x2
-; SIMD129-VM-NOT: f62x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.mul $push0=, $0, $1 # encoding: [0xfd,0x81]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-VM-NOT: f62x2
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.mul $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x double> @mul_v2f64(<2 x double> %x, <2 x double> %y) {
   %a = fmul <2 x double> %x, %y
   ret <2 x double> %a
diff --git a/llvm/test/CodeGen/WebAssembly/simd-comparisons.ll b/llvm/test/CodeGen/WebAssembly/simd-comparisons.ll
index 9d2a968..862bf21 100644
--- a/llvm/test/CodeGen/WebAssembly/simd-comparisons.ll
+++ b/llvm/test/CodeGen/WebAssembly/simd-comparisons.ll
@@ -1,6 +1,6 @@
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -wasm-enable-unimplemented-simd -mattr=+simd128,+sign-ext --show-mc-encoding | FileCheck %s --check-prefixes CHECK,SIMD128
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -mattr=+simd128,+sign-ext --show-mc-encoding | FileCheck %s --check-prefixes CHECK,SIMD128-VM
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -mattr=-simd128,+sign-ext --show-mc-encoding | FileCheck %s --check-prefixes CHECK,NO-SIMD128
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -wasm-enable-unimplemented-simd -mattr=+simd128,+sign-ext --show-mc-encoding | FileCheck %s --check-prefixes CHECK,SIMD128
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -mattr=+simd128,+sign-ext --show-mc-encoding | FileCheck %s --check-prefixes CHECK,SIMD128-VM
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -mattr=-simd128,+sign-ext --show-mc-encoding | FileCheck %s --check-prefixes CHECK,NO-SIMD128
 
 ; Test SIMD comparison operators
 
@@ -9,10 +9,10 @@ target triple = "wasm32-unknown-unknown"
 
 ; CHECK-LABEL: compare_eq_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.eq $push0=, $0, $1 # encoding: [0xfd,0x48]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.eq $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i1> @compare_eq_v16i8 (<16 x i8> %x, <16 x i8> %y) {
   %res = icmp eq <16 x i8> %x, %y
   ret <16 x i1> %res
@@ -20,10 +20,10 @@ define <16 x i1> @compare_eq_v16i8 (<16 x i8> %x, <16 x i8> %y) {
 
 ; CHECK-LABEL: compare_ne_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.ne $push0=, $0, $1 # encoding: [0xfd,0x4d]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.ne $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i1> @compare_ne_v16i8 (<16 x i8> %x, <16 x i8> %y) {
   %res = icmp ne <16 x i8> %x, %y
   ret <16 x i1> %res
@@ -31,10 +31,10 @@ define <16 x i1> @compare_ne_v16i8 (<16 x i8> %x, <16 x i8> %y) {
 
 ; CHECK-LABEL: compare_slt_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.lt_s $push0=, $0, $1 # encoding: [0xfd,0x52]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.lt_s $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i1> @compare_slt_v16i8 (<16 x i8> %x, <16 x i8> %y) {
   %res = icmp slt <16 x i8> %x, %y
   ret <16 x i1> %res
@@ -42,10 +42,10 @@ define <16 x i1> @compare_slt_v16i8 (<16 x i8> %x, <16 x i8> %y) {
 
 ; CHECK-LABEL: compare_ult_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.lt_u $push0=, $0, $1 # encoding: [0xfd,0x53]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.lt_u $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i1> @compare_ult_v16i8 (<16 x i8> %x, <16 x i8> %y) {
   %res = icmp ult <16 x i8> %x, %y
   ret <16 x i1> %res
@@ -53,10 +53,10 @@ define <16 x i1> @compare_ult_v16i8 (<16 x i8> %x, <16 x i8> %y) {
 
 ; CHECK-LABEL: compare_sle_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.le_s $push0=, $0, $1 # encoding: [0xfd,0x5a]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.le_s $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i1> @compare_sle_v16i8 (<16 x i8> %x, <16 x i8> %y) {
   %res = icmp sle <16 x i8> %x, %y
   ret <16 x i1> %res
@@ -64,10 +64,10 @@ define <16 x i1> @compare_sle_v16i8 (<16 x i8> %x, <16 x i8> %y) {
 
 ; CHECK-LABEL: compare_ule_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.le_u $push0=, $0, $1 # encoding: [0xfd,0x5b]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.le_u $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i1> @compare_ule_v16i8 (<16 x i8> %x, <16 x i8> %y) {
   %res = icmp ule <16 x i8> %x, %y
   ret <16 x i1> %res
@@ -75,10 +75,10 @@ define <16 x i1> @compare_ule_v16i8 (<16 x i8> %x, <16 x i8> %y) {
 
 ; CHECK-LABEL: compare_sgt_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.gt_s $push0=, $0, $1 # encoding: [0xfd,0x62]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.gt_s $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i1> @compare_sgt_v16i8 (<16 x i8> %x, <16 x i8> %y) {
   %res = icmp sgt <16 x i8> %x, %y
   ret <16 x i1> %res
@@ -86,10 +86,10 @@ define <16 x i1> @compare_sgt_v16i8 (<16 x i8> %x, <16 x i8> %y) {
 
 ; CHECK-LABEL: compare_ugt_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.gt_u $push0=, $0, $1 # encoding: [0xfd,0x63]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.gt_u $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i1> @compare_ugt_v16i8 (<16 x i8> %x, <16 x i8> %y) {
   %res = icmp ugt <16 x i8> %x, %y
   ret <16 x i1> %res
@@ -97,10 +97,10 @@ define <16 x i1> @compare_ugt_v16i8 (<16 x i8> %x, <16 x i8> %y) {
 
 ; CHECK-LABEL: compare_sge_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.ge_s $push0=, $0, $1 # encoding: [0xfd,0x6a]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.ge_s $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i1> @compare_sge_v16i8 (<16 x i8> %x, <16 x i8> %y) {
   %res = icmp sge <16 x i8> %x, %y
   ret <16 x i1> %res
@@ -108,10 +108,10 @@ define <16 x i1> @compare_sge_v16i8 (<16 x i8> %x, <16 x i8> %y) {
 
 ; CHECK-LABEL: compare_uge_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.ge_u $push0=, $0, $1 # encoding: [0xfd,0x6b]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.ge_u $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i1> @compare_uge_v16i8 (<16 x i8> %x, <16 x i8> %y) {
   %res = icmp uge <16 x i8> %x, %y
   ret <16 x i1> %res
@@ -119,10 +119,10 @@ define <16 x i1> @compare_uge_v16i8 (<16 x i8> %x, <16 x i8> %y) {
 
 ; CHECK-LABEL: compare_eq_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.eq $push0=, $0, $1 # encoding: [0xfd,0x49]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.eq $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i1> @compare_eq_v8i16 (<8 x i16> %x, <8 x i16> %y) {
   %res = icmp eq <8 x i16> %x, %y
   ret <8 x i1> %res
@@ -130,10 +130,10 @@ define <8 x i1> @compare_eq_v8i16 (<8 x i16> %x, <8 x i16> %y) {
 
 ; CHECK-LABEL: compare_ne_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.ne $push0=, $0, $1 # encoding: [0xfd,0x4e]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.ne $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i1> @compare_ne_v8i16 (<8 x i16> %x, <8 x i16> %y) {
   %res = icmp ne <8 x i16> %x, %y
   ret <8 x i1> %res
@@ -141,10 +141,10 @@ define <8 x i1> @compare_ne_v8i16 (<8 x i16> %x, <8 x i16> %y) {
 
 ; CHECK-LABEL: compare_slt_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.lt_s $push0=, $0, $1 # encoding: [0xfd,0x54]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.lt_s $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i1> @compare_slt_v8i16 (<8 x i16> %x, <8 x i16> %y) {
   %res = icmp slt <8 x i16> %x, %y
   ret <8 x i1> %res
@@ -152,10 +152,10 @@ define <8 x i1> @compare_slt_v8i16 (<8 x i16> %x, <8 x i16> %y) {
 
 ; CHECK-LABEL: compare_ult_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.lt_u $push0=, $0, $1 # encoding: [0xfd,0x55]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.lt_u $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i1> @compare_ult_v8i16 (<8 x i16> %x, <8 x i16> %y) {
   %res = icmp ult <8 x i16> %x, %y
   ret <8 x i1> %res
@@ -163,10 +163,10 @@ define <8 x i1> @compare_ult_v8i16 (<8 x i16> %x, <8 x i16> %y) {
 
 ; CHECK-LABEL: compare_sle_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.le_s $push0=, $0, $1 # encoding: [0xfd,0x5c]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.le_s $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i1> @compare_sle_v8i16 (<8 x i16> %x, <8 x i16> %y) {
   %res = icmp sle <8 x i16> %x, %y
   ret <8 x i1> %res
@@ -174,10 +174,10 @@ define <8 x i1> @compare_sle_v8i16 (<8 x i16> %x, <8 x i16> %y) {
 
 ; CHECK-LABEL: compare_ule_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.le_u $push0=, $0, $1 # encoding: [0xfd,0x5d]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.le_u $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i1> @compare_ule_v8i16 (<8 x i16> %x, <8 x i16> %y) {
   %res = icmp ule <8 x i16> %x, %y
   ret <8 x i1> %res
@@ -185,10 +185,10 @@ define <8 x i1> @compare_ule_v8i16 (<8 x i16> %x, <8 x i16> %y) {
 
 ; CHECK-LABEL: compare_sgt_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.gt_s $push0=, $0, $1 # encoding: [0xfd,0x64]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.gt_s $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i1> @compare_sgt_v8i16 (<8 x i16> %x, <8 x i16> %y) {
   %res = icmp sgt <8 x i16> %x, %y
   ret <8 x i1> %res
@@ -196,10 +196,10 @@ define <8 x i1> @compare_sgt_v8i16 (<8 x i16> %x, <8 x i16> %y) {
 
 ; CHECK-LABEL: compare_ugt_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.gt_u $push0=, $0, $1 # encoding: [0xfd,0x65]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.gt_u $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i1> @compare_ugt_v8i16 (<8 x i16> %x, <8 x i16> %y) {
   %res = icmp ugt <8 x i16> %x, %y
   ret <8 x i1> %res
@@ -207,10 +207,10 @@ define <8 x i1> @compare_ugt_v8i16 (<8 x i16> %x, <8 x i16> %y) {
 
 ; CHECK-LABEL: compare_sge_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.ge_s $push0=, $0, $1 # encoding: [0xfd,0x6c]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.ge_s $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i1> @compare_sge_v8i16 (<8 x i16> %x, <8 x i16> %y) {
   %res = icmp sge <8 x i16> %x, %y
   ret <8 x i1> %res
@@ -218,10 +218,10 @@ define <8 x i1> @compare_sge_v8i16 (<8 x i16> %x, <8 x i16> %y) {
 
 ; CHECK-LABEL: compare_uge_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.ge_u $push0=, $0, $1 # encoding: [0xfd,0x6d]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.ge_u $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i1> @compare_uge_v8i16 (<8 x i16> %x, <8 x i16> %y) {
   %res = icmp uge <8 x i16> %x, %y
   ret <8 x i1> %res
@@ -229,10 +229,10 @@ define <8 x i1> @compare_uge_v8i16 (<8 x i16> %x, <8 x i16> %y) {
 
 ; CHECK-LABEL: compare_eq_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.eq $push0=, $0, $1 # encoding: [0xfd,0x4a]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.eq $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_eq_v4i32 (<4 x i32> %x, <4 x i32> %y) {
   %res = icmp eq <4 x i32> %x, %y
   ret <4 x i1> %res
@@ -240,10 +240,10 @@ define <4 x i1> @compare_eq_v4i32 (<4 x i32> %x, <4 x i32> %y) {
 
 ; CHECK-LABEL: compare_ne_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.ne $push0=, $0, $1 # encoding: [0xfd,0x4f]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.ne $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_ne_v4i32 (<4 x i32> %x, <4 x i32> %y) {
   %res = icmp ne <4 x i32> %x, %y
   ret <4 x i1> %res
@@ -251,10 +251,10 @@ define <4 x i1> @compare_ne_v4i32 (<4 x i32> %x, <4 x i32> %y) {
 
 ; CHECK-LABEL: compare_slt_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.lt_s $push0=, $0, $1 # encoding: [0xfd,0x56]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.lt_s $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_slt_v4i32 (<4 x i32> %x, <4 x i32> %y) {
   %res = icmp slt <4 x i32> %x, %y
   ret <4 x i1> %res
@@ -262,10 +262,10 @@ define <4 x i1> @compare_slt_v4i32 (<4 x i32> %x, <4 x i32> %y) {
 
 ; CHECK-LABEL: compare_ult_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.lt_u $push0=, $0, $1 # encoding: [0xfd,0x57]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.lt_u $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_ult_v4i32 (<4 x i32> %x, <4 x i32> %y) {
   %res = icmp ult <4 x i32> %x, %y
   ret <4 x i1> %res
@@ -273,10 +273,10 @@ define <4 x i1> @compare_ult_v4i32 (<4 x i32> %x, <4 x i32> %y) {
 
 ; CHECK-LABEL: compare_sle_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.le_s $push0=, $0, $1 # encoding: [0xfd,0x5e]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.le_s $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_sle_v4i32 (<4 x i32> %x, <4 x i32> %y) {
   %res = icmp sle <4 x i32> %x, %y
   ret <4 x i1> %res
@@ -284,10 +284,10 @@ define <4 x i1> @compare_sle_v4i32 (<4 x i32> %x, <4 x i32> %y) {
 
 ; CHECK-LABEL: compare_ule_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.le_u $push0=, $0, $1 # encoding: [0xfd,0x5f]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.le_u $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_ule_v4i32 (<4 x i32> %x, <4 x i32> %y) {
   %res = icmp ule <4 x i32> %x, %y
   ret <4 x i1> %res
@@ -295,10 +295,10 @@ define <4 x i1> @compare_ule_v4i32 (<4 x i32> %x, <4 x i32> %y) {
 
 ; CHECK-LABEL: compare_sgt_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.gt_s $push0=, $0, $1 # encoding: [0xfd,0x66]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.gt_s $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_sgt_v4i32 (<4 x i32> %x, <4 x i32> %y) {
   %res = icmp sgt <4 x i32> %x, %y
   ret <4 x i1> %res
@@ -306,10 +306,10 @@ define <4 x i1> @compare_sgt_v4i32 (<4 x i32> %x, <4 x i32> %y) {
 
 ; CHECK-LABEL: compare_ugt_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.gt_u $push0=, $0, $1 # encoding: [0xfd,0x67]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.gt_u $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_ugt_v4i32 (<4 x i32> %x, <4 x i32> %y) {
   %res = icmp ugt <4 x i32> %x, %y
   ret <4 x i1> %res
@@ -317,10 +317,10 @@ define <4 x i1> @compare_ugt_v4i32 (<4 x i32> %x, <4 x i32> %y) {
 
 ; CHECK-LABEL: compare_sge_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.ge_s $push0=, $0, $1 # encoding: [0xfd,0x6e]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.ge_s $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_sge_v4i32 (<4 x i32> %x, <4 x i32> %y) {
   %res = icmp sge <4 x i32> %x, %y
   ret <4 x i1> %res
@@ -328,10 +328,10 @@ define <4 x i1> @compare_sge_v4i32 (<4 x i32> %x, <4 x i32> %y) {
 
