[llvm] [X86] Don't request 0x90 nop filling in p2align directives (PR #110134)

Jeremy Morse via llvm-commits llvm-commits at lists.llvm.org
Thu Sep 26 08:36:47 PDT 2024


https://github.com/jmorse created https://github.com/llvm/llvm-project/pull/110134

As of rev ea222be0d, LLVMs assembler will actually try to honour the "fill value" part of p2align directives. X86 always prints these as 0x90, however, I don't believe that's what it actually wants. If you compile an LLVM-IR file with -filetype=obj, you'll get multi-byte nops for .text padding.  If you go via a textual assembly file, you'll now get single-byte-nop padding. This divergent behaviour is undesirable IMO.

To fix: don't set the byte padding field for x86 which allows the assembler to pick multi-byte nops. Test that we get the same multi-byte padding when compiled via textual assembly or directly to object file. Added same-align-bytes-with-llasm-llobj.ll to that effect.

A whole load of test files get updated because of this change: the vast majority of them are co-incidental. The most suspicious ones are:
 *  loop-align-debug.ll: this is actually checking for line-number assignments,
 *  xray-tail-call-sled.ll: XRay installs a nop sled for reasons I don't understand, but it's independent of .p2align,
 * code-align-loops.ll: is checking that various IR constructs lead to .p2align directives, not what the padding is,

Everything else looked totally coincidental.

>From 4f2c3dea86e1dd8ffdc7bb042c3e249ee762bf0b Mon Sep 17 00:00:00 2001
From: Jeremy Morse <jeremy.morse at sony.com>
Date: Thu, 26 Sep 2024 15:34:02 +0100
Subject: [PATCH] [X86] Don't request 0x90 nop filling in p2align directives

As of rev ea222be0d, LLVMs assembler will actually try to honour the "fill
value" part of p2align directives. X86 always prints these as 0x90,
however, I don't believe that's what it actually wants. If you compile an
LLVM-IR file with -filetype=obj, you'll get multi-byte nops for .text
padding.  If you go via a textual assembly file, you'll now get
single-byte-nop padding. This divergent behaviour is undesirable IMO.

To fix: don't set the byte padding field for x86, and test that we get the
same multi-byte padding when compiled via textual assembly. Added
same-align-bytes-with-llasm-llobj.ll to that effect.
---
 .../Target/X86/MCTargetDesc/X86MCAsmInfo.cpp  |  12 +-
 .../CodeGen/X86/2006-08-21-ExtraMovInst.ll    |   2 +-
 .../CodeGen/X86/2007-01-13-StackPtrIndex.ll   |  34 +-
 .../CodeGen/X86/2007-03-15-GEP-Idx-Sink.ll    |   2 +-
 .../X86/2007-10-12-CoalesceExtSubReg.ll       |   2 +-
 .../CodeGen/X86/2007-10-12-SpillerUnfold2.ll  |   2 +-
 .../test/CodeGen/X86/2007-11-06-InstrSched.ll |   2 +-
 .../CodeGen/X86/2007-11-30-LoadFolding-Bug.ll |   6 +-
 .../CodeGen/X86/2008-04-28-CoalescerBug.ll    |   6 +-
 llvm/test/CodeGen/X86/2008-08-06-CmpStride.ll |   2 +-
 .../2008-12-01-loop-iv-used-outside-loop.ll   |   2 +-
 .../CodeGen/X86/2009-02-26-MachineLICMBug.ll  |   2 +-
 .../CodeGen/X86/2009-04-25-CoalescerBug.ll    |   2 +-
 llvm/test/CodeGen/X86/2009-08-12-badswitch.ll |   2 +-
 .../X86/2020_12_02_decrementing_loop.ll       |   8 +-
 llvm/test/CodeGen/X86/AMX/amx-across-func.ll  |   8 +-
 .../CodeGen/X86/AMX/amx-ldtilecfg-insert.ll   |   4 +-
 .../CodeGen/X86/AMX/amx-lower-tile-copy.ll    |   8 +-
 llvm/test/CodeGen/X86/AMX/amx-spill-merge.ll  |   4 +-
 llvm/test/CodeGen/X86/AMX/amx-tile-basic.ll   |   4 +-
 .../CodeGen/X86/MachineSink-Issue98477.ll     |   2 +-
 .../CodeGen/X86/MergeConsecutiveStores.ll     |  82 ++--
 .../X86/PR71178-register-coalescer-crash.ll   |   2 +-
 llvm/test/CodeGen/X86/SwitchLowering.ll       |   2 +-
 llvm/test/CodeGen/X86/addr-mode-matcher-2.ll  |  24 +-
 .../X86/align-basic-block-sections.mir        |   2 +-
 llvm/test/CodeGen/X86/and-sink.ll             |   2 +-
 llvm/test/CodeGen/X86/apx/push2-pop2.ll       |   6 +-
 llvm/test/CodeGen/X86/apx/setzucc.ll          |   2 +-
 llvm/test/CodeGen/X86/assertzext-demanded.ll  |   4 +-
 .../CodeGen/X86/atom-pad-short-functions.ll   |   2 +-
 llvm/test/CodeGen/X86/atomic-bit-test.ll      |  14 +-
 llvm/test/CodeGen/X86/atomic-flags.ll         |   2 +-
 llvm/test/CodeGen/X86/atomic-idempotent.ll    |  24 +-
 llvm/test/CodeGen/X86/atomic-minmax-i6432.ll  |  20 +-
 .../CodeGen/X86/atomic-non-integer-fp128.ll   |   6 +-
 llvm/test/CodeGen/X86/atomic-non-integer.ll   |   8 +-
 .../test/CodeGen/X86/atomic-rm-bit-test-64.ll |  74 ++--
 llvm/test/CodeGen/X86/atomic-rm-bit-test.ll   | 340 ++++++++---------
 llvm/test/CodeGen/X86/atomic-xor.ll           |   8 +-
 llvm/test/CodeGen/X86/atomic128.ll            |  23 +-
 .../CodeGen/X86/atomicrmw-cond-sub-clamp.ll   |  32 +-
 .../CodeGen/X86/atomicrmw-fadd-fp-vector.ll   |   4 +-
 .../CodeGen/X86/atomicrmw-uinc-udec-wrap.ll   |  16 +-
 llvm/test/CodeGen/X86/avx-cmp.ll              |   2 +-
 llvm/test/CodeGen/X86/avx-vbroadcast.ll       |   4 +-
 llvm/test/CodeGen/X86/avx-vzeroupper.ll       |  16 +-
 llvm/test/CodeGen/X86/avx2-vbroadcast.ll      |   4 +-
 .../CodeGen/X86/avx512-broadcast-unfold.ll    | 264 ++++++-------
 llvm/test/CodeGen/X86/avx512-i1test.ll        |   2 +-
 llvm/test/CodeGen/X86/avx512vnni-combine.ll   |   6 +-
 llvm/test/CodeGen/X86/avxvnni-combine.ll      |  24 +-
 llvm/test/CodeGen/X86/block-placement.ll      |   6 +-
 llvm/test/CodeGen/X86/break-false-dep.ll      |  40 +-
 .../CodeGen/X86/callbr-asm-blockplacement.ll  |   2 +-
 llvm/test/CodeGen/X86/cast-vsel.ll            |  16 +-
 .../test/CodeGen/X86/cmpxchg-clobber-flags.ll |   8 +-
 llvm/test/CodeGen/X86/cmpxchg-i128-i1.ll      |   2 +-
 llvm/test/CodeGen/X86/coalesce-esp.ll         |   2 +-
 ...r-breaks-subreg-to-reg-liveness-reduced.ll |   2 +-
 llvm/test/CodeGen/X86/coalescer-commute1.ll   |   2 +-
 llvm/test/CodeGen/X86/coalescer-commute4.ll   |   2 +-
 .../X86/coalescer-dead-flag-verifier-error.ll |   8 +-
 llvm/test/CodeGen/X86/code-align-loops.ll     |  28 +-
 .../CodeGen/X86/code_placement_align_all.ll   |   6 +-
 llvm/test/CodeGen/X86/combine-pmuldq.ll       |  24 +-
 .../test/CodeGen/X86/constant-pool-sharing.ll |   8 +-
 llvm/test/CodeGen/X86/copy-eflags.ll          |   4 +-
 .../CodeGen/X86/dag-update-nodetomatch.ll     |   6 +-
 .../X86/div-rem-pair-recomposition-signed.ll  |   2 +-
 .../div-rem-pair-recomposition-unsigned.ll    |   2 +-
 llvm/test/CodeGen/X86/fdiv-combine.ll         |   2 +-
 llvm/test/CodeGen/X86/fixup-lea.ll            |   8 +-
 llvm/test/CodeGen/X86/fma-commute-loop.ll     |   2 +-
 .../X86/fma-intrinsics-phi-213-to-231.ll      |  48 +--
 llvm/test/CodeGen/X86/fold-call-3.ll          |   4 +-
 llvm/test/CodeGen/X86/fold-loop-of-urem.ll    |  56 +--
 llvm/test/CodeGen/X86/fp-une-cmp.ll           |   2 +-
 llvm/test/CodeGen/X86/hoist-invariant-load.ll |  12 +-
 llvm/test/CodeGen/X86/i128-mul.ll             |   8 +-
 llvm/test/CodeGen/X86/i386-shrink-wrapping.ll |   4 +-
 llvm/test/CodeGen/X86/icmp-shift-opt.ll       |   4 +-
 llvm/test/CodeGen/X86/ifunc-asm.ll            |   6 +-
 .../CodeGen/X86/innermost-loop-alignment.ll   |  12 +-
 .../test/CodeGen/X86/ins_subreg_coalesce-3.ll |   4 +-
 llvm/test/CodeGen/X86/issue76416.ll           |   4 +-
 .../X86/kcfi-patchable-function-prefix.ll     |   8 +-
 llvm/test/CodeGen/X86/kcfi.ll                 |   2 +-
 llvm/test/CodeGen/X86/known-bits.ll           |   8 +-
 llvm/test/CodeGen/X86/lea-opt-cse2.ll         |   4 +-
 llvm/test/CodeGen/X86/lea-opt-cse4.ll         |   4 +-
 llvm/test/CodeGen/X86/licm-symbol.ll          |   2 +-
 llvm/test/CodeGen/X86/loop-search.ll          |   2 +-
 .../test/CodeGen/X86/loop-strength-reduce5.ll |   2 +-
 .../test/CodeGen/X86/loop-strength-reduce7.ll |   4 +-
 llvm/test/CodeGen/X86/lsr-addrecloops.ll      |  10 +-
 llvm/test/CodeGen/X86/lsr-interesting-step.ll |   4 +-
 llvm/test/CodeGen/X86/lsr-loop-exit-cond.ll   |   8 +-
 llvm/test/CodeGen/X86/lsr-negative-stride.ll  |   6 +-
 llvm/test/CodeGen/X86/lsr-sort.ll             |   2 +-
 llvm/test/CodeGen/X86/lsr-static-addr.ll      |   4 +-
 llvm/test/CodeGen/X86/machine-cp.ll           |   4 +-
 llvm/test/CodeGen/X86/machine-cse.ll          |   4 +-
 llvm/test/CodeGen/X86/madd.ll                 | 102 ++---
 llvm/test/CodeGen/X86/masked-iv-safe.ll       |  16 +-
 llvm/test/CodeGen/X86/masked-iv-unsafe.ll     |  26 +-
 llvm/test/CodeGen/X86/merge_store.ll          |   2 +-
 .../CodeGen/X86/min-legal-vector-width.ll     |  24 +-
 llvm/test/CodeGen/X86/mmx-arith.ll            |   4 +-
 .../X86/negative-stride-fptosi-user.ll        |   2 +-
 llvm/test/CodeGen/X86/optimize-max-0.ll       |  20 +-
 llvm/test/CodeGen/X86/optimize-max-1.ll       |   8 +-
 llvm/test/CodeGen/X86/optimize-max-2.ll       |   2 +-
 llvm/test/CodeGen/X86/or-address.ll           |   4 +-
 .../CodeGen/X86/overflowing-iv-codegen.ll     |  10 +-
 llvm/test/CodeGen/X86/patchable-prologue.ll   |  12 +-
 llvm/test/CodeGen/X86/pcsections-atomics.ll   | 354 +++++++++---------
 llvm/test/CodeGen/X86/peep-test-0.ll          |   2 +-
 llvm/test/CodeGen/X86/peep-test-1.ll          |   2 +-
 llvm/test/CodeGen/X86/peephole-copy.ll        |   2 +-
 llvm/test/CodeGen/X86/pic-load-remat.ll       |   2 +-
 llvm/test/CodeGen/X86/postalloc-coalescing.ll |   2 +-
 llvm/test/CodeGen/X86/pr14314.ll              |   2 +-
 llvm/test/CodeGen/X86/pr22338.ll              |   4 +-
 llvm/test/CodeGen/X86/pr30562.ll              |   2 +-
 llvm/test/CodeGen/X86/pr32108.ll              |   2 +-
 llvm/test/CodeGen/X86/pr33290.ll              |   4 +-
 llvm/test/CodeGen/X86/pr33747.ll              |   4 +-
 llvm/test/CodeGen/X86/pr37916.ll              |   2 +-
 llvm/test/CodeGen/X86/pr38185.ll              |   2 +-
 llvm/test/CodeGen/X86/pr38217.ll              |   2 +-
 llvm/test/CodeGen/X86/pr38539.ll              |   2 +-
 llvm/test/CodeGen/X86/pr38795.ll              |  20 +-
 llvm/test/CodeGen/X86/pr42565.ll              |   2 +-
 llvm/test/CodeGen/X86/pr42909.ll              |   2 +-
 llvm/test/CodeGen/X86/pr43529.ll              |   2 +-
 llvm/test/CodeGen/X86/pr44140.ll              |   2 +-
 llvm/test/CodeGen/X86/pr44412.ll              |   4 +-
 llvm/test/CodeGen/X86/pr47874.ll              |  16 +-
 llvm/test/CodeGen/X86/pr49393.ll              |   2 +-
 llvm/test/CodeGen/X86/pr49451.ll              |   4 +-
 llvm/test/CodeGen/X86/pr50374.ll              |   2 +-
 llvm/test/CodeGen/X86/pr50782.ll              |   2 +-
 llvm/test/CodeGen/X86/pr51371.ll              |   4 +-
 llvm/test/CodeGen/X86/pr5145.ll               |   8 +-
 llvm/test/CodeGen/X86/pr51615.ll              |   4 +-
 llvm/test/CodeGen/X86/pr53842.ll              |   2 +-
 .../X86/pr53990-incorrect-machine-sink.ll     |   2 +-
 llvm/test/CodeGen/X86/pr55648.ll              |   2 +-
 llvm/test/CodeGen/X86/pr61923.ll              |   2 +-
 llvm/test/CodeGen/X86/pr63108.ll              |   8 +-
 llvm/test/CodeGen/X86/pr63692.ll              |   2 +-
 llvm/test/CodeGen/X86/pr65895.ll              |   2 +-
 llvm/test/CodeGen/X86/pr68539.ll              |   2 +-
 llvm/test/CodeGen/X86/pr93000.ll              |   2 +-
 .../test/CodeGen/X86/promote-sra-by-itself.ll |   2 +-
 llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll |  24 +-
 llvm/test/CodeGen/X86/rdrand.ll               |   4 +-
 llvm/test/CodeGen/X86/retpoline.ll            |  10 +-
 llvm/test/CodeGen/X86/reverse_branches.ll     |  10 +-
 llvm/test/CodeGen/X86/sad.ll                  |  34 +-
 llvm/test/CodeGen/X86/saddo-redundant-add.ll  |   2 +-
 .../X86/same-align-bytes-with-llasm-llobj.ll  |  46 +++
 llvm/test/CodeGen/X86/scalar_widen_div.ll     |   2 +-
 llvm/test/CodeGen/X86/setcc-lowering.ll       |   6 +-
 .../test/CodeGen/X86/setcc-non-simple-type.ll |   8 +-
 llvm/test/CodeGen/X86/shift-parts.ll          |   2 +-
 llvm/test/CodeGen/X86/sink-out-of-loop.ll     |  10 +-
 .../CodeGen/X86/speculative-load-hardening.ll |  16 +-
 .../CodeGen/X86/split-extend-vector-inreg.ll  |   2 +-
 llvm/test/CodeGen/X86/sse-domains.ll          |   2 +-
 llvm/test/CodeGen/X86/stack-coloring-wineh.ll |   8 +-
 llvm/test/CodeGen/X86/switch.ll               |   2 +-
 .../X86/tail-dup-merge-loop-headers.ll        |   8 +-
 .../X86/tail-dup-multiple-latch-loop.ll       |  14 +-
 llvm/test/CodeGen/X86/tail-dup-partial.ll     |   6 +-
 llvm/test/CodeGen/X86/tail-dup-repeat.ll      |   4 +-
 llvm/test/CodeGen/X86/tailcall-cgp-dup.ll     |   2 +-
 llvm/test/CodeGen/X86/tls-loads-control3.ll   |   8 +-
 llvm/test/CodeGen/X86/trunc-store.ll          |   2 +-
 llvm/test/CodeGen/X86/twoaddr-coalesce.ll     |   2 +-
 llvm/test/CodeGen/X86/twoaddr-lea.ll          |   8 +-
 llvm/test/CodeGen/X86/unaligned-load.ll       |  12 +-
 llvm/test/CodeGen/X86/undef-label.ll          |   2 +-
 llvm/test/CodeGen/X86/vec_setcc-2.ll          |   8 +-
 llvm/test/CodeGen/X86/vector-fshl-128.ll      |  24 +-
 llvm/test/CodeGen/X86/vector-fshl-256.ll      |  20 +-
 llvm/test/CodeGen/X86/vector-pack-128.ll      |   2 +-
 .../X86/vector-shift-by-select-loop.ll        |  24 +-
 .../CodeGen/X86/vector-shuffle-combining.ll   |   2 +-
 llvm/test/CodeGen/X86/vselect-avx.ll          |   2 +-
 llvm/test/CodeGen/X86/widen_arith-1.ll        |   2 +-
 llvm/test/CodeGen/X86/widen_arith-2.ll        |   2 +-
 llvm/test/CodeGen/X86/widen_arith-3.ll        |   2 +-
 llvm/test/CodeGen/X86/widen_arith-4.ll        |   4 +-
 llvm/test/CodeGen/X86/widen_arith-5.ll        |   2 +-
 llvm/test/CodeGen/X86/widen_arith-6.ll        |   2 +-
 llvm/test/CodeGen/X86/widen_cast-1.ll         |   4 +-
 llvm/test/CodeGen/X86/widen_cast-2.ll         |   2 +-
 llvm/test/CodeGen/X86/widen_cast-4.ll         |   2 +-
 llvm/test/CodeGen/X86/x86-shrink-wrapping.ll  |  48 +--
 .../CodeGen/X86/x86-win64-shrink-wrapping.ll  |   8 +-
 llvm/test/CodeGen/X86/xor.ll                  |  24 +-
 .../X86/xray-attribute-instrumentation.ll     |  10 +-
 llvm/test/CodeGen/X86/xray-custom-log.ll      |   2 +-
 ...xray-partial-instrumentation-skip-entry.ll |   6 +-
 .../xray-partial-instrumentation-skip-exit.ll |   4 +-
 .../X86/xray-selective-instrumentation.ll     |   4 +-
 llvm/test/CodeGen/X86/xray-tail-call-sled.ll  |  14 +-
 llvm/test/DebugInfo/COFF/pieces.ll            |   2 +-
 llvm/test/DebugInfo/X86/header.ll             |   2 +-
 llvm/test/DebugInfo/X86/loop-align-debug.ll   |   2 +-
 .../X86/2011-11-29-postincphi.ll              |   2 +-
 .../LoopStrengthReduce/X86/ivchain-X86.ll     |  24 +-
 .../LoopStrengthReduce/X86/lsr-insns-1.ll     |   2 +-
 .../LoopStrengthReduce/X86/macro-fuse-cmp.ll  |   4 +-
 216 files changed, 1425 insertions(+), 1376 deletions(-)
 create mode 100644 llvm/test/CodeGen/X86/same-align-bytes-with-llasm-llobj.ll

diff --git a/llvm/lib/Target/X86/MCTargetDesc/X86MCAsmInfo.cpp b/llvm/lib/Target/X86/MCTargetDesc/X86MCAsmInfo.cpp
index 3ce044387ada29..5f5c4055bf1ba1 100644
--- a/llvm/lib/Target/X86/MCTargetDesc/X86MCAsmInfo.cpp
+++ b/llvm/lib/Target/X86/MCTargetDesc/X86MCAsmInfo.cpp
@@ -43,7 +43,8 @@ X86MCAsmInfoDarwin::X86MCAsmInfoDarwin(const Triple &T) {
 
   AssemblerDialect = AsmWriterFlavor;
 
-  TextAlignFillValue = 0x90;
+  // This will be padded with appropriately sized nops.
+  TextAlignFillValue = 0;
 
   if (!is64Bit)
     Data64bitsDirective = nullptr;       // we can't emit a 64-bit unit
@@ -93,7 +94,8 @@ X86ELFMCAsmInfo::X86ELFMCAsmInfo(const Triple &T) {
 
   AssemblerDialect = AsmWriterFlavor;
 
-  TextAlignFillValue = 0x90;
+  // This will be padded with appropriately sized nops.
+  TextAlignFillValue = 0;
 
   // Debug Information
   SupportsDebugInformation = true;
@@ -132,7 +134,8 @@ X86MCAsmInfoMicrosoft::X86MCAsmInfoMicrosoft(const Triple &Triple) {
 
   AssemblerDialect = AsmWriterFlavor;
 
-  TextAlignFillValue = 0x90;
+  // This will be padded with appropriately sized nops.
+  TextAlignFillValue = 0;
 
   AllowAtInName = true;
 }
@@ -167,7 +170,8 @@ X86MCAsmInfoGNUCOFF::X86MCAsmInfoGNUCOFF(const Triple &Triple) {
 
   AssemblerDialect = AsmWriterFlavor;
 
-  TextAlignFillValue = 0x90;
+  // This will be padded with appropriately sized nops.
+  TextAlignFillValue = 0;
 
   AllowAtInName = true;
 }
diff --git a/llvm/test/CodeGen/X86/2006-08-21-ExtraMovInst.ll b/llvm/test/CodeGen/X86/2006-08-21-ExtraMovInst.ll
index ac749bccb3c55d..f3bdf561a94569 100644
--- a/llvm/test/CodeGen/X86/2006-08-21-ExtraMovInst.ll
+++ b/llvm/test/CodeGen/X86/2006-08-21-ExtraMovInst.ll
@@ -7,7 +7,7 @@ define i32 @foo(i32 %t, i32 %C) {
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; CHECK-NEXT:    decl %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %cond_true
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    incl %eax
diff --git a/llvm/test/CodeGen/X86/2007-01-13-StackPtrIndex.ll b/llvm/test/CodeGen/X86/2007-01-13-StackPtrIndex.ll
index 46dddd8fcd851a..1e5ee2f71d9b47 100644
--- a/llvm/test/CodeGen/X86/2007-01-13-StackPtrIndex.ll
+++ b/llvm/test/CodeGen/X86/2007-01-13-StackPtrIndex.ll
@@ -27,7 +27,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    js .LBB0_14
 ; CHECK-NEXT:  # %bb.12:
 ; CHECK-NEXT:    xorl %r8d, %r8d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_13: # %a25b
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb %r8b, %r8b
@@ -38,7 +38,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    jne .LBB0_1
 ; CHECK-NEXT:  # %bb.15:
 ; CHECK-NEXT:    xorl %r8d, %r8d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_16: # %a25b140
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb %r8b, %r8b
@@ -56,7 +56,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    xorps %xmm0, %xmm0
 ; CHECK-NEXT:    movb $1, %r10b
 ; CHECK-NEXT:    jmp .LBB0_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_9: # %b1606
 ; CHECK-NEXT:    # in Loop: Header=BB0_3 Depth=1
 ; CHECK-NEXT:    testb %r9b, %r9b
@@ -83,7 +83,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    # in Loop: Header=BB0_3 Depth=1
 ; CHECK-NEXT:    testq %rdx, %rdx
 ; CHECK-NEXT:    js .LBB0_18
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_36: # %a30b
 ; CHECK-NEXT:    # Parent Loop BB0_3 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
@@ -93,7 +93,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    # in Loop: Header=BB0_3 Depth=1
 ; CHECK-NEXT:    testb %r10b, %r10b
 ; CHECK-NEXT:    jne .LBB0_4
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_19: # %a30b294
 ; CHECK-NEXT:    # Parent Loop BB0_3 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
@@ -115,7 +115,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    # in Loop: Header=BB0_3 Depth=1
 ; CHECK-NEXT:    testb %r8b, %r8b
 ; CHECK-NEXT:    jne .LBB0_8
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_33: # %a74b
 ; CHECK-NEXT:    # Parent Loop BB0_3 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
@@ -128,7 +128,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    # in Loop: Header=BB0_3 Depth=1
 ; CHECK-NEXT:    testl %eax, %eax
 ; CHECK-NEXT:    js .LBB0_9
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_35: # %a97b
 ; CHECK-NEXT:    # Parent Loop BB0_3 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
@@ -142,7 +142,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    testb %r9b, %r9b
 ; CHECK-NEXT:    jne .LBB0_35
 ; CHECK-NEXT:    jmp .LBB0_9
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_21: # %b377
 ; CHECK-NEXT:    # in Loop: Header=BB0_20 Depth=2
 ; CHECK-NEXT:    testb %r9b, %r9b
@@ -153,7 +153,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    # Child Loop BB0_37 Depth 3
 ; CHECK-NEXT:    testq %rsi, %rsi
 ; CHECK-NEXT:    js .LBB0_21
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_37: # %a35b
 ; CHECK-NEXT:    # Parent Loop BB0_3 Depth=1
 ; CHECK-NEXT:    # Parent Loop BB0_20 Depth=2
@@ -161,7 +161,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    testb %r9b, %r9b
 ; CHECK-NEXT:    je .LBB0_37
 ; CHECK-NEXT:    jmp .LBB0_21
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_27: # %b1016
 ; CHECK-NEXT:    # in Loop: Header=BB0_25 Depth=2
 ; CHECK-NEXT:    testq %rsi, %rsi
@@ -173,7 +173,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    # Child Loop BB0_28 Depth 3
 ; CHECK-NEXT:    testq %rdx, %rdx
 ; CHECK-NEXT:    js .LBB0_26
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_38: # %a53b
 ; CHECK-NEXT:    # Parent Loop BB0_3 Depth=1
 ; CHECK-NEXT:    # Parent Loop BB0_25 Depth=2
@@ -184,7 +184,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    # in Loop: Header=BB0_25 Depth=2
 ; CHECK-NEXT:    testb %r10b, %r10b
 ; CHECK-NEXT:    jne .LBB0_27
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_28: # %a53b1019
 ; CHECK-NEXT:    # Parent Loop BB0_3 Depth=1
 ; CHECK-NEXT:    # Parent Loop BB0_25 Depth=2
@@ -192,7 +192,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    testq %rdx, %rdx
 ; CHECK-NEXT:    jle .LBB0_28
 ; CHECK-NEXT:    jmp .LBB0_27
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_31: # %b1263
 ; CHECK-NEXT:    # in Loop: Header=BB0_29 Depth=2
 ; CHECK-NEXT:    testq %rdx, %rdx
@@ -204,7 +204,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    # Child Loop BB0_32 Depth 3
 ; CHECK-NEXT:    testq %rsi, %rsi
 ; CHECK-NEXT:    js .LBB0_30
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_39: # %a63b
 ; CHECK-NEXT:    # Parent Loop BB0_3 Depth=1
 ; CHECK-NEXT:    # Parent Loop BB0_29 Depth=2
@@ -215,7 +215,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    # in Loop: Header=BB0_29 Depth=2
 ; CHECK-NEXT:    testq %rsi, %rsi
 ; CHECK-NEXT:    jle .LBB0_31
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_32: # %a63b1266
 ; CHECK-NEXT:    # Parent Loop BB0_3 Depth=1
 ; CHECK-NEXT:    # Parent Loop BB0_29 Depth=2
@@ -223,7 +223,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    testq %rsi, %rsi
 ; CHECK-NEXT:    jle .LBB0_32
 ; CHECK-NEXT:    jmp .LBB0_31
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_24: # %b712
 ; CHECK-NEXT:    # in Loop: Header=BB0_22 Depth=2
 ; CHECK-NEXT:    testb %r9b, %r9b
@@ -234,7 +234,7 @@ define dso_local void @foo(ptr %a0, ptr %a1, ptr %a2, ptr %a3, ptr %a4, ptr %a5)
 ; CHECK-NEXT:    # Child Loop BB0_23 Depth 3
 ; CHECK-NEXT:    testq %rdx, %rdx
 ; CHECK-NEXT:    js .LBB0_24
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_23: # %a45b
 ; CHECK-NEXT:    # Parent Loop BB0_3 Depth=1
 ; CHECK-NEXT:    # Parent Loop BB0_22 Depth=2
diff --git a/llvm/test/CodeGen/X86/2007-03-15-GEP-Idx-Sink.ll b/llvm/test/CodeGen/X86/2007-03-15-GEP-Idx-Sink.ll
index f21aaca7ca5f17..49e2bf207e52a8 100644
--- a/llvm/test/CodeGen/X86/2007-03-15-GEP-Idx-Sink.ll
+++ b/llvm/test/CodeGen/X86/2007-03-15-GEP-Idx-Sink.ll
@@ -15,7 +15,7 @@ define void @foo(ptr %buf, i32 %size, i32 %col, ptr %p) nounwind {
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; CHECK-NEXT:    addl $8, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_2: ## %bb
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl (%esi), %edi
diff --git a/llvm/test/CodeGen/X86/2007-10-12-CoalesceExtSubReg.ll b/llvm/test/CodeGen/X86/2007-10-12-CoalesceExtSubReg.ll
index 2f75ab29e708fe..cfb3e508576dda 100644
--- a/llvm/test/CodeGen/X86/2007-10-12-CoalesceExtSubReg.ll
+++ b/llvm/test/CodeGen/X86/2007-10-12-CoalesceExtSubReg.ll
@@ -9,7 +9,7 @@ define signext i16 @f(ptr %bp, ptr %ss)   {
 ; CHECK-NEXT:    .cfi_offset %esi, -8
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %cond_next127
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl (%eax), %edx
diff --git a/llvm/test/CodeGen/X86/2007-10-12-SpillerUnfold2.ll b/llvm/test/CodeGen/X86/2007-10-12-SpillerUnfold2.ll
index f9996e2df50e0e..6ebb97d63e7c65 100644
--- a/llvm/test/CodeGen/X86/2007-10-12-SpillerUnfold2.ll
+++ b/llvm/test/CodeGen/X86/2007-10-12-SpillerUnfold2.ll
@@ -6,7 +6,7 @@ define signext   i16 @t(ptr %qmatrix, ptr %dct, ptr %acBaseTable, ptr %acExtTabl
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %cond_next127
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %eax, %edx
diff --git a/llvm/test/CodeGen/X86/2007-11-06-InstrSched.ll b/llvm/test/CodeGen/X86/2007-11-06-InstrSched.ll
index 750d06d9e6031f..bbce246a5d394a 100644
--- a/llvm/test/CodeGen/X86/2007-11-06-InstrSched.ll
+++ b/llvm/test/CodeGen/X86/2007-11-06-InstrSched.ll
@@ -14,7 +14,7 @@ define float @foo(ptr %x, ptr %y, i32 %c) nounwind {
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; CHECK-NEXT:    xorps %xmm0, %xmm0
 ; CHECK-NEXT:    xorl %esi, %esi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_3: # %bb18
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    xorps %xmm1, %xmm1
diff --git a/llvm/test/CodeGen/X86/2007-11-30-LoadFolding-Bug.ll b/llvm/test/CodeGen/X86/2007-11-30-LoadFolding-Bug.ll
index 68566c7b370979..8d690ba06e3bd6 100644
--- a/llvm/test/CodeGen/X86/2007-11-30-LoadFolding-Bug.ll
+++ b/llvm/test/CodeGen/X86/2007-11-30-LoadFolding-Bug.ll
@@ -16,7 +16,7 @@ define fastcc void @mp_sqrt(i32 %n, i32 %radix, ptr %in, ptr %out, ptr %tmp1, pt
 ; CHECK-NEXT:    movb $1, %cl
 ; CHECK-NEXT:    movl $1, %ebx
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %esi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb.i5
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %ecx, %eax
@@ -37,7 +37,7 @@ define fastcc void @mp_sqrt(i32 %n, i32 %radix, ptr %in, ptr %out, ptr %tmp1, pt
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    xorl %ecx, %ecx
 ; CHECK-NEXT:    xorpd %xmm1, %xmm1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_7: # %bb.i28.i
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cvttsd2si %xmm1, %edi
@@ -85,7 +85,7 @@ define fastcc void @mp_sqrt(i32 %n, i32 %radix, ptr %in, ptr %out, ptr %tmp1, pt
 ; CHECK-NEXT:    popl %ebx
 ; CHECK-NEXT:    popl %ebp
 ; CHECK-NEXT:    retl
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_9: # %bb.i.i
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB0_9
diff --git a/llvm/test/CodeGen/X86/2008-04-28-CoalescerBug.ll b/llvm/test/CodeGen/X86/2008-04-28-CoalescerBug.ll
index 8e6d2c11b7b3dc..c95fc00b3ee6d4 100644
--- a/llvm/test/CodeGen/X86/2008-04-28-CoalescerBug.ll
+++ b/llvm/test/CodeGen/X86/2008-04-28-CoalescerBug.ll
@@ -16,13 +16,13 @@ define void @t(ptr %depth, ptr %bop, i32 %mode) nounwind  {
 ; CHECK-NEXT:  ## %bb.1: ## %entry
 ; CHECK-NEXT:    cmpl $1, %edx
 ; CHECK-NEXT:    jne LBB0_10
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_2: ## %bb2898.us
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp LBB0_2
 ; CHECK-NEXT:  LBB0_3: ## %bb13086.preheader
 ; CHECK-NEXT:    movb $1, %al
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_4: ## %bb13088
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb %al, %al
@@ -31,7 +31,7 @@ define void @t(ptr %depth, ptr %bop, i32 %mode) nounwind  {
 ; CHECK-NEXT:    ## in Loop: Header=BB0_4 Depth=1
 ; CHECK-NEXT:    xorl %ecx, %ecx
 ; CHECK-NEXT:    jmp LBB0_7
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_5: ## in Loop: Header=BB0_4 Depth=1
 ; CHECK-NEXT:    movl $65535, %ecx ## imm = 0xFFFF
 ; CHECK-NEXT:  LBB0_7: ## %bb13107
diff --git a/llvm/test/CodeGen/X86/2008-08-06-CmpStride.ll b/llvm/test/CodeGen/X86/2008-08-06-CmpStride.ll
index ca92c555058abb..5086ed40a43a21 100644
--- a/llvm/test/CodeGen/X86/2008-08-06-CmpStride.ll
+++ b/llvm/test/CodeGen/X86/2008-08-06-CmpStride.ll
@@ -10,7 +10,7 @@ define i32 @main() nounwind {
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    movl $10271, %ebx # imm = 0x281F
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %forbody
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $.str, %edi
diff --git a/llvm/test/CodeGen/X86/2008-12-01-loop-iv-used-outside-loop.ll b/llvm/test/CodeGen/X86/2008-12-01-loop-iv-used-outside-loop.ll
index 18d3cec442c6c2..c2a7d6be8baa00 100644
--- a/llvm/test/CodeGen/X86/2008-12-01-loop-iv-used-outside-loop.ll
+++ b/llvm/test/CodeGen/X86/2008-12-01-loop-iv-used-outside-loop.ll
@@ -11,7 +11,7 @@ define ptr @test(ptr %Q, ptr %L) nounwind {
 ; CHECK:       ## %bb.0: ## %entry
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; CHECK-NEXT:    jmp LBB0_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_1: ## %bb
 ; CHECK-NEXT:    ## in Loop: Header=BB0_2 Depth=1
 ; CHECK-NEXT:    incl %eax
diff --git a/llvm/test/CodeGen/X86/2009-02-26-MachineLICMBug.ll b/llvm/test/CodeGen/X86/2009-02-26-MachineLICMBug.ll
index 7807d49269e64c..c421541001c5d8 100644
--- a/llvm/test/CodeGen/X86/2009-02-26-MachineLICMBug.ll
+++ b/llvm/test/CodeGen/X86/2009-02-26-MachineLICMBug.ll
@@ -20,7 +20,7 @@ define ptr @t(ptr %desc, i64 %p) nounwind ssp {
 ; CHECK-NEXT:    movq %rdi, %r14
 ; CHECK-NEXT:    orq $2097152, %rbx ## imm = 0x200000
 ; CHECK-NEXT:    andl $15728640, %ebx ## imm = 0xF00000
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_1: ## %bb4
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    xorl %eax, %eax
diff --git a/llvm/test/CodeGen/X86/2009-04-25-CoalescerBug.ll b/llvm/test/CodeGen/X86/2009-04-25-CoalescerBug.ll
index ce28893090c43f..1dd30e82630992 100644
--- a/llvm/test/CodeGen/X86/2009-04-25-CoalescerBug.ll
+++ b/llvm/test/CodeGen/X86/2009-04-25-CoalescerBug.ll
@@ -8,7 +8,7 @@ define i64 @test(ptr %tmp13) nounwind {
 ; CHECK-NEXT:    movl (%rdi), %ecx
 ; CHECK-NEXT:    movl %ecx, %eax
 ; CHECK-NEXT:    shrl %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %while.cond
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb $1, %cl
diff --git a/llvm/test/CodeGen/X86/2009-08-12-badswitch.ll b/llvm/test/CodeGen/X86/2009-08-12-badswitch.ll
index 4b8085a995f083..7050889d71029c 100644
--- a/llvm/test/CodeGen/X86/2009-08-12-badswitch.ll
+++ b/llvm/test/CodeGen/X86/2009-08-12-badswitch.ll
@@ -123,7 +123,7 @@ define internal fastcc i32 @foo(i64 %bar) nounwind ssp {
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    popq %rcx
 ; CHECK-NEXT:    retq
-; CHECK-NEXT:    .p2align 2, 0x90
+; CHECK-NEXT:    .p2align 2
 ; CHECK-NEXT:    .data_region jt32
 ; CHECK-NEXT:  .set L0_0_set_3, LBB0_3-LJTI0_0
 ; CHECK-NEXT:  .set L0_0_set_4, LBB0_4-LJTI0_0
diff --git a/llvm/test/CodeGen/X86/2020_12_02_decrementing_loop.ll b/llvm/test/CodeGen/X86/2020_12_02_decrementing_loop.ll
index 43b52898c79a2c..22bf4581c6b42a 100644
--- a/llvm/test/CodeGen/X86/2020_12_02_decrementing_loop.ll
+++ b/llvm/test/CodeGen/X86/2020_12_02_decrementing_loop.ll
@@ -4,7 +4,7 @@
 define i32 @test_01(ptr %p, i64 %len, i32 %x) {
 ; CHECK-LABEL: test_01:
 ; CHECK:       ## %bb.0: ## %entry
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_1: ## %loop
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    subq $1, %rsi
@@ -44,7 +44,7 @@ failure:                                          ; preds = %backedge
 define i32 @test_01a(ptr %p, i64 %len, i32 %x) {
 ; CHECK-LABEL: test_01a:
 ; CHECK:       ## %bb.0: ## %entry
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB1_1: ## %loop
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    subq $1, %rsi
@@ -84,7 +84,7 @@ failure:                                          ; preds = %backedge
 define i32 @test_02(ptr %p, i64 %len, i32 %x) {
 ; CHECK-LABEL: test_02:
 ; CHECK:       ## %bb.0: ## %entry
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB2_1: ## %loop
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    subq $1, %rsi
@@ -126,7 +126,7 @@ failure:                                          ; preds = %backedge
 define i32 @test_03(ptr %p, i64 %len, i32 %x) {
 ; CHECK-LABEL: test_03:
 ; CHECK:       ## %bb.0: ## %entry
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB3_1: ## %loop
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    subq $1, %rsi
diff --git a/llvm/test/CodeGen/X86/AMX/amx-across-func.ll b/llvm/test/CodeGen/X86/AMX/amx-across-func.ll
index ae0be9b5a5bcd9..320c96535abba0 100644
--- a/llvm/test/CodeGen/X86/AMX/amx-across-func.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-across-func.ll
@@ -235,7 +235,7 @@ define dso_local i32 @test_loop(i32 %0) nounwind {
 ; CHECK-NEXT:    movl $32, %r15d
 ; CHECK-NEXT:    movw $8, %r12w
 ; CHECK-NEXT:    movl $buf+2048, %r13d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB2_2: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    tileloadd (%r14,%r15), %tmm0
 ; CHECK-NEXT:    movabsq $64, %rax
@@ -300,7 +300,7 @@ define dso_local i32 @test_loop(i32 %0) nounwind {
 ; IPRA-NEXT:    movl $32, %esi
 ; IPRA-NEXT:    movw $8, %di
 ; IPRA-NEXT:    movl $buf+2048, %r8d
-; IPRA-NEXT:    .p2align 4, 0x90
+; IPRA-NEXT:    .p2align 4
 ; IPRA-NEXT:  .LBB2_2: # =>This Inner Loop Header: Depth=1
 ; IPRA-NEXT:    tileloadd (%rdx,%rsi), %tmm0
 ; IPRA-NEXT:    callq foo
@@ -494,7 +494,7 @@ define dso_local void @test_loop2(i32 %0) nounwind {
 ; CHECK-NEXT:    movl $32, %r15d
 ; CHECK-NEXT:    movw $8, %bp
 ; CHECK-NEXT:    movl $buf+2048, %r12d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB3_1: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vzeroupper
 ; CHECK-NEXT:    callq foo
@@ -535,7 +535,7 @@ define dso_local void @test_loop2(i32 %0) nounwind {
 ; IPRA-NEXT:    movl $32, %ecx
 ; IPRA-NEXT:    movw $8, %dx
 ; IPRA-NEXT:    movl $buf+2048, %esi
-; IPRA-NEXT:    .p2align 4, 0x90
+; IPRA-NEXT:    .p2align 4
 ; IPRA-NEXT:  .LBB3_1: # =>This Inner Loop Header: Depth=1
 ; IPRA-NEXT:    callq foo
 ; IPRA-NEXT:    testl %edi, %edi
diff --git a/llvm/test/CodeGen/X86/AMX/amx-ldtilecfg-insert.ll b/llvm/test/CodeGen/X86/AMX/amx-ldtilecfg-insert.ll
index 714590d3c156b6..8595024103dbd3 100644
--- a/llvm/test/CodeGen/X86/AMX/amx-ldtilecfg-insert.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-ldtilecfg-insert.ll
@@ -241,7 +241,7 @@ define dso_local void @test5(i16 signext %0, i16 signext %1) nounwind {
 ; CHECK-NEXT:    movl $32, %edx
 ; CHECK-NEXT:    leal -1(%rsi), %r8d
 ; CHECK-NEXT:    jmp .LBB4_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB4_3: # %if.false
 ; CHECK-NEXT:    # in Loop: Header=BB4_1 Depth=1
 ; CHECK-NEXT:    movl %r8d, %esi
@@ -301,7 +301,7 @@ define dso_local void @test6(i16 signext %0) nounwind {
 ; CHECK-NEXT:    movl $32, %edx
 ; CHECK-NEXT:    xorl %esi, %esi
 ; CHECK-NEXT:    jmp .LBB5_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB5_3: # %if.false
 ; CHECK-NEXT:    # in Loop: Header=BB5_1 Depth=1
 ; CHECK-NEXT:    decl %esi
diff --git a/llvm/test/CodeGen/X86/AMX/amx-lower-tile-copy.ll b/llvm/test/CodeGen/X86/AMX/amx-lower-tile-copy.ll
index a0085afbaf0253..e9bb68e711f889 100644
--- a/llvm/test/CodeGen/X86/AMX/amx-lower-tile-copy.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-lower-tile-copy.ll
@@ -32,7 +32,7 @@ define dso_local void @test1(ptr%buf) nounwind {
 ; CHECK-NEXT:    movq %rdi, %rbx
 ; CHECK-NEXT:    xorl %r14d, %r14d
 ; CHECK-NEXT:    movl $32, %r15d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %loop.header
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movabsq $64, %rax
@@ -92,7 +92,7 @@ define dso_local void @test1(ptr%buf) nounwind {
 ; EGPR-NEXT:    movq %rdi, %rbx # encoding: [0x48,0x89,0xfb]
 ; EGPR-NEXT:    xorl %r14d, %r14d # encoding: [0x45,0x31,0xf6]
 ; EGPR-NEXT:    movl $32, %r15d # encoding: [0x41,0xbf,0x20,0x00,0x00,0x00]
-; EGPR-NEXT:    .p2align 4, 0x90
+; EGPR-NEXT:    .p2align 4
 ; EGPR-NEXT:  .LBB0_2: # %loop.header
 ; EGPR-NEXT:    # =>This Inner Loop Header: Depth=1
 ; EGPR-NEXT:    movabsq $64, %rax # encoding: [0x48,0xb8,0x40,0x00,0x00,0x00,0x00,0x00,0x00,0x00]
@@ -179,7 +179,7 @@ define dso_local void @test2(ptr%buf) nounwind {
 ; CHECK-NEXT:    movq %rdi, %rbx
 ; CHECK-NEXT:    xorl %r14d, %r14d
 ; CHECK-NEXT:    movl $32, %r15d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_2: # %loop.header
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    tilezero %tmm0
@@ -231,7 +231,7 @@ define dso_local void @test2(ptr%buf) nounwind {
 ; EGPR-NEXT:    movq %rdi, %rbx # encoding: [0x48,0x89,0xfb]
 ; EGPR-NEXT:    xorl %r14d, %r14d # encoding: [0x45,0x31,0xf6]
 ; EGPR-NEXT:    movl $32, %r15d # encoding: [0x41,0xbf,0x20,0x00,0x00,0x00]
-; EGPR-NEXT:    .p2align 4, 0x90
+; EGPR-NEXT:    .p2align 4
 ; EGPR-NEXT:  .LBB1_2: # %loop.header
 ; EGPR-NEXT:    # =>This Inner Loop Header: Depth=1
 ; EGPR-NEXT:    tilezero %tmm0 # encoding: [0xc4,0xe2,0x7b,0x49,0xc0]
diff --git a/llvm/test/CodeGen/X86/AMX/amx-spill-merge.ll b/llvm/test/CodeGen/X86/AMX/amx-spill-merge.ll
index c7c919c7cbb30d..4fb0a4445862ff 100644
--- a/llvm/test/CodeGen/X86/AMX/amx-spill-merge.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-spill-merge.ll
@@ -244,7 +244,7 @@ define dso_local void @test3(ptr%buf) nounwind {
 ; CHECK-NEXT:    movq %rdi, %rbx
 ; CHECK-NEXT:    movl $32, %r14d
 ; CHECK-NEXT:    xorl %r15d, %r15d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_2: # %loop.header
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    tilestored %tmm0, (%rbx,%r14)
@@ -299,7 +299,7 @@ define dso_local void @test3(ptr%buf) nounwind {
 ; EGPR-NEXT:    movq %rdi, %rbx # encoding: [0x48,0x89,0xfb]
 ; EGPR-NEXT:    movl $32, %r14d # encoding: [0x41,0xbe,0x20,0x00,0x00,0x00]
 ; EGPR-NEXT:    xorl %r15d, %r15d # encoding: [0x45,0x31,0xff]
-; EGPR-NEXT:    .p2align 4, 0x90
+; EGPR-NEXT:    .p2align 4
 ; EGPR-NEXT:  .LBB1_2: # %loop.header
 ; EGPR-NEXT:    # =>This Inner Loop Header: Depth=1
 ; EGPR-NEXT:    tilestored %tmm0, (%rbx,%r14) # EVEX TO VEX Compression encoding: [0xc4,0xa2,0x7a,0x4b,0x04,0x33]
diff --git a/llvm/test/CodeGen/X86/AMX/amx-tile-basic.ll b/llvm/test/CodeGen/X86/AMX/amx-tile-basic.ll
index 15e7136f4a5030..ec087f23248c4c 100644
--- a/llvm/test/CodeGen/X86/AMX/amx-tile-basic.ll
+++ b/llvm/test/CodeGen/X86/AMX/amx-tile-basic.ll
@@ -85,7 +85,7 @@ define void @PR90954(ptr %0, ptr %1, i32 %2) nounwind {
 ; CHECK-NEXT:    xorl %ebx, %ebx
 ; CHECK-NEXT:    xorl %r14d, %r14d
 ; CHECK-NEXT:    jmp .LBB1_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_5: # in Loop: Header=BB1_1 Depth=1
 ; CHECK-NEXT:    incq %r14
 ; CHECK-NEXT:    addl %edx, %ebx
@@ -96,7 +96,7 @@ define void @PR90954(ptr %0, ptr %1, i32 %2) nounwind {
 ; CHECK-NEXT:    xorl %r12d, %r12d
 ; CHECK-NEXT:    xorl %r13d, %r13d
 ; CHECK-NEXT:    jmp .LBB1_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_4: # in Loop: Header=BB1_2 Depth=2
 ; CHECK-NEXT:    tilestored %tmm1, (%r15,%rax)
 ; CHECK-NEXT:    incq %r13
diff --git a/llvm/test/CodeGen/X86/MachineSink-Issue98477.ll b/llvm/test/CodeGen/X86/MachineSink-Issue98477.ll
index 4df32854cdae44..4abb1f8e1ca429 100644
--- a/llvm/test/CodeGen/X86/MachineSink-Issue98477.ll
+++ b/llvm/test/CodeGen/X86/MachineSink-Issue98477.ll