 ; CHECK-LABEL: compare_uge_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.ge_u $push0=, $0, $1 # encoding: [0xfd,0x6f]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.ge_u $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_uge_v4i32 (<4 x i32> %x, <4 x i32> %y) {
   %res = icmp uge <4 x i32> %x, %y
   ret <4 x i1> %res
@@ -339,10 +339,10 @@ define <4 x i1> @compare_uge_v4i32 (<4 x i32> %x, <4 x i32> %y) {
 
 ; CHECK-LABEL: compare_oeq_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.eq $push0=, $0, $1 # encoding: [0xfd,0x4b]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.eq $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_oeq_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp oeq <4 x float> %x, %y
   ret <4 x i1> %res
@@ -350,10 +350,10 @@ define <4 x i1> @compare_oeq_v4f32 (<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: compare_ogt_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.gt $push0=, $0, $1 # encoding: [0xfd,0x68]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.gt $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_ogt_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp ogt <4 x float> %x, %y
   ret <4 x i1> %res
@@ -361,10 +361,10 @@ define <4 x i1> @compare_ogt_v4f32 (<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: compare_oge_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.ge $push0=, $0, $1 # encoding: [0xfd,0x70]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.ge $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_oge_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp oge <4 x float> %x, %y
   ret <4 x i1> %res
@@ -372,10 +372,10 @@ define <4 x i1> @compare_oge_v4f32 (<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: compare_olt_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.lt $push0=, $0, $1 # encoding: [0xfd,0x58]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.lt $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_olt_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp olt <4 x float> %x, %y
   ret <4 x i1> %res
@@ -383,10 +383,10 @@ define <4 x i1> @compare_olt_v4f32 (<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: compare_ole_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.le $push0=, $0, $1 # encoding: [0xfd,0x60]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.le $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_ole_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp ole <4 x float> %x, %y
   ret <4 x i1> %res
@@ -394,9 +394,9 @@ define <4 x i1> @compare_ole_v4f32 (<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: compare_one_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.ne
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.ne
 define <4 x i1> @compare_one_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp one <4 x float> %x, %y
   ret <4 x i1> %res
@@ -404,9 +404,9 @@ define <4 x i1> @compare_one_v4f32 (<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: compare_ord_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.eq
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.eq
 define <4 x i1> @compare_ord_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp ord <4 x float> %x, %y
   ret <4 x i1> %res
@@ -414,9 +414,9 @@ define <4 x i1> @compare_ord_v4f32 (<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: compare_ueq_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.eq
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.eq
 define <4 x i1> @compare_ueq_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp ueq <4 x float> %x, %y
   ret <4 x i1> %res
@@ -424,9 +424,9 @@ define <4 x i1> @compare_ueq_v4f32 (<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: compare_ugt_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.le
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.le
 define <4 x i1> @compare_ugt_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp ugt <4 x float> %x, %y
   ret <4 x i1> %res
@@ -434,9 +434,9 @@ define <4 x i1> @compare_ugt_v4f32 (<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: compare_uge_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.lt
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.lt
 define <4 x i1> @compare_uge_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp uge <4 x float> %x, %y
   ret <4 x i1> %res
@@ -444,9 +444,9 @@ define <4 x i1> @compare_uge_v4f32 (<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: compare_ult_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.ge
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.ge
 define <4 x i1> @compare_ult_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp ult <4 x float> %x, %y
   ret <4 x i1> %res
@@ -454,9 +454,9 @@ define <4 x i1> @compare_ult_v4f32 (<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: compare_ule_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.gt
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.gt
 define <4 x i1> @compare_ule_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp ule <4 x float> %x, %y
   ret <4 x i1> %res
@@ -464,10 +464,10 @@ define <4 x i1> @compare_ule_v4f32 (<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: compare_une_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.ne $push0=, $0, $1 # encoding: [0xfd,0x50]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.ne $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i1> @compare_une_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp une <4 x float> %x, %y
   ret <4 x i1> %res
@@ -475,9 +475,9 @@ define <4 x i1> @compare_une_v4f32 (<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: compare_uno_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.ne
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.ne
 define <4 x i1> @compare_uno_v4f32 (<4 x float> %x, <4 x float> %y) {
   %res = fcmp uno <4 x float> %x, %y
   ret <4 x i1> %res
@@ -486,10 +486,10 @@ define <4 x i1> @compare_uno_v4f32 (<4 x float> %x, <4 x float> %y) {
 ; CHECK-LABEL: compare_oeq_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.eq $push0=, $0, $1 # encoding: [0xfd,0x4c]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.eq $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i1> @compare_oeq_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp oeq <2 x double> %x, %y
   ret <2 x i1> %res
@@ -498,10 +498,10 @@ define <2 x i1> @compare_oeq_v2f64 (<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: compare_ogt_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.gt $push0=, $0, $1 # encoding: [0xfd,0x69]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.gt $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i1> @compare_ogt_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp ogt <2 x double> %x, %y
   ret <2 x i1> %res
@@ -510,10 +510,10 @@ define <2 x i1> @compare_ogt_v2f64 (<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: compare_oge_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.ge $push0=, $0, $1 # encoding: [0xfd,0x71]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.ge $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i1> @compare_oge_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp oge <2 x double> %x, %y
   ret <2 x i1> %res
@@ -522,10 +522,10 @@ define <2 x i1> @compare_oge_v2f64 (<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: compare_olt_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.lt $push0=, $0, $1 # encoding: [0xfd,0x59]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.lt $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i1> @compare_olt_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp olt <2 x double> %x, %y
   ret <2 x i1> %res
@@ -534,10 +534,10 @@ define <2 x i1> @compare_olt_v2f64 (<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: compare_ole_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.le $push0=, $0, $1 # encoding: [0xfd,0x61]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.le $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i1> @compare_ole_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp ole <2 x double> %x, %y
   ret <2 x i1> %res
@@ -546,9 +546,9 @@ define <2 x i1> @compare_ole_v2f64 (<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: compare_one_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.ne
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.ne
 define <2 x i1> @compare_one_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp one <2 x double> %x, %y
   ret <2 x i1> %res
@@ -557,9 +557,9 @@ define <2 x i1> @compare_one_v2f64 (<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: compare_ord_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.eq
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.eq
 define <2 x i1> @compare_ord_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp ord <2 x double> %x, %y
   ret <2 x i1> %res
@@ -568,9 +568,9 @@ define <2 x i1> @compare_ord_v2f64 (<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: compare_ueq_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.eq
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.eq
 define <2 x i1> @compare_ueq_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp ueq <2 x double> %x, %y
   ret <2 x i1> %res
@@ -579,9 +579,9 @@ define <2 x i1> @compare_ueq_v2f64 (<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: compare_ugt_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.le
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.le
 define <2 x i1> @compare_ugt_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp ugt <2 x double> %x, %y
   ret <2 x i1> %res
@@ -590,9 +590,9 @@ define <2 x i1> @compare_ugt_v2f64 (<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: compare_uge_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.lt
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.lt
 define <2 x i1> @compare_uge_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp uge <2 x double> %x, %y
   ret <2 x i1> %res
@@ -601,9 +601,9 @@ define <2 x i1> @compare_uge_v2f64 (<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: compare_ult_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.ge
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.ge
 define <2 x i1> @compare_ult_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp ult <2 x double> %x, %y
   ret <2 x i1> %res
@@ -612,9 +612,9 @@ define <2 x i1> @compare_ult_v2f64 (<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: compare_ule_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.gt
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.gt
 define <2 x i1> @compare_ule_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp ule <2 x double> %x, %y
   ret <2 x i1> %res
@@ -623,10 +623,10 @@ define <2 x i1> @compare_ule_v2f64 (<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: compare_une_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.ne $push0=, $0, $1 # encoding: [0xfd,0x51]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.ne $push0=, $0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i1> @compare_une_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp une <2 x double> %x, %y
   ret <2 x i1> %res
@@ -635,9 +635,9 @@ define <2 x i1> @compare_une_v2f64 (<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: compare_uno_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.ne
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.ne
 define <2 x i1> @compare_uno_v2f64 (<2 x double> %x, <2 x double> %y) {
   %res = fcmp uno <2 x double> %x, %y
   ret <2 x i1> %res
diff --git a/llvm/test/CodeGen/WebAssembly/simd-conversions.ll b/llvm/test/CodeGen/WebAssembly/simd-conversions.ll
index 72290d6..b36f519 100644
--- a/llvm/test/CodeGen/WebAssembly/simd-conversions.ll
+++ b/llvm/test/CodeGen/WebAssembly/simd-conversions.ll
@@ -1,6 +1,6 @@
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -wasm-enable-unimplemented-simd -mattr=+simd128,+sign-ext | FileCheck %s --check-prefixes CHECK,SIMD128
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -mattr=+simd128,+sign-ext | FileCheck %s --check-prefixes CHECK,SIMD128-VM
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -mattr=-simd128,+sign-ext | FileCheck %s --check-prefixes CHECK,NO-SIMD128
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -wasm-enable-unimplemented-simd -mattr=+simd128,+sign-ext | FileCheck %s --check-prefixes CHECK,SIMD128
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -mattr=+simd128,+sign-ext | FileCheck %s --check-prefixes CHECK,SIMD128-VM
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -mattr=-simd128,+sign-ext | FileCheck %s --check-prefixes CHECK,NO-SIMD128
 
 ; Test that bitcasts between vector types are lowered to zero instructions
 
diff --git a/llvm/test/CodeGen/WebAssembly/simd-offset.ll b/llvm/test/CodeGen/WebAssembly/simd-offset.ll
index fb78f66..dd8f3a1 100644
--- a/llvm/test/CodeGen/WebAssembly/simd-offset.ll
+++ b/llvm/test/CodeGen/WebAssembly/simd-offset.ll
@@ -1,6 +1,6 @@
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -wasm-enable-unimplemented-simd -mattr=+simd128,+sign-ext --show-mc-encoding | FileCheck %s --check-prefixes CHECK,SIMD128
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -mattr=+simd128,+sign-ext --show-mc-encoding | FileCheck %s --check-prefixes CHECK,SIMD128-VM
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -mattr=-simd128,+sign-ext --show-mc-encoding | FileCheck %s --check-prefixes CHECK,NO-SIMD128
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -wasm-enable-unimplemented-simd -mattr=+simd128,+sign-ext | FileCheck %s --check-prefixes CHECK,SIMD128
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -mattr=+simd128,+sign-ext | FileCheck %s --check-prefixes CHECK,SIMD128-VM
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-keep-registers -wasm-disable-explicit-locals -mattr=-simd128,+sign-ext | FileCheck %s --check-prefixes CHECK,NO-SIMD128
 
 ; Test SIMD loads and stores
 
@@ -12,11 +12,10 @@ target triple = "wasm32-unknown-unknown"
 ; ==============================================================================
 ; CHECK-LABEL: load_v16i8:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 0($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 0($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @load_v16i8(<16 x i8>* %p) {
   %v = load <16 x i8>, <16 x i8>* %p
   ret <16 x i8> %v
@@ -24,11 +23,10 @@ define <16 x i8> @load_v16i8(<16 x i8>* %p) {
 
 ; CHECK-LABEL: load_v16i8_with_folded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 16($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x10]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 16($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @load_v16i8_with_folded_offset(<16 x i8>* %p) {
   %q = ptrtoint <16 x i8>* %p to i32
   %r = add nuw i32 %q, 16
@@ -39,11 +37,10 @@ define <16 x i8> @load_v16i8_with_folded_offset(<16 x i8>* %p) {
 
 ; CHECK-LABEL: load_v16i8_with_folded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 16($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x10]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 16($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @load_v16i8_with_folded_gep_offset(<16 x i8>* %p) {
   %s = getelementptr inbounds <16 x i8>, <16 x i8>* %p, i32 1
   %v = load <16 x i8>, <16 x i8>* %s
@@ -52,13 +49,12 @@ define <16 x i8> @load_v16i8_with_folded_gep_offset(<16 x i8>* %p) {
 
 ; CHECK-LABEL: load_v16i8_with_unfolded_gep_negative_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <16 x i8> @load_v16i8_with_unfolded_gep_negative_offset(<16 x i8>* %p) {
   %s = getelementptr inbounds <16 x i8>, <16 x i8>* %p, i32 -1
   %v = load <16 x i8>, <16 x i8>* %s
@@ -67,13 +63,12 @@ define <16 x i8> @load_v16i8_with_unfolded_gep_negative_offset(<16 x i8>* %p) {
 
 ; CHECK-LABEL: load_v16i8_with_unfolded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <16 x i8> @load_v16i8_with_unfolded_offset(<16 x i8>* %p) {
   %q = ptrtoint <16 x i8>* %p to i32
   %r = add nsw i32 %q, 16
@@ -84,13 +79,12 @@ define <16 x i8> @load_v16i8_with_unfolded_offset(<16 x i8>* %p) {
 
 ; CHECK-LABEL: load_v16i8_with_unfolded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <16 x i8> @load_v16i8_with_unfolded_gep_offset(<16 x i8>* %p) {
   %s = getelementptr <16 x i8>, <16 x i8>* %p, i32 1
   %v = load <16 x i8>, <16 x i8>* %s
@@ -99,11 +93,10 @@ define <16 x i8> @load_v16i8_with_unfolded_gep_offset(<16 x i8>* %p) {
 
 ; CHECK-LABEL: load_v16i8_from_numeric_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.load $push1=, 32($pop0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x20]{{$}}
-; SIMD128: return $pop1 #
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.load $push1=, 32($pop0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 define <16 x i8> @load_v16i8_from_numeric_address() {
   %s = inttoptr i32 32 to <16 x i8>*
   %v = load <16 x i8>, <16 x i8>* %s
@@ -112,11 +105,10 @@ define <16 x i8> @load_v16i8_from_numeric_address() {
 
 ; CHECK-LABEL: load_v16i8_from_global_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.load $push1=, gv_v16i8($pop0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,
-; SIMD128: return $pop1 #
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.load $push1=, gv_v16i8($pop0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 @gv_v16i8 = global <16 x i8> <i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42>
 define <16 x i8> @load_v16i8_from_global_address() {
   %v = load <16 x i8>, <16 x i8>* @gv_v16i8
@@ -125,9 +117,8 @@ define <16 x i8> @load_v16i8_from_global_address() {
 
 ; CHECK-LABEL: store_v16i8:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 0($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 0($1):p2align=0, $0{{$}}
 define void @store_v16i8(<16 x i8> %v, <16 x i8>* %p) {
   store <16 x i8> %v , <16 x i8>* %p
   ret void
@@ -135,9 +126,8 @@ define void @store_v16i8(<16 x i8> %v, <16 x i8>* %p) {
 
 ; CHECK-LABEL: store_v16i8_with_folded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 16($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x10]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 16($1):p2align=0, $0{{$}}
 define void @store_v16i8_with_folded_offset(<16 x i8> %v, <16 x i8>* %p) {
   %q = ptrtoint <16 x i8>* %p to i32
   %r = add nuw i32 %q, 16
@@ -148,9 +138,8 @@ define void @store_v16i8_with_folded_offset(<16 x i8> %v, <16 x i8>* %p) {
 