@@ -13,7 +13,7 @@ define i32 @main(i1 %tobool.not, i32 %0) {
 ; CHECK-NEXT:  .LBB0_1: # %j.preheader
 ; CHECK-NEXT:    xorl %r9d, %r9d
 ; CHECK-NEXT:    jmp .LBB0_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_5: # %if.then4
 ; CHECK-NEXT:    # in Loop: Header=BB0_2 Depth=1
 ; CHECK-NEXT:    movl $1, %eax
diff --git a/llvm/test/CodeGen/X86/MergeConsecutiveStores.ll b/llvm/test/CodeGen/X86/MergeConsecutiveStores.ll
index fa9ed49da1b7f9..0103d2bf3cc2c6 100644
--- a/llvm/test/CodeGen/X86/MergeConsecutiveStores.ll
+++ b/llvm/test/CodeGen/X86/MergeConsecutiveStores.ll
@@ -17,7 +17,7 @@ define void @merge_const_store(i32 %count, ptr nocapture %p) nounwind uwtable no
 ; X86-NEXT:    jle .LBB0_3
 ; X86-NEXT:  # %bb.1: # %.lr.ph.preheader
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB0_2: # %.lr.ph
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl $67305985, (%ecx) # imm = 0x4030201
@@ -34,7 +34,7 @@ define void @merge_const_store(i32 %count, ptr nocapture %p) nounwind uwtable no
 ; X64-NEXT:    jle .LBB0_3
 ; X64-NEXT:  # %bb.1: # %.lr.ph.preheader
 ; X64-NEXT:    movabsq $578437695752307201, %rax # imm = 0x807060504030201
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB0_2: # %.lr.ph
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movq %rax, (%rsi)
@@ -81,7 +81,7 @@ define void @merge_const_store_no_vec(i32 %count, ptr nocapture %p) noimplicitfl
 ; X86-NEXT:    jle .LBB1_3
 ; X86-NEXT:  # %bb.1: # %.lr.ph.preheader
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB1_2: # %.lr.ph
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl $0, (%ecx)
@@ -102,7 +102,7 @@ define void @merge_const_store_no_vec(i32 %count, ptr nocapture %p) noimplicitfl
 ; X64:       # %bb.0:
 ; X64-NEXT:    testl %edi, %edi
 ; X64-NEXT:    jle .LBB1_2
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB1_1: # %.lr.ph
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movq $0, (%rsi)
@@ -153,7 +153,7 @@ define void @merge_const_store_vec(i32 %count, ptr nocapture %p) nounwind uwtabl
 ; X86-NEXT:  # %bb.1: # %.lr.ph.preheader
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    vxorps %xmm0, %xmm0, %xmm0
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB2_2: # %.lr.ph
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    vmovups %ymm0, (%ecx)
@@ -170,7 +170,7 @@ define void @merge_const_store_vec(i32 %count, ptr nocapture %p) nounwind uwtabl
 ; X64-NEXT:    jle .LBB2_3
 ; X64-NEXT:  # %bb.1: # %.lr.ph.preheader
 ; X64-NEXT:    vxorps %xmm0, %xmm0, %xmm0
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB2_2: # %.lr.ph
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    vmovups %ymm0, (%rsi)
@@ -219,7 +219,7 @@ define void @merge_nonconst_store(i32 %count, i8 %zz, ptr nocapture %p) nounwind
 ; X86-BWON-NEXT:  # %bb.1: # %.lr.ph.preheader
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-BWON-NEXT:    movzbl {{[0-9]+}}(%esp), %edx
-; X86-BWON-NEXT:    .p2align 4, 0x90
+; X86-BWON-NEXT:    .p2align 4
 ; X86-BWON-NEXT:  .LBB3_2: # %.lr.ph
 ; X86-BWON-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-BWON-NEXT:    movl $67305985, (%ecx) # imm = 0x4030201
@@ -240,7 +240,7 @@ define void @merge_nonconst_store(i32 %count, i8 %zz, ptr nocapture %p) nounwind
 ; X86-BWOFF-NEXT:  # %bb.1: # %.lr.ph.preheader
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-BWOFF-NEXT:    movb {{[0-9]+}}(%esp), %dl
-; X86-BWOFF-NEXT:    .p2align 4, 0x90
+; X86-BWOFF-NEXT:    .p2align 4
 ; X86-BWOFF-NEXT:  .LBB3_2: # %.lr.ph
 ; X86-BWOFF-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-BWOFF-NEXT:    movl $67305985, (%ecx) # imm = 0x4030201
@@ -257,7 +257,7 @@ define void @merge_nonconst_store(i32 %count, i8 %zz, ptr nocapture %p) nounwind
 ; X64:       # %bb.0:
 ; X64-NEXT:    testl %edi, %edi
 ; X64-NEXT:    jle .LBB3_2
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB3_1: # %.lr.ph
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl $67305985, (%rdx) # imm = 0x4030201
@@ -310,7 +310,7 @@ define void @merge_loads_i16(i32 %count, ptr noalias nocapture %q, ptr noalias n
 ; X86-BWON-NEXT:  # %bb.1: # %.lr.ph
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %edx
-; X86-BWON-NEXT:    .p2align 4, 0x90
+; X86-BWON-NEXT:    .p2align 4
 ; X86-BWON-NEXT:  .LBB4_2: # =>This Inner Loop Header: Depth=1
 ; X86-BWON-NEXT:    movzwl (%edx), %esi
 ; X86-BWON-NEXT:    movw %si, (%ecx)
@@ -333,7 +333,7 @@ define void @merge_loads_i16(i32 %count, ptr noalias nocapture %q, ptr noalias n
 ; X86-BWOFF-NEXT:  # %bb.1: # %.lr.ph
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %edx
-; X86-BWOFF-NEXT:    .p2align 4, 0x90
+; X86-BWOFF-NEXT:    .p2align 4
 ; X86-BWOFF-NEXT:  .LBB4_2: # =>This Inner Loop Header: Depth=1
 ; X86-BWOFF-NEXT:    movw (%edx), %si
 ; X86-BWOFF-NEXT:    movw %si, (%ecx)
@@ -349,7 +349,7 @@ define void @merge_loads_i16(i32 %count, ptr noalias nocapture %q, ptr noalias n
 ; X64-BWON:       # %bb.0:
 ; X64-BWON-NEXT:    testl %edi, %edi
 ; X64-BWON-NEXT:    jle .LBB4_2
-; X64-BWON-NEXT:    .p2align 4, 0x90
+; X64-BWON-NEXT:    .p2align 4
 ; X64-BWON-NEXT:  .LBB4_1: # =>This Inner Loop Header: Depth=1
 ; X64-BWON-NEXT:    movzwl (%rsi), %eax
 ; X64-BWON-NEXT:    movw %ax, (%rdx)
@@ -363,7 +363,7 @@ define void @merge_loads_i16(i32 %count, ptr noalias nocapture %q, ptr noalias n
 ; X64-BWOFF:       # %bb.0:
 ; X64-BWOFF-NEXT:    testl %edi, %edi
 ; X64-BWOFF-NEXT:    jle .LBB4_2
-; X64-BWOFF-NEXT:    .p2align 4, 0x90
+; X64-BWOFF-NEXT:    .p2align 4
 ; X64-BWOFF-NEXT:  .LBB4_1: # =>This Inner Loop Header: Depth=1
 ; X64-BWOFF-NEXT:    movw (%rsi), %ax
 ; X64-BWOFF-NEXT:    movw %ax, (%rdx)
@@ -411,7 +411,7 @@ define void @no_merge_loads(i32 %count, ptr noalias nocapture %q, ptr noalias no
 ; X86-BWON-NEXT:  # %bb.1: # %.lr.ph
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %edx
-; X86-BWON-NEXT:    .p2align 4, 0x90
+; X86-BWON-NEXT:    .p2align 4
 ; X86-BWON-NEXT:  .LBB5_2: # %a4
 ; X86-BWON-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-BWON-NEXT:    movzbl (%edx), %ebx
@@ -437,7 +437,7 @@ define void @no_merge_loads(i32 %count, ptr noalias nocapture %q, ptr noalias no
 ; X86-BWOFF-NEXT:  # %bb.1: # %.lr.ph
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %edx
-; X86-BWOFF-NEXT:    .p2align 4, 0x90
+; X86-BWOFF-NEXT:    .p2align 4
 ; X86-BWOFF-NEXT:  .LBB5_2: # %a4
 ; X86-BWOFF-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-BWOFF-NEXT:    movb (%edx), %bl
@@ -456,7 +456,7 @@ define void @no_merge_loads(i32 %count, ptr noalias nocapture %q, ptr noalias no
 ; X64-BWON:       # %bb.0:
 ; X64-BWON-NEXT:    testl %edi, %edi
 ; X64-BWON-NEXT:    jle .LBB5_2
-; X64-BWON-NEXT:    .p2align 4, 0x90
+; X64-BWON-NEXT:    .p2align 4
 ; X64-BWON-NEXT:  .LBB5_1: # %a4
 ; X64-BWON-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-BWON-NEXT:    movzbl (%rsi), %eax
@@ -473,7 +473,7 @@ define void @no_merge_loads(i32 %count, ptr noalias nocapture %q, ptr noalias no
 ; X64-BWOFF:       # %bb.0:
 ; X64-BWOFF-NEXT:    testl %edi, %edi
 ; X64-BWOFF-NEXT:    jle .LBB5_2
-; X64-BWOFF-NEXT:    .p2align 4, 0x90
+; X64-BWOFF-NEXT:    .p2align 4
 ; X64-BWOFF-NEXT:  .LBB5_1: # %a4
 ; X64-BWOFF-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-BWOFF-NEXT:    movb (%rsi), %al
@@ -526,7 +526,7 @@ define void @merge_loads_integer(i32 %count, ptr noalias nocapture %q, ptr noali
 ; X86-NEXT:  # %bb.1: # %.lr.ph
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB6_2: # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl (%edx), %esi
 ; X86-NEXT:    movl 4(%edx), %edi
@@ -546,7 +546,7 @@ define void @merge_loads_integer(i32 %count, ptr noalias nocapture %q, ptr noali
 ; X64:       # %bb.0:
 ; X64-NEXT:    testl %edi, %edi
 ; X64-NEXT:    jle .LBB6_2
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB6_1: # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movq (%rsi), %rax
 ; X64-NEXT:    movq %rax, (%rdx)
@@ -590,7 +590,7 @@ define void @merge_loads_vector(i32 %count, ptr noalias nocapture %q, ptr noalia
 ; X86-NEXT:  # %bb.1: # %.lr.ph
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB7_2: # %block4
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    vmovups (%edx), %xmm0
@@ -605,7 +605,7 @@ define void @merge_loads_vector(i32 %count, ptr noalias nocapture %q, ptr noalia
 ; X64:       # %bb.0:
 ; X64-NEXT:    testl %edi, %edi
 ; X64-NEXT:    jle .LBB7_2
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB7_1: # %block4
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    vmovups (%rsi), %xmm0
@@ -659,7 +659,7 @@ define void @merge_loads_no_align(i32 %count, ptr noalias nocapture %q, ptr noal
 ; X86-NEXT:  # %bb.1: # %.lr.ph
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB8_2: # %block4
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    vmovups (%edx), %xmm0
@@ -674,7 +674,7 @@ define void @merge_loads_no_align(i32 %count, ptr noalias nocapture %q, ptr noal
 ; X64:       # %bb.0:
 ; X64-NEXT:    testl %edi, %edi
 ; X64-NEXT:    jle .LBB8_2
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB8_1: # %block4
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    vmovups (%rsi), %xmm0
@@ -737,7 +737,7 @@ define void @MergeLoadStoreBaseIndexOffset(ptr %a, ptr %b, ptr %c, i32 %n) {
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %edi
-; X86-BWON-NEXT:    .p2align 4, 0x90
+; X86-BWON-NEXT:    .p2align 4
 ; X86-BWON-NEXT:  .LBB9_1: # =>This Inner Loop Header: Depth=1
 ; X86-BWON-NEXT:    movl (%edi,%eax,8), %ebx
 ; X86-BWON-NEXT:    movzwl (%edx,%ebx), %ebx
@@ -770,7 +770,7 @@ define void @MergeLoadStoreBaseIndexOffset(ptr %a, ptr %b, ptr %c, i32 %n) {
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %edi
-; X86-BWOFF-NEXT:    .p2align 4, 0x90
+; X86-BWOFF-NEXT:    .p2align 4
 ; X86-BWOFF-NEXT:  .LBB9_1: # =>This Inner Loop Header: Depth=1
 ; X86-BWOFF-NEXT:    movl (%edi,%eax,8), %ebx
 ; X86-BWOFF-NEXT:    movw (%edx,%ebx), %bx
@@ -791,7 +791,7 @@ define void @MergeLoadStoreBaseIndexOffset(ptr %a, ptr %b, ptr %c, i32 %n) {
 ; X64-BWON:       # %bb.0:
 ; X64-BWON-NEXT:    movl %ecx, %eax
 ; X64-BWON-NEXT:    xorl %ecx, %ecx
-; X64-BWON-NEXT:    .p2align 4, 0x90
+; X64-BWON-NEXT:    .p2align 4
 ; X64-BWON-NEXT:  .LBB9_1: # =>This Inner Loop Header: Depth=1
 ; X64-BWON-NEXT:    movq (%rdi,%rcx,8), %r8
 ; X64-BWON-NEXT:    movzwl (%rdx,%r8), %r8d
@@ -806,7 +806,7 @@ define void @MergeLoadStoreBaseIndexOffset(ptr %a, ptr %b, ptr %c, i32 %n) {
 ; X64-BWOFF:       # %bb.0:
 ; X64-BWOFF-NEXT:    movl %ecx, %eax
 ; X64-BWOFF-NEXT:    xorl %ecx, %ecx
-; X64-BWOFF-NEXT:    .p2align 4, 0x90
+; X64-BWOFF-NEXT:    .p2align 4
 ; X64-BWOFF-NEXT:  .LBB9_1: # =>This Inner Loop Header: Depth=1
 ; X64-BWOFF-NEXT:    movq (%rdi,%rcx,8), %r8
 ; X64-BWOFF-NEXT:    movw (%rdx,%r8), %r8w
@@ -863,7 +863,7 @@ define void @MergeLoadStoreBaseIndexOffsetComplicated(ptr %a, ptr %b, ptr %c, i6
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %edi
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %ebx
 ; X86-BWON-NEXT:    xorl %ebp, %ebp
-; X86-BWON-NEXT:    .p2align 4, 0x90
+; X86-BWON-NEXT:    .p2align 4
 ; X86-BWON-NEXT:  .LBB10_1: # =>This Inner Loop Header: Depth=1
 ; X86-BWON-NEXT:    movsbl (%edi), %ecx
 ; X86-BWON-NEXT:    movzbl (%esi,%ecx), %edx
@@ -909,7 +909,7 @@ define void @MergeLoadStoreBaseIndexOffsetComplicated(ptr %a, ptr %b, ptr %c, i6
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %edi
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %ebx
 ; X86-BWOFF-NEXT:    xorl %ebp, %ebp
-; X86-BWOFF-NEXT:    .p2align 4, 0x90
+; X86-BWOFF-NEXT:    .p2align 4
 ; X86-BWOFF-NEXT:  .LBB10_1: # =>This Inner Loop Header: Depth=1
 ; X86-BWOFF-NEXT:    movsbl (%edi), %ecx
 ; X86-BWOFF-NEXT:    movb (%esi,%ecx), %dl
@@ -939,7 +939,7 @@ define void @MergeLoadStoreBaseIndexOffsetComplicated(ptr %a, ptr %b, ptr %c, i6
 ; X64-BWON-LABEL: MergeLoadStoreBaseIndexOffsetComplicated:
 ; X64-BWON:       # %bb.0:
 ; X64-BWON-NEXT:    xorl %eax, %eax
-; X64-BWON-NEXT:    .p2align 4, 0x90
+; X64-BWON-NEXT:    .p2align 4
 ; X64-BWON-NEXT:  .LBB10_1: # =>This Inner Loop Header: Depth=1
 ; X64-BWON-NEXT:    movsbq (%rsi), %r8
 ; X64-BWON-NEXT:    movzwl (%rdx,%r8), %r8d
@@ -954,7 +954,7 @@ define void @MergeLoadStoreBaseIndexOffsetComplicated(ptr %a, ptr %b, ptr %c, i6
 ; X64-BWOFF-LABEL: MergeLoadStoreBaseIndexOffsetComplicated:
 ; X64-BWOFF:       # %bb.0:
 ; X64-BWOFF-NEXT:    xorl %eax, %eax
-; X64-BWOFF-NEXT:    .p2align 4, 0x90
+; X64-BWOFF-NEXT:    .p2align 4
 ; X64-BWOFF-NEXT:  .LBB10_1: # =>This Inner Loop Header: Depth=1
 ; X64-BWOFF-NEXT:    movsbq (%rsi), %r8
 ; X64-BWOFF-NEXT:    movw (%rdx,%r8), %r8w
@@ -1011,7 +1011,7 @@ define void @MergeLoadStoreBaseIndexOffsetSext(ptr %a, ptr %b, ptr %c, i32 %n) {
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %edi
-; X86-BWON-NEXT:    .p2align 4, 0x90
+; X86-BWON-NEXT:    .p2align 4
 ; X86-BWON-NEXT:  .LBB11_1: # =>This Inner Loop Header: Depth=1
 ; X86-BWON-NEXT:    movsbl (%edi,%eax), %ebx
 ; X86-BWON-NEXT:    movzwl (%edx,%ebx), %ebx
@@ -1044,7 +1044,7 @@ define void @MergeLoadStoreBaseIndexOffsetSext(ptr %a, ptr %b, ptr %c, i32 %n) {
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %edi
-; X86-BWOFF-NEXT:    .p2align 4, 0x90
+; X86-BWOFF-NEXT:    .p2align 4
 ; X86-BWOFF-NEXT:  .LBB11_1: # =>This Inner Loop Header: Depth=1
 ; X86-BWOFF-NEXT:    movsbl (%edi,%eax), %ebx
 ; X86-BWOFF-NEXT:    movw (%edx,%ebx), %bx
@@ -1065,7 +1065,7 @@ define void @MergeLoadStoreBaseIndexOffsetSext(ptr %a, ptr %b, ptr %c, i32 %n) {
 ; X64-BWON:       # %bb.0:
 ; X64-BWON-NEXT:    movl %ecx, %eax
 ; X64-BWON-NEXT:    xorl %ecx, %ecx
-; X64-BWON-NEXT:    .p2align 4, 0x90
+; X64-BWON-NEXT:    .p2align 4
 ; X64-BWON-NEXT:  .LBB11_1: # =>This Inner Loop Header: Depth=1
 ; X64-BWON-NEXT:    movsbq (%rdi,%rcx), %r8
 ; X64-BWON-NEXT:    movzwl (%rdx,%r8), %r8d
@@ -1080,7 +1080,7 @@ define void @MergeLoadStoreBaseIndexOffsetSext(ptr %a, ptr %b, ptr %c, i32 %n) {
 ; X64-BWOFF:       # %bb.0:
 ; X64-BWOFF-NEXT:    movl %ecx, %eax
 ; X64-BWOFF-NEXT:    xorl %ecx, %ecx
-; X64-BWOFF-NEXT:    .p2align 4, 0x90
+; X64-BWOFF-NEXT:    .p2align 4
 ; X64-BWOFF-NEXT:  .LBB11_1: # =>This Inner Loop Header: Depth=1
 ; X64-BWOFF-NEXT:    movsbq (%rdi,%rcx), %r8
 ; X64-BWOFF-NEXT:    movw (%rdx,%r8), %r8w
@@ -1138,7 +1138,7 @@ define void @loadStoreBaseIndexOffsetSextNoSex(ptr %a, ptr %b, ptr %c, i32 %n) {
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; X86-BWON-NEXT:    movl {{[0-9]+}}(%esp), %edi
-; X86-BWON-NEXT:    .p2align 4, 0x90
+; X86-BWON-NEXT:    .p2align 4
 ; X86-BWON-NEXT:  .LBB12_1: # =>This Inner Loop Header: Depth=1
 ; X86-BWON-NEXT:    movsbl (%edi,%eax), %ebx
 ; X86-BWON-NEXT:    movzbl (%edx,%ebx), %ecx
@@ -1180,7 +1180,7 @@ define void @loadStoreBaseIndexOffsetSextNoSex(ptr %a, ptr %b, ptr %c, i32 %n) {
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; X86-BWOFF-NEXT:    movl {{[0-9]+}}(%esp), %edi
-; X86-BWOFF-NEXT:    .p2align 4, 0x90
+; X86-BWOFF-NEXT:    .p2align 4
 ; X86-BWOFF-NEXT:  .LBB12_1: # =>This Inner Loop Header: Depth=1
 ; X86-BWOFF-NEXT:    movsbl (%edi,%eax), %ebx
 ; X86-BWOFF-NEXT:    movb (%edx,%ebx), %cl
@@ -1207,7 +1207,7 @@ define void @loadStoreBaseIndexOffsetSextNoSex(ptr %a, ptr %b, ptr %c, i32 %n) {
 ; X64-BWON:       # %bb.0:
 ; X64-BWON-NEXT:    movl %ecx, %eax
 ; X64-BWON-NEXT:    xorl %ecx, %ecx
-; X64-BWON-NEXT:    .p2align 4, 0x90
+; X64-BWON-NEXT:    .p2align 4
 ; X64-BWON-NEXT:  .LBB12_1: # =>This Inner Loop Header: Depth=1
 ; X64-BWON-NEXT:    movsbq (%rdi,%rcx), %r8
 ; X64-BWON-NEXT:    movzbl (%rdx,%r8), %r9d
@@ -1226,7 +1226,7 @@ define void @loadStoreBaseIndexOffsetSextNoSex(ptr %a, ptr %b, ptr %c, i32 %n) {
 ; X64-BWOFF:       # %bb.0:
 ; X64-BWOFF-NEXT:    movl %ecx, %eax
 ; X64-BWOFF-NEXT:    xorl %ecx, %ecx
-; X64-BWOFF-NEXT:    .p2align 4, 0x90
+; X64-BWOFF-NEXT:    .p2align 4
 ; X64-BWOFF-NEXT:  .LBB12_1: # =>This Inner Loop Header: Depth=1
 ; X64-BWOFF-NEXT:    movsbq (%rdi,%rcx), %r8
 ; X64-BWOFF-NEXT:    movb (%rdx,%r8), %r9b
@@ -1561,7 +1561,7 @@ define void @merge_const_store_heterogeneous(i32 %count, ptr nocapture %p) nounw
 ; X86-NEXT:    jle .LBB23_3
 ; X86-NEXT:  # %bb.1: # %.lr.ph.preheader
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB23_2: # %.lr.ph
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl $67305985, (%ecx) # imm = 0x4030201
@@ -1578,7 +1578,7 @@ define void @merge_const_store_heterogeneous(i32 %count, ptr nocapture %p) nounw
 ; X64-NEXT:    jle .LBB23_3
 ; X64-NEXT:  # %bb.1: # %.lr.ph.preheader
 ; X64-NEXT:    movabsq $578437695752307201, %rax # imm = 0x807060504030201
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB23_2: # %.lr.ph
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movq %rax, (%rsi)
diff --git a/llvm/test/CodeGen/X86/PR71178-register-coalescer-crash.ll b/llvm/test/CodeGen/X86/PR71178-register-coalescer-crash.ll
index 0ce346f7c2e02c..12d66f64cb73d5 100644
--- a/llvm/test/CodeGen/X86/PR71178-register-coalescer-crash.ll
+++ b/llvm/test/CodeGen/X86/PR71178-register-coalescer-crash.ll
@@ -8,7 +8,7 @@ define i32 @h(i1 %arg, i32 %arg1) {
 ; CHECK-NEXT:    movabsq $9166129423, %rcx # imm = 0x22258090F
 ; CHECK-NEXT:    xorl %edx, %edx
 ; CHECK-NEXT:    jmp .LBB0_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_9: # %bb18
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    xorl %eax, %eax
diff --git a/llvm/test/CodeGen/X86/SwitchLowering.ll b/llvm/test/CodeGen/X86/SwitchLowering.ll
index ac80fda69fccdb..921b4e3d24d114 100644
--- a/llvm/test/CodeGen/X86/SwitchLowering.ll
+++ b/llvm/test/CodeGen/X86/SwitchLowering.ll
@@ -13,7 +13,7 @@ define ptr @FindChar(ptr %CurPtr) {
 ; CHECK-NEXT:    .cfi_offset %edi, -8
 ; CHECK-NEXT:    xorl %edi, %edi
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %esi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movzbl (%esi,%edi), %eax
diff --git a/llvm/test/CodeGen/X86/addr-mode-matcher-2.ll b/llvm/test/CodeGen/X86/addr-mode-matcher-2.ll
index daba729bf040f2..c810fe137024ce 100644
--- a/llvm/test/CodeGen/X86/addr-mode-matcher-2.ll
+++ b/llvm/test/CodeGen/X86/addr-mode-matcher-2.ll
@@ -30,7 +30,7 @@ define void @foo_sext_nsw(i1 zeroext, i32) nounwind {
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB0_1: # %.preheader
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB0_2: # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    leal (%eax,%eax,4), %eax
 ; X86-NEXT:    leal 20(,%eax,4), %eax
@@ -49,7 +49,7 @@ define void @foo_sext_nsw(i1 zeroext, i32) nounwind {
 ; X64-NEXT:    retq
 ; X64-NEXT:  .LBB0_1: # %.preheader
 ; X64-NEXT:    movl %esi, %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB0_2: # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    cltq
 ; X64-NEXT:    shlq $2, %rax
@@ -77,7 +77,7 @@ define void @foo_sext_nuw(i1 zeroext, i32) nounwind {
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB1_1: # %.preheader
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB1_2: # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    leal (%eax,%eax,4), %eax
 ; X86-NEXT:    leal 20(,%eax,4), %eax
@@ -96,7 +96,7 @@ define void @foo_sext_nuw(i1 zeroext, i32) nounwind {
 ; X64-NEXT:    retq
 ; X64-NEXT:  .LBB1_1: # %.preheader
 ; X64-NEXT:    movl %esi, %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB1_2: # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    incl %eax
 ; X64-NEXT:    cltq
@@ -125,7 +125,7 @@ define void @foo_zext_nsw(i1 zeroext, i32) nounwind {
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB2_1: # %.preheader
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB2_2: # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    leal (%eax,%eax,4), %eax
 ; X86-NEXT:    leal 20(,%eax,4), %eax
@@ -144,7 +144,7 @@ define void @foo_zext_nsw(i1 zeroext, i32) nounwind {
 ; X64-NEXT:    retq
 ; X64-NEXT:  .LBB2_1: # %.preheader
 ; X64-NEXT:    movl %esi, %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB2_2: # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    incl %eax
 ; X64-NEXT:    shlq $2, %rax
@@ -173,7 +173,7 @@ define void @foo_zext_nuw(i1 zeroext, i32) nounwind {
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB3_1: # %.preheader
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB3_2: # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    leal (%eax,%eax,4), %eax
 ; X86-NEXT:    leal 20(,%eax,4), %eax
@@ -192,7 +192,7 @@ define void @foo_zext_nuw(i1 zeroext, i32) nounwind {
 ; X64-NEXT:    retq
 ; X64-NEXT:  .LBB3_1: # %.preheader
 ; X64-NEXT:    movl %esi, %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB3_2: # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %eax
 ; X64-NEXT:    shlq $2, %rax
@@ -220,7 +220,7 @@ define void @foo_sext(i1 zeroext, i32) nounwind {
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB4_1: # %.preheader
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB4_2: # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    leal (%eax,%eax,4), %eax
 ; X86-NEXT:    leal 20(,%eax,4), %eax
@@ -239,7 +239,7 @@ define void @foo_sext(i1 zeroext, i32) nounwind {
 ; X64-NEXT:    retq
 ; X64-NEXT:  .LBB4_1: # %.preheader
 ; X64-NEXT:    movl %esi, %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB4_2: # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    incl %eax
 ; X64-NEXT:    cltq
@@ -268,7 +268,7 @@ define void @foo_zext(i1 zeroext, i32) nounwind {
 ; X86-NEXT:    retl
 ; X86-NEXT:  .LBB5_1: # %.preheader
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB5_2: # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    leal (%eax,%eax,4), %eax
 ; X86-NEXT:    leal 20(,%eax,4), %eax
@@ -287,7 +287,7 @@ define void @foo_zext(i1 zeroext, i32) nounwind {
 ; X64-NEXT:    retq
 ; X64-NEXT:  .LBB5_1: # %.preheader
 ; X64-NEXT:    movl %esi, %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB5_2: # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    incl %eax
 ; X64-NEXT:    shlq $2, %rax
diff --git a/llvm/test/CodeGen/X86/align-basic-block-sections.mir b/llvm/test/CodeGen/X86/align-basic-block-sections.mir
index e7ad5dfe6478f8..7521341ff3ea01 100644
--- a/llvm/test/CodeGen/X86/align-basic-block-sections.mir
+++ b/llvm/test/CodeGen/X86/align-basic-block-sections.mir
@@ -132,5 +132,5 @@ body:             |
 ...
 
 # CHECK: .section	.text.test,"ax", at progbits,unique,2
-# CHECK-NEXT: .p2align	8, 0x90
+# CHECK-NEXT: .p2align	8
 # CHECK-NEXT: test.__part.2: # %entry
diff --git a/llvm/test/CodeGen/X86/and-sink.ll b/llvm/test/CodeGen/X86/and-sink.ll
index 965e84844758fc..d9a34d743ac657 100644
--- a/llvm/test/CodeGen/X86/and-sink.ll
+++ b/llvm/test/CodeGen/X86/and-sink.ll
@@ -54,7 +54,7 @@ define i32 @and_sink2(i32 %a, i1 %c, i1 %c2) {
 ; CHECK-NEXT:  # %bb.1: # %bb0.preheader
 ; CHECK-NEXT:    movzbl {{[0-9]+}}(%esp), %eax
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_2: # %bb0
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $0, B
diff --git a/llvm/test/CodeGen/X86/apx/push2-pop2.ll b/llvm/test/CodeGen/X86/apx/push2-pop2.ll
index 6bd9f525090ee2..f5be484be2b1a6 100644
--- a/llvm/test/CodeGen/X86/apx/push2-pop2.ll
+++ b/llvm/test/CodeGen/X86/apx/push2-pop2.ll
@@ -286,7 +286,7 @@ define void @lea_in_epilog(i1 %arg, ptr %arg1, ptr %arg2, i64 %arg3, i64 %arg4,
 ; CHECK-NEXT:    xorl %ebp, %ebp
 ; CHECK-NEXT:    xorl %r12d, %r12d
 ; CHECK-NEXT:    movl %edi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB6_2: # %bb15
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    incq %r12
@@ -338,7 +338,7 @@ define void @lea_in_epilog(i1 %arg, ptr %arg1, ptr %arg2, i64 %arg3, i64 %arg4,
 ; PPX-NEXT:    xorl %ebp, %ebp
 ; PPX-NEXT:    xorl %r12d, %r12d
 ; PPX-NEXT:    movl %edi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
-; PPX-NEXT:    .p2align 4, 0x90
+; PPX-NEXT:    .p2align 4
 ; PPX-NEXT:  .LBB6_2: # %bb15
 ; PPX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; PPX-NEXT:    incq %r12
@@ -390,7 +390,7 @@ define void @lea_in_epilog(i1 %arg, ptr %arg1, ptr %arg2, i64 %arg3, i64 %arg4,
 ; FRAME-NEXT:    xorl %r13d, %r13d
 ; FRAME-NEXT:    xorl %r14d, %r14d
 ; FRAME-NEXT:    movl %edi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
-; FRAME-NEXT:    .p2align 4, 0x90
+; FRAME-NEXT:    .p2align 4
 ; FRAME-NEXT:  .LBB6_2: # %bb15
 ; FRAME-NEXT:    # =>This Inner Loop Header: Depth=1
 ; FRAME-NEXT:    movq %r9, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
diff --git a/llvm/test/CodeGen/X86/apx/setzucc.ll b/llvm/test/CodeGen/X86/apx/setzucc.ll
index 084e54235330c2..1f2b612a170883 100644
--- a/llvm/test/CodeGen/X86/apx/setzucc.ll
+++ b/llvm/test/CodeGen/X86/apx/setzucc.ll
@@ -53,7 +53,7 @@ define i32 @flags_copy_lowering() nounwind {
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    xorl %edx, %edx
 ; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB4_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    addl %edx, 0
diff --git a/llvm/test/CodeGen/X86/assertzext-demanded.ll b/llvm/test/CodeGen/X86/assertzext-demanded.ll
index 3d2120578b49e4..33a8c543ed9ab0 100644
--- a/llvm/test/CodeGen/X86/assertzext-demanded.ll
+++ b/llvm/test/CodeGen/X86/assertzext-demanded.ll
@@ -7,7 +7,7 @@ define void @simplify_assertzext(ptr %0) {
 ; CHECK:       # %bb.0: # %BB
 ; CHECK-NEXT:    movl $275047, %eax # imm = 0x43267
 ; CHECK-NEXT:    movb $1, %cl
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %CF246
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb %cl, %cl
@@ -15,7 +15,7 @@ define void @simplify_assertzext(ptr %0) {
 ; CHECK-NEXT:  # %bb.2: # %CF260
 ; CHECK-NEXT:    orl $278403, %eax # imm = 0x43F83
 ; CHECK-NEXT:    movl %eax, (%rdi)
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_3: # %CF242
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB0_3
diff --git a/llvm/test/CodeGen/X86/atom-pad-short-functions.ll b/llvm/test/CodeGen/X86/atom-pad-short-functions.ll
index 06800bd244de3c..301995dfef0a3d 100644
--- a/llvm/test/CodeGen/X86/atom-pad-short-functions.ll
+++ b/llvm/test/CodeGen/X86/atom-pad-short-functions.ll
@@ -110,7 +110,7 @@ define void @test_branch_to_same_bb(i32 %x, i32 %y) nounwind {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    cmpl $0, {{[0-9]+}}(%esp)
 ; CHECK-NEXT:    jle .LBB7_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB7_1: # %while.cond
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB7_1
diff --git a/llvm/test/CodeGen/X86/atomic-bit-test.ll b/llvm/test/CodeGen/X86/atomic-bit-test.ll
index 10b6605c3fb05e..8f91f4120842b3 100644
--- a/llvm/test/CodeGen/X86/atomic-bit-test.ll
+++ b/llvm/test/CodeGen/X86/atomic-bit-test.ll
@@ -106,7 +106,7 @@ define i64 @bts63() nounwind {
 ; X86-NEXT:    movl $-2147483648, %esi # imm = 0x80000000
 ; X86-NEXT:    movl v64+4, %edx
 ; X86-NEXT:    movl v64, %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB4_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %edx, %ecx
@@ -230,7 +230,7 @@ define i64 @btc63() nounwind {
 ; X86-NEXT:    movl $-2147483648, %esi # imm = 0x80000000
 ; X86-NEXT:    movl v64+4, %edx
 ; X86-NEXT:    movl v64, %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB9_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %edx, %ecx
@@ -360,7 +360,7 @@ define i64 @btr63() nounwind {
 ; X86-NEXT:    movl $-1, %edi
 ; X86-NEXT:    movl v64+4, %edx
 ; X86-NEXT:    movl v64, %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB14_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ebx
@@ -396,7 +396,7 @@ define i16 @multi_use1() nounwind {
 ; X86-LABEL: multi_use1:
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movzwl v16, %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB15_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -416,7 +416,7 @@ define i16 @multi_use1() nounwind {
 ; X64-LABEL: multi_use1:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movzwl v16(%rip), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB15_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -471,7 +471,7 @@ define i16 @use_in_diff_bb() nounwind {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    pushl %esi
 ; X86-NEXT:    movzwl v16, %esi
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB17_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %esi, %ecx
@@ -496,7 +496,7 @@ define i16 @use_in_diff_bb() nounwind {
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    pushq %rbx
 ; X64-NEXT:    movzwl v16(%rip), %ebx
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB17_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %ebx, %ecx
diff --git a/llvm/test/CodeGen/X86/atomic-flags.ll b/llvm/test/CodeGen/X86/atomic-flags.ll
index 00a6308a749694..317af67deb1632 100644
--- a/llvm/test/CodeGen/X86/atomic-flags.ll
+++ b/llvm/test/CodeGen/X86/atomic-flags.ll
@@ -144,7 +144,7 @@ define zeroext i1 @xadd_cmp0_i64(ptr %x) nounwind {
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; X86-NEXT:    movl (%esi), %eax
 ; X86-NEXT:    movl 4(%esi), %edx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB2_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ebx
diff --git a/llvm/test/CodeGen/X86/atomic-idempotent.ll b/llvm/test/CodeGen/X86/atomic-idempotent.ll
index d5c46485068a64..55b4d1af094f67 100644
--- a/llvm/test/CodeGen/X86/atomic-idempotent.ll
+++ b/llvm/test/CodeGen/X86/atomic-idempotent.ll
@@ -64,7 +64,7 @@ define i16 @or16(ptr %p) {
 ; X86-SLM:       # %bb.0:
 ; X86-SLM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-SLM-NEXT:    movzwl (%ecx), %eax
-; X86-SLM-NEXT:    .p2align 4, 0x90
+; X86-SLM-NEXT:    .p2align 4
 ; X86-SLM-NEXT:  .LBB1_1: # %atomicrmw.start
 ; X86-SLM-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-SLM-NEXT:    lock cmpxchgw %ax, (%ecx)
@@ -76,7 +76,7 @@ define i16 @or16(ptr %p) {
 ; X86-ATOM:       # %bb.0:
 ; X86-ATOM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-ATOM-NEXT:    movzwl (%ecx), %eax
-; X86-ATOM-NEXT:    .p2align 4, 0x90
+; X86-ATOM-NEXT:    .p2align 4
 ; X86-ATOM-NEXT:  .LBB1_1: # %atomicrmw.start
 ; X86-ATOM-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-ATOM-NEXT:    lock cmpxchgw %ax, (%ecx)
@@ -105,7 +105,7 @@ define i32 @xor32(ptr %p) {
 ; X86-SLM:       # %bb.0:
 ; X86-SLM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-SLM-NEXT:    movl (%ecx), %eax
-; X86-SLM-NEXT:    .p2align 4, 0x90
+; X86-SLM-NEXT:    .p2align 4
 ; X86-SLM-NEXT:  .LBB2_1: # %atomicrmw.start
 ; X86-SLM-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-SLM-NEXT:    lock cmpxchgl %eax, (%ecx)
@@ -117,7 +117,7 @@ define i32 @xor32(ptr %p) {
 ; X86-ATOM:       # %bb.0:
 ; X86-ATOM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-ATOM-NEXT:    movl (%ecx), %eax
-; X86-ATOM-NEXT:    .p2align 4, 0x90
+; X86-ATOM-NEXT:    .p2align 4
 ; X86-ATOM-NEXT:  .LBB2_1: # %atomicrmw.start
 ; X86-ATOM-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-ATOM-NEXT:    lock cmpxchgl %eax, (%ecx)
@@ -146,7 +146,7 @@ define i64 @sub64(ptr %p) {
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; X86-NEXT:    movl (%esi), %eax
 ; X86-NEXT:    movl 4(%esi), %edx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB3_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %edx, %ecx
@@ -196,7 +196,7 @@ define i128 @or128(ptr %p) {
 ; X86-GENERIC-NEXT:    movl 8(%edi), %edx
 ; X86-GENERIC-NEXT:    movl (%edi), %ebx
 ; X86-GENERIC-NEXT:    movl 4(%edi), %esi
-; X86-GENERIC-NEXT:    .p2align 4, 0x90
+; X86-GENERIC-NEXT:    .p2align 4
 ; X86-GENERIC-NEXT:  .LBB4_1: # %atomicrmw.start
 ; X86-GENERIC-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-GENERIC-NEXT:    movl %ebx, (%esp)
@@ -257,7 +257,7 @@ define i128 @or128(ptr %p) {
 ; X86-ATOM-NEXT:    movl 8(%edi), %edx
 ; X86-ATOM-NEXT:    movl (%edi), %esi
 ; X86-ATOM-NEXT:    movl 4(%edi), %ebx
-; X86-ATOM-NEXT:    .p2align 4, 0x90
+; X86-ATOM-NEXT:    .p2align 4
 ; X86-ATOM-NEXT:  .LBB4_1: # %atomicrmw.start
 ; X86-ATOM-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-ATOM-NEXT:    movl %esi, (%esp)
@@ -320,7 +320,7 @@ define i32 @and32 (ptr %p) {
 ; X86-SLM:       # %bb.0:
 ; X86-SLM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-SLM-NEXT:    movl (%ecx), %eax
-; X86-SLM-NEXT:    .p2align 4, 0x90
+; X86-SLM-NEXT:    .p2align 4
 ; X86-SLM-NEXT:  .LBB5_1: # %atomicrmw.start
 ; X86-SLM-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-SLM-NEXT:    lock cmpxchgl %eax, (%ecx)
@@ -332,7 +332,7 @@ define i32 @and32 (ptr %p) {
 ; X86-ATOM:       # %bb.0:
 ; X86-ATOM-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-ATOM-NEXT:    movl (%ecx), %eax
-; X86-ATOM-NEXT:    .p2align 4, 0x90
+; X86-ATOM-NEXT:    .p2align 4
 ; X86-ATOM-NEXT:  .LBB5_1: # %atomicrmw.start
 ; X86-ATOM-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-ATOM-NEXT:    lock cmpxchgl %eax, (%ecx)
@@ -495,7 +495,7 @@ define void @or64_nouse_seq_cst(ptr %p) {
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; X86-NEXT:    movl (%esi), %eax
 ; X86-NEXT:    movl 4(%esi), %edx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB11_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %edx, %ecx
@@ -546,7 +546,7 @@ define void @or128_nouse_seq_cst(ptr %p) {
 ; X86-GENERIC-NEXT:    movl 8(%esi), %edi
 ; X86-GENERIC-NEXT:    movl (%esi), %edx
 ; X86-GENERIC-NEXT:    movl 4(%esi), %ebx
-; X86-GENERIC-NEXT:    .p2align 4, 0x90
+; X86-GENERIC-NEXT:    .p2align 4
 ; X86-GENERIC-NEXT:  .LBB12_1: # %atomicrmw.start
 ; X86-GENERIC-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-GENERIC-NEXT:    movl %edx, (%esp)
@@ -603,7 +603,7 @@ define void @or128_nouse_seq_cst(ptr %p) {
 ; X86-ATOM-NEXT:    movl 8(%esi), %edx
 ; X86-ATOM-NEXT:    movl (%esi), %eax
 ; X86-ATOM-NEXT:    movl 4(%esi), %edi
-; X86-ATOM-NEXT:    .p2align 4, 0x90
+; X86-ATOM-NEXT:    .p2align 4
 ; X86-ATOM-NEXT:  .LBB12_1: # %atomicrmw.start
 ; X86-ATOM-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-ATOM-NEXT:    movl %eax, (%esp)
diff --git a/llvm/test/CodeGen/X86/atomic-minmax-i6432.ll b/llvm/test/CodeGen/X86/atomic-minmax-i6432.ll
index 809457f4d8291a..f8cbd0a6a9ee0f 100644
--- a/llvm/test/CodeGen/X86/atomic-minmax-i6432.ll
+++ b/llvm/test/CodeGen/X86/atomic-minmax-i6432.ll
@@ -12,7 +12,7 @@ define i64 @atomic_max_i64() nounwind {
 ; LINUX-NEXT:    movl sc64+4, %edx
 ; LINUX-NEXT:    movl sc64, %eax
 ; LINUX-NEXT:    movl $5, %esi
-; LINUX-NEXT:    .p2align 4, 0x90
+; LINUX-NEXT:    .p2align 4
 ; LINUX-NEXT:  .LBB0_1: # %atomicrmw.start
 ; LINUX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; LINUX-NEXT:    cmpl %eax, %esi
@@ -41,7 +41,7 @@ define i64 @atomic_max_i64() nounwind {
 ; PIC-NEXT:    movl (%esi), %eax
 ; PIC-NEXT:    movl 4(%esi), %edx
 ; PIC-NEXT:    movl $5, %edi
-; PIC-NEXT:    .p2align 4, 0x90
+; PIC-NEXT:    .p2align 4
 ; PIC-NEXT:  LBB0_1: ## %atomicrmw.start
 ; PIC-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; PIC-NEXT:    cmpl %eax, %edi
@@ -69,7 +69,7 @@ define i64 @atomic_min_i64() nounwind {
 ; LINUX-NEXT:    pushl %ebx
 ; LINUX-NEXT:    movl sc64+4, %edx
 ; LINUX-NEXT:    movl sc64, %eax
-; LINUX-NEXT:    .p2align 4, 0x90
+; LINUX-NEXT:    .p2align 4
 ; LINUX-NEXT:  .LBB1_1: # %atomicrmw.start
 ; LINUX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; LINUX-NEXT:    cmpl $7, %eax
@@ -95,7 +95,7 @@ define i64 @atomic_min_i64() nounwind {
 ; PIC-NEXT:    movl L_sc64$non_lazy_ptr-L1$pb(%eax), %esi
 ; PIC-NEXT:    movl (%esi), %eax
 ; PIC-NEXT:    movl 4(%esi), %edx
-; PIC-NEXT:    .p2align 4, 0x90
+; PIC-NEXT:    .p2align 4
 ; PIC-NEXT:  LBB1_1: ## %atomicrmw.start
 ; PIC-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; PIC-NEXT:    cmpl $7, %eax
@@ -124,7 +124,7 @@ define i64 @atomic_umax_i64() nounwind {
 ; LINUX-NEXT:    movl sc64+4, %edx
 ; LINUX-NEXT:    movl sc64, %eax
 ; LINUX-NEXT:    movl $7, %esi
-; LINUX-NEXT:    .p2align 4, 0x90
+; LINUX-NEXT:    .p2align 4
 ; LINUX-NEXT:  .LBB2_1: # %atomicrmw.start
 ; LINUX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; LINUX-NEXT:    cmpl %eax, %esi
@@ -153,7 +153,7 @@ define i64 @atomic_umax_i64() nounwind {
 ; PIC-NEXT:    movl (%esi), %eax
 ; PIC-NEXT:    movl 4(%esi), %edx
 ; PIC-NEXT:    movl $7, %edi
-; PIC-NEXT:    .p2align 4, 0x90
+; PIC-NEXT:    .p2align 4
 ; PIC-NEXT:  LBB2_1: ## %atomicrmw.start
 ; PIC-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; PIC-NEXT:    cmpl %eax, %edi
@@ -181,7 +181,7 @@ define i64 @atomic_umin_i64() nounwind {
 ; LINUX-NEXT:    pushl %ebx
 ; LINUX-NEXT:    movl sc64+4, %edx
 ; LINUX-NEXT:    movl sc64, %eax
-; LINUX-NEXT:    .p2align 4, 0x90
+; LINUX-NEXT:    .p2align 4
 ; LINUX-NEXT:  .LBB3_1: # %atomicrmw.start
 ; LINUX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; LINUX-NEXT:    cmpl $9, %eax
@@ -207,7 +207,7 @@ define i64 @atomic_umin_i64() nounwind {
 ; PIC-NEXT:    movl L_sc64$non_lazy_ptr-L3$pb(%eax), %esi
 ; PIC-NEXT:    movl (%esi), %eax
 ; PIC-NEXT:    movl 4(%esi), %edx
-; PIC-NEXT:    .p2align 4, 0x90
+; PIC-NEXT:    .p2align 4
 ; PIC-NEXT:  LBB3_1: ## %atomicrmw.start
 ; PIC-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; PIC-NEXT:    cmpl $9, %eax
@@ -238,7 +238,7 @@ define void @tf_bug(ptr %ptr) nounwind {
 ; LINUX-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; LINUX-NEXT:    movl id+4, %edx
 ; LINUX-NEXT:    movl id, %eax
-; LINUX-NEXT:    .p2align 4, 0x90
+; LINUX-NEXT:    .p2align 4
 ; LINUX-NEXT:  .LBB4_1: # %atomicrmw.start
 ; LINUX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; LINUX-NEXT:    movl %eax, %ebx
@@ -267,7 +267,7 @@ define void @tf_bug(ptr %ptr) nounwind {
 ; PIC-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; PIC-NEXT:    movl (_id-L4$pb)+4(%edi), %edx
 ; PIC-NEXT:    movl _id-L4$pb(%edi), %eax
-; PIC-NEXT:    .p2align 4, 0x90
+; PIC-NEXT:    .p2align 4
 ; PIC-NEXT:  LBB4_1: ## %atomicrmw.start
 ; PIC-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; PIC-NEXT:    movl %eax, %ebx
diff --git a/llvm/test/CodeGen/X86/atomic-non-integer-fp128.ll b/llvm/test/CodeGen/X86/atomic-non-integer-fp128.ll
index 5960787fe30de1..e8b4d3f6812d26 100644
--- a/llvm/test/CodeGen/X86/atomic-non-integer-fp128.ll
+++ b/llvm/test/CodeGen/X86/atomic-non-integer-fp128.ll
@@ -16,7 +16,7 @@ define void @store_fp128(ptr %fptr, fp128 %v) {
 ; X64-SSE-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx
 ; X64-SSE-NEXT:    movq (%rdi), %rax
 ; X64-SSE-NEXT:    movq 8(%rdi), %rdx
-; X64-SSE-NEXT:    .p2align 4, 0x90
+; X64-SSE-NEXT:    .p2align 4
 ; X64-SSE-NEXT:  .LBB0_1: # %atomicrmw.start
 ; X64-SSE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-SSE-NEXT:    lock cmpxchg16b (%rdi)
@@ -73,7 +73,7 @@ define fp128 @exchange_fp128(ptr %fptr, fp128 %x) {
 ; X64-SSE-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx
 ; X64-SSE-NEXT:    movq (%rdi), %rax
 ; X64-SSE-NEXT:    movq 8(%rdi), %rdx
-; X64-SSE-NEXT:    .p2align 4, 0x90
+; X64-SSE-NEXT:    .p2align 4
 ; X64-SSE-NEXT:  .LBB2_1: # %atomicrmw.start
 ; X64-SSE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-SSE-NEXT:    lock cmpxchg16b (%rdi)
@@ -96,7 +96,7 @@ define fp128 @exchange_fp128(ptr %fptr, fp128 %x) {
 ; X64-AVX-NEXT:    movq -{{[0-9]+}}(%rsp), %rcx
 ; X64-AVX-NEXT:    movq (%rdi), %rax
 ; X64-AVX-NEXT:    movq 8(%rdi), %rdx
-; X64-AVX-NEXT:    .p2align 4, 0x90
+; X64-AVX-NEXT:    .p2align 4
 ; X64-AVX-NEXT:  .LBB2_1: # %atomicrmw.start
 ; X64-AVX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-AVX-NEXT:    lock cmpxchg16b (%rdi)
diff --git a/llvm/test/CodeGen/X86/atomic-non-integer.ll b/llvm/test/CodeGen/X86/atomic-non-integer.ll
index d7633cb11e44c1..d12fc74abef8ae 100644
--- a/llvm/test/CodeGen/X86/atomic-non-integer.ll
+++ b/llvm/test/CodeGen/X86/atomic-non-integer.ll
@@ -440,7 +440,7 @@ define double @exchange_double(ptr %fptr, double %x) {
 ; X86-SSE1-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-SSE1-NEXT:    movl (%esi), %eax
 ; X86-SSE1-NEXT:    movl 4(%esi), %edx
-; X86-SSE1-NEXT:    .p2align 4, 0x90
+; X86-SSE1-NEXT:    .p2align 4
 ; X86-SSE1-NEXT:  .LBB8_1: # %atomicrmw.start
 ; X86-SSE1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-SSE1-NEXT:    lock cmpxchg8b (%esi)
@@ -472,7 +472,7 @@ define double @exchange_double(ptr %fptr, double %x) {
 ; X86-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-SSE2-NEXT:    movl (%esi), %eax
 ; X86-SSE2-NEXT:    movl 4(%esi), %edx
-; X86-SSE2-NEXT:    .p2align 4, 0x90
+; X86-SSE2-NEXT:    .p2align 4
 ; X86-SSE2-NEXT:  .LBB8_1: # %atomicrmw.start
 ; X86-SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-SSE2-NEXT:    lock cmpxchg8b (%esi)
@@ -506,7 +506,7 @@ define double @exchange_double(ptr %fptr, double %x) {
 ; X86-AVX-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-AVX-NEXT:    movl (%esi), %eax
 ; X86-AVX-NEXT:    movl 4(%esi), %edx
-; X86-AVX-NEXT:    .p2align 4, 0x90
+; X86-AVX-NEXT:    .p2align 4
 ; X86-AVX-NEXT:  .LBB8_1: # %atomicrmw.start
 ; X86-AVX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-AVX-NEXT:    lock cmpxchg8b (%esi)
@@ -539,7 +539,7 @@ define double @exchange_double(ptr %fptr, double %x) {
 ; X86-NOSSE-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NOSSE-NEXT:    movl (%esi), %eax
 ; X86-NOSSE-NEXT:    movl 4(%esi), %edx
-; X86-NOSSE-NEXT:    .p2align 4, 0x90
+; X86-NOSSE-NEXT:    .p2align 4
 ; X86-NOSSE-NEXT:  .LBB8_1: # %atomicrmw.start
 ; X86-NOSSE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NOSSE-NEXT:    lock cmpxchg8b (%esi)
diff --git a/llvm/test/CodeGen/X86/atomic-rm-bit-test-64.ll b/llvm/test/CodeGen/X86/atomic-rm-bit-test-64.ll
index 8ff4f4067dabda..3fe5b70edc7183 100644
--- a/llvm/test/CodeGen/X86/atomic-rm-bit-test-64.ll
+++ b/llvm/test/CodeGen/X86/atomic-rm-bit-test-64.ll
@@ -27,7 +27,7 @@ define i64 @atomic_shl2_xor_64_gpr_val(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    # kill: def $cl killed $cl killed $rcx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rcx
@@ -51,7 +51,7 @@ define i64 @atomic_shl1_neq_xor_64_gpr_val(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB2_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -159,7 +159,7 @@ define i64 @atomic_blsi_xor_64_gpr_val(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    negq %rcx
 ; CHECK-NEXT:    andq %rsi, %rcx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB7_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rdx
@@ -184,7 +184,7 @@ define i64 @atomic_shl1_xor_64_gpr_valz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB8_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -214,7 +214,7 @@ define i64 @atomic_shl2_xor_64_gpr_valz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    # kill: def $cl killed $cl killed $rcx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB9_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rcx
@@ -243,7 +243,7 @@ define i64 @atomic_shl1_neq_xor_64_gpr_valz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB10_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -276,7 +276,7 @@ define i64 @atomic_shl1_small_mask_xor_64_gpr_valz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB11_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -306,7 +306,7 @@ define i64 @atomic_shl1_mask0_xor_64_gpr_valz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB12_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -336,7 +336,7 @@ define i64 @atomic_shl1_mask1_xor_64_gpr_valz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB13_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -367,7 +367,7 @@ define i64 @atomic_shl1_mask01_xor_64_gpr_valz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB14_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -397,7 +397,7 @@ define i64 @atomic_blsi_xor_64_gpr_valz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    negq %rdx
 ; CHECK-NEXT:    andq %rsi, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB15_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rcx
@@ -427,7 +427,7 @@ define i64 @atomic_shl1_xor_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB16_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -456,7 +456,7 @@ define i64 @atomic_shl2_xor_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    # kill: def $cl killed $cl killed $rcx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB17_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rcx
@@ -485,7 +485,7 @@ define i64 @atomic_shl1_neq_xor_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB18_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -517,7 +517,7 @@ define i64 @atomic_shl1_small_mask_xor_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB19_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -546,7 +546,7 @@ define i64 @atomic_shl1_mask0_xor_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB20_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -575,7 +575,7 @@ define i64 @atomic_shl1_mask1_xor_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB21_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -605,7 +605,7 @@ define i64 @atomic_shl1_mask01_xor_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    shlq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB22_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -634,7 +634,7 @@ define i64 @atomic_blsi_xor_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    negq %rdx
 ; CHECK-NEXT:    andq %rsi, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB23_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rcx
@@ -686,7 +686,7 @@ define i64 @atomic_shl2_and_64_gpr_val(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movq %rdx, %rcx
 ; CHECK-NEXT:    notq %rcx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB25_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -711,7 +711,7 @@ define i64 @atomic_shl1_neq_and_64_gpr_val(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movq $-2, %rdx
 ; CHECK-NEXT:    rolq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB26_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -826,7 +826,7 @@ define i64 @atomic_blsi_and_64_gpr_val(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movq %rcx, %rdx
 ; CHECK-NEXT:    notq %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB31_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -853,7 +853,7 @@ define i64 @atomic_shl1_and_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movq $-2, %rdx
 ; CHECK-NEXT:    rolq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB32_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -885,7 +885,7 @@ define i64 @atomic_shl2_and_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movq %rdx, %rcx