 ; CHECK-LABEL: store_v16i8_with_folded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 16($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x10]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 16($1):p2align=0, $0{{$}}
 define void @store_v16i8_with_folded_gep_offset(<16 x i8> %v, <16 x i8>* %p) {
   %s = getelementptr inbounds <16 x i8>, <16 x i8>* %p, i32 1
   store <16 x i8> %v , <16 x i8>* %s
@@ -159,11 +148,10 @@ define void @store_v16i8_with_folded_gep_offset(<16 x i8> %v, <16 x i8>* %p) {
 
 ; CHECK-LABEL: store_v16i8_with_unfolded_gep_negative_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v16i8_with_unfolded_gep_negative_offset(<16 x i8> %v, <16 x i8>* %p) {
   %s = getelementptr inbounds <16 x i8>, <16 x i8>* %p, i32 -1
   store <16 x i8> %v , <16 x i8>* %s
@@ -172,11 +160,10 @@ define void @store_v16i8_with_unfolded_gep_negative_offset(<16 x i8> %v, <16 x i
 
 ; CHECK-LABEL: store_v16i8_with_unfolded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v16i8_with_unfolded_offset(<16 x i8> %v, <16 x i8>* %p) {
   %s = getelementptr inbounds <16 x i8>, <16 x i8>* %p, i32 -1
   store <16 x i8> %v , <16 x i8>* %s
@@ -185,11 +172,10 @@ define void @store_v16i8_with_unfolded_offset(<16 x i8> %v, <16 x i8>* %p) {
 
 ; CHECK-LABEL: store_v16i8_with_unfolded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v16i8_with_unfolded_gep_offset(<16 x i8> %v, <16 x i8>* %p) {
   %s = getelementptr <16 x i8>, <16 x i8>* %p, i32 1
   store <16 x i8> %v , <16 x i8>* %s
@@ -198,10 +184,9 @@ define void @store_v16i8_with_unfolded_gep_offset(<16 x i8> %v, <16 x i8>* %p) {
 
 ; CHECK-LABEL: store_v16i8_to_numeric_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.store 32($pop0):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x20]{{$}}
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.store 32($pop0):p2align=0, $0{{$}}
 define void @store_v16i8_to_numeric_address(<16 x i8> %v) {
   %s = inttoptr i32 32 to <16 x i8>*
   store <16 x i8> %v , <16 x i8>* %s
@@ -210,10 +195,9 @@ define void @store_v16i8_to_numeric_address(<16 x i8> %v) {
 
 ; CHECK-LABEL: store_v16i8_to_global_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.store gv_v16i8($pop0):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.store gv_v16i8($pop0):p2align=0, $0{{$}}
 define void @store_v16i8_to_global_address(<16 x i8> %v) {
   store <16 x i8> %v , <16 x i8>* @gv_v16i8
   ret void
@@ -224,11 +208,10 @@ define void @store_v16i8_to_global_address(<16 x i8> %v) {
 ; ==============================================================================
 ; CHECK-LABEL: load_v8i16:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 0($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 0($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @load_v8i16(<8 x i16>* %p) {
   %v = load <8 x i16>, <8 x i16>* %p
   ret <8 x i16> %v
@@ -236,11 +219,10 @@ define <8 x i16> @load_v8i16(<8 x i16>* %p) {
 
 ; CHECK-LABEL: load_v8i16_with_folded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 16($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x10]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 16($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @load_v8i16_with_folded_offset(<8 x i16>* %p) {
   %q = ptrtoint <8 x i16>* %p to i32
   %r = add nuw i32 %q, 16
@@ -251,11 +233,10 @@ define <8 x i16> @load_v8i16_with_folded_offset(<8 x i16>* %p) {
 
 ; CHECK-LABEL: load_v8i16_with_folded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 16($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x10]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 16($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @load_v8i16_with_folded_gep_offset(<8 x i16>* %p) {
   %s = getelementptr inbounds <8 x i16>, <8 x i16>* %p, i32 1
   %v = load <8 x i16>, <8 x i16>* %s
@@ -264,13 +245,12 @@ define <8 x i16> @load_v8i16_with_folded_gep_offset(<8 x i16>* %p) {
 
 ; CHECK-LABEL: load_v8i16_with_unfolded_gep_negative_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <8 x i16> @load_v8i16_with_unfolded_gep_negative_offset(<8 x i16>* %p) {
   %s = getelementptr inbounds <8 x i16>, <8 x i16>* %p, i32 -1
   %v = load <8 x i16>, <8 x i16>* %s
@@ -279,13 +259,12 @@ define <8 x i16> @load_v8i16_with_unfolded_gep_negative_offset(<8 x i16>* %p) {
 
 ; CHECK-LABEL: load_v8i16_with_unfolded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <8 x i16> @load_v8i16_with_unfolded_offset(<8 x i16>* %p) {
   %q = ptrtoint <8 x i16>* %p to i32
   %r = add nsw i32 %q, 16
@@ -296,13 +275,12 @@ define <8 x i16> @load_v8i16_with_unfolded_offset(<8 x i16>* %p) {
 
 ; CHECK-LABEL: load_v8i16_with_unfolded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <8 x i16> @load_v8i16_with_unfolded_gep_offset(<8 x i16>* %p) {
   %s = getelementptr <8 x i16>, <8 x i16>* %p, i32 1
   %v = load <8 x i16>, <8 x i16>* %s
@@ -311,11 +289,10 @@ define <8 x i16> @load_v8i16_with_unfolded_gep_offset(<8 x i16>* %p) {
 
 ; CHECK-LABEL: load_v8i16_from_numeric_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.load $push1=, 32($pop0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x20]{{$}}
-; SIMD128: return $pop1 #
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.load $push1=, 32($pop0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 define <8 x i16> @load_v8i16_from_numeric_address() {
   %s = inttoptr i32 32 to <8 x i16>*
   %v = load <8 x i16>, <8 x i16>* %s
@@ -324,11 +301,10 @@ define <8 x i16> @load_v8i16_from_numeric_address() {
 
 ; CHECK-LABEL: load_v8i16_from_global_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.load $push1=, gv_v8i16($pop0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,
-; SIMD128: return $pop1 #
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.load $push1=, gv_v8i16($pop0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 @gv_v8i16 = global <8 x i16> <i16 42, i16 42, i16 42, i16 42, i16 42, i16 42, i16 42, i16 42>
 define <8 x i16> @load_v8i16_from_global_address() {
   %v = load <8 x i16>, <8 x i16>* @gv_v8i16
@@ -337,9 +313,8 @@ define <8 x i16> @load_v8i16_from_global_address() {
 
 ; CHECK-LABEL: store_v8i16:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 0($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 0($1):p2align=0, $0{{$}}
 define void @store_v8i16(<8 x i16> %v, <8 x i16>* %p) {
   store <8 x i16> %v , <8 x i16>* %p
   ret void
@@ -347,9 +322,8 @@ define void @store_v8i16(<8 x i16> %v, <8 x i16>* %p) {
 
 ; CHECK-LABEL: store_v8i16_with_folded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 16($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x10]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 16($1):p2align=0, $0{{$}}
 define void @store_v8i16_with_folded_offset(<8 x i16> %v, <8 x i16>* %p) {
   %q = ptrtoint <8 x i16>* %p to i32
   %r = add nuw i32 %q, 16
@@ -360,9 +334,8 @@ define void @store_v8i16_with_folded_offset(<8 x i16> %v, <8 x i16>* %p) {
 
 ; CHECK-LABEL: store_v8i16_with_folded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 16($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x10]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 16($1):p2align=0, $0{{$}}
 define void @store_v8i16_with_folded_gep_offset(<8 x i16> %v, <8 x i16>* %p) {
   %s = getelementptr inbounds <8 x i16>, <8 x i16>* %p, i32 1
   store <8 x i16> %v , <8 x i16>* %s
@@ -371,11 +344,10 @@ define void @store_v8i16_with_folded_gep_offset(<8 x i16> %v, <8 x i16>* %p) {
 
 ; CHECK-LABEL: store_v8i16_with_unfolded_gep_negative_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v8i16_with_unfolded_gep_negative_offset(<8 x i16> %v, <8 x i16>* %p) {
   %s = getelementptr inbounds <8 x i16>, <8 x i16>* %p, i32 -1
   store <8 x i16> %v , <8 x i16>* %s
@@ -384,11 +356,10 @@ define void @store_v8i16_with_unfolded_gep_negative_offset(<8 x i16> %v, <8 x i1
 
 ; CHECK-LABEL: store_v8i16_with_unfolded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v8i16_with_unfolded_offset(<8 x i16> %v, <8 x i16>* %p) {
   %s = getelementptr inbounds <8 x i16>, <8 x i16>* %p, i32 -1
   store <8 x i16> %v , <8 x i16>* %s
@@ -397,11 +368,10 @@ define void @store_v8i16_with_unfolded_offset(<8 x i16> %v, <8 x i16>* %p) {
 
 ; CHECK-LABEL: store_v8i16_with_unfolded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v8i16_with_unfolded_gep_offset(<8 x i16> %v, <8 x i16>* %p) {
   %s = getelementptr <8 x i16>, <8 x i16>* %p, i32 1
   store <8 x i16> %v , <8 x i16>* %s
@@ -410,10 +380,9 @@ define void @store_v8i16_with_unfolded_gep_offset(<8 x i16> %v, <8 x i16>* %p) {
 
 ; CHECK-LABEL: store_v8i16_to_numeric_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.store 32($pop0):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x20]{{$}}
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.store 32($pop0):p2align=0, $0{{$}}
 define void @store_v8i16_to_numeric_address(<8 x i16> %v) {
   %s = inttoptr i32 32 to <8 x i16>*
   store <8 x i16> %v , <8 x i16>* %s
@@ -422,10 +391,9 @@ define void @store_v8i16_to_numeric_address(<8 x i16> %v) {
 
 ; CHECK-LABEL: store_v8i16_to_global_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.store gv_v8i16($pop0):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.store gv_v8i16($pop0):p2align=0, $0{{$}}
 define void @store_v8i16_to_global_address(<8 x i16> %v) {
   store <8 x i16> %v , <8 x i16>* @gv_v8i16
   ret void
@@ -436,11 +404,10 @@ define void @store_v8i16_to_global_address(<8 x i16> %v) {
 ; ==============================================================================
 ; CHECK-LABEL: load_v4i32:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 0($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 0($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @load_v4i32(<4 x i32>* %p) {
   %v = load <4 x i32>, <4 x i32>* %p
   ret <4 x i32> %v
@@ -448,11 +415,10 @@ define <4 x i32> @load_v4i32(<4 x i32>* %p) {
 
 ; CHECK-LABEL: load_v4i32_with_folded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 16($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x10]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 16($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @load_v4i32_with_folded_offset(<4 x i32>* %p) {
   %q = ptrtoint <4 x i32>* %p to i32
   %r = add nuw i32 %q, 16
@@ -463,11 +429,10 @@ define <4 x i32> @load_v4i32_with_folded_offset(<4 x i32>* %p) {
 
 ; CHECK-LABEL: load_v4i32_with_folded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 16($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x10]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 16($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @load_v4i32_with_folded_gep_offset(<4 x i32>* %p) {
   %s = getelementptr inbounds <4 x i32>, <4 x i32>* %p, i32 1
   %v = load <4 x i32>, <4 x i32>* %s
@@ -476,13 +441,12 @@ define <4 x i32> @load_v4i32_with_folded_gep_offset(<4 x i32>* %p) {
 
 ; CHECK-LABEL: load_v4i32_with_unfolded_gep_negative_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <4 x i32> @load_v4i32_with_unfolded_gep_negative_offset(<4 x i32>* %p) {
   %s = getelementptr inbounds <4 x i32>, <4 x i32>* %p, i32 -1
   %v = load <4 x i32>, <4 x i32>* %s
@@ -491,13 +455,12 @@ define <4 x i32> @load_v4i32_with_unfolded_gep_negative_offset(<4 x i32>* %p) {
 
 ; CHECK-LABEL: load_v4i32_with_unfolded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <4 x i32> @load_v4i32_with_unfolded_offset(<4 x i32>* %p) {
   %q = ptrtoint <4 x i32>* %p to i32
   %r = add nsw i32 %q, 16
@@ -508,13 +471,12 @@ define <4 x i32> @load_v4i32_with_unfolded_offset(<4 x i32>* %p) {
 
 ; CHECK-LABEL: load_v4i32_with_unfolded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <4 x i32> @load_v4i32_with_unfolded_gep_offset(<4 x i32>* %p) {
   %s = getelementptr <4 x i32>, <4 x i32>* %p, i32 1
   %v = load <4 x i32>, <4 x i32>* %s
@@ -523,11 +485,10 @@ define <4 x i32> @load_v4i32_with_unfolded_gep_offset(<4 x i32>* %p) {
 
 ; CHECK-LABEL: load_v4i32_from_numeric_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.load $push1=, 32($pop0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x20]{{$}}
-; SIMD128: return $pop1 #
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.load $push1=, 32($pop0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 define <4 x i32> @load_v4i32_from_numeric_address() {
   %s = inttoptr i32 32 to <4 x i32>*
   %v = load <4 x i32>, <4 x i32>* %s
@@ -536,11 +497,10 @@ define <4 x i32> @load_v4i32_from_numeric_address() {
 
 ; CHECK-LABEL: load_v4i32_from_global_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.load $push1=, gv_v4i32($pop0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,
-; SIMD128: return $pop1 #
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.load $push1=, gv_v4i32($pop0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 @gv_v4i32 = global <4 x i32> <i32 42, i32 42, i32 42, i32 42>
 define <4 x i32> @load_v4i32_from_global_address() {
   %v = load <4 x i32>, <4 x i32>* @gv_v4i32
@@ -549,9 +509,8 @@ define <4 x i32> @load_v4i32_from_global_address() {
 
 ; CHECK-LABEL: store_v4i32:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 0($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 0($1):p2align=0, $0{{$}}
 define void @store_v4i32(<4 x i32> %v, <4 x i32>* %p) {
   store <4 x i32> %v , <4 x i32>* %p
   ret void
@@ -559,9 +518,8 @@ define void @store_v4i32(<4 x i32> %v, <4 x i32>* %p) {
 
 ; CHECK-LABEL: store_v4i32_with_folded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 16($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x10]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 16($1):p2align=0, $0{{$}}
 define void @store_v4i32_with_folded_offset(<4 x i32> %v, <4 x i32>* %p) {
   %q = ptrtoint <4 x i32>* %p to i32
   %r = add nuw i32 %q, 16
@@ -572,9 +530,8 @@ define void @store_v4i32_with_folded_offset(<4 x i32> %v, <4 x i32>* %p) {
 
 ; CHECK-LABEL: store_v4i32_with_folded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 16($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x10]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 16($1):p2align=0, $0{{$}}
 define void @store_v4i32_with_folded_gep_offset(<4 x i32> %v, <4 x i32>* %p) {
   %s = getelementptr inbounds <4 x i32>, <4 x i32>* %p, i32 1
   store <4 x i32> %v , <4 x i32>* %s
@@ -583,11 +540,10 @@ define void @store_v4i32_with_folded_gep_offset(<4 x i32> %v, <4 x i32>* %p) {
 
 ; CHECK-LABEL: store_v4i32_with_unfolded_gep_negative_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v4i32_with_unfolded_gep_negative_offset(<4 x i32> %v, <4 x i32>* %p) {
   %s = getelementptr inbounds <4 x i32>, <4 x i32>* %p, i32 -1
   store <4 x i32> %v , <4 x i32>* %s
@@ -596,11 +552,10 @@ define void @store_v4i32_with_unfolded_gep_negative_offset(<4 x i32> %v, <4 x i3
 