 ; CHECK-NEXT:    notq %rcx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB33_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -915,7 +915,7 @@ define i64 @atomic_shl1_neq_and_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movq $-2, %rdx
 ; CHECK-NEXT:    rolq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB34_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -948,7 +948,7 @@ define i64 @atomic_shl1_small_mask_and_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movq $-2, %rdx
 ; CHECK-NEXT:    rolq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB35_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -978,7 +978,7 @@ define i64 @atomic_shl1_mask0_and_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movq $-2, %rdx
 ; CHECK-NEXT:    rolq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB36_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -1008,7 +1008,7 @@ define i64 @atomic_shl1_mask1_and_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movq $-2, %rdx
 ; CHECK-NEXT:    rolq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB37_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -1041,7 +1041,7 @@ define i64 @atomic_shl1_mask01_and_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    # kill: def $cl killed $cl killed $rcx
 ; CHECK-NEXT:    rolq %cl, %rsi
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB38_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rcx
@@ -1073,7 +1073,7 @@ define i64 @atomic_blsi_and_64_gpr_valnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movq %rdx, %rcx
 ; CHECK-NEXT:    notq %rcx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB39_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -1137,7 +1137,7 @@ define i64 @atomic_shl2_and_64_gpr_brnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movq %rdx, %rsi
 ; CHECK-NEXT:    notq %rsi
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB41_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %r8
@@ -1178,7 +1178,7 @@ define i64 @atomic_shl1_neq_and_64_gpr_brnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movq $-2, %rdx
 ; CHECK-NEXT:    rolq %cl, %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB42_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rsi
@@ -1354,7 +1354,7 @@ define i64 @atomic_blsi_and_64_gpr_brnz(ptr %v, i64 %c) nounwind {
 ; CHECK-NEXT:    movq %rcx, %rdx
 ; CHECK-NEXT:    notq %rdx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB47_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %r8
@@ -1420,7 +1420,7 @@ define i64 @atomic_shl1_neq_xor_64_const_br(ptr %v) nounwind {
 ; CHECK-LABEL: atomic_shl1_neq_xor_64_const_br:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB49_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rcx
@@ -1483,7 +1483,7 @@ define i64 @atomic_shl1_neq_xor_64_const_brz(ptr %v) nounwind {
 ; CHECK-LABEL: atomic_shl1_neq_xor_64_const_brz:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB51_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rcx
@@ -1546,7 +1546,7 @@ define i64 @atomic_shl1_neq_xor_64_const_brnz(ptr %v) nounwind {
 ; CHECK-LABEL: atomic_shl1_neq_xor_64_const_brnz:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB53_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rcx
@@ -1583,7 +1583,7 @@ define i64 @atomic_and_with_not_arg(ptr %v, i64 %c) nounwind {
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    movq $-1, %rcx
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB54_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rdx
diff --git a/llvm/test/CodeGen/X86/atomic-rm-bit-test.ll b/llvm/test/CodeGen/X86/atomic-rm-bit-test.ll
index 5594d13a234d02..b4d40fee01e419 100644
--- a/llvm/test/CodeGen/X86/atomic-rm-bit-test.ll
+++ b/llvm/test/CodeGen/X86/atomic-rm-bit-test.ll
@@ -11,7 +11,7 @@ define zeroext i8 @atomic_shl1_or_8_gpr_val(ptr %v, i8 zeroext %c) nounwind {
 ; X86-NEXT:    movl $1, %edx
 ; X86-NEXT:    shll %cl, %edx
 ; X86-NEXT:    movzbl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB0_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -31,7 +31,7 @@ define zeroext i8 @atomic_shl1_or_8_gpr_val(ptr %v, i8 zeroext %c) nounwind {
 ; X64-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzbl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB0_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -63,7 +63,7 @@ define zeroext i8 @atomic_shl1_mask0_or_8_gpr_val(ptr %v, i8 zeroext %c) nounwin
 ; X86-NEXT:    movb $1, %ah
 ; X86-NEXT:    shlb %cl, %ah
 ; X86-NEXT:    movb (%esi), %al
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB1_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -86,7 +86,7 @@ define zeroext i8 @atomic_shl1_mask0_or_8_gpr_val(ptr %v, i8 zeroext %c) nounwin
 ; X64-NEXT:    movb $1, %dl
 ; X64-NEXT:    shlb %cl, %dl
 ; X64-NEXT:    movzbl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB1_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -120,7 +120,7 @@ define zeroext i8 @atomic_shl1_mask01_or_8_gpr_val(ptr %v, i8 zeroext %c) nounwi
 ; X86-NEXT:    movb $1, %dl
 ; X86-NEXT:    shlb %cl, %dl
 ; X86-NEXT:    movzbl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB2_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -141,7 +141,7 @@ define zeroext i8 @atomic_shl1_mask01_or_8_gpr_val(ptr %v, i8 zeroext %c) nounwi
 ; X64-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X64-NEXT:    shlb %cl, %dl
 ; X64-NEXT:    movzbl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB2_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -169,7 +169,7 @@ define zeroext i8 @atomic_shl1_xor_8_gpr_valz(ptr %v, i8 zeroext %c) nounwind {
 ; X86-NEXT:    movl $1, %edx
 ; X86-NEXT:    shll %cl, %edx
 ; X86-NEXT:    movzbl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB3_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -190,7 +190,7 @@ define zeroext i8 @atomic_shl1_xor_8_gpr_valz(ptr %v, i8 zeroext %c) nounwind {
 ; X64-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzbl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB3_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -225,7 +225,7 @@ define zeroext i8 @atomic_shl1_mask0_xor_8_gpr_valz(ptr %v, i8 zeroext %c) nounw
 ; X86-NEXT:    movb $1, %ah
 ; X86-NEXT:    shlb %cl, %ah
 ; X86-NEXT:    movb (%esi), %al
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB4_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -247,7 +247,7 @@ define zeroext i8 @atomic_shl1_mask0_xor_8_gpr_valz(ptr %v, i8 zeroext %c) nounw
 ; X64-NEXT:    movb $1, %dl
 ; X64-NEXT:    shlb %cl, %dl
 ; X64-NEXT:    movzbl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB4_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -283,7 +283,7 @@ define zeroext i8 @atomic_shl1_mask01_xor_8_gpr_valz(ptr %v, i8 zeroext %c) noun
 ; X86-NEXT:    movl $1, %ebx
 ; X86-NEXT:    shll %cl, %ebx
 ; X86-NEXT:    movzbl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB5_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -305,7 +305,7 @@ define zeroext i8 @atomic_shl1_mask01_xor_8_gpr_valz(ptr %v, i8 zeroext %c) noun
 ; X64-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzbl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB5_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -341,7 +341,7 @@ define zeroext i8 @atomic_shl1_and_8_gpr_brnz(ptr %v, i8 zeroext %c) nounwind {
 ; X86-NEXT:    movb %bl, %ah
 ; X86-NEXT:    notb %ah
 ; X86-NEXT:    movb (%edx), %al
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB6_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movb %al, %ch
@@ -370,7 +370,7 @@ define zeroext i8 @atomic_shl1_and_8_gpr_brnz(ptr %v, i8 zeroext %c) nounwind {
 ; X64-NEXT:    movl %edx, %esi
 ; X64-NEXT:    notb %sil
 ; X64-NEXT:    movzbl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB6_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %r8d
@@ -419,7 +419,7 @@ define zeroext i8 @atomic_shl1_mask0_and_8_gpr_brnz(ptr %v, i8 zeroext %c) nounw
 ; X86-NEXT:    movb $-2, %ah
 ; X86-NEXT:    rolb %cl, %ah
 ; X86-NEXT:    movb (%edx), %al
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB7_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movb %al, %ch
@@ -446,7 +446,7 @@ define zeroext i8 @atomic_shl1_mask0_and_8_gpr_brnz(ptr %v, i8 zeroext %c) nounw
 ; X64-NEXT:    movb $-2, %dl
 ; X64-NEXT:    rolb %cl, %dl
 ; X64-NEXT:    movzbl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB7_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -500,7 +500,7 @@ define zeroext i8 @atomic_shl1_mask01_and_8_gpr_brnz(ptr %v, i8 zeroext %c) noun
 ; X86-NEXT:    movl %ebx, %ecx
 ; X86-NEXT:    notb %cl
 ; X86-NEXT:    movb (%edx), %al
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB8_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movb %al, %ch
@@ -530,7 +530,7 @@ define zeroext i8 @atomic_shl1_mask01_and_8_gpr_brnz(ptr %v, i8 zeroext %c) noun
 ; X64-NEXT:    movl %edx, %ecx
 ; X64-NEXT:    notb %cl
 ; X64-NEXT:    movzbl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB8_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %r8d
@@ -576,7 +576,7 @@ define zeroext i8 @atomic_shl1_and_8_gpr_val(ptr %v) nounwind {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movzbl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB9_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edx
@@ -590,7 +590,7 @@ define zeroext i8 @atomic_shl1_and_8_gpr_val(ptr %v) nounwind {
 ; X64-LABEL: atomic_shl1_and_8_gpr_val:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movzbl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB9_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -611,7 +611,7 @@ define zeroext i8 @atomic_shl1_or_8_gpr_valnz(ptr %v) nounwind {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movzbl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB10_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edx
@@ -626,7 +626,7 @@ define zeroext i8 @atomic_shl1_or_8_gpr_valnz(ptr %v) nounwind {
 ; X64-LABEL: atomic_shl1_or_8_gpr_valnz:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movzbl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB10_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -649,7 +649,7 @@ define zeroext i8 @atomic_shl1_xor_8_gpr_brz(ptr %v) nounwind {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X86-NEXT:    movzbl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB11_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -669,7 +669,7 @@ define zeroext i8 @atomic_shl1_xor_8_gpr_brz(ptr %v) nounwind {
 ; X64-LABEL: atomic_shl1_xor_8_gpr_brz:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movzbl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB11_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -710,7 +710,7 @@ define zeroext i16 @atomic_shl1_xor_16_gpr_val(ptr %v, i16 zeroext %c) nounwind
 ; X86-NEXT:    movl $1, %edx
 ; X86-NEXT:    shll %cl, %edx
 ; X86-NEXT:    movzwl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB12_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -732,7 +732,7 @@ define zeroext i16 @atomic_shl1_xor_16_gpr_val(ptr %v, i16 zeroext %c) nounwind
 ; X64-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB12_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -799,7 +799,7 @@ define zeroext i16 @atomic_shl1_mask0_xor_16_gpr_val(ptr %v, i16 zeroext %c) nou
 ; X86-NEXT:    movl $1, %edi
 ; X86-NEXT:    shll %cl, %edi
 ; X86-NEXT:    movzwl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB14_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -825,7 +825,7 @@ define zeroext i16 @atomic_shl1_mask0_xor_16_gpr_val(ptr %v, i16 zeroext %c) nou
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB14_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -862,7 +862,7 @@ define zeroext i16 @atomic_shl1_mask1_xor_16_gpr_val(ptr %v, i16 zeroext %c) nou
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB15_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -888,7 +888,7 @@ define zeroext i16 @atomic_shl1_mask1_xor_16_gpr_val(ptr %v, i16 zeroext %c) nou
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB15_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -959,7 +959,7 @@ define zeroext i16 @atomic_blsi_xor_16_gpr_val(ptr %v, i16 zeroext %c) nounwind
 ; X86-NEXT:    negl %ecx
 ; X86-NEXT:    andl %eax, %ecx
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB17_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %esi
@@ -980,7 +980,7 @@ define zeroext i16 @atomic_blsi_xor_16_gpr_val(ptr %v, i16 zeroext %c) nounwind
 ; X64-NEXT:    negl %ecx
 ; X64-NEXT:    andl %esi, %ecx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB17_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %edx
@@ -1010,7 +1010,7 @@ define zeroext i16 @atomic_shl1_xor_16_gpr_valz(ptr %v, i16 zeroext %c) nounwind
 ; X86-NEXT:    movl $1, %edx
 ; X86-NEXT:    shll %cl, %edx
 ; X86-NEXT:    movzwl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB18_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -1035,7 +1035,7 @@ define zeroext i16 @atomic_shl1_xor_16_gpr_valz(ptr %v, i16 zeroext %c) nounwind
 ; X64-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB18_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -1075,7 +1075,7 @@ define zeroext i16 @atomic_shl1_small_mask_xor_16_gpr_valz(ptr %v, i16 zeroext %
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
 ; X86-NEXT:    movzwl %si, %esi
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB19_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -1102,7 +1102,7 @@ define zeroext i16 @atomic_shl1_small_mask_xor_16_gpr_valz(ptr %v, i16 zeroext %
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
 ; X64-NEXT:    movzwl %dx, %edx
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB19_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -1143,7 +1143,7 @@ define zeroext i16 @atomic_shl1_mask0_xor_16_gpr_valz(ptr %v, i16 zeroext %c) no
 ; X86-NEXT:    movl $1, %edi
 ; X86-NEXT:    shll %cl, %edi
 ; X86-NEXT:    movzwl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB20_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -1169,7 +1169,7 @@ define zeroext i16 @atomic_shl1_mask0_xor_16_gpr_valz(ptr %v, i16 zeroext %c) no
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB20_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -1208,7 +1208,7 @@ define zeroext i16 @atomic_shl1_mask1_xor_16_gpr_valz(ptr %v, i16 zeroext %c) no
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB21_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -1234,7 +1234,7 @@ define zeroext i16 @atomic_shl1_mask1_xor_16_gpr_valz(ptr %v, i16 zeroext %c) no
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB21_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -1276,7 +1276,7 @@ define zeroext i16 @atomic_shl1_mask01_xor_16_gpr_valz(ptr %v, i16 zeroext %c) n
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB22_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -1302,7 +1302,7 @@ define zeroext i16 @atomic_shl1_mask01_xor_16_gpr_valz(ptr %v, i16 zeroext %c) n
 ; X64-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB22_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -1341,7 +1341,7 @@ define zeroext i16 @atomic_blsi_xor_16_gpr_valz(ptr %v, i16 zeroext %c) nounwind
 ; X86-NEXT:    negl %ecx
 ; X86-NEXT:    andl %eax, %ecx
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB23_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %esi
@@ -1365,7 +1365,7 @@ define zeroext i16 @atomic_blsi_xor_16_gpr_valz(ptr %v, i16 zeroext %c) nounwind
 ; X64-NEXT:    negl %ecx
 ; X64-NEXT:    andl %esi, %ecx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB23_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %edx
@@ -1403,7 +1403,7 @@ define zeroext i16 @atomic_shl1_xor_16_gpr_valnz(ptr %v, i16 zeroext %c) nounwin
 ; X86-NEXT:    movl $1, %edx
 ; X86-NEXT:    shll %cl, %edx
 ; X86-NEXT:    movzwl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB24_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -1428,7 +1428,7 @@ define zeroext i16 @atomic_shl1_xor_16_gpr_valnz(ptr %v, i16 zeroext %c) nounwin
 ; X64-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB24_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -1468,7 +1468,7 @@ define zeroext i16 @atomic_shl1_small_mask_xor_16_gpr_valnz(ptr %v, i16 zeroext
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
 ; X86-NEXT:    movzwl %si, %esi
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB25_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -1495,7 +1495,7 @@ define zeroext i16 @atomic_shl1_small_mask_xor_16_gpr_valnz(ptr %v, i16 zeroext
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
 ; X64-NEXT:    movzwl %dx, %edx
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB25_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -1536,7 +1536,7 @@ define zeroext i16 @atomic_shl1_mask0_xor_16_gpr_valnz(ptr %v, i16 zeroext %c) n
 ; X86-NEXT:    movl $1, %edi
 ; X86-NEXT:    shll %cl, %edi
 ; X86-NEXT:    movzwl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB26_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -1562,7 +1562,7 @@ define zeroext i16 @atomic_shl1_mask0_xor_16_gpr_valnz(ptr %v, i16 zeroext %c) n
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB26_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -1601,7 +1601,7 @@ define zeroext i16 @atomic_shl1_mask1_xor_16_gpr_valnz(ptr %v, i16 zeroext %c) n
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB27_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -1627,7 +1627,7 @@ define zeroext i16 @atomic_shl1_mask1_xor_16_gpr_valnz(ptr %v, i16 zeroext %c) n
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB27_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -1669,7 +1669,7 @@ define zeroext i16 @atomic_shl1_mask01_xor_16_gpr_valnz(ptr %v, i16 zeroext %c)
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB28_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -1695,7 +1695,7 @@ define zeroext i16 @atomic_shl1_mask01_xor_16_gpr_valnz(ptr %v, i16 zeroext %c)
 ; X64-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB28_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -1734,7 +1734,7 @@ define zeroext i16 @atomic_blsi_xor_16_gpr_valnz(ptr %v, i16 zeroext %c) nounwin
 ; X86-NEXT:    negl %ecx
 ; X86-NEXT:    andl %eax, %ecx
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB29_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %esi
@@ -1758,7 +1758,7 @@ define zeroext i16 @atomic_blsi_xor_16_gpr_valnz(ptr %v, i16 zeroext %c) nounwin
 ; X64-NEXT:    negl %ecx
 ; X64-NEXT:    andl %esi, %ecx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB29_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %edx
@@ -1797,7 +1797,7 @@ define zeroext i16 @atomic_shl1_xor_16_gpr_brz(ptr %v, i16 zeroext %c) nounwind
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB30_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -1825,7 +1825,7 @@ define zeroext i16 @atomic_shl1_xor_16_gpr_brz(ptr %v, i16 zeroext %c) nounwind
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB30_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -1878,7 +1878,7 @@ define zeroext i16 @atomic_shl1_small_mask_xor_16_gpr_brz(ptr %v, i16 zeroext %c
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
 ; X86-NEXT:    movzwl %si, %esi
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB31_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -1908,7 +1908,7 @@ define zeroext i16 @atomic_shl1_small_mask_xor_16_gpr_brz(ptr %v, i16 zeroext %c
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
 ; X64-NEXT:    movzwl %dx, %edx
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB31_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -1962,7 +1962,7 @@ define zeroext i16 @atomic_shl1_mask0_xor_16_gpr_brz(ptr %v, i16 zeroext %c) nou
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB32_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -1991,7 +1991,7 @@ define zeroext i16 @atomic_shl1_mask0_xor_16_gpr_brz(ptr %v, i16 zeroext %c) nou
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB32_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -2043,7 +2043,7 @@ define zeroext i16 @atomic_shl1_mask1_xor_16_gpr_brz(ptr %v, i16 zeroext %c) nou
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB33_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -2073,7 +2073,7 @@ define zeroext i16 @atomic_shl1_mask1_xor_16_gpr_brz(ptr %v, i16 zeroext %c) nou
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB33_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -2131,7 +2131,7 @@ define zeroext i16 @atomic_shl1_mask01_xor_16_gpr_brz(ptr %v, i16 zeroext %c) no
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB34_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -2160,7 +2160,7 @@ define zeroext i16 @atomic_shl1_mask01_xor_16_gpr_brz(ptr %v, i16 zeroext %c) no
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB34_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -2213,7 +2213,7 @@ define zeroext i16 @atomic_blsi_xor_16_gpr_brz(ptr %v, i16 zeroext %c) nounwind
 ; X86-NEXT:    negl %esi
 ; X86-NEXT:    andl %ecx, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB35_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -2241,7 +2241,7 @@ define zeroext i16 @atomic_blsi_xor_16_gpr_brz(ptr %v, i16 zeroext %c) nounwind
 ; X64-NEXT:    negl %ecx
 ; X64-NEXT:    andl %esi, %ecx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB35_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %edx
@@ -2295,7 +2295,7 @@ define zeroext i16 @atomic_shl1_and_16_gpr_val(ptr %v, i16 zeroext %c) nounwind
 ; X86-NEXT:    movl $-2, %edi
 ; X86-NEXT:    roll %cl, %edi
 ; X86-NEXT:    movzwl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB36_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -2320,7 +2320,7 @@ define zeroext i16 @atomic_shl1_and_16_gpr_val(ptr %v, i16 zeroext %c) nounwind
 ; X64-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X64-NEXT:    roll %cl, %esi
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB36_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -2387,7 +2387,7 @@ define zeroext i16 @atomic_shl1_mask0_and_16_gpr_val(ptr %v, i16 zeroext %c) nou
 ; X86-NEXT:    movw $-2, %si
 ; X86-NEXT:    rolw %cl, %si
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB38_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -2412,7 +2412,7 @@ define zeroext i16 @atomic_shl1_mask0_and_16_gpr_val(ptr %v, i16 zeroext %c) nou
 ; X64-NEXT:    movw $-2, %dx
 ; X64-NEXT:    rolw %cl, %dx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB38_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -2450,7 +2450,7 @@ define zeroext i16 @atomic_shl1_mask1_and_16_gpr_val(ptr %v, i16 zeroext %c) nou
 ; X86-NEXT:    movl $-2, %esi
 ; X86-NEXT:    roll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB39_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -2476,7 +2476,7 @@ define zeroext i16 @atomic_shl1_mask1_and_16_gpr_val(ptr %v, i16 zeroext %c) nou
 ; X64-NEXT:    movl $-2, %edx
 ; X64-NEXT:    roll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB39_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -2552,7 +2552,7 @@ define zeroext i16 @atomic_blsi_and_16_gpr_val(ptr %v, i16 zeroext %c) nounwind
 ; X86-NEXT:    movl %ecx, %esi
 ; X86-NEXT:    notl %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB41_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -2576,7 +2576,7 @@ define zeroext i16 @atomic_blsi_and_16_gpr_val(ptr %v, i16 zeroext %c) nounwind
 ; X64-NEXT:    movl %ecx, %edx
 ; X64-NEXT:    notl %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB41_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -2610,7 +2610,7 @@ define zeroext i16 @atomic_shl1_and_16_gpr_valnz(ptr %v, i16 zeroext %c) nounwin
 ; X86-NEXT:    movl $-2, %edi
 ; X86-NEXT:    roll %cl, %edi
 ; X86-NEXT:    movzwl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB42_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -2638,7 +2638,7 @@ define zeroext i16 @atomic_shl1_and_16_gpr_valnz(ptr %v, i16 zeroext %c) nounwin
 ; X64-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X64-NEXT:    roll %cl, %esi
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB42_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -2678,7 +2678,7 @@ define zeroext i16 @atomic_shl1_small_mask_and_16_gpr_valnz(ptr %v, i16 zeroext
 ; X86-NEXT:    movw $-2, %si
 ; X86-NEXT:    rolw %cl, %si
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB43_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -2704,7 +2704,7 @@ define zeroext i16 @atomic_shl1_small_mask_and_16_gpr_valnz(ptr %v, i16 zeroext
 ; X64-NEXT:    movw $-2, %dx
 ; X64-NEXT:    rolw %cl, %dx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB43_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -2744,7 +2744,7 @@ define zeroext i16 @atomic_shl1_mask0_and_16_gpr_valnz(ptr %v, i16 zeroext %c) n
 ; X86-NEXT:    movw $-2, %si
 ; X86-NEXT:    rolw %cl, %si
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB44_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -2769,7 +2769,7 @@ define zeroext i16 @atomic_shl1_mask0_and_16_gpr_valnz(ptr %v, i16 zeroext %c) n
 ; X64-NEXT:    movw $-2, %dx
 ; X64-NEXT:    rolw %cl, %dx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB44_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -2809,7 +2809,7 @@ define zeroext i16 @atomic_shl1_mask1_and_16_gpr_valnz(ptr %v, i16 zeroext %c) n
 ; X86-NEXT:    movl $-2, %esi
 ; X86-NEXT:    roll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB45_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -2835,7 +2835,7 @@ define zeroext i16 @atomic_shl1_mask1_and_16_gpr_valnz(ptr %v, i16 zeroext %c) n
 ; X64-NEXT:    movl $-2, %edx
 ; X64-NEXT:    roll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB45_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -2881,7 +2881,7 @@ define zeroext i16 @atomic_shl1_mask01_and_16_gpr_valnz(ptr %v, i16 zeroext %c)
 ; X86-NEXT:    movl $-2, %edi
 ; X86-NEXT:    roll %cl, %edi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB46_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -2910,7 +2910,7 @@ define zeroext i16 @atomic_shl1_mask01_and_16_gpr_valnz(ptr %v, i16 zeroext %c)
 ; X64-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X64-NEXT:    roll %cl, %esi
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB46_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -2953,7 +2953,7 @@ define zeroext i16 @atomic_blsi_and_16_gpr_valnz(ptr %v, i16 zeroext %c) nounwin
 ; X86-NEXT:    movl %ecx, %esi
 ; X86-NEXT:    notl %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB47_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -2980,7 +2980,7 @@ define zeroext i16 @atomic_blsi_and_16_gpr_valnz(ptr %v, i16 zeroext %c) nounwin
 ; X64-NEXT:    movl %ecx, %edx
 ; X64-NEXT:    notl %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB47_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -3023,7 +3023,7 @@ define zeroext i16 @atomic_shl1_and_16_gpr_brnz(ptr %v, i16 zeroext %c) nounwind
 ; X86-NEXT:    movl $-2, %edi
 ; X86-NEXT:    roll %cl, %edi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB48_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ebx
@@ -3056,7 +3056,7 @@ define zeroext i16 @atomic_shl1_and_16_gpr_brnz(ptr %v, i16 zeroext %c) nounwind
 ; X64-NEXT:    movl $-2, %esi
 ; X64-NEXT:    roll %cl, %esi
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB48_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %r8d
@@ -3109,7 +3109,7 @@ define zeroext i16 @atomic_shl1_small_mask_and_16_gpr_brnz(ptr %v, i16 zeroext %
 ; X86-NEXT:    movw $-2, %si
 ; X86-NEXT:    rolw %cl, %si
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB49_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -3140,7 +3140,7 @@ define zeroext i16 @atomic_shl1_small_mask_and_16_gpr_brnz(ptr %v, i16 zeroext %
 ; X64-NEXT:    movw $-2, %dx
 ; X64-NEXT:    rolw %cl, %dx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB49_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -3193,7 +3193,7 @@ define zeroext i16 @atomic_shl1_mask0_and_16_gpr_brnz(ptr %v, i16 zeroext %c) no
 ; X86-NEXT:    movw $-2, %si
 ; X86-NEXT:    rolw %cl, %si
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB50_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -3223,7 +3223,7 @@ define zeroext i16 @atomic_shl1_mask0_and_16_gpr_brnz(ptr %v, i16 zeroext %c) no
 ; X64-NEXT:    movw $-2, %dx
 ; X64-NEXT:    rolw %cl, %dx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB50_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -3276,7 +3276,7 @@ define zeroext i16 @atomic_shl1_mask1_and_16_gpr_brnz(ptr %v, i16 zeroext %c) no
 ; X86-NEXT:    movl $-2, %esi
 ; X86-NEXT:    roll %cl, %esi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB51_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -3308,7 +3308,7 @@ define zeroext i16 @atomic_shl1_mask1_and_16_gpr_brnz(ptr %v, i16 zeroext %c) no
 ; X64-NEXT:    movl $-2, %edx
 ; X64-NEXT:    roll %cl, %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB51_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -3370,7 +3370,7 @@ define zeroext i16 @atomic_shl1_mask01_and_16_gpr_brnz(ptr %v, i16 zeroext %c) n
 ; X86-NEXT:    movl $-2, %edi
 ; X86-NEXT:    roll %cl, %edi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB52_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -3404,7 +3404,7 @@ define zeroext i16 @atomic_shl1_mask01_and_16_gpr_brnz(ptr %v, i16 zeroext %c) n
 ; X64-NEXT:    movl $-2, %r8d
 ; X64-NEXT:    roll %cl, %r8d
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB52_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -3461,7 +3461,7 @@ define zeroext i16 @atomic_blsi_and_16_gpr_brnz(ptr %v, i16 zeroext %c) nounwind
 ; X86-NEXT:    movl %esi, %edi
 ; X86-NEXT:    notl %edi
 ; X86-NEXT:    movzwl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB53_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ebx
@@ -3494,7 +3494,7 @@ define zeroext i16 @atomic_blsi_and_16_gpr_brnz(ptr %v, i16 zeroext %c) nounwind
 ; X64-NEXT:    movl %ecx, %edx
 ; X64-NEXT:    notl %edx
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB53_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %r8d
@@ -3567,7 +3567,7 @@ define zeroext i16 @atomic_shl1_or_16_const_valnz(ptr %v) nounwind {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movzwl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB55_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edx
@@ -3585,7 +3585,7 @@ define zeroext i16 @atomic_shl1_or_16_const_valnz(ptr %v) nounwind {
 ; X64-LABEL: atomic_shl1_or_16_const_valnz:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB55_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -3675,7 +3675,7 @@ define zeroext i16 @atomic_shl1_and_16_const_valz(ptr %v) nounwind {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movzwl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB58_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edx
@@ -3694,7 +3694,7 @@ define zeroext i16 @atomic_shl1_and_16_const_valz(ptr %v) nounwind {
 ; X64-LABEL: atomic_shl1_and_16_const_valz:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB58_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -3922,7 +3922,7 @@ define i32 @atomic_blsi_or_32_gpr_val(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    negl %ecx
 ; X86-NEXT:    andl %eax, %ecx
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB65_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %esi
@@ -3940,7 +3940,7 @@ define i32 @atomic_blsi_or_32_gpr_val(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    negl %ecx
 ; X64-NEXT:    andl %esi, %ecx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB65_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %edx
@@ -3968,7 +3968,7 @@ define i32 @atomic_shl1_or_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB66_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -3990,7 +3990,7 @@ define i32 @atomic_shl1_or_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB66_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -4023,7 +4023,7 @@ define i32 @atomic_shl1_small_mask_or_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB67_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -4046,7 +4046,7 @@ define i32 @atomic_shl1_small_mask_or_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB67_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -4079,7 +4079,7 @@ define i32 @atomic_shl1_mask0_or_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB68_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -4101,7 +4101,7 @@ define i32 @atomic_shl1_mask0_or_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB68_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -4134,7 +4134,7 @@ define i32 @atomic_shl1_mask1_or_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB69_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -4156,7 +4156,7 @@ define i32 @atomic_shl1_mask1_or_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB69_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -4190,7 +4190,7 @@ define i32 @atomic_shl1_mask01_or_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB70_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -4213,7 +4213,7 @@ define i32 @atomic_shl1_mask01_or_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB70_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -4246,7 +4246,7 @@ define i32 @atomic_blsi_or_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    negl %edx
 ; X86-NEXT:    andl %eax, %edx
 ; X86-NEXT:    movl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB71_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %esi
@@ -4267,7 +4267,7 @@ define i32 @atomic_blsi_or_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    negl %edx
 ; X64-NEXT:    andl %esi, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB71_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -4300,7 +4300,7 @@ define i32 @atomic_shl1_or_32_gpr_valnz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB72_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -4322,7 +4322,7 @@ define i32 @atomic_shl1_or_32_gpr_valnz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB72_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -4354,7 +4354,7 @@ define i32 @atomic_shl1_small_mask_or_32_gpr_valnz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB73_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -4377,7 +4377,7 @@ define i32 @atomic_shl1_small_mask_or_32_gpr_valnz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB73_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -4409,7 +4409,7 @@ define i32 @atomic_shl1_mask0_or_32_gpr_valnz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB74_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -4431,7 +4431,7 @@ define i32 @atomic_shl1_mask0_or_32_gpr_valnz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB74_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -4463,7 +4463,7 @@ define i32 @atomic_shl1_mask1_or_32_gpr_valnz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB75_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -4485,7 +4485,7 @@ define i32 @atomic_shl1_mask1_or_32_gpr_valnz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB75_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -4518,7 +4518,7 @@ define i32 @atomic_shl1_mask01_or_32_gpr_valnz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB76_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -4541,7 +4541,7 @@ define i32 @atomic_shl1_mask01_or_32_gpr_valnz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB76_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -4573,7 +4573,7 @@ define i32 @atomic_blsi_or_32_gpr_valnz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    negl %edx
 ; X86-NEXT:    andl %eax, %edx
 ; X86-NEXT:    movl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB77_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %esi
@@ -4594,7 +4594,7 @@ define i32 @atomic_blsi_or_32_gpr_valnz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    negl %edx
 ; X64-NEXT:    andl %esi, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB77_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -4867,7 +4867,7 @@ define i32 @atomic_blsi_or_32_gpr_br(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    negl %esi
 ; X86-NEXT:    andl %ecx, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB83_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -4893,7 +4893,7 @@ define i32 @atomic_blsi_or_32_gpr_br(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    negl %ecx
 ; X64-NEXT:    andl %esi, %ecx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB83_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %edx
@@ -5179,7 +5179,7 @@ define i32 @atomic_blsi_or_32_gpr_brz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    negl %edi
 ; X86-NEXT:    andl %edx, %edi
 ; X86-NEXT:    movl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB89_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -5204,7 +5204,7 @@ define i32 @atomic_blsi_or_32_gpr_brz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    negl %edx
 ; X64-NEXT:    andl %esi, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB89_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -5492,7 +5492,7 @@ define i32 @atomic_blsi_or_32_gpr_brnz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    negl %esi
 ; X86-NEXT:    andl %ecx, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB95_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -5518,7 +5518,7 @@ define i32 @atomic_blsi_or_32_gpr_brnz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    negl %ecx
 ; X64-NEXT:    andl %esi, %ecx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB95_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %edx
@@ -5564,7 +5564,7 @@ define i32 @atomic_shl1_and_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB96_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -5586,7 +5586,7 @@ define i32 @atomic_shl1_and_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB96_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -5619,7 +5619,7 @@ define i32 @atomic_shl1_small_mask_and_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB97_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -5642,7 +5642,7 @@ define i32 @atomic_shl1_small_mask_and_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB97_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -5675,7 +5675,7 @@ define i32 @atomic_shl1_mask0_and_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB98_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -5697,7 +5697,7 @@ define i32 @atomic_shl1_mask0_and_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB98_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -5730,7 +5730,7 @@ define i32 @atomic_shl1_mask1_and_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB99_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -5752,7 +5752,7 @@ define i32 @atomic_shl1_mask1_and_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB99_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -5786,7 +5786,7 @@ define i32 @atomic_shl1_mask01_and_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB100_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -5809,7 +5809,7 @@ define i32 @atomic_shl1_mask01_and_32_gpr_valz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB100_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -5969,7 +5969,7 @@ define i32 @atomic_shl1_mask0_and_32_gpr_br(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB104_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -5995,7 +5995,7 @@ define i32 @atomic_shl1_mask0_and_32_gpr_br(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB104_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -6042,7 +6042,7 @@ define i32 @atomic_shl1_mask1_and_32_gpr_br(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB105_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -6068,7 +6068,7 @@ define i32 @atomic_shl1_mask1_and_32_gpr_br(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB105_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -6305,7 +6305,7 @@ define i32 @atomic_shl1_mask0_and_32_gpr_brz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %edx
 ; X86-NEXT:    shll %cl, %edx
 ; X86-NEXT:    movl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB110_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -6330,7 +6330,7 @@ define i32 @atomic_shl1_mask0_and_32_gpr_brz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB110_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -6379,7 +6379,7 @@ define i32 @atomic_shl1_mask1_and_32_gpr_brz(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %edx
 ; X86-NEXT:    shll %cl, %edx
 ; X86-NEXT:    movl (%esi), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB111_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edi
@@ -6404,7 +6404,7 @@ define i32 @atomic_shl1_mask1_and_32_gpr_brz(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    movl $1, %edx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB111_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %esi
@@ -6566,7 +6566,7 @@ define i32 @atomic_shl1_xor_32_const_valz(ptr %v) nounwind {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB115_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edx
@@ -6583,7 +6583,7 @@ define i32 @atomic_shl1_xor_32_const_valz(ptr %v) nounwind {
 ; X64-LABEL: atomic_shl1_xor_32_const_valz:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB115_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -6609,7 +6609,7 @@ define i32 @atomic_shl1_xor_32_const_valnz(ptr %v) nounwind {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB116_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edx
@@ -6624,7 +6624,7 @@ define i32 @atomic_shl1_xor_32_const_valnz(ptr %v) nounwind {
 ; X64-LABEL: atomic_shl1_xor_32_const_valnz:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB116_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -6670,7 +6670,7 @@ define i32 @atomic_shl1_and_32_const_valz(ptr %v) nounwind {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB118_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edx
@@ -6687,7 +6687,7 @@ define i32 @atomic_shl1_and_32_const_valz(ptr %v) nounwind {
 ; X64-LABEL: atomic_shl1_and_32_const_valz:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB118_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -6713,7 +6713,7 @@ define i32 @atomic_shl1_and_32_const_valnz(ptr %v) nounwind {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB119_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edx
@@ -6728,7 +6728,7 @@ define i32 @atomic_shl1_and_32_const_valnz(ptr %v) nounwind {
 ; X64-LABEL: atomic_shl1_and_32_const_valnz:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB119_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -6835,7 +6835,7 @@ define i32 @atomic_xor_dead_and(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl $1, %esi
 ; X86-NEXT:    shll %cl, %esi
 ; X86-NEXT:    movl (%edx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB122_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %ecx
@@ -6855,7 +6855,7 @@ define i32 @atomic_xor_dead_and(ptr %v, i32 %c) nounwind {
 ; X64-NEXT:    # kill: def $cl killed $cl killed $ecx
 ; X64-NEXT:    shll %cl, %edx
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB122_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -6882,7 +6882,7 @@ define i32 @atomic_xor_with_not_arg(ptr %v, i32 %c) nounwind {
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X86-NEXT:    notl %edx
 ; X86-NEXT:    movl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB123_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %esi
@@ -6897,7 +6897,7 @@ define i32 @atomic_xor_with_not_arg(ptr %v, i32 %c) nounwind {
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    notl %esi
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB123_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -6920,7 +6920,7 @@ define i16 @atomic_or_with_not_arg(ptr %v, i16 %c) nounwind {
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X86-NEXT:    notl %edx
 ; X86-NEXT:    movzwl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB124_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %esi
@@ -6938,7 +6938,7 @@ define i16 @atomic_or_with_not_arg(ptr %v, i16 %c) nounwind {
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    notl %esi
 ; X64-NEXT:    movzwl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB124_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
@@ -6963,7 +6963,7 @@ define i8 @atomic_and_with_not_arg(ptr %v, i8 %c) nounwind {
 ; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %edx
 ; X86-NEXT:    notb %dl
 ; X86-NEXT:    movzbl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB125_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movb %al, %ah
@@ -6977,7 +6977,7 @@ define i8 @atomic_and_with_not_arg(ptr %v, i8 %c) nounwind {
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    notb %sil
 ; X64-NEXT:    movzbl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB125_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
diff --git a/llvm/test/CodeGen/X86/atomic-xor.ll b/llvm/test/CodeGen/X86/atomic-xor.ll
index 930286c8e5fb34..c648ecdfbe674b 100644
--- a/llvm/test/CodeGen/X86/atomic-xor.ll
+++ b/llvm/test/CodeGen/X86/atomic-xor.ll
@@ -32,7 +32,7 @@ define i128 @xor128_signbit_used(ptr %p) nounwind {
 ; X86-NEXT:    movl 8(%edi), %edx
 ; X86-NEXT:    movl (%edi), %ebx
 ; X86-NEXT:    movl 4(%edi), %esi
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB1_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %ebx, (%esp)
@@ -94,7 +94,7 @@ define i64 @xor64_signbit_used(ptr %p) nounwind {
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; X86-NEXT:    movl (%esi), %eax
 ; X86-NEXT:    movl 4(%esi), %edx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB2_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    leal -2147483648(%edx), %ecx
@@ -171,7 +171,7 @@ define i32 @xor32_not_signbit_used(ptr %p) nounwind {
 ; X86:       # %bb.0:
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl (%ecx), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB6_1: # %atomicrmw.start
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %eax, %edx
@@ -184,7 +184,7 @@ define i32 @xor32_not_signbit_used(ptr %p) nounwind {
 ; X64-LABEL: xor32_not_signbit_used:
 ; X64:       # %bb.0:
 ; X64-NEXT:    movl (%rdi), %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB6_1: # %atomicrmw.start
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, %ecx
diff --git a/llvm/test/CodeGen/X86/atomic128.ll b/llvm/test/CodeGen/X86/atomic128.ll
index 949ee9e276a43c..8d43c612aa07fc 100644
--- a/llvm/test/CodeGen/X86/atomic128.ll
+++ b/llvm/test/CodeGen/X86/atomic128.ll
@@ -47,7 +47,6 @@ define i128 @load_global_with_offset() nounwind {
 ; CHECK-AVX-NEXT:    vmovq %xmm0, %rax
 ; CHECK-AVX-NEXT:    vpextrq $1, %xmm0, %rdx
 ; CHECK-AVX-NEXT:    retq
-;
 entry:
   %0 = load atomic i128, ptr getelementptr inbounds ({i128, i128}, ptr @cmpxchg16b_global, i64 0, i32 1) acquire, align 16
   ret i128 %0
@@ -62,7 +61,7 @@ define void @fetch_and_nand(ptr %p, i128 %bits) {
 ; CHECK-NEXT:    movq %rdx, %r8
 ; CHECK-NEXT:    movq (%rdi), %rax
 ; CHECK-NEXT:    movq 8(%rdi), %rdx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB2_1: ## %atomicrmw.start
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rdx, %rcx
@@ -92,7 +91,7 @@ define void @fetch_and_or(ptr %p, i128 %bits) {
 ; CHECK-NEXT:    movq %rdx, %r8
 ; CHECK-NEXT:    movq (%rdi), %rax
 ; CHECK-NEXT:    movq 8(%rdi), %rdx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB3_1: ## %atomicrmw.start
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rbx
@@ -120,7 +119,7 @@ define void @fetch_and_add(ptr %p, i128 %bits) {
 ; CHECK-NEXT:    movq %rdx, %r8
 ; CHECK-NEXT:    movq (%rdi), %rax