 ; CHECK-LABEL: store_v4i32_with_unfolded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v4i32_with_unfolded_offset(<4 x i32> %v, <4 x i32>* %p) {
   %s = getelementptr inbounds <4 x i32>, <4 x i32>* %p, i32 -1
   store <4 x i32> %v , <4 x i32>* %s
@@ -609,11 +564,10 @@ define void @store_v4i32_with_unfolded_offset(<4 x i32> %v, <4 x i32>* %p) {
 
 ; CHECK-LABEL: store_v4i32_with_unfolded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v4i32_with_unfolded_gep_offset(<4 x i32> %v, <4 x i32>* %p) {
   %s = getelementptr <4 x i32>, <4 x i32>* %p, i32 1
   store <4 x i32> %v , <4 x i32>* %s
@@ -622,10 +576,9 @@ define void @store_v4i32_with_unfolded_gep_offset(<4 x i32> %v, <4 x i32>* %p) {
 
 ; CHECK-LABEL: store_v4i32_to_numeric_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.store 32($pop0):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x20]{{$}}
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.store 32($pop0):p2align=0, $0{{$}}
 define void @store_v4i32_to_numeric_address(<4 x i32> %v) {
   %s = inttoptr i32 32 to <4 x i32>*
   store <4 x i32> %v , <4 x i32>* %s
@@ -634,10 +587,9 @@ define void @store_v4i32_to_numeric_address(<4 x i32> %v) {
 
 ; CHECK-LABEL: store_v4i32_to_global_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.store gv_v4i32($pop0):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.store gv_v4i32($pop0):p2align=0, $0{{$}}
 define void @store_v4i32_to_global_address(<4 x i32> %v) {
   store <4 x i32> %v , <4 x i32>* @gv_v4i32
   ret void
@@ -649,11 +601,10 @@ define void @store_v4i32_to_global_address(<4 x i32> %v) {
 ; CHECK-LABEL: load_v2i64:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 0($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 0($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i64> @load_v2i64(<2 x i64>* %p) {
   %v = load <2 x i64>, <2 x i64>* %p
   ret <2 x i64> %v
@@ -662,11 +613,10 @@ define <2 x i64> @load_v2i64(<2 x i64>* %p) {
 ; CHECK-LABEL: load_v2i64_with_folded_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 16($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x10]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 16($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i64> @load_v2i64_with_folded_offset(<2 x i64>* %p) {
   %q = ptrtoint <2 x i64>* %p to i32
   %r = add nuw i32 %q, 16
@@ -678,11 +628,10 @@ define <2 x i64> @load_v2i64_with_folded_offset(<2 x i64>* %p) {
 ; CHECK-LABEL: load_v2i64_with_folded_gep_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 16($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x10]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 16($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i64> @load_v2i64_with_folded_gep_offset(<2 x i64>* %p) {
   %s = getelementptr inbounds <2 x i64>, <2 x i64>* %p, i32 1
   %v = load <2 x i64>, <2 x i64>* %s
@@ -692,13 +641,12 @@ define <2 x i64> @load_v2i64_with_folded_gep_offset(<2 x i64>* %p) {
 ; CHECK-LABEL: load_v2i64_with_unfolded_gep_negative_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <2 x i64> @load_v2i64_with_unfolded_gep_negative_offset(<2 x i64>* %p) {
   %s = getelementptr inbounds <2 x i64>, <2 x i64>* %p, i32 -1
   %v = load <2 x i64>, <2 x i64>* %s
@@ -708,13 +656,12 @@ define <2 x i64> @load_v2i64_with_unfolded_gep_negative_offset(<2 x i64>* %p) {
 ; CHECK-LABEL: load_v2i64_with_unfolded_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <2 x i64> @load_v2i64_with_unfolded_offset(<2 x i64>* %p) {
   %q = ptrtoint <2 x i64>* %p to i32
   %r = add nsw i32 %q, 16
@@ -726,13 +673,12 @@ define <2 x i64> @load_v2i64_with_unfolded_offset(<2 x i64>* %p) {
 ; CHECK-LABEL: load_v2i64_with_unfolded_gep_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <2 x i64> @load_v2i64_with_unfolded_gep_offset(<2 x i64>* %p) {
   %s = getelementptr <2 x i64>, <2 x i64>* %p, i32 1
   %v = load <2 x i64>, <2 x i64>* %s
@@ -742,11 +688,10 @@ define <2 x i64> @load_v2i64_with_unfolded_gep_offset(<2 x i64>* %p) {
 ; CHECK-LABEL: load_v2i64_from_numeric_address:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.load $push1=, 32($pop0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x20]{{$}}
-; SIMD128: return $pop1 #
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.load $push1=, 32($pop0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 define <2 x i64> @load_v2i64_from_numeric_address() {
   %s = inttoptr i32 32 to <2 x i64>*
   %v = load <2 x i64>, <2 x i64>* %s
@@ -756,11 +701,10 @@ define <2 x i64> @load_v2i64_from_numeric_address() {
 ; CHECK-LABEL: load_v2i64_from_global_address:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.load $push1=, gv_v2i64($pop0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,
-; SIMD128: return $pop1 #
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.load $push1=, gv_v2i64($pop0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 @gv_v2i64 = global <2 x i64> <i64 42, i64 42>
 define <2 x i64> @load_v2i64_from_global_address() {
   %v = load <2 x i64>, <2 x i64>* @gv_v2i64
@@ -770,9 +714,8 @@ define <2 x i64> @load_v2i64_from_global_address() {
 ; CHECK-LABEL: store_v2i64:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 0($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 0($1):p2align=0, $0{{$}}
 define void @store_v2i64(<2 x i64> %v, <2 x i64>* %p) {
   store <2 x i64> %v , <2 x i64>* %p
   ret void
@@ -781,9 +724,8 @@ define void @store_v2i64(<2 x i64> %v, <2 x i64>* %p) {
 ; CHECK-LABEL: store_v2i64_with_folded_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 16($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x10]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 16($1):p2align=0, $0{{$}}
 define void @store_v2i64_with_folded_offset(<2 x i64> %v, <2 x i64>* %p) {
   %q = ptrtoint <2 x i64>* %p to i32
   %r = add nuw i32 %q, 16
@@ -795,9 +737,8 @@ define void @store_v2i64_with_folded_offset(<2 x i64> %v, <2 x i64>* %p) {
 ; CHECK-LABEL: store_v2i64_with_folded_gep_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 16($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x10]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 16($1):p2align=0, $0{{$}}
 define void @store_v2i64_with_folded_gep_offset(<2 x i64> %v, <2 x i64>* %p) {
   %s = getelementptr inbounds <2 x i64>, <2 x i64>* %p, i32 1
   store <2 x i64> %v , <2 x i64>* %s
@@ -807,11 +748,10 @@ define void @store_v2i64_with_folded_gep_offset(<2 x i64> %v, <2 x i64>* %p) {
 ; CHECK-LABEL: store_v2i64_with_unfolded_gep_negative_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v2i64_with_unfolded_gep_negative_offset(<2 x i64> %v, <2 x i64>* %p) {
   %s = getelementptr inbounds <2 x i64>, <2 x i64>* %p, i32 -1
   store <2 x i64> %v , <2 x i64>* %s
@@ -821,11 +761,10 @@ define void @store_v2i64_with_unfolded_gep_negative_offset(<2 x i64> %v, <2 x i6
 ; CHECK-LABEL: store_v2i64_with_unfolded_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v2i64_with_unfolded_offset(<2 x i64> %v, <2 x i64>* %p) {
   %s = getelementptr inbounds <2 x i64>, <2 x i64>* %p, i32 -1
   store <2 x i64> %v , <2 x i64>* %s
@@ -835,11 +774,10 @@ define void @store_v2i64_with_unfolded_offset(<2 x i64> %v, <2 x i64>* %p) {
 ; CHECK-LABEL: store_v2i64_with_unfolded_gep_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v2i64_with_unfolded_gep_offset(<2 x i64> %v, <2 x i64>* %p) {
   %s = getelementptr <2 x i64>, <2 x i64>* %p, i32 1
   store <2 x i64> %v , <2 x i64>* %s
@@ -849,10 +787,9 @@ define void @store_v2i64_with_unfolded_gep_offset(<2 x i64> %v, <2 x i64>* %p) {
 ; CHECK-LABEL: store_v2i64_to_numeric_address:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.store 32($pop0):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x20]{{$}}
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.store 32($pop0):p2align=0, $0{{$}}
 define void @store_v2i64_to_numeric_address(<2 x i64> %v) {
   %s = inttoptr i32 32 to <2 x i64>*
   store <2 x i64> %v , <2 x i64>* %s
@@ -862,10 +799,9 @@ define void @store_v2i64_to_numeric_address(<2 x i64> %v) {
 ; CHECK-LABEL: store_v2i64_to_global_address:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.store gv_v2i64($pop0):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.store gv_v2i64($pop0):p2align=0, $0{{$}}
 define void @store_v2i64_to_global_address(<2 x i64> %v) {
   store <2 x i64> %v , <2 x i64>* @gv_v2i64
   ret void
@@ -876,11 +812,10 @@ define void @store_v2i64_to_global_address(<2 x i64> %v) {
 ; ==============================================================================
 ; CHECK-LABEL: load_v4f32:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 0($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 0($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x float> @load_v4f32(<4 x float>* %p) {
   %v = load <4 x float>, <4 x float>* %p
   ret <4 x float> %v
@@ -888,11 +823,10 @@ define <4 x float> @load_v4f32(<4 x float>* %p) {
 
 ; CHECK-LABEL: load_v4f32_with_folded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 16($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x10]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 16($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x float> @load_v4f32_with_folded_offset(<4 x float>* %p) {
   %q = ptrtoint <4 x float>* %p to i32
   %r = add nuw i32 %q, 16
@@ -903,11 +837,10 @@ define <4 x float> @load_v4f32_with_folded_offset(<4 x float>* %p) {
 
 ; CHECK-LABEL: load_v4f32_with_folded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 16($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x10]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 16($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x float> @load_v4f32_with_folded_gep_offset(<4 x float>* %p) {
   %s = getelementptr inbounds <4 x float>, <4 x float>* %p, i32 1
   %v = load <4 x float>, <4 x float>* %s
@@ -916,13 +849,12 @@ define <4 x float> @load_v4f32_with_folded_gep_offset(<4 x float>* %p) {
 
 ; CHECK-LABEL: load_v4f32_with_unfolded_gep_negative_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <4 x float> @load_v4f32_with_unfolded_gep_negative_offset(<4 x float>* %p) {
   %s = getelementptr inbounds <4 x float>, <4 x float>* %p, i32 -1
   %v = load <4 x float>, <4 x float>* %s
@@ -931,13 +863,12 @@ define <4 x float> @load_v4f32_with_unfolded_gep_negative_offset(<4 x float>* %p
 
 ; CHECK-LABEL: load_v4f32_with_unfolded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <4 x float> @load_v4f32_with_unfolded_offset(<4 x float>* %p) {
   %q = ptrtoint <4 x float>* %p to i32
   %r = add nsw i32 %q, 16
@@ -948,13 +879,12 @@ define <4 x float> @load_v4f32_with_unfolded_offset(<4 x float>* %p) {
 
 ; CHECK-LABEL: load_v4f32_with_unfolded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <4 x float> @load_v4f32_with_unfolded_gep_offset(<4 x float>* %p) {
   %s = getelementptr <4 x float>, <4 x float>* %p, i32 1
   %v = load <4 x float>, <4 x float>* %s
@@ -963,11 +893,10 @@ define <4 x float> @load_v4f32_with_unfolded_gep_offset(<4 x float>* %p) {
 
 ; CHECK-LABEL: load_v4f32_from_numeric_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.load $push1=, 32($pop0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x20]{{$}}
-; SIMD128: return $pop1 #
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.load $push1=, 32($pop0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 define <4 x float> @load_v4f32_from_numeric_address() {
   %s = inttoptr i32 32 to <4 x float>*
   %v = load <4 x float>, <4 x float>* %s
@@ -976,11 +905,10 @@ define <4 x float> @load_v4f32_from_numeric_address() {
 
 ; CHECK-LABEL: load_v4f32_from_global_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.load $push1=, gv_v4f32($pop0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,
-; SIMD128: return $pop1 #
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.load $push1=, gv_v4f32($pop0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 @gv_v4f32 = global <4 x float> <float 42., float 42., float 42., float 42.>
 define <4 x float> @load_v4f32_from_global_address() {
   %v = load <4 x float>, <4 x float>* @gv_v4f32
@@ -989,9 +917,8 @@ define <4 x float> @load_v4f32_from_global_address() {
 
 ; CHECK-LABEL: store_v4f32:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 0($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 0($1):p2align=0, $0{{$}}
 define void @store_v4f32(<4 x float> %v, <4 x float>* %p) {
   store <4 x float> %v , <4 x float>* %p
   ret void
@@ -999,9 +926,8 @@ define void @store_v4f32(<4 x float> %v, <4 x float>* %p) {
 
 ; CHECK-LABEL: store_v4f32_with_folded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 16($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x10]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 16($1):p2align=0, $0{{$}}
 define void @store_v4f32_with_folded_offset(<4 x float> %v, <4 x float>* %p) {
   %q = ptrtoint <4 x float>* %p to i32
   %r = add nuw i32 %q, 16
@@ -1012,9 +938,8 @@ define void @store_v4f32_with_folded_offset(<4 x float> %v, <4 x float>* %p) {
 
 ; CHECK-LABEL: store_v4f32_with_folded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 16($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x10]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 16($1):p2align=0, $0{{$}}
 define void @store_v4f32_with_folded_gep_offset(<4 x float> %v, <4 x float>* %p) {
   %s = getelementptr inbounds <4 x float>, <4 x float>* %p, i32 1
   store <4 x float> %v , <4 x float>* %s
@@ -1023,11 +948,10 @@ define void @store_v4f32_with_folded_gep_offset(<4 x float> %v, <4 x float>* %p)
 
 ; CHECK-LABEL: store_v4f32_with_unfolded_gep_negative_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v4f32_with_unfolded_gep_negative_offset(<4 x float> %v, <4 x float>* %p) {
   %s = getelementptr inbounds <4 x float>, <4 x float>* %p, i32 -1
   store <4 x float> %v , <4 x float>* %s
@@ -1036,11 +960,10 @@ define void @store_v4f32_with_unfolded_gep_negative_offset(<4 x float> %v, <4 x
 
 ; CHECK-LABEL: store_v4f32_with_unfolded_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v4f32_with_unfolded_offset(<4 x float> %v, <4 x float>* %p) {
   %s = getelementptr inbounds <4 x float>, <4 x float>* %p, i32 -1
   store <4 x float> %v , <4 x float>* %s
@@ -1049,11 +972,10 @@ define void @store_v4f32_with_unfolded_offset(<4 x float> %v, <4 x float>* %p) {
 
 ; CHECK-LABEL: store_v4f32_with_unfolded_gep_offset:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v4f32_with_unfolded_gep_offset(<4 x float> %v, <4 x float>* %p) {
   %s = getelementptr <4 x float>, <4 x float>* %p, i32 1
   store <4 x float> %v , <4 x float>* %s
@@ -1062,10 +984,9 @@ define void @store_v4f32_with_unfolded_gep_offset(<4 x float> %v, <4 x float>* %
 
 ; CHECK-LABEL: store_v4f32_to_numeric_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.store 32($pop0):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x20]{{$}}
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.store 32($pop0):p2align=0, $0{{$}}
 define void @store_v4f32_to_numeric_address(<4 x float> %v) {
   %s = inttoptr i32 32 to <4 x float>*
   store <4 x float> %v , <4 x float>* %s
@@ -1074,10 +995,9 @@ define void @store_v4f32_to_numeric_address(<4 x float> %v) {
 
 ; CHECK-LABEL: store_v4f32_to_global_address:
 ; NO-SIMD128-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.store gv_v4f32($pop0):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.store gv_v4f32($pop0):p2align=0, $0{{$}}
 define void @store_v4f32_to_global_address(<4 x float> %v) {
   store <4 x float> %v , <4 x float>* @gv_v4f32
   ret void
@@ -1089,11 +1009,10 @@ define void @store_v4f32_to_global_address(<4 x float> %v) {
 ; CHECK-LABEL: load_v2f64:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 0($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 0($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x double> @load_v2f64(<2 x double>* %p) {
   %v = load <2 x double>, <2 x double>* %p
   ret <2 x double> %v
@@ -1102,11 +1021,10 @@ define <2 x double> @load_v2f64(<2 x double>* %p) {
 ; CHECK-LABEL: load_v2f64_with_folded_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 16($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x10]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 16($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x double> @load_v2f64_with_folded_offset(<2 x double>* %p) {
   %q = ptrtoint <2 x double>* %p to i32
   %r = add nuw i32 %q, 16
@@ -1118,11 +1036,10 @@ define <2 x double> @load_v2f64_with_folded_offset(<2 x double>* %p) {
 ; CHECK-LABEL: load_v2f64_with_folded_gep_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.load $push0=, 16($0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x10]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.load $push0=, 16($0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x double> @load_v2f64_with_folded_gep_offset(<2 x double>* %p) {
   %s = getelementptr inbounds <2 x double>, <2 x double>* %p, i32 1
   %v = load <2 x double>, <2 x double>* %s
@@ -1132,13 +1049,12 @@ define <2 x double> @load_v2f64_with_folded_gep_offset(<2 x double>* %p) {
 ; CHECK-LABEL: load_v2f64_with_unfolded_gep_negative_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <2 x double> @load_v2f64_with_unfolded_gep_negative_offset(<2 x double>* %p) {
   %s = getelementptr inbounds <2 x double>, <2 x double>* %p, i32 -1
   %v = load <2 x double>, <2 x double>* %s
@@ -1148,13 +1064,12 @@ define <2 x double> @load_v2f64_with_unfolded_gep_negative_offset(<2 x double>*
 ; CHECK-LABEL: load_v2f64_with_unfolded_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <2 x double> @load_v2f64_with_unfolded_offset(<2 x double>* %p) {
   %q = ptrtoint <2 x double>* %p to i32
   %r = add nsw i32 %q, 16
@@ -1166,13 +1081,12 @@ define <2 x double> @load_v2f64_with_unfolded_offset(<2 x double>* %p) {
 ; CHECK-LABEL: load_v2f64_with_unfolded_gep_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $0, $pop0 #
-; SIMD128: v128.load $push2=, 0($pop1):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x00]{{$}}
-; SIMD128: return $pop2 #
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $0, $pop0{{$}}
+; SIMD128-NEXT: v128.load $push2=, 0($pop1):p2align=0{{$}}
+; SIMD128-NEXT: return $pop2{{$}}
 define <2 x double> @load_v2f64_with_unfolded_gep_offset(<2 x double>* %p) {
   %s = getelementptr <2 x double>, <2 x double>* %p, i32 1
   %v = load <2 x double>, <2 x double>* %s
@@ -1182,11 +1096,10 @@ define <2 x double> @load_v2f64_with_unfolded_gep_offset(<2 x double>* %p) {
 ; CHECK-LABEL: load_v2f64_from_numeric_address:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.load $push1=, 32($pop0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,0x20]{{$}}
-; SIMD128: return $pop1 #
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.load $push1=, 32($pop0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 define <2 x double> @load_v2f64_from_numeric_address() {
   %s = inttoptr i32 32 to <2 x double>*
   %v = load <2 x double>, <2 x double>* %s
@@ -1196,11 +1109,10 @@ define <2 x double> @load_v2f64_from_numeric_address() {
 ; CHECK-LABEL: load_v2f64_from_global_address:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .result v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.load $push1=, gv_v2f64($pop0):p2align=0
-; SIMD128-SAME: # encoding: [0xfd,0x01,0x00,
-; SIMD128: return $pop1 #
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.load $push1=, gv_v2f64($pop0):p2align=0{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 @gv_v2f64 = global <2 x double> <double 42., double 42.>
 define <2 x double> @load_v2f64_from_global_address() {
   %v = load <2 x double>, <2 x double>* @gv_v2f64
@@ -1210,9 +1122,8 @@ define <2 x double> @load_v2f64_from_global_address() {
 ; CHECK-LABEL: store_v2f64:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 0($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 0($1):p2align=0, $0{{$}}
 define void @store_v2f64(<2 x double> %v, <2 x double>* %p) {
   store <2 x double> %v , <2 x double>* %p
   ret void
@@ -1221,9 +1132,8 @@ define void @store_v2f64(<2 x double> %v, <2 x double>* %p) {
 ; CHECK-LABEL: store_v2f64_with_folded_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 16($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x10]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 16($1):p2align=0, $0{{$}}
 define void @store_v2f64_with_folded_offset(<2 x double> %v, <2 x double>* %p) {
   %q = ptrtoint <2 x double>* %p to i32
   %r = add nuw i32 %q, 16
@@ -1235,9 +1145,8 @@ define void @store_v2f64_with_folded_offset(<2 x double> %v, <2 x double>* %p) {
 ; CHECK-LABEL: store_v2f64_with_folded_gep_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: v128.store 16($1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x10]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: v128.store 16($1):p2align=0, $0{{$}}
 define void @store_v2f64_with_folded_gep_offset(<2 x double> %v, <2 x double>* %p) {
   %s = getelementptr inbounds <2 x double>, <2 x double>* %p, i32 1
   store <2 x double> %v , <2 x double>* %s
@@ -1247,11 +1156,10 @@ define void @store_v2f64_with_folded_gep_offset(<2 x double> %v, <2 x double>* %
 ; CHECK-LABEL: store_v2f64_with_unfolded_gep_negative_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v2f64_with_unfolded_gep_negative_offset(<2 x double> %v, <2 x double>* %p) {
   %s = getelementptr inbounds <2 x double>, <2 x double>* %p, i32 -1
   store <2 x double> %v , <2 x double>* %s
@@ -1261,11 +1169,10 @@ define void @store_v2f64_with_unfolded_gep_negative_offset(<2 x double> %v, <2 x
 ; CHECK-LABEL: store_v2f64_with_unfolded_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, -16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, -16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v2f64_with_unfolded_offset(<2 x double> %v, <2 x double>* %p) {
   %s = getelementptr inbounds <2 x double>, <2 x double>* %p, i32 -1
   store <2 x double> %v , <2 x double>* %s
@@ -1275,11 +1182,10 @@ define void @store_v2f64_with_unfolded_offset(<2 x double> %v, <2 x double>* %p)
 ; CHECK-LABEL: store_v2f64_with_unfolded_gep_offset:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: i32.const $push0=, 16 #
-; SIMD128: i32.add $push1=, $1, $pop0 #
-; SIMD128: v128.store 0($pop1):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x00]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: i32.const $push0=, 16{{$}}
+; SIMD128-NEXT: i32.add $push1=, $1, $pop0{{$}}
+; SIMD128-NEXT: v128.store 0($pop1):p2align=0, $0{{$}}
 define void @store_v2f64_with_unfolded_gep_offset(<2 x double> %v, <2 x double>* %p) {
   %s = getelementptr <2 x double>, <2 x double>* %p, i32 1
   store <2 x double> %v , <2 x double>* %s
@@ -1289,10 +1195,9 @@ define void @store_v2f64_with_unfolded_gep_offset(<2 x double> %v, <2 x double>*
 ; CHECK-LABEL: store_v2f64_to_numeric_address:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.store 32($pop0):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,0x20]{{$}}
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.store 32($pop0):p2align=0, $0{{$}}
 define void @store_v2f64_to_numeric_address(<2 x double> %v) {
   %s = inttoptr i32 32 to <2 x double>*
   store <2 x double> %v , <2 x double>* %s
@@ -1302,10 +1207,9 @@ define void @store_v2f64_to_numeric_address(<2 x double> %v) {
 ; CHECK-LABEL: store_v2f64_to_global_address:
 ; NO-SIMD128-NOT: v128
 ; SIMD128-VM-NOT: v128
-; SIMD128: .param v128{{$}}
-; SIMD128: i32.const $push0=, 0 #
-; SIMD128: v128.store gv_v2f64($pop0):p2align=0, $0
-; SIMD128-SAME: # encoding: [0xfd,0x02,0x00,
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: i32.const $push0=, 0{{$}}
+; SIMD128-NEXT: v128.store gv_v2f64($pop0):p2align=0, $0{{$}}
 define void @store_v2f64_to_global_address(<2 x double> %v) {
   store <2 x double> %v , <2 x double>* @gv_v2f64
   ret void
diff --git a/llvm/test/CodeGen/WebAssembly/simd.ll b/llvm/test/CodeGen/WebAssembly/simd.ll
index a5cabbc..ede8d84 100644
--- a/llvm/test/CodeGen/WebAssembly/simd.ll
+++ b/llvm/test/CodeGen/WebAssembly/simd.ll
@@ -1,6 +1,6 @@
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -wasm-enable-unimplemented-simd -mattr=+simd128,+sign-ext --show-mc-encoding | FileCheck %s --check-prefixes CHECK,SIMD128
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=+simd128,+sign-ext --show-mc-encoding | FileCheck %s --check-prefixes CHECK,SIMD128-VM
-; RUN: llc < %s -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=-simd128,+sign-ext --show-mc-encoding | FileCheck %s --check-prefixes CHECK,NO-SIMD128
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -wasm-enable-unimplemented-simd -mattr=+simd128,+sign-ext | FileCheck %s --check-prefixes CHECK,SIMD128
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=+simd128,+sign-ext | FileCheck %s --check-prefixes CHECK,SIMD128-VM
+; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=-simd128,+sign-ext | FileCheck %s --check-prefixes CHECK,NO-SIMD128
 
 ; Test that basic SIMD128 vector manipulation operations assemble as expected.
 
@@ -12,12 +12,10 @@ target triple = "wasm32-unknown-unknown"
 ; ==============================================================================
 ; CHECK-LABEL: const_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.const $push0=,
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.const $push0=,
 ; SIMD128-SAME: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
-; SIMD128-SAME: # encoding: [0xfd,0x00,
-; SIMD128-SAME: 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
-; SIMD128-SAME: 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f]{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @const_v16i8() {
   ret <16 x i8> <i8 00, i8 01, i8 02, i8 03, i8 04, i8 05, i8 06, i8 07,
                  i8 08, i8 09, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15>
@@ -25,10 +23,10 @@ define <16 x i8> @const_v16i8() {
 
 ; CHECK-LABEL: splat_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.splat $push0=, $0 # encoding: [0xfd,0x03]{{$}}
-; SIMD128: return $pop0 # encoding: [0x0f]{{$}}
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.splat $push0=, $0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @splat_v16i8(i8 %x) {
   %v = insertelement <16 x i8> undef, i8 %x, i32 0
   %res = shufflevector <16 x i8> %v, <16 x i8> undef,
@@ -38,7 +36,7 @@ define <16 x i8> @splat_v16i8(i8 %x) {
 }
 
 ; CHECK-LABEL: const_splat_v16i8:
-; SIMD128; i8x16.splat
+; SIMD128: i8x16.splat
 define <16 x i8> @const_splat_v16i8() {
   ret <16 x i8> <i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42,
                  i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42, i8 42>
@@ -46,10 +44,10 @@ define <16 x i8> @const_splat_v16i8() {
 
 ; CHECK-LABEL: extract_v16i8_s:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128{{$}}
-; SIMD128: .result i32{{$}}
-; SIMD128: i8x16.extract_lane_s $push0=, $0, 13 # encoding: [0xfd,0x09,0x0d]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result i32{{$}}
+; SIMD128-NEXT: i8x16.extract_lane_s $push0=, $0, 13{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define i32 @extract_v16i8_s(<16 x i8> %v) {
   %elem = extractelement <16 x i8> %v, i8 13
   %a = sext i8 %elem to i32
@@ -58,10 +56,10 @@ define i32 @extract_v16i8_s(<16 x i8> %v) {
 
 ; CHECK-LABEL: extract_v16i8_u:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128{{$}}
-; SIMD128: .result i32{{$}}
-; SIMD128: i8x16.extract_lane_u $push0=, $0, 13 # encoding: [0xfd,0x0a,0x0d]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result i32{{$}}
+; SIMD128-NEXT: i8x16.extract_lane_u $push0=, $0, 13{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define i32 @extract_v16i8_u(<16 x i8> %v) {
   %elem = extractelement <16 x i8> %v, i8 13
   %a = zext i8 %elem to i32
@@ -70,10 +68,10 @@ define i32 @extract_v16i8_u(<16 x i8> %v) {
 
 ; CHECK-LABEL: extract_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128{{$}}
-; SIMD128: .result i32{{$}}
-; SIMD128: i8x16.extract_lane_u $push0=, $0, 13 # encoding: [0xfd,0x0a,0x0d]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result i32{{$}}
+; SIMD128-NEXT: i8x16.extract_lane_u $push0=, $0, 13{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define i8 @extract_v16i8(<16 x i8> %v) {
   %elem = extractelement <16 x i8> %v, i8 13
   ret i8 %elem
@@ -81,10 +79,10 @@ define i8 @extract_v16i8(<16 x i8> %v) {
 
 ; CHECK-LABEL: replace_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.replace_lane $push0=, $0, 11, $1 # encoding: [0xfd,0x11,0x0b]{{$}}
-; SIMD128: return $pop0 # encoding: [0x0f]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push0=, $0, 11, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @replace_v16i8(<16 x i8> %v, i8 %x) {
   %res = insertelement <16 x i8> %v, i8 %x, i32 11
   ret <16 x i8> %res
@@ -92,14 +90,11 @@ define <16 x i8> @replace_v16i8(<16 x i8> %v, i8 %x) {
 
 ; CHECK-LABEL: shuffle_v16i8:
 ; NO-SIMD128-NOT: v8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v8x16.shuffle $push0=, $0, $1,
-; SIMD128-SAME: 0, 17, 2, 19, 4, 21, 6, 23, 8, 25, 10, 27, 12, 29, 14, 31
-; SIMD128-SAME: # encoding: [0xfd,0x17,
-; SIMD128-SAME: 0x00,0x11,0x02,0x13,0x04,0x15,0x06,0x17,
-; SIMD128-SAME: 0x08,0x19,0x0a,0x1b,0x0c,0x1d,0x0e,0x1f]
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v8x16.shuffle $push0=, $0, $1,
+; SIMD128-SAME: 0, 17, 2, 19, 4, 21, 6, 23, 8, 25, 10, 27, 12, 29, 14, 31{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <16 x i8> @shuffle_v16i8(<16 x i8> %x, <16 x i8> %y) {
   %res = shufflevector <16 x i8> %x, <16 x i8> %y,
     <16 x i32> <i32 0, i32 17, i32 2, i32 19, i32 4, i32 21, i32 6, i32 23,
@@ -109,25 +104,25 @@ define <16 x i8> @shuffle_v16i8(<16 x i8> %x, <16 x i8> %y) {
 