 ; CHECK-NEXT:    movq 8(%rdi), %rdx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB4_1: ## %atomicrmw.start
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rbx
@@ -148,7 +147,7 @@ define void @fetch_and_sub(ptr %p, i128 %bits) {
 ; CHECK-NEXT:    movq %rdx, %r8
 ; CHECK-NEXT:    movq (%rdi), %rax
 ; CHECK-NEXT:    movq 8(%rdi), %rdx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB5_1: ## %atomicrmw.start
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %rbx
@@ -176,7 +175,7 @@ define void @fetch_and_min(ptr %p, i128 %bits) {
 ; CHECK-NEXT:    movq %rdx, %r8
 ; CHECK-NEXT:    movq (%rdi), %rax
 ; CHECK-NEXT:    movq 8(%rdi), %rdx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB6_1: ## %atomicrmw.start
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpq %rax, %rsi
@@ -207,7 +206,7 @@ define void @fetch_and_max(ptr %p, i128 %bits) {
 ; CHECK-NEXT:    movq %rdx, %r8
 ; CHECK-NEXT:    movq (%rdi), %rax
 ; CHECK-NEXT:    movq 8(%rdi), %rdx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB7_1: ## %atomicrmw.start
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpq %rax, %rsi
@@ -238,7 +237,7 @@ define void @fetch_and_umin(ptr %p, i128 %bits) {
 ; CHECK-NEXT:    movq %rdx, %r8
 ; CHECK-NEXT:    movq (%rdi), %rax
 ; CHECK-NEXT:    movq 8(%rdi), %rdx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB8_1: ## %atomicrmw.start
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpq %rax, %rsi
@@ -269,7 +268,7 @@ define void @fetch_and_umax(ptr %p, i128 %bits) {
 ; CHECK-NEXT:    movq %rdx, %r8
 ; CHECK-NEXT:    movq (%rdi), %rax
 ; CHECK-NEXT:    movq 8(%rdi), %rdx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB9_1: ## %atomicrmw.start
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpq %rax, %rsi
@@ -349,7 +348,7 @@ define void @atomic_store_seq_cst(ptr %p, i128 %in) {
 ; CHECK-NOAVX-NEXT:    movq %rsi, %rbx
 ; CHECK-NOAVX-NEXT:    movq (%rdi), %rax
 ; CHECK-NOAVX-NEXT:    movq 8(%rdi), %rdx
-; CHECK-NOAVX-NEXT:    .p2align 4, 0x90
+; CHECK-NOAVX-NEXT:    .p2align 4
 ; CHECK-NOAVX-NEXT:  LBB12_1: ## %atomicrmw.start
 ; CHECK-NOAVX-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NOAVX-NEXT:    lock cmpxchg16b (%rdi)
@@ -380,7 +379,7 @@ define void @atomic_store_release(ptr %p, i128 %in) {
 ; CHECK-NOAVX-NEXT:    movq %rsi, %rbx
 ; CHECK-NOAVX-NEXT:    movq (%rdi), %rax
 ; CHECK-NOAVX-NEXT:    movq 8(%rdi), %rdx
-; CHECK-NOAVX-NEXT:    .p2align 4, 0x90
+; CHECK-NOAVX-NEXT:    .p2align 4
 ; CHECK-NOAVX-NEXT:  LBB13_1: ## %atomicrmw.start
 ; CHECK-NOAVX-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NOAVX-NEXT:    lock cmpxchg16b (%rdi)
@@ -410,7 +409,7 @@ define void @atomic_store_relaxed(ptr %p, i128 %in) {
 ; CHECK-NOAVX-NEXT:    movq %rsi, %rbx
 ; CHECK-NOAVX-NEXT:    movq (%rdi), %rax
 ; CHECK-NOAVX-NEXT:    movq 8(%rdi), %rdx
-; CHECK-NOAVX-NEXT:    .p2align 4, 0x90
+; CHECK-NOAVX-NEXT:    .p2align 4
 ; CHECK-NOAVX-NEXT:  LBB14_1: ## %atomicrmw.start
 ; CHECK-NOAVX-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NOAVX-NEXT:    lock cmpxchg16b (%rdi)
diff --git a/llvm/test/CodeGen/X86/atomicrmw-cond-sub-clamp.ll b/llvm/test/CodeGen/X86/atomicrmw-cond-sub-clamp.ll
index 04bfb4e367b9d7..3e1a631e39b069 100644
--- a/llvm/test/CodeGen/X86/atomicrmw-cond-sub-clamp.ll
+++ b/llvm/test/CodeGen/X86/atomicrmw-cond-sub-clamp.ll
@@ -9,7 +9,7 @@ define i8 @atomicrmw_usub_cond_i8(ptr %ptr, i8 %val) {
 ; CHECK-32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; CHECK-32-NEXT:    movzbl (%edx), %eax
 ; CHECK-32-NEXT:    jmp .LBB0_1
-; CHECK-32-NEXT:    .p2align 4, 0x90
+; CHECK-32-NEXT:    .p2align 4
 ; CHECK-32-NEXT:  .LBB0_3: # %atomicrmw.start
 ; CHECK-32-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-32-NEXT:    lock cmpxchgb %ah, (%edx)
@@ -29,7 +29,7 @@ define i8 @atomicrmw_usub_cond_i8(ptr %ptr, i8 %val) {
 ; CHECK-64-LABEL: atomicrmw_usub_cond_i8:
 ; CHECK-64:       # %bb.0:
 ; CHECK-64-NEXT:    movzbl (%rdi), %eax
-; CHECK-64-NEXT:    .p2align 4, 0x90
+; CHECK-64-NEXT:    .p2align 4
 ; CHECK-64-NEXT:  .LBB0_1: # %atomicrmw.start
 ; CHECK-64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-64-NEXT:    movzbl %al, %ecx
@@ -55,7 +55,7 @@ define i16 @atomicrmw_usub_cond_i16(ptr %ptr, i16 %val) {
 ; CHECK-32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; CHECK-32-NEXT:    movzwl (%edx), %eax
 ; CHECK-32-NEXT:    jmp .LBB1_1
-; CHECK-32-NEXT:    .p2align 4, 0x90
+; CHECK-32-NEXT:    .p2align 4
 ; CHECK-32-NEXT:  .LBB1_3: # %atomicrmw.start
 ; CHECK-32-NEXT:    # in Loop: Header=BB1_1 Depth=1
 ; CHECK-32-NEXT:    # kill: def $ax killed $ax killed $eax
@@ -80,7 +80,7 @@ define i16 @atomicrmw_usub_cond_i16(ptr %ptr, i16 %val) {
 ; CHECK-64-LABEL: atomicrmw_usub_cond_i16:
 ; CHECK-64:       # %bb.0:
 ; CHECK-64-NEXT:    movzwl (%rdi), %eax
-; CHECK-64-NEXT:    .p2align 4, 0x90
+; CHECK-64-NEXT:    .p2align 4
 ; CHECK-64-NEXT:  .LBB1_1: # %atomicrmw.start
 ; CHECK-64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-64-NEXT:    movl %eax, %ecx
@@ -107,7 +107,7 @@ define i32 @atomicrmw_usub_cond_i32(ptr %ptr, i32 %val) {
 ; CHECK-32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; CHECK-32-NEXT:    movl (%edx), %eax
 ; CHECK-32-NEXT:    jmp .LBB2_1
-; CHECK-32-NEXT:    .p2align 4, 0x90
+; CHECK-32-NEXT:    .p2align 4
 ; CHECK-32-NEXT:  .LBB2_3: # %atomicrmw.start
 ; CHECK-32-NEXT:    # in Loop: Header=BB2_1 Depth=1
 ; CHECK-32-NEXT:    lock cmpxchgl %esi, (%edx)
@@ -129,7 +129,7 @@ define i32 @atomicrmw_usub_cond_i32(ptr %ptr, i32 %val) {
 ; CHECK-64-LABEL: atomicrmw_usub_cond_i32:
 ; CHECK-64:       # %bb.0:
 ; CHECK-64-NEXT:    movl (%rdi), %eax
-; CHECK-64-NEXT:    .p2align 4, 0x90
+; CHECK-64-NEXT:    .p2align 4
 ; CHECK-64-NEXT:  .LBB2_1: # %atomicrmw.start
 ; CHECK-64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-64-NEXT:    movl %eax, %ecx
@@ -164,7 +164,7 @@ define i64 @atomicrmw_usub_cond_i64(ptr %ptr, i64 %val) {
 ; CHECK-32-NEXT:    movl (%ebp), %eax
 ; CHECK-32-NEXT:    movl 4(%ebp), %edx
 ; CHECK-32-NEXT:    jmp .LBB3_1
-; CHECK-32-NEXT:    .p2align 4, 0x90
+; CHECK-32-NEXT:    .p2align 4
 ; CHECK-32-NEXT:  .LBB3_3: # %atomicrmw.start
 ; CHECK-32-NEXT:    # in Loop: Header=BB3_1 Depth=1
 ; CHECK-32-NEXT:    lock cmpxchg8b (%ebp)
@@ -195,7 +195,7 @@ define i64 @atomicrmw_usub_cond_i64(ptr %ptr, i64 %val) {
 ; CHECK-64-LABEL: atomicrmw_usub_cond_i64:
 ; CHECK-64:       # %bb.0:
 ; CHECK-64-NEXT:    movq (%rdi), %rax
-; CHECK-64-NEXT:    .p2align 4, 0x90
+; CHECK-64-NEXT:    .p2align 4
 ; CHECK-64-NEXT:  .LBB3_1: # %atomicrmw.start
 ; CHECK-64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-64-NEXT:    movq %rax, %rcx
@@ -219,7 +219,7 @@ define i8 @atomicrmw_usub_sat_i8(ptr %ptr, i8 %val) {
 ; CHECK-32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; CHECK-32-NEXT:    movzbl (%edx), %eax
 ; CHECK-32-NEXT:    jmp .LBB4_1
-; CHECK-32-NEXT:    .p2align 4, 0x90
+; CHECK-32-NEXT:    .p2align 4
 ; CHECK-32-NEXT:  .LBB4_3: # %atomicrmw.start
 ; CHECK-32-NEXT:    # in Loop: Header=BB4_1 Depth=1
 ; CHECK-32-NEXT:    lock cmpxchgb %bl, (%edx)
@@ -241,7 +241,7 @@ define i8 @atomicrmw_usub_sat_i8(ptr %ptr, i8 %val) {
 ; CHECK-64:       # %bb.0:
 ; CHECK-64-NEXT:    movzbl (%rdi), %eax
 ; CHECK-64-NEXT:    xorl %ecx, %ecx
-; CHECK-64-NEXT:    .p2align 4, 0x90
+; CHECK-64-NEXT:    .p2align 4
 ; CHECK-64-NEXT:  .LBB4_1: # %atomicrmw.start
 ; CHECK-64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-64-NEXT:    movl %eax, %edx
@@ -269,7 +269,7 @@ define i16 @atomicrmw_usub_sat_i16(ptr %ptr, i16 %val) {
 ; CHECK-32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; CHECK-32-NEXT:    movzwl (%edx), %eax
 ; CHECK-32-NEXT:    jmp .LBB5_1
-; CHECK-32-NEXT:    .p2align 4, 0x90
+; CHECK-32-NEXT:    .p2align 4
 ; CHECK-32-NEXT:  .LBB5_3: # %atomicrmw.start
 ; CHECK-32-NEXT:    # in Loop: Header=BB5_1 Depth=1
 ; CHECK-32-NEXT:    lock cmpxchgw %si, (%edx)
@@ -295,7 +295,7 @@ define i16 @atomicrmw_usub_sat_i16(ptr %ptr, i16 %val) {
 ; CHECK-64:       # %bb.0:
 ; CHECK-64-NEXT:    movzwl (%rdi), %eax
 ; CHECK-64-NEXT:    xorl %ecx, %ecx
-; CHECK-64-NEXT:    .p2align 4, 0x90
+; CHECK-64-NEXT:    .p2align 4
 ; CHECK-64-NEXT:  .LBB5_1: # %atomicrmw.start
 ; CHECK-64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-64-NEXT:    movl %eax, %edx
@@ -322,7 +322,7 @@ define i32 @atomicrmw_usub_sat_i32(ptr %ptr, i32 %val) {
 ; CHECK-32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; CHECK-32-NEXT:    movl (%edx), %eax
 ; CHECK-32-NEXT:    jmp .LBB6_1
-; CHECK-32-NEXT:    .p2align 4, 0x90
+; CHECK-32-NEXT:    .p2align 4
 ; CHECK-32-NEXT:  .LBB6_3: # %atomicrmw.start
 ; CHECK-32-NEXT:    # in Loop: Header=BB6_1 Depth=1
 ; CHECK-32-NEXT:    lock cmpxchgl %esi, (%edx)
@@ -348,7 +348,7 @@ define i32 @atomicrmw_usub_sat_i32(ptr %ptr, i32 %val) {
 ; CHECK-64:       # %bb.0:
 ; CHECK-64-NEXT:    movl (%rdi), %eax
 ; CHECK-64-NEXT:    xorl %ecx, %ecx
-; CHECK-64-NEXT:    .p2align 4, 0x90
+; CHECK-64-NEXT:    .p2align 4
 ; CHECK-64-NEXT:  .LBB6_1: # %atomicrmw.start
 ; CHECK-64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-64-NEXT:    movl %eax, %edx
@@ -381,7 +381,7 @@ define i64 @atomicrmw_usub_sat_i64(ptr %ptr, i64 %val) {
 ; CHECK-32-NEXT:    movl (%ebp), %esi
 ; CHECK-32-NEXT:    movl 4(%ebp), %edi
 ; CHECK-32-NEXT:    jmp .LBB7_1
-; CHECK-32-NEXT:    .p2align 4, 0x90
+; CHECK-32-NEXT:    .p2align 4
 ; CHECK-32-NEXT:  .LBB7_3: # %atomicrmw.start
 ; CHECK-32-NEXT:    # in Loop: Header=BB7_1 Depth=1
 ; CHECK-32-NEXT:    movl %esi, %eax
@@ -421,7 +421,7 @@ define i64 @atomicrmw_usub_sat_i64(ptr %ptr, i64 %val) {
 ; CHECK-64:       # %bb.0:
 ; CHECK-64-NEXT:    movq (%rdi), %rax
 ; CHECK-64-NEXT:    xorl %ecx, %ecx
-; CHECK-64-NEXT:    .p2align 4, 0x90
+; CHECK-64-NEXT:    .p2align 4
 ; CHECK-64-NEXT:  .LBB7_1: # %atomicrmw.start
 ; CHECK-64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-64-NEXT:    movq %rax, %rdx
diff --git a/llvm/test/CodeGen/X86/atomicrmw-fadd-fp-vector.ll b/llvm/test/CodeGen/X86/atomicrmw-fadd-fp-vector.ll
index 4f8cd5a52ed4c7..105ee7f82ee79d 100644
--- a/llvm/test/CodeGen/X86/atomicrmw-fadd-fp-vector.ll
+++ b/llvm/test/CodeGen/X86/atomicrmw-fadd-fp-vector.ll
@@ -13,7 +13,7 @@ define <2 x half> @test_atomicrmw_fadd_v2f16_align4(ptr addrspace(1) %ptr, <2 x
 ; CHECK-NEXT:    movdqa %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
 ; CHECK-NEXT:    pinsrw $0, 2(%rdi), %xmm1
 ; CHECK-NEXT:    pinsrw $0, (%rdi), %xmm0
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movdqa %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
@@ -65,7 +65,7 @@ define <2 x float> @test_atomicrmw_fadd_v2f32_align8(ptr addrspace(1) %ptr, <2 x
 ; CHECK-LABEL: test_atomicrmw_fadd_v2f32_align8:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movq {{.*#+}} xmm1 = mem[0],zero
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %xmm1, %rax
diff --git a/llvm/test/CodeGen/X86/atomicrmw-uinc-udec-wrap.ll b/llvm/test/CodeGen/X86/atomicrmw-uinc-udec-wrap.ll
index 3126917917fdec..f6fc65e3db4595 100644
--- a/llvm/test/CodeGen/X86/atomicrmw-uinc-udec-wrap.ll
+++ b/llvm/test/CodeGen/X86/atomicrmw-uinc-udec-wrap.ll
@@ -6,7 +6,7 @@ define i8 @atomicrmw_uinc_wrap_i8(ptr %ptr, i8 %val) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movzbl (%rdi), %eax
 ; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    leal 1(%rax), %edx
@@ -29,7 +29,7 @@ define i16 @atomicrmw_uinc_wrap_i16(ptr %ptr, i16 %val) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movzwl (%rdi), %eax
 ; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    leal 1(%rax), %edx
@@ -51,7 +51,7 @@ define i32 @atomicrmw_uinc_wrap_i32(ptr %ptr, i32 %val) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movl (%rdi), %eax
 ; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB2_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    leal 1(%rax), %edx
@@ -73,7 +73,7 @@ define i64 @atomicrmw_uinc_wrap_i64(ptr %ptr, i64 %val) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movq (%rdi), %rax
 ; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB3_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    leaq 1(%rax), %rdx
@@ -92,7 +92,7 @@ define i8 @atomicrmw_udec_wrap_i8(ptr %ptr, i8 %val) {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movzbl (%rdi), %eax
 ; CHECK-NEXT:    movzbl %sil, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB4_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %eax, %edx
@@ -114,7 +114,7 @@ define i16 @atomicrmw_udec_wrap_i16(ptr %ptr, i16 %val) {
 ; CHECK-LABEL: atomicrmw_udec_wrap_i16:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movzwl (%rdi), %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB5_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %eax, %ecx
@@ -135,7 +135,7 @@ define i32 @atomicrmw_udec_wrap_i32(ptr %ptr, i32 %val) {
 ; CHECK-LABEL: atomicrmw_udec_wrap_i32:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movl (%rdi), %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB6_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    leal -1(%rax), %ecx
@@ -158,7 +158,7 @@ define i64 @atomicrmw_udec_wrap_i64(ptr %ptr, i64 %val) {
 ; CHECK-LABEL: atomicrmw_udec_wrap_i64:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movq (%rdi), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB7_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    leaq -1(%rax), %rcx
diff --git a/llvm/test/CodeGen/X86/avx-cmp.ll b/llvm/test/CodeGen/X86/avx-cmp.ll
index 4ab9c545ed90da..d31107bfeb7bb7 100644
--- a/llvm/test/CodeGen/X86/avx-cmp.ll
+++ b/llvm/test/CodeGen/X86/avx-cmp.ll
@@ -34,7 +34,7 @@ define void @render(double %a0) nounwind {
 ; CHECK-NEXT:    jne .LBB2_5
 ; CHECK-NEXT:  # %bb.1: # %for.cond5.preheader
 ; CHECK-NEXT:    movb $1, %bl
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB2_2: # %for.cond5
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb %bl, %bl
diff --git a/llvm/test/CodeGen/X86/avx-vbroadcast.ll b/llvm/test/CodeGen/X86/avx-vbroadcast.ll
index c69886df82bdfb..0bfd8921e8b42a 100644
--- a/llvm/test/CodeGen/X86/avx-vbroadcast.ll
+++ b/llvm/test/CodeGen/X86/avx-vbroadcast.ll
@@ -923,7 +923,7 @@ define void @fmul_by_v2f32_broadcast() nounwind {
 ; X86-NEXT:    vmovddup {{.*#+}} xmm0 = [3.1E+1,0.0E+0,3.1E+1,0.0E+0]
 ; X86-NEXT:    ## xmm0 = mem[0,0]
 ; X86-NEXT:    ## implicit-def: $xmm1
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  LBB42_1: ## =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    vmovsd {{.*#+}} xmm2 = mem[0],zero
 ; X86-NEXT:    vmulps %xmm0, %xmm2, %xmm2
@@ -937,7 +937,7 @@ define void @fmul_by_v2f32_broadcast() nounwind {
 ; X64-NEXT:    vmovddup {{.*#+}} xmm0 = [3.1E+1,0.0E+0,3.1E+1,0.0E+0]
 ; X64-NEXT:    ## xmm0 = mem[0,0]
 ; X64-NEXT:    ## implicit-def: $xmm1
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  LBB42_1: ## =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    vmovsd {{.*#+}} xmm2 = mem[0],zero
 ; X64-NEXT:    vmulps %xmm0, %xmm2, %xmm2
diff --git a/llvm/test/CodeGen/X86/avx-vzeroupper.ll b/llvm/test/CodeGen/X86/avx-vzeroupper.ll
index 2fa71386c8056d..b84b0c2c5cc305 100644
--- a/llvm/test/CodeGen/X86/avx-vzeroupper.ll
+++ b/llvm/test/CodeGen/X86/avx-vzeroupper.ll
@@ -131,7 +131,7 @@ define <4 x float> @test03(<4 x float> %a, <4 x float> %b) nounwind {
 ; VZ-NEXT:    subq $16, %rsp
 ; VZ-NEXT:    vaddps %xmm1, %xmm0, %xmm0
 ; VZ-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
-; VZ-NEXT:    .p2align 4, 0x90
+; VZ-NEXT:    .p2align 4
 ; VZ-NEXT:  .LBB3_1: # %while.cond
 ; VZ-NEXT:    # =>This Inner Loop Header: Depth=1
 ; VZ-NEXT:    callq foo
@@ -140,7 +140,7 @@ define <4 x float> @test03(<4 x float> %a, <4 x float> %b) nounwind {
 ; VZ-NEXT:  # %bb.2: # %for.body.preheader
 ; VZ-NEXT:    movl $4, %ebx
 ; VZ-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
-; VZ-NEXT:    .p2align 4, 0x90
+; VZ-NEXT:    .p2align 4
 ; VZ-NEXT:  .LBB3_3: # %for.body
 ; VZ-NEXT:    # =>This Inner Loop Header: Depth=1
 ; VZ-NEXT:    callq do_sse
@@ -160,7 +160,7 @@ define <4 x float> @test03(<4 x float> %a, <4 x float> %b) nounwind {
 ; DISABLE-VZ-NEXT:    subq $16, %rsp
 ; DISABLE-VZ-NEXT:    vaddps %xmm1, %xmm0, %xmm0
 ; DISABLE-VZ-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
-; DISABLE-VZ-NEXT:    .p2align 4, 0x90
+; DISABLE-VZ-NEXT:    .p2align 4
 ; DISABLE-VZ-NEXT:  .LBB3_1: # %while.cond
 ; DISABLE-VZ-NEXT:    # =>This Inner Loop Header: Depth=1
 ; DISABLE-VZ-NEXT:    callq foo
@@ -169,7 +169,7 @@ define <4 x float> @test03(<4 x float> %a, <4 x float> %b) nounwind {
 ; DISABLE-VZ-NEXT:  # %bb.2: # %for.body.preheader
 ; DISABLE-VZ-NEXT:    movl $4, %ebx
 ; DISABLE-VZ-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
-; DISABLE-VZ-NEXT:    .p2align 4, 0x90
+; DISABLE-VZ-NEXT:    .p2align 4
 ; DISABLE-VZ-NEXT:  .LBB3_3: # %for.body
 ; DISABLE-VZ-NEXT:    # =>This Inner Loop Header: Depth=1
 ; DISABLE-VZ-NEXT:    callq do_sse
@@ -189,7 +189,7 @@ define <4 x float> @test03(<4 x float> %a, <4 x float> %b) nounwind {
 ; BDVER2-NEXT:    subq $16, %rsp
 ; BDVER2-NEXT:    vaddps %xmm1, %xmm0, %xmm0
 ; BDVER2-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
-; BDVER2-NEXT:    .p2align 4, 0x90
+; BDVER2-NEXT:    .p2align 4
 ; BDVER2-NEXT:  .LBB3_1: # %while.cond
 ; BDVER2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; BDVER2-NEXT:    callq foo
@@ -198,7 +198,7 @@ define <4 x float> @test03(<4 x float> %a, <4 x float> %b) nounwind {
 ; BDVER2-NEXT:  # %bb.2: # %for.body.preheader
 ; BDVER2-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
 ; BDVER2-NEXT:    movl $4, %ebx
-; BDVER2-NEXT:    .p2align 4, 0x90
+; BDVER2-NEXT:    .p2align 4
 ; BDVER2-NEXT:  .LBB3_3: # %for.body
 ; BDVER2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; BDVER2-NEXT:    callq do_sse
@@ -218,7 +218,7 @@ define <4 x float> @test03(<4 x float> %a, <4 x float> %b) nounwind {
 ; BTVER2-NEXT:    subq $16, %rsp
 ; BTVER2-NEXT:    vaddps %xmm1, %xmm0, %xmm0
 ; BTVER2-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
-; BTVER2-NEXT:    .p2align 4, 0x90
+; BTVER2-NEXT:    .p2align 4
 ; BTVER2-NEXT:  .LBB3_1: # %while.cond
 ; BTVER2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; BTVER2-NEXT:    callq foo
@@ -227,7 +227,7 @@ define <4 x float> @test03(<4 x float> %a, <4 x float> %b) nounwind {
 ; BTVER2-NEXT:  # %bb.2: # %for.body.preheader
 ; BTVER2-NEXT:    vmovaps (%rsp), %xmm0 # 16-byte Reload
 ; BTVER2-NEXT:    movl $4, %ebx
-; BTVER2-NEXT:    .p2align 4, 0x90
+; BTVER2-NEXT:    .p2align 4
 ; BTVER2-NEXT:  .LBB3_3: # %for.body
 ; BTVER2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; BTVER2-NEXT:    callq do_sse
diff --git a/llvm/test/CodeGen/X86/avx2-vbroadcast.ll b/llvm/test/CodeGen/X86/avx2-vbroadcast.ll
index 9ac0503831eb7f..c50af6968f5bb2 100644
--- a/llvm/test/CodeGen/X86/avx2-vbroadcast.ll
+++ b/llvm/test/CodeGen/X86/avx2-vbroadcast.ll
@@ -683,7 +683,7 @@ define void @crash() nounwind alwaysinline {
 ; X86-NEXT:    je LBB33_1
 ; X86-NEXT:  ## %bb.2: ## %ret
 ; X86-NEXT:    retl
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  LBB33_1: ## %footer329VF
 ; X86-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    jmp LBB33_1
@@ -695,7 +695,7 @@ define void @crash() nounwind alwaysinline {
 ; X64-NEXT:    je LBB33_1
 ; X64-NEXT:  ## %bb.2: ## %ret
 ; X64-NEXT:    retq
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  LBB33_1: ## %footer329VF
 ; X64-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    jmp LBB33_1
diff --git a/llvm/test/CodeGen/X86/avx512-broadcast-unfold.ll b/llvm/test/CodeGen/X86/avx512-broadcast-unfold.ll
index ac65a1112be439..d7ecbb41e3b149 100644
--- a/llvm/test/CodeGen/X86/avx512-broadcast-unfold.ll
+++ b/llvm/test/CodeGen/X86/avx512-broadcast-unfold.ll
@@ -9,7 +9,7 @@ define void @bcast_unfold_add_v16i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} zmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpaddd 4096(%rdi,%rax), %zmm0, %zmm1
@@ -41,7 +41,7 @@ define void @bcast_unfold_add_v8i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} ymm0 = [2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpaddd 4096(%rdi,%rax), %ymm0, %ymm1
@@ -73,7 +73,7 @@ define void @bcast_unfold_add_v4i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} xmm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB2_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpaddd 4096(%rdi,%rax), %xmm0, %xmm1
@@ -104,7 +104,7 @@ define void @bcast_unfold_add_v8i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} zmm0 = [2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB3_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpaddq 8192(%rdi,%rax), %zmm0, %zmm1
@@ -136,7 +136,7 @@ define void @bcast_unfold_add_v4i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} ymm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB4_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpaddq 8192(%rdi,%rax), %ymm0, %ymm1
@@ -168,7 +168,7 @@ define void @bcast_unfold_add_v2i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} xmm0 = [2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB5_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpaddq 8192(%rdi,%rax), %xmm0, %xmm1
@@ -198,7 +198,7 @@ define void @bcast_unfold_mul_v16i32(ptr %arg) {
 ; CHECK-LABEL: bcast_unfold_mul_v16i32:
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB6_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu64 4096(%rdi,%rax), %zmm0
@@ -231,7 +231,7 @@ define void @bcast_unfold_mul_v8i32(ptr %arg) {
 ; CHECK-LABEL: bcast_unfold_mul_v8i32:
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB7_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 4096(%rdi,%rax), %ymm0
@@ -264,7 +264,7 @@ define void @bcast_unfold_mul_v4i32(ptr %arg) {
 ; CHECK-LABEL: bcast_unfold_mul_v4i32:
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB8_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 4096(%rdi,%rax), %xmm0
@@ -296,7 +296,7 @@ define void @bcast_unfold_mul_v8i64(ptr %arg) {
 ; CHECK-LABEL: bcast_unfold_mul_v8i64:
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB9_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu64 8192(%rdi,%rax), %zmm0
@@ -329,7 +329,7 @@ define void @bcast_unfold_mul_v4i64(ptr %arg) {
 ; CHECK-LABEL: bcast_unfold_mul_v4i64:
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB10_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 8192(%rdi,%rax), %ymm0
@@ -362,7 +362,7 @@ define void @bcast_unfold_mul_v2i64(ptr %arg) {
 ; CHECK-LABEL: bcast_unfold_mul_v2i64:
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB11_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 8192(%rdi,%rax), %xmm0
@@ -395,7 +395,7 @@ define void @bcast_unfold_or_v16i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} zmm0 = [3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB12_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpord 4096(%rdi,%rax), %zmm0, %zmm1
@@ -427,7 +427,7 @@ define void @bcast_unfold_or_v8i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm0 = [3,3,3,3,3,3,3,3]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB13_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vorps 4096(%rdi,%rax), %ymm0, %ymm1
@@ -459,7 +459,7 @@ define void @bcast_unfold_or_v4i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} xmm0 = [3,3,3,3]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB14_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vorps 4096(%rdi,%rax), %xmm0, %xmm1
@@ -490,7 +490,7 @@ define void @bcast_unfold_or_v8i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} zmm0 = [3,3,3,3,3,3,3,3]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB15_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vporq 8192(%rdi,%rax), %zmm0, %zmm1
@@ -522,7 +522,7 @@ define void @bcast_unfold_or_v4i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} ymm0 = [3,3,3,3]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB16_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vorps 8192(%rdi,%rax), %ymm0, %ymm1
@@ -555,7 +555,7 @@ define void @bcast_unfold_or_v2i64(ptr %arg) {
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vmovddup {{.*#+}} xmm0 = [3,3]