 ; CHECK-LABEL: build_v16i8:
 ; NO-SIMD128-NOT: i8x16
-; SIMD128: .param i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i8x16.splat $push0=, $0 # encoding: [0xfd,0x03]
-; SIMD128: i8x16.replace_lane $push1=, $pop0, 1, $1 # encoding: [0xfd,0x11,0x01]
-; SIMD128: i8x16.replace_lane $push2=, $pop1, 2, $2 # encoding: [0xfd,0x11,0x02]
-; SIMD128: i8x16.replace_lane $push3=, $pop2, 3, $3 # encoding: [0xfd,0x11,0x03]
-; SIMD128: i8x16.replace_lane $push4=, $pop3, 4, $4 # encoding: [0xfd,0x11,0x04]
-; SIMD128: i8x16.replace_lane $push5=, $pop4, 5, $5 # encoding: [0xfd,0x11,0x05]
-; SIMD128: i8x16.replace_lane $push6=, $pop5, 6, $6 # encoding: [0xfd,0x11,0x06]
-; SIMD128: i8x16.replace_lane $push7=, $pop6, 7, $7 # encoding: [0xfd,0x11,0x07]
-; SIMD128: i8x16.replace_lane $push8=, $pop7, 8, $8 # encoding: [0xfd,0x11,0x08]
-; SIMD128: i8x16.replace_lane $push9=, $pop8, 9, $9 # encoding: [0xfd,0x11,0x09]
-; SIMD128: i8x16.replace_lane $push10=, $pop9, 10, $10 # encoding: [0xfd,0x11,0x0a]
-; SIMD128: i8x16.replace_lane $push11=, $pop10, 11, $11 # encoding: [0xfd,0x11,0x0b]
-; SIMD128: i8x16.replace_lane $push12=, $pop11, 12, $12 # encoding: [0xfd,0x11,0x0c]
-; SIMD128: i8x16.replace_lane $push13=, $pop12, 13, $13 # encoding: [0xfd,0x11,0x0d]
-; SIMD128: i8x16.replace_lane $push14=, $pop13, 14, $14 # encoding: [0xfd,0x11,0x0e]
-; SIMD128: i8x16.replace_lane $push15=, $pop14, 15, $15 # encoding: [0xfd,0x11,0x0f]
-; SIMD128: return $pop15 # encoding: [0x0f]
+; SIMD128-NEXT: .param i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32, i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i8x16.splat $push0=, $0{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push1=, $pop0, 1, $1{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push2=, $pop1, 2, $2{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push3=, $pop2, 3, $3{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push4=, $pop3, 4, $4{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push5=, $pop4, 5, $5{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push6=, $pop5, 6, $6{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push7=, $pop6, 7, $7{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push8=, $pop7, 8, $8{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push9=, $pop8, 9, $9{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push10=, $pop9, 10, $10{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push11=, $pop10, 11, $11{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push12=, $pop11, 12, $12{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push13=, $pop12, 13, $13{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push14=, $pop13, 14, $14{{$}}
+; SIMD128-NEXT: i8x16.replace_lane $push15=, $pop14, 15, $15{{$}}
+; SIMD128-NEXT: return $pop15{{$}}
 define <16 x i8> @build_v16i8(i8 %x0, i8 %x1, i8 %x2, i8 %x3,
                               i8 %x4, i8 %x5, i8 %x6, i8 %x7,
                               i8 %x8, i8 %x9, i8 %x10, i8 %x11,
@@ -156,11 +151,9 @@ define <16 x i8> @build_v16i8(i8 %x0, i8 %x1, i8 %x2, i8 %x3,
 ; ==============================================================================
 ; CHECK-LABEL: const_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.const $push0=, 256, 770, 1284, 1798, 2312, 2826, 3340, 3854
-; SIMD128-SAME: # encoding: [0xfd,0x00,
-; SIMD128-SAME: 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
-; SIMD128-SAME: 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f]{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.const $push0=, 256, 770, 1284, 1798, 2312, 2826, 3340, 3854{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @const_v8i16() {
   ret <8 x i16> <i16 256, i16 770, i16 1284, i16 1798,
                  i16 2312, i16 2826, i16 3340, i16 3854>
@@ -168,10 +161,10 @@ define <8 x i16> @const_v8i16() {
 
 ; CHECK-LABEL: splat_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.splat $push0=, $0 # encoding: [0xfd,0x04]{{$}}
-; SIMD128: return $pop0 # encoding: [0x0f]{{$}}
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.splat $push0=, $0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @splat_v8i16(i16 %x) {
   %v = insertelement <8 x i16> undef, i16 %x, i32 0
   %res = shufflevector <8 x i16> %v, <8 x i16> undef,
@@ -180,17 +173,17 @@ define <8 x i16> @splat_v8i16(i16 %x) {
 }
 
 ; CHECK-LABEL: const_splat_v8i16:
-; SIMD128; i16x8.splat
+; SIMD128: i16x8.splat
 define <8 x i16> @const_splat_v8i16() {
   ret <8 x i16> <i16 42, i16 42, i16 42, i16 42, i16 42, i16 42, i16 42, i16 42>
 }
 
 ; CHECK-LABEL: extract_v8i16_s:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128{{$}}
-; SIMD128: .result i32{{$}}
-; SIMD128: i16x8.extract_lane_s $push0=, $0, 5 # encoding: [0xfd,0x0b,0x05]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result i32{{$}}
+; SIMD128-NEXT: i16x8.extract_lane_s $push0=, $0, 5{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define i32 @extract_v8i16_s(<8 x i16> %v) {
   %elem = extractelement <8 x i16> %v, i16 5
   %a = sext i16 %elem to i32
@@ -199,10 +192,10 @@ define i32 @extract_v8i16_s(<8 x i16> %v) {
 
 ; CHECK-LABEL: extract_v8i16_u:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128{{$}}
-; SIMD128: .result i32{{$}}
-; SIMD128: i16x8.extract_lane_u $push0=, $0, 5 # encoding: [0xfd,0x0c,0x05]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result i32{{$}}
+; SIMD128-NEXT: i16x8.extract_lane_u $push0=, $0, 5{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define i32 @extract_v8i16_u(<8 x i16> %v) {
   %elem = extractelement <8 x i16> %v, i16 5
   %a = zext i16 %elem to i32
@@ -211,10 +204,10 @@ define i32 @extract_v8i16_u(<8 x i16> %v) {
 
 ; CHECK-LABEL: extract_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128{{$}}
-; SIMD128: .result i32{{$}}
-; SIMD128: i16x8.extract_lane_u $push0=, $0, 5 # encoding: [0xfd,0x0c,0x05]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result i32{{$}}
+; SIMD128-NEXT: i16x8.extract_lane_u $push0=, $0, 5{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define i16 @extract_v8i16(<8 x i16> %v) {
   %elem = extractelement <8 x i16> %v, i16 5
   ret i16 %elem
@@ -222,10 +215,10 @@ define i16 @extract_v8i16(<8 x i16> %v) {
 
 ; CHECK-LABEL: replace_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.replace_lane $push0=, $0, 7, $1 # encoding: [0xfd,0x12,0x07]{{$}}
-; SIMD128: return $pop0 # encoding: [0x0f]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.replace_lane $push0=, $0, 7, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @replace_v8i16(<8 x i16> %v, i16 %x) {
   %res = insertelement <8 x i16> %v, i16 %x, i32 7
   ret <8 x i16> %res
@@ -233,14 +226,11 @@ define <8 x i16> @replace_v8i16(<8 x i16> %v, i16 %x) {
 
 ; CHECK-LABEL: shuffle_v8i16:
 ; NO-SIMD128-NOT: v8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v8x16.shuffle $push0=, $0, $1,
-; SIMD128-SAME: 0, 1, 18, 19, 4, 5, 22, 23, 8, 9, 26, 27, 12, 13, 30, 31
-; SIMD128-SAME: # encoding: [0xfd,0x17,
-; SIMD128-SAME: 0x00,0x01,0x12,0x13,0x04,0x05,0x16,0x17,
-; SIMD128-SAME: 0x08,0x09,0x1a,0x1b,0x0c,0x0d,0x1e,0x1f]
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v8x16.shuffle $push0=, $0, $1,
+; SIMD128-SAME: 0, 1, 18, 19, 4, 5, 22, 23, 8, 9, 26, 27, 12, 13, 30, 31{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <8 x i16> @shuffle_v8i16(<8 x i16> %x, <8 x i16> %y) {
   %res = shufflevector <8 x i16> %x, <8 x i16> %y,
     <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
@@ -249,17 +239,17 @@ define <8 x i16> @shuffle_v8i16(<8 x i16> %x, <8 x i16> %y) {
 
 ; CHECK-LABEL: build_v8i16:
 ; NO-SIMD128-NOT: i16x8
-; SIMD128: .param i32, i32, i32, i32, i32, i32, i32, i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i16x8.splat $push0=, $0 # encoding: [0xfd,0x04]
-; SIMD128: i16x8.replace_lane $push1=, $pop0, 1, $1 # encoding: [0xfd,0x12,0x01]
-; SIMD128: i16x8.replace_lane $push2=, $pop1, 2, $2 # encoding: [0xfd,0x12,0x02]
-; SIMD128: i16x8.replace_lane $push3=, $pop2, 3, $3 # encoding: [0xfd,0x12,0x03]
-; SIMD128: i16x8.replace_lane $push4=, $pop3, 4, $4 # encoding: [0xfd,0x12,0x04]
-; SIMD128: i16x8.replace_lane $push5=, $pop4, 5, $5 # encoding: [0xfd,0x12,0x05]
-; SIMD128: i16x8.replace_lane $push6=, $pop5, 6, $6 # encoding: [0xfd,0x12,0x06]
-; SIMD128: i16x8.replace_lane $push7=, $pop6, 7, $7 # encoding: [0xfd,0x12,0x07]
-; SIMD128: return $pop7 # encoding: [0x0f]
+; SIMD128-NEXT: .param i32, i32, i32, i32, i32, i32, i32, i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i16x8.splat $push0=, $0{{$}}
+; SIMD128-NEXT: i16x8.replace_lane $push1=, $pop0, 1, $1{{$}}
+; SIMD128-NEXT: i16x8.replace_lane $push2=, $pop1, 2, $2{{$}}
+; SIMD128-NEXT: i16x8.replace_lane $push3=, $pop2, 3, $3{{$}}
+; SIMD128-NEXT: i16x8.replace_lane $push4=, $pop3, 4, $4{{$}}
+; SIMD128-NEXT: i16x8.replace_lane $push5=, $pop4, 5, $5{{$}}
+; SIMD128-NEXT: i16x8.replace_lane $push6=, $pop5, 6, $6{{$}}
+; SIMD128-NEXT: i16x8.replace_lane $push7=, $pop6, 7, $7{{$}}
+; SIMD128-NEXT: return $pop7{{$}}
 define <8 x i16> @build_v8i16(i16 %x0, i16 %x1, i16 %x2, i16 %x3,
                               i16 %x4, i16 %x5, i16 %x6, i16 %x7) {
   %t0 = insertelement <8 x i16> undef, i16 %x0, i32 0
@@ -278,21 +268,19 @@ define <8 x i16> @build_v8i16(i16 %x0, i16 %x1, i16 %x2, i16 %x3,
 ; ==============================================================================
 ; CHECK-LABEL: const_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.const $push0=, 50462976, 117835012, 185207048, 252579084
-; SIMD128-SAME: # encoding: [0xfd,0x00,
-; SIMD128-SAME: 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
-; SIMD128-SAME: 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f]{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.const $push0=, 50462976, 117835012, 185207048, 252579084{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @const_v4i32() {
   ret <4 x i32> <i32 50462976, i32 117835012, i32 185207048, i32 252579084>
 }
 
 ; CHECK-LABEL: splat_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.splat $push0=, $0 # encoding: [0xfd,0x05]{{$}}
-; SIMD128: return $pop0 # encoding: [0x0f]{{$}}
+; SIMD128-NEXT: .param i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.splat $push0=, $0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @splat_v4i32(i32 %x) {
   %v = insertelement <4 x i32> undef, i32 %x, i32 0
   %res = shufflevector <4 x i32> %v, <4 x i32> undef,
@@ -301,17 +289,17 @@ define <4 x i32> @splat_v4i32(i32 %x) {
 }
 
 ; CHECK-LABEL: const_splat_v4i32:
-; SIMD128; i32x4.splat
+; SIMD128: i32x4.splat
 define <4 x i32> @const_splat_v4i32() {
   ret <4 x i32> <i32 42, i32 42, i32 42, i32 42>
 }
 
 ; CHECK-LABEL: extract_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128{{$}}
-; SIMD128: .result i32{{$}}
-; SIMD128: i32x4.extract_lane $push0=, $0, 3 # encoding: [0xfd,0x0d,0x03]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result i32{{$}}
+; SIMD128-NEXT: i32x4.extract_lane $push0=, $0, 3{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define i32 @extract_v4i32(<4 x i32> %v) {
   %elem = extractelement <4 x i32> %v, i32 3
   ret i32 %elem
@@ -319,10 +307,10 @@ define i32 @extract_v4i32(<4 x i32> %v) {
 
 ; CHECK-LABEL: replace_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param v128, i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.replace_lane $push0=, $0, 2, $1 # encoding: [0xfd,0x13,0x02]{{$}}
-; SIMD128: return $pop0 # encoding: [0x0f]{{$}}
+; SIMD128-NEXT: .param v128, i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.replace_lane $push0=, $0, 2, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @replace_v4i32(<4 x i32> %v, i32 %x) {
   %res = insertelement <4 x i32> %v, i32 %x, i32 2
   ret <4 x i32> %res
@@ -330,14 +318,11 @@ define <4 x i32> @replace_v4i32(<4 x i32> %v, i32 %x) {
 
 ; CHECK-LABEL: shuffle_v4i32:
 ; NO-SIMD128-NOT: v8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v8x16.shuffle $push0=, $0, $1,
-; SIMD128-SAME: 0, 1, 2, 3, 20, 21, 22, 23, 8, 9, 10, 11, 28, 29, 30, 31
-; SIMD128-SAME: # encoding: [0xfd,0x17,
-; SIMD128-SAME: 0x00,0x01,0x02,0x03,0x14,0x15,0x16,0x17,
-; SIMD128-SAME: 0x08,0x09,0x0a,0x0b,0x1c,0x1d,0x1e,0x1f]
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v8x16.shuffle $push0=, $0, $1,
+; SIMD128-SAME: 0, 1, 2, 3, 20, 21, 22, 23, 8, 9, 10, 11, 28, 29, 30, 31{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x i32> @shuffle_v4i32(<4 x i32> %x, <4 x i32> %y) {
   %res = shufflevector <4 x i32> %x, <4 x i32> %y,
     <4 x i32> <i32 0, i32 5, i32 2, i32 7>
@@ -346,13 +331,13 @@ define <4 x i32> @shuffle_v4i32(<4 x i32> %x, <4 x i32> %y) {
 
 ; CHECK-LABEL: build_v4i32:
 ; NO-SIMD128-NOT: i32x4
-; SIMD128: .param i32, i32, i32, i32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i32x4.splat $push0=, $0 # encoding: [0xfd,0x05]
-; SIMD128: i32x4.replace_lane $push1=, $pop0, 1, $1 # encoding: [0xfd,0x13,0x01]
-; SIMD128: i32x4.replace_lane $push2=, $pop1, 2, $2 # encoding: [0xfd,0x13,0x02]
-; SIMD128: i32x4.replace_lane $push3=, $pop2, 3, $3 # encoding: [0xfd,0x13,0x03]
-; SIMD128: return $pop3 # encoding: [0x0f]
+; SIMD128-NEXT: .param i32, i32, i32, i32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i32x4.splat $push0=, $0{{$}}
+; SIMD128-NEXT: i32x4.replace_lane $push1=, $pop0, 1, $1{{$}}
+; SIMD128-NEXT: i32x4.replace_lane $push2=, $pop1, 2, $2{{$}}
+; SIMD128-NEXT: i32x4.replace_lane $push3=, $pop2, 3, $3{{$}}
+; SIMD128-NEXT: return $pop3{{$}}
 define <4 x i32> @build_v4i32(i32 %x0, i32 %x1, i32 %x2, i32 %x3) {
   %t0 = insertelement <4 x i32> undef, i32 %x0, i32 0
   %t1 = insertelement <4 x i32> %t0, i32 %x1, i32 1
@@ -367,11 +352,9 @@ define <4 x i32> @build_v4i32(i32 %x0, i32 %x1, i32 %x2, i32 %x3) {
 ; CHECK-LABEL: const_v2i64:
 ; NO-SIMD128-NOT: i64x2
 ; SIMD128-VM-NOT: i64x2
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.const $push0=, 506097522914230528, 1084818905618843912
-; SIMD128-SAME: # encoding: [0xfd,0x00,
-; SIMD128-SAME: 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
-; SIMD128-SAME: 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f]{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.const $push0=, 506097522914230528, 1084818905618843912{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i64> @const_v2i64() {
   ret <2 x i64> <i64 506097522914230528, i64 1084818905618843912>
 }
@@ -379,10 +362,10 @@ define <2 x i64> @const_v2i64() {
 ; CHECK-LABEL: splat_v2i64:
 ; NO-SIMD128-NOT: i64x2
 ; SIMD128-VM-NOT: i64x2
-; SIMD128: .param i64{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i64x2.splat $push0=, $0 # encoding: [0xfd,0x06]{{$}}
-; SIMD128: return $pop0 # encoding: [0x0f]{{$}}
+; SIMD128-NEXT: .param i64{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i64x2.splat $push0=, $0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i64> @splat_v2i64(i64 %x) {
   %t1 = insertelement <2 x i64> zeroinitializer, i64 %x, i32 0
   %res = insertelement <2 x i64> %t1, i64 %x, i32 1
@@ -390,7 +373,7 @@ define <2 x i64> @splat_v2i64(i64 %x) {
 }
 
 ; CHECK-LABEL: const_splat_v2i64:
-; SIMD128; i64x2.splat
+; SIMD128: i64x2.splat
 define <2 x i64> @const_splat_v2i64() {
   ret <2 x i64> <i64 42, i64 42>
 }
@@ -398,10 +381,10 @@ define <2 x i64> @const_splat_v2i64() {
 ; CHECK-LABEL: extract_v2i64:
 ; NO-SIMD128-NOT: i64x2
 ; SIMD128-VM-NOT: i64x2
-; SIMD128: .param v128{{$}}
-; SIMD128: .result i64{{$}}
-; SIMD128: i64x2.extract_lane $push0=, $0, 1 # encoding: [0xfd,0x0e,0x01]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result i64{{$}}
+; SIMD128-NEXT: i64x2.extract_lane $push0=, $0, 1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define i64 @extract_v2i64(<2 x i64> %v) {
   %elem = extractelement <2 x i64> %v, i64 1
   ret i64 %elem
@@ -410,10 +393,10 @@ define i64 @extract_v2i64(<2 x i64> %v) {
 ; CHECK-LABEL: replace_v2i64:
 ; NO-SIMD128-NOT: i64x2
 ; SIMD128-VM-NOT: i64x2
-; SIMD128: .param v128, i64{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i64x2.replace_lane $push0=, $0, 0, $1 # encoding: [0xfd,0x14,0x00]{{$}}
-; SIMD128: return $pop0 # encoding: [0x0f]{{$}}
+; SIMD128-NEXT: .param v128, i64{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i64x2.replace_lane $push0=, $0, 0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i64> @replace_v2i64(<2 x i64> %v, i64 %x) {
   %res = insertelement <2 x i64> %v, i64 %x, i32 0
   ret <2 x i64> %res
@@ -421,14 +404,11 @@ define <2 x i64> @replace_v2i64(<2 x i64> %v, i64 %x) {
 
 ; CHECK-LABEL: shuffle_v2i64:
 ; NO-SIMD128-NOT: v8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v8x16.shuffle $push0=, $0, $1,
-; SIMD128-SAME: 0, 1, 2, 3, 4, 5, 6, 7, 24, 25, 26, 27, 28, 29, 30, 31
-; SIMD128-SAME: # encoding: [0xfd,0x17,
-; SIMD128-SAME: 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
-; SIMD128-SAME: 0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f]
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v8x16.shuffle $push0=, $0, $1,
+; SIMD128-SAME: 0, 1, 2, 3, 4, 5, 6, 7, 24, 25, 26, 27, 28, 29, 30, 31{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x i64> @shuffle_v2i64(<2 x i64> %x, <2 x i64> %y) {
   %res = shufflevector <2 x i64> %x, <2 x i64> %y, <2 x i32> <i32 0, i32 3>
   ret <2 x i64> %res
@@ -437,11 +417,11 @@ define <2 x i64> @shuffle_v2i64(<2 x i64> %x, <2 x i64> %y) {
 ; CHECK-LABEL: build_v2i64:
 ; NO-SIMD128-NOT: i64x2
 ; SIMD128-VM-NOT: i64x2
-; SIMD128: .param i64, i64{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: i64x2.splat $push0=, $0 # encoding: [0xfd,0x06]
-; SIMD128: i64x2.replace_lane $push1=, $pop0, 1, $1 # encoding: [0xfd,0x14,0x01]
-; SIMD128: return $pop1 # encoding: [0x0f]
+; SIMD128-NEXT: .param i64, i64{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: i64x2.splat $push0=, $0{{$}}
+; SIMD128-NEXT: i64x2.replace_lane $push1=, $pop0, 1, $1{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 define <2 x i64> @build_v2i64(i64 %x0, i64 %x1) {
   %t0 = insertelement <2 x i64> undef, i64 %x0, i32 0
   %res = insertelement <2 x i64> %t0, i64 %x1, i32 1
@@ -453,12 +433,10 @@ define <2 x i64> @build_v2i64(i64 %x0, i64 %x1) {
 ; ==============================================================================
 ; CHECK-LABEL: const_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.const $push0=,
-; SIMD128-SAME: 0x1.0402p-121, 0x1.0c0a08p-113, 0x1.14121p-105, 0x1.1c1a18p-97
-; SIMD128-SAME: # encoding: [0xfd,0x00,
-; SIMD128-SAME: 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
-; SIMD128-SAME: 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f]{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.const $push0=,
+; SIMD128-SAME: 0x1.0402p-121, 0x1.0c0a08p-113, 0x1.14121p-105, 0x1.1c1a18p-97{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x float> @const_v4f32() {
   ret <4 x float> <float 0x3860402000000000, float 0x38e0c0a080000000,
                    float 0x3961412100000000, float 0x39e1c1a180000000>
@@ -466,10 +444,10 @@ define <4 x float> @const_v4f32() {
 
 ; CHECK-LABEL: splat_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param f32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.splat $push0=, $0 # encoding: [0xfd,0x07]{{$}}
-; SIMD128: return $pop0 # encoding: [0x0f]{{$}}
+; SIMD128-NEXT: .param f32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.splat $push0=, $0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x float> @splat_v4f32(float %x) {
   %v = insertelement <4 x float> undef, float %x, i32 0
   %res = shufflevector <4 x float> %v, <4 x float> undef,
@@ -478,17 +456,17 @@ define <4 x float> @splat_v4f32(float %x) {
 }
 
 ; CHECK-LABEL: const_splat_v4f32
-; SIMD128; f32x4.splat
+; SIMD128: f32x4.splat
 define <4 x float> @const_splat_v4f32() {
   ret <4 x float> <float 42., float 42., float 42., float 42.>
 }
 
 ; CHECK-LABEL: extract_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128{{$}}
-; SIMD128: .result f32{{$}}
-; SIMD128: f32x4.extract_lane $push0=, $0, 3 # encoding: [0xfd,0x0f,0x03]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result f32{{$}}
+; SIMD128-NEXT: f32x4.extract_lane $push0=, $0, 3{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define float @extract_v4f32(<4 x float> %v) {
   %elem = extractelement <4 x float> %v, i32 3
   ret float %elem
@@ -496,10 +474,10 @@ define float @extract_v4f32(<4 x float> %v) {
 
 ; CHECK-LABEL: replace_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param v128, f32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.replace_lane $push0=, $0, 2, $1 # encoding: [0xfd,0x15,0x02]{{$}}
-; SIMD128: return $pop0 # encoding: [0x0f]{{$}}
+; SIMD128-NEXT: .param v128, f32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.replace_lane $push0=, $0, 2, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x float> @replace_v4f32(<4 x float> %v, float %x) {
   %res = insertelement <4 x float> %v, float %x, i32 2
   ret <4 x float> %res
@@ -507,14 +485,11 @@ define <4 x float> @replace_v4f32(<4 x float> %v, float %x) {
 
 ; CHECK-LABEL: shuffle_v4f32:
 ; NO-SIMD128-NOT: v8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v8x16.shuffle $push0=, $0, $1,
-; SIMD128-SAME: 0, 1, 2, 3, 20, 21, 22, 23, 8, 9, 10, 11, 28, 29, 30, 31
-; SIMD128-SAME: # encoding: [0xfd,0x17,
-; SIMD128-SAME: 0x00,0x01,0x02,0x03,0x14,0x15,0x16,0x17,
-; SIMD128-SAME: 0x08,0x09,0x0a,0x0b,0x1c,0x1d,0x1e,0x1f]
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v8x16.shuffle $push0=, $0, $1,
+; SIMD128-SAME: 0, 1, 2, 3, 20, 21, 22, 23, 8, 9, 10, 11, 28, 29, 30, 31{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <4 x float> @shuffle_v4f32(<4 x float> %x, <4 x float> %y) {
   %res = shufflevector <4 x float> %x, <4 x float> %y,
     <4 x i32> <i32 0, i32 5, i32 2, i32 7>
@@ -523,13 +498,13 @@ define <4 x float> @shuffle_v4f32(<4 x float> %x, <4 x float> %y) {
 
 ; CHECK-LABEL: build_v4f32:
 ; NO-SIMD128-NOT: f32x4
-; SIMD128: .param f32, f32, f32, f32{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f32x4.splat $push0=, $0 # encoding: [0xfd,0x07]
-; SIMD128: f32x4.replace_lane $push1=, $pop0, 1, $1 # encoding: [0xfd,0x15,0x01]
-; SIMD128: f32x4.replace_lane $push2=, $pop1, 2, $2 # encoding: [0xfd,0x15,0x02]
-; SIMD128: f32x4.replace_lane $push3=, $pop2, 3, $3 # encoding: [0xfd,0x15,0x03]
-; SIMD128: return $pop3 # encoding: [0x0f]
+; SIMD128-NEXT: .param f32, f32, f32, f32{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f32x4.splat $push0=, $0{{$}}
+; SIMD128-NEXT: f32x4.replace_lane $push1=, $pop0, 1, $1{{$}}
+; SIMD128-NEXT: f32x4.replace_lane $push2=, $pop1, 2, $2{{$}}
+; SIMD128-NEXT: f32x4.replace_lane $push3=, $pop2, 3, $3{{$}}
+; SIMD128-NEXT: return $pop3{{$}}
 define <4 x float> @build_v4f32(float %x0, float %x1, float %x2, float %x3) {
   %t0 = insertelement <4 x float> undef, float %x0, i32 0
   %t1 = insertelement <4 x float> %t0, float %x1, i32 1
@@ -543,11 +518,9 @@ define <4 x float> @build_v4f32(float %x0, float %x1, float %x2, float %x3) {
 ; ==============================================================================
 ; CHECK-LABEL: const_v2f64:
 ; NO-SIMD128-NOT: f64x2
-; SIMD128: .result v128{{$}}
-; SIMD128: v128.const $push0=, 0x1.60504030201p-911, 0x1.e0d0c0b0a0908p-783
-; SIMD128-SAME: # encoding: [0xfd,0x00,
-; SIMD128-SAME: 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
-; SIMD128-SAME: 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f]{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v128.const $push0=, 0x1.60504030201p-911, 0x1.e0d0c0b0a0908p-783{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x double> @const_v2f64() {
   ret <2 x double> <double 0x0706050403020100, double 0x0F0E0D0C0B0A0908>
 }
@@ -555,10 +528,10 @@ define <2 x double> @const_v2f64() {
 ; CHECK-LABEL: splat_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param f64{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.splat $push0=, $0 # encoding: [0xfd,0x08]{{$}}
-; SIMD128: return $pop0 # encoding: [0x0f]{{$}}
+; SIMD128-NEXT: .param f64{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.splat $push0=, $0{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x double> @splat_v2f64(double %x) {
   %t1 = insertelement <2 x double> zeroinitializer, double %x, i3 0
   %res = insertelement <2 x double> %t1, double %x, i32 1
@@ -566,7 +539,7 @@ define <2 x double> @splat_v2f64(double %x) {
 }
 
 ; CHECK-LABEL: const_splat_v2f64:
-; SIMD128; f64x2.splat
+; SIMD128: f64x2.splat
 define <2 x double> @const_splat_v2f64() {
   ret <2 x double> <double 42., double 42.>
 }
@@ -574,10 +547,10 @@ define <2 x double> @const_splat_v2f64() {
 ; CHECK-LABEL: extract_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128{{$}}
-; SIMD128: .result f64{{$}}
-; SIMD128: f64x2.extract_lane $push0=, $0, 1 # encoding: [0xfd,0x10,0x01]{{$}}
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128{{$}}
+; SIMD128-NEXT: .result f64{{$}}
+; SIMD128-NEXT: f64x2.extract_lane $push0=, $0, 1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define double @extract_v2f64(<2 x double> %v) {
   %elem = extractelement <2 x double> %v, i32 1
   ret double %elem
@@ -586,10 +559,10 @@ define double @extract_v2f64(<2 x double> %v) {
 ; CHECK-LABEL: replace_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param v128, f64{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.replace_lane $push0=, $0, 0, $1 # encoding: [0xfd,0x16,0x00]{{$}}
-; SIMD128: return $pop0 # encoding: [0x0f]{{$}}
+; SIMD128-NEXT: .param v128, f64{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.replace_lane $push0=, $0, 0, $1{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x double> @replace_v2f64(<2 x double> %v, double %x) {
   %res = insertelement <2 x double> %v, double %x, i32 0
   ret <2 x double> %res
@@ -597,14 +570,11 @@ define <2 x double> @replace_v2f64(<2 x double> %v, double %x) {
 
 ; CHECK-LABEL: shuffle_v2f64:
 ; NO-SIMD128-NOT: v8x16
-; SIMD128: .param v128, v128{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: v8x16.shuffle $push0=, $0, $1,
-; SIMD128-SAME: 0, 1, 2, 3, 4, 5, 6, 7, 24, 25, 26, 27, 28, 29, 30, 31
-; SIMD128-SAME: # encoding: [0xfd,0x17,
-; SIMD128-SAME: 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
-; SIMD128-SAME: 0x18,0x19,0x1a,0x1b,0x1c,0x1d,0x1e,0x1f]
-; SIMD128: return $pop0 #
+; SIMD128-NEXT: .param v128, v128{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: v8x16.shuffle $push0=, $0, $1,
+; SIMD128-SAME: 0, 1, 2, 3, 4, 5, 6, 7, 24, 25, 26, 27, 28, 29, 30, 31{{$}}
+; SIMD128-NEXT: return $pop0{{$}}
 define <2 x double> @shuffle_v2f64(<2 x double> %x, <2 x double> %y) {
   %res = shufflevector <2 x double> %x, <2 x double> %y,
     <2 x i32> <i32 0, i32 3>
@@ -614,11 +584,11 @@ define <2 x double> @shuffle_v2f64(<2 x double> %x, <2 x double> %y) {
 ; CHECK-LABEL: build_v2f64:
 ; NO-SIMD128-NOT: f64x2
 ; SIMD128-VM-NOT: f64x2
-; SIMD128: .param f64, f64{{$}}
-; SIMD128: .result v128{{$}}
-; SIMD128: f64x2.splat $push0=, $0 # encoding: [0xfd,0x08]
-; SIMD128: f64x2.replace_lane $push1=, $pop0, 1, $1 # encoding: [0xfd,0x16,0x01]
-; SIMD128: return $pop1 # encoding: [0x0f]
+; SIMD128-NEXT: .param f64, f64{{$}}
+; SIMD128-NEXT: .result v128{{$}}
+; SIMD128-NEXT: f64x2.splat $push0=, $0{{$}}
+; SIMD128-NEXT: f64x2.replace_lane $push1=, $pop0, 1, $1{{$}}
+; SIMD128-NEXT: return $pop1{{$}}
 define <2 x double> @build_v2f64(double %x0, double %x1) {
   %t0 = insertelement <2 x double> undef, double %x0, i32 0
   %res = insertelement <2 x double> %t0, double %x1, i32 1
diff --git a/llvm/test/MC/WebAssembly/simd-encodings.s b/llvm/test/MC/WebAssembly/simd-encodings.s
new file mode 100644
index 0000000..0c7aa20
--- /dev/null
+++ b/llvm/test/MC/WebAssembly/simd-encodings.s
@@ -0,0 +1,298 @@
+# RUN: llvm-mc -show-encoding -triple=wasm32-unkown-unknown -mattr=+sign-ext,+simd128 < %s | FileCheck %s
+
+    # CHECK: v128.const 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
+    # CHECK-SAME: # encoding: [0xfd,0x00,
+    # CHECK-SAME: 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
+    # CHECK-SAME: 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f]
+    v128.const 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
+
+    # CHECK: v128.const 256, 770, 1284, 1798, 2312, 2826, 3340, 3854
+    # CHECK-SAME: # encoding: [0xfd,0x00,
+    # CHECK-SAME: 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
+    # CHECK-SAME: 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f]
+    v128.const 256, 770, 1284, 1798, 2312, 2826, 3340, 3854
+
+    # TODO(tlively): Fix assembler so v128.const works with 4xi32 and 2xi64
+
+    # CHECK: v128.const 0x1.0402p-121, 0x1.0c0a08p-113,
+    # CHECK-SAME:       0x1.14121p-105, 0x1.1c1a18p-97
+    # CHECK-SAME: # encoding: [0xfd,0x00,
+    # CHECK-SAME: 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
+    # CHECK-SAME: 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f]
+    v128.const 0x1.0402p-121, 0x1.0c0a08p-113, 0x1.14121p-105, 0x1.1c1a18p-97
+
+    # CHECK: v128.const 0x1.60504030201p-911, 0x1.e0d0c0b0a0908p-783
+    # CHECK-SAME: # encoding: [0xfd,0x00,
+    # CHECK-SAME: 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
+    # CHECK-SAME: 0x08,0x09,0x0a,0x0b,0x0c,0x0d,0x0e,0x0f]
+    v128.const 0x1.60504030201p-911, 0x1.e0d0c0b0a0908p-783
+
+    # CHECK: v128.load 48:p2align=0 # encoding: [0xfd,0x01,0x00,0x30]
+    v128.load 48
+
+    # CHECK: v128.store 48:p2align=0 # encoding: [0xfd,0x02,0x00,0x30]
+    v128.store 48
+
+    # CHECK: i8x16.splat # encoding: [0xfd,0x03]
+    i8x16.splat
+
+    # CHECK: i16x8.splat # encoding: [0xfd,0x04]
+    i16x8.splat
+
+    # CHECK: i32x4.splat # encoding: [0xfd,0x05]
+    i32x4.splat
+
+    # CHECK: i64x2.splat # encoding: [0xfd,0x06]
+    i64x2.splat
+
+    # CHECK: f32x4.splat # encoding: [0xfd,0x07]
+    f32x4.splat
+
+    # CHECK: f64x2.splat # encoding: [0xfd,0x08]
+    f64x2.splat
+
+    # CHECK: i8x16.extract_lane_s 15 # encoding: [0xfd,0x09,0x0f]
+    i8x16.extract_lane_s 15
+
+    # CHECK: i8x16.extract_lane_u 15 # encoding: [0xfd,0x0a,0x0f]
+    i8x16.extract_lane_u 15
+
+    # CHECK: i16x8.extract_lane_s 7 # encoding: [0xfd,0x0b,0x07]
+    i16x8.extract_lane_s 7
+
+    # CHECK: i16x8.extract_lane_u 7 # encoding: [0xfd,0x0c,0x07]
+    i16x8.extract_lane_u 7
+
+    # CHECK: i32x4.extract_lane 3 # encoding: [0xfd,0x0d,0x03]
+    i32x4.extract_lane 3
+
+    # CHECK: i64x2.extract_lane 1 # encoding: [0xfd,0x0e,0x01]
+    i64x2.extract_lane 1
+
+    # CHECK: f32x4.extract_lane 3 # encoding: [0xfd,0x0f,0x03]
+    f32x4.extract_lane 3
+
+    # CHECK: f64x2.extract_lane 1 # encoding: [0xfd,0x10,0x01]
+    f64x2.extract_lane 1
+
+    # CHECK: i8x16.replace_lane 15 # encoding: [0xfd,0x11,0x0f]
+    i8x16.replace_lane 15
+
+    # CHECK: i16x8.replace_lane 7 # encoding: [0xfd,0x12,0x07]
+    i16x8.replace_lane 7
+
+    # CHECK: i32x4.replace_lane 3 # encoding: [0xfd,0x13,0x03]
+    i32x4.replace_lane 3
+
+    # CHECK: i64x2.replace_lane 1 # encoding: [0xfd,0x14,0x01]
+    i64x2.replace_lane 1
+
+    # CHECK: f32x4.replace_lane 3 # encoding: [0xfd,0x15,0x03]
+    f32x4.replace_lane 3
+
+    # CHECK: f64x2.replace_lane 1 # encoding: [0xfd,0x16,0x01]
+    f64x2.replace_lane 1
+
+    # CHECK: v8x16.shuffle 0, 17, 2, 19, 4, 21, 6, 23,
+    # CHECK-SAME:          8, 25, 10, 27, 12, 29, 14, 31
+    # CHECK-SAME: # encoding: [0xfd,0x17,
+    # CHECK-SAME: 0x00,0x11,0x02,0x13,0x04,0x15,0x06,0x17,
+    # CHECK-SAME: 0x08,0x19,0x0a,0x1b,0x0c,0x1d,0x0e,0x1f]
+    v8x16.shuffle 0, 17, 2, 19, 4, 21, 6, 23, 8, 25, 10, 27, 12, 29, 14, 31
+
+    # CHECK: i8x16.add # encoding: [0xfd,0x18]
+    i8x16.add
+
+    # CHECK: i16x8.add # encoding: [0xfd,0x19]
+    i16x8.add
+
+    # CHECK: i32x4.add # encoding: [0xfd,0x1a]
+    i32x4.add
+
+    # CHECK: i64x2.add # encoding: [0xfd,0x1b]
+    i64x2.add
+
+    # CHECK: i8x16.sub # encoding: [0xfd,0x1c]
+    i8x16.sub
+
+    # CHECK: i16x8.sub # encoding: [0xfd,0x1d]
+    i16x8.sub
+
+    # CHECK: i32x4.sub # encoding: [0xfd,0x1e]
+    i32x4.sub
+
+    # CHECK: i64x2.sub # encoding: [0xfd,0x1f]
+    i64x2.sub
+
+    # CHECK: i8x16.mul # encoding: [0xfd,0x20]
+    i8x16.mul
+
+    # CHECK: i16x8.mul # encoding: [0xfd,0x21]
+    i16x8.mul
+
+    # CHECK: i32x4.mul # encoding: [0xfd,0x22]
+    i32x4.mul
+
+    # CHECK: v128.and # encoding: [0xfd,0x3b]
+    v128.and
+
+    # CHECK: v128.or # encoding: [0xfd,0x3c]
+    v128.or
+
+    # CHECK: v128.xor # encoding: [0xfd,0x3d]
+    v128.xor
+
+    # CHECK: v128.not # encoding: [0xfd,0x3e]
+    v128.not
+
+    # CHECK: i8x16.eq # encoding: [0xfd,0x48]
+    i8x16.eq
+
+    # CHECK: i16x8.eq # encoding: [0xfd,0x49]
+    i16x8.eq
+
+    # CHECK: i32x4.eq # encoding: [0xfd,0x4a]
+    i32x4.eq
+
+    # CHECK: f32x4.eq # encoding: [0xfd,0x4b]
+    f32x4.eq
+
+    # CHECK: f64x2.eq # encoding: [0xfd,0x4c]
+    f64x2.eq
+
+    # CHECK: i8x16.ne # encoding: [0xfd,0x4d]
+    i8x16.ne
+
+    # CHECK: i16x8.ne # encoding: [0xfd,0x4e]
+    i16x8.ne
+
+    # CHECK: i32x4.ne # encoding: [0xfd,0x4f]
+    i32x4.ne
+
+    # CHECK: f32x4.ne # encoding: [0xfd,0x50]
+    f32x4.ne
+
+    # CHECK: f64x2.ne # encoding: [0xfd,0x51]
+    f64x2.ne
+
+    # CHECK: i8x16.lt_s # encoding: [0xfd,0x52]
+    i8x16.lt_s
+
+    # CHECK: i8x16.lt_u # encoding: [0xfd,0x53]
+    i8x16.lt_u
+
+    # CHECK: i16x8.lt_s # encoding: [0xfd,0x54]
+    i16x8.lt_s
+
+    # CHECK: i16x8.lt_u # encoding: [0xfd,0x55]
+    i16x8.lt_u
+
+    # CHECK: i32x4.lt_s # encoding: [0xfd,0x56]
+    i32x4.lt_s
+
+    # CHECK: i32x4.lt_u # encoding: [0xfd,0x57]
+    i32x4.lt_u
+
+    # CHECK: f32x4.lt # encoding: [0xfd,0x58]
+    f32x4.lt
+
+    # CHECK: f64x2.lt # encoding: [0xfd,0x59]
+    f64x2.lt
+
+    # CHECK: i8x16.le_s # encoding: [0xfd,0x5a]
+    i8x16.le_s
+
+    # CHECK: i8x16.le_u # encoding: [0xfd,0x5b]
+    i8x16.le_u
+
+    # CHECK: i16x8.le_s # encoding: [0xfd,0x5c]
+    i16x8.le_s
+
+    # CHECK: i16x8.le_u # encoding: [0xfd,0x5d]
+    i16x8.le_u
+
+    # CHECK: i32x4.le_s # encoding: [0xfd,0x5e]
+    i32x4.le_s
+
+    # CHECK: i32x4.le_u # encoding: [0xfd,0x5f]
+    i32x4.le_u
+
+    # CHECK: f32x4.le # encoding: [0xfd,0x60]
+    f32x4.le
+
+    # CHECK: f64x2.le # encoding: [0xfd,0x61]
+    f64x2.le
+
+    # CHECK: i8x16.gt_s # encoding: [0xfd,0x62]
+    i8x16.gt_s
+
+    # CHECK: i8x16.gt_u # encoding: [0xfd,0x63]
+    i8x16.gt_u
+
+    # CHECK: i16x8.gt_s # encoding: [0xfd,0x64]
+    i16x8.gt_s
+
+    # CHECK: i16x8.gt_u # encoding: [0xfd,0x65]
+    i16x8.gt_u
+
+    # CHECK: i32x4.gt_s # encoding: [0xfd,0x66]
+    i32x4.gt_s
+
+    # CHECK: i32x4.gt_u # encoding: [0xfd,0x67]
+    i32x4.gt_u
+
+    # CHECK: f32x4.gt # encoding: [0xfd,0x68]
+    f32x4.gt
+
+    # CHECK: f64x2.gt # encoding: [0xfd,0x69]
+    f64x2.gt
+
+    # CHECK: i8x16.ge_s # encoding: [0xfd,0x6a]
+    i8x16.ge_s
+
+    # CHECK: i8x16.ge_u # encoding: [0xfd,0x6b]
+    i8x16.ge_u
+
+    # CHECK: i16x8.ge_s # encoding: [0xfd,0x6c]
+    i16x8.ge_s
+
+    # CHECK: i16x8.ge_u # encoding: [0xfd,0x6d]
+    i16x8.ge_u
+
+    # CHECK: i32x4.ge_s # encoding: [0xfd,0x6e]
+    i32x4.ge_s
+
+    # CHECK: i32x4.ge_u # encoding: [0xfd,0x6f]
+    i32x4.ge_u
+
+    # CHECK: f32x4.ge # encoding: [0xfd,0x70]
+    f32x4.ge
+
+    # CHECK: f64x2.ge # encoding: [0xfd,0x71]
+    f64x2.ge
+
+    # CHECK: f32x4.add # encoding: [0xfd,0x7a]
+    f32x4.add
+
+    # CHECK: f64x2.add # encoding: [0xfd,0x7b]
+    f64x2.add
+
+    # CHECK: f32x4.sub # encoding: [0xfd,0x7c]
+    f32x4.sub
+
+    # CHECK: f64x2.sub # encoding: [0xfd,0x7d]
+    f64x2.sub
+
+    # CHECK: f32x4.div # encoding: [0xfd,0x7e]
+    f32x4.div
+
+    # CHECK: f64x2.div # encoding: [0xfd,0x7f]
+    f64x2.div
+
+    # CHECK: f32x4.mul # encoding: [0xfd,0x80]
+    f32x4.mul
+
+    # CHECK: f64x2.mul # encoding: [0xfd,0x81]
+    f64x2.mul
+
+    end_function
-- 
2.7.4