 ; CHECK-NEXT:    # xmm0 = mem[0,0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB17_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vorps 8192(%rdi,%rax), %xmm0, %xmm1
@@ -586,7 +586,7 @@ define void @bcast_unfold_fneg_v16f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} zmm0 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB18_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpxord 4096(%rdi,%rax), %zmm0, %zmm1
@@ -618,7 +618,7 @@ define void @bcast_unfold_fneg_v8f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm0 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB19_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vxorps 4096(%rdi,%rax), %ymm0, %ymm1
@@ -650,7 +650,7 @@ define void @bcast_unfold_fneg_v4f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} xmm0 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB20_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vxorps 4096(%rdi,%rax), %xmm0, %xmm1
@@ -681,7 +681,7 @@ define void @bcast_unfold_fneg_v8f64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} zmm0 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB21_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpxorq 8192(%rdi,%rax), %zmm0, %zmm1
@@ -713,7 +713,7 @@ define void @bcast_unfold_fneg_v4f64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} ymm0 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB22_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vxorps 8192(%rdi,%rax), %ymm0, %ymm1
@@ -746,7 +746,7 @@ define void @bcast_unfold_fneg_v2f64(ptr %arg) {
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vmovddup {{.*#+}} xmm0 = [-0.0E+0,-0.0E+0]
 ; CHECK-NEXT:    # xmm0 = mem[0,0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB23_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vxorps 8192(%rdi,%rax), %xmm0, %xmm1
@@ -777,7 +777,7 @@ define void @bcast_unfold_fabs_v16f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} zmm0 = [NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB24_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpandd 4096(%rdi,%rax), %zmm0, %zmm1
@@ -812,7 +812,7 @@ define void @bcast_unfold_fabs_v8f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm0 = [NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB25_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vandps 4096(%rdi,%rax), %ymm0, %ymm1
@@ -847,7 +847,7 @@ define void @bcast_unfold_fabs_v4f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} xmm0 = [NaN,NaN,NaN,NaN]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB26_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vandps 4096(%rdi,%rax), %xmm0, %xmm1
@@ -881,7 +881,7 @@ define void @bcast_unfold_fabs_v8f64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} zmm0 = [NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB27_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpandq 8192(%rdi,%rax), %zmm0, %zmm1
@@ -916,7 +916,7 @@ define void @bcast_unfold_fabs_v4f64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} ymm0 = [NaN,NaN,NaN,NaN]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB28_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vandps 8192(%rdi,%rax), %ymm0, %ymm1
@@ -952,7 +952,7 @@ define void @bcast_unfold_fabs_v2f64(ptr %arg) {
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vmovddup {{.*#+}} xmm0 = [NaN,NaN]
 ; CHECK-NEXT:    # xmm0 = mem[0,0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB29_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vandps 8192(%rdi,%rax), %xmm0, %xmm1
@@ -986,7 +986,7 @@ define void @bcast_unfold_fadd_v16f32(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} zmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB30_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vaddps 4096(%rdi,%rax), %zmm0, %zmm1
@@ -1018,7 +1018,7 @@ define void @bcast_unfold_fadd_v8f32(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB31_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vaddps 4096(%rdi,%rax), %ymm0, %ymm1
@@ -1050,7 +1050,7 @@ define void @bcast_unfold_fadd_v4f32(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} xmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB32_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vaddps 4096(%rdi,%rax), %xmm0, %xmm1
@@ -1081,7 +1081,7 @@ define void @bcast_unfold_fadd_v8f64(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} zmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB33_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vaddpd 8192(%rdi,%rax), %zmm0, %zmm1
@@ -1113,7 +1113,7 @@ define void @bcast_unfold_fadd_v4f64(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} ymm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB34_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vaddpd 8192(%rdi,%rax), %ymm0, %ymm1
@@ -1146,7 +1146,7 @@ define void @bcast_unfold_fadd_v2f64(ptr nocapture %arg) {
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vmovddup {{.*#+}} xmm0 = [2.0E+0,2.0E+0]
 ; CHECK-NEXT:    # xmm0 = mem[0,0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB35_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vaddpd 8192(%rdi,%rax), %xmm0, %xmm1
@@ -1177,7 +1177,7 @@ define void @bcast_unfold_fmul_v16f32(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} zmm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB36_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmulps 4096(%rdi,%rax), %zmm0, %zmm1
@@ -1209,7 +1209,7 @@ define void @bcast_unfold_fmul_v8f32(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB37_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmulps 4096(%rdi,%rax), %ymm0, %ymm1
@@ -1241,7 +1241,7 @@ define void @bcast_unfold_fmul_v4f32(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} xmm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB38_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmulps 4096(%rdi,%rax), %xmm0, %xmm1
@@ -1272,7 +1272,7 @@ define void @bcast_unfold_fmul_v8f64(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} zmm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB39_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmulpd 8192(%rdi,%rax), %zmm0, %zmm1
@@ -1304,7 +1304,7 @@ define void @bcast_unfold_fmul_v4f64(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} ymm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB40_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmulpd 8192(%rdi,%rax), %ymm0, %ymm1
@@ -1337,7 +1337,7 @@ define void @bcast_unfold_fmul_v2f64(ptr nocapture %arg) {
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vmovddup {{.*#+}} xmm0 = [3.0E+0,3.0E+0]
 ; CHECK-NEXT:    # xmm0 = mem[0,0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB41_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmulpd 8192(%rdi,%rax), %xmm0, %xmm1
@@ -1368,7 +1368,7 @@ define void @bcast_unfold_fdiv_v16f32(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} zmm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB42_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %zmm1
@@ -1401,7 +1401,7 @@ define void @bcast_unfold_fdiv_v8f32(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB43_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %ymm1
@@ -1434,7 +1434,7 @@ define void @bcast_unfold_fdiv_v4f32(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} xmm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB44_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %xmm1
@@ -1466,7 +1466,7 @@ define void @bcast_unfold_fdiv_v8f64(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} zmm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB45_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %zmm1
@@ -1499,7 +1499,7 @@ define void @bcast_unfold_fdiv_v4f64(ptr nocapture %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} ymm0 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB46_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %ymm1
@@ -1533,7 +1533,7 @@ define void @bcast_unfold_fdiv_v2f64(ptr nocapture %arg) {
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vmovddup {{.*#+}} xmm0 = [3.0E+0,3.0E+0]
 ; CHECK-NEXT:    # xmm0 = mem[0,0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB47_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %xmm1
@@ -1565,7 +1565,7 @@ define void @bcast_unfold_fma213_v4f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} xmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB48_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %xmm1
@@ -1598,7 +1598,7 @@ define void @bcast_unfold_fma231_v4f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} xmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB49_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %xmm1
@@ -1631,7 +1631,7 @@ define void @bcast_unfold_fma213_v8f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB50_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %ymm1
@@ -1665,7 +1665,7 @@ define void @bcast_unfold_fma231_v8f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB51_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %ymm1
@@ -1699,7 +1699,7 @@ define void @bcast_unfold_fma213_v16f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} zmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB52_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %zmm1
@@ -1733,7 +1733,7 @@ define void @bcast_unfold_fma231_v16f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} zmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB53_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %zmm1
@@ -1768,7 +1768,7 @@ define void @bcast_unfold_fma213_v2f64(ptr %arg) {
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vmovddup {{.*#+}} xmm0 = [2.0E+0,2.0E+0]
 ; CHECK-NEXT:    # xmm0 = mem[0,0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB54_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %xmm1
@@ -1802,7 +1802,7 @@ define void @bcast_unfold_fma231_v2f64(ptr %arg) {
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vmovddup {{.*#+}} xmm0 = [2.0E+0,2.0E+0]
 ; CHECK-NEXT:    # xmm0 = mem[0,0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB55_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %xmm1
@@ -1835,7 +1835,7 @@ define void @bcast_unfold_fma213_v4f64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} ymm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB56_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %ymm1
@@ -1869,7 +1869,7 @@ define void @bcast_unfold_fma231_v4f64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} ymm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB57_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %ymm1
@@ -1903,7 +1903,7 @@ define void @bcast_unfold_fma213_v8f64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} zmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB58_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %zmm1
@@ -1937,7 +1937,7 @@ define void @bcast_unfold_fma231_v8f64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} zmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB59_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %zmm1
@@ -1971,7 +1971,7 @@ define void @bcast_unfold_fmax_v4f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} xmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB60_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %xmm1
@@ -2004,7 +2004,7 @@ define void @bcast_unfold_fmax_v8f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB61_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %ymm1
@@ -2038,7 +2038,7 @@ define void @bcast_unfold_fmax_v16f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} zmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB62_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %zmm1
@@ -2073,7 +2073,7 @@ define void @bcast_unfold_fmax_v2f64(ptr %arg) {
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vmovddup {{.*#+}} xmm0 = [2.0E+0,2.0E+0]
 ; CHECK-NEXT:    # xmm0 = mem[0,0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB63_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %xmm1
@@ -2106,7 +2106,7 @@ define void @bcast_unfold_fmax_v4f64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} ymm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB64_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %ymm1
@@ -2140,7 +2140,7 @@ define void @bcast_unfold_fmax_v8f64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} zmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB65_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %zmm1
@@ -2174,7 +2174,7 @@ define void @bcast_unfold_fmin_v4f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} xmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB66_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %xmm1
@@ -2207,7 +2207,7 @@ define void @bcast_unfold_fmin_v8f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB67_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %ymm1
@@ -2241,7 +2241,7 @@ define void @bcast_unfold_fmin_v16f32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} zmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB68_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %zmm1
@@ -2276,7 +2276,7 @@ define void @bcast_unfold_fmin_v2f64(ptr %arg) {
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vmovddup {{.*#+}} xmm0 = [2.0E+0,2.0E+0]
 ; CHECK-NEXT:    # xmm0 = mem[0,0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB69_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %xmm1
@@ -2309,7 +2309,7 @@ define void @bcast_unfold_fmin_v4f64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} ymm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB70_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %ymm1
@@ -2343,7 +2343,7 @@ define void @bcast_unfold_fmin_v8f64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} zmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB71_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %zmm1
@@ -2377,7 +2377,7 @@ define void @bcast_unfold_smin_v4i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} xmm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB72_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpminsd 4096(%rdi,%rax), %xmm0, %xmm1
@@ -2409,7 +2409,7 @@ define void @bcast_unfold_smin_v8i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} ymm0 = [2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB73_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpminsd 4096(%rdi,%rax), %ymm0, %ymm1
@@ -2442,7 +2442,7 @@ define void @bcast_unfold_smin_v16i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} zmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB74_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpminsd 4096(%rdi,%rax), %zmm0, %zmm1
@@ -2475,7 +2475,7 @@ define void @bcast_unfold_smin_v2i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} xmm0 = [2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB75_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpminsq 8192(%rdi,%rax), %xmm0, %xmm1
@@ -2507,7 +2507,7 @@ define void @bcast_unfold_smin_v4i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} ymm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB76_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpminsq 8192(%rdi,%rax), %ymm0, %ymm1
@@ -2540,7 +2540,7 @@ define void @bcast_unfold_smin_v8i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} zmm0 = [2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB77_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpminsq 8192(%rdi,%rax), %zmm0, %zmm1
@@ -2573,7 +2573,7 @@ define void @bcast_unfold_smax_v4i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} xmm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB78_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpmaxsd 4096(%rdi,%rax), %xmm0, %xmm1
@@ -2605,7 +2605,7 @@ define void @bcast_unfold_smax_v8i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} ymm0 = [2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB79_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpmaxsd 4096(%rdi,%rax), %ymm0, %ymm1
@@ -2638,7 +2638,7 @@ define void @bcast_unfold_smax_v16i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} zmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB80_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpmaxsd 4096(%rdi,%rax), %zmm0, %zmm1
@@ -2671,7 +2671,7 @@ define void @bcast_unfold_smax_v2i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} xmm0 = [2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB81_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpmaxsq 8192(%rdi,%rax), %xmm0, %xmm1
@@ -2703,7 +2703,7 @@ define void @bcast_unfold_smax_v4i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} ymm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB82_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpmaxsq 8192(%rdi,%rax), %ymm0, %ymm1
@@ -2736,7 +2736,7 @@ define void @bcast_unfold_smax_v8i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} zmm0 = [2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB83_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpmaxsq 8192(%rdi,%rax), %zmm0, %zmm1
@@ -2769,7 +2769,7 @@ define void @bcast_unfold_umin_v4i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} xmm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB84_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpminud 4096(%rdi,%rax), %xmm0, %xmm1
@@ -2801,7 +2801,7 @@ define void @bcast_unfold_umin_v8i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} ymm0 = [2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB85_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpminud 4096(%rdi,%rax), %ymm0, %ymm1
@@ -2834,7 +2834,7 @@ define void @bcast_unfold_umin_v16i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} zmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB86_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpminud 4096(%rdi,%rax), %zmm0, %zmm1
@@ -2867,7 +2867,7 @@ define void @bcast_unfold_umin_v2i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} xmm0 = [2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB87_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpminuq 8192(%rdi,%rax), %xmm0, %xmm1
@@ -2899,7 +2899,7 @@ define void @bcast_unfold_umin_v4i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} ymm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB88_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpminuq 8192(%rdi,%rax), %ymm0, %ymm1
@@ -2932,7 +2932,7 @@ define void @bcast_unfold_umin_v8i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} zmm0 = [2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB89_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpminuq 8192(%rdi,%rax), %zmm0, %zmm1
@@ -2965,7 +2965,7 @@ define void @bcast_unfold_umax_v4i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} xmm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB90_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpmaxud 4096(%rdi,%rax), %xmm0, %xmm1
@@ -2997,7 +2997,7 @@ define void @bcast_unfold_umax_v8i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} ymm0 = [2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB91_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpmaxud 4096(%rdi,%rax), %ymm0, %ymm1
@@ -3030,7 +3030,7 @@ define void @bcast_unfold_umax_v16i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} zmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB92_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpmaxud 4096(%rdi,%rax), %zmm0, %zmm1
@@ -3063,7 +3063,7 @@ define void @bcast_unfold_umax_v2i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} xmm0 = [2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB93_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpmaxuq 8192(%rdi,%rax), %xmm0, %xmm1
@@ -3095,7 +3095,7 @@ define void @bcast_unfold_umax_v4i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} ymm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB94_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpmaxuq 8192(%rdi,%rax), %ymm0, %ymm1
@@ -3128,7 +3128,7 @@ define void @bcast_unfold_umax_v8i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} zmm0 = [2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB95_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpmaxuq 8192(%rdi,%rax), %zmm0, %zmm1
@@ -3161,7 +3161,7 @@ define void @bcast_unfold_pcmpgt_v4i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} xmm0 = [1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB96_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 4096(%rdi,%rax), %xmm1
@@ -3195,7 +3195,7 @@ define void @bcast_unfold_pcmpgt_v8i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} ymm0 = [1,1,1,1,1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB97_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 4096(%rdi,%rax), %ymm1
@@ -3230,7 +3230,7 @@ define void @bcast_unfold_pcmpgt_v16i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} zmm0 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB98_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu64 4096(%rdi,%rax), %zmm1
@@ -3265,7 +3265,7 @@ define void @bcast_unfold_pcmpgt_v2i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} xmm0 = [1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB99_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 8192(%rdi,%rax), %xmm1
@@ -3299,7 +3299,7 @@ define void @bcast_unfold_pcmpgt_v4i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} ymm0 = [1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB100_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 8192(%rdi,%rax), %ymm1
@@ -3334,7 +3334,7 @@ define void @bcast_unfold_pcmpgt_v8i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} zmm0 = [1,1,1,1,1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB101_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu64 8192(%rdi,%rax), %zmm1
@@ -3369,7 +3369,7 @@ define void @bcast_unfold_pcmpeq_v4i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} xmm0 = [1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB102_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 4096(%rdi,%rax), %xmm1
@@ -3403,7 +3403,7 @@ define void @bcast_unfold_pcmpeq_v8i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} ymm0 = [1,1,1,1,1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB103_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 4096(%rdi,%rax), %ymm1
@@ -3438,7 +3438,7 @@ define void @bcast_unfold_pcmpeq_v16i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} zmm0 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB104_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu64 4096(%rdi,%rax), %zmm1
@@ -3473,7 +3473,7 @@ define void @bcast_unfold_pcmpeq_v2i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} xmm0 = [1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB105_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 8192(%rdi,%rax), %xmm1
@@ -3507,7 +3507,7 @@ define void @bcast_unfold_pcmpeq_v4i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} ymm0 = [1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB106_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 8192(%rdi,%rax), %ymm1
@@ -3542,7 +3542,7 @@ define void @bcast_unfold_pcmpeq_v8i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} zmm0 = [1,1,1,1,1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB107_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu64 8192(%rdi,%rax), %zmm1
@@ -3577,7 +3577,7 @@ define void @bcast_unfold_pcmp_v4i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} xmm0 = [1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB108_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu (%rdi,%rax,4), %xmm1
@@ -3612,7 +3612,7 @@ define void @bcast_unfold_pcmp_v8i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} ymm0 = [1,1,1,1,1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB109_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu (%rdi,%rax,4), %ymm1
@@ -3648,7 +3648,7 @@ define void @bcast_unfold_pcmp_v16i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} zmm0 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB110_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu64 (%rdi,%rax,4), %zmm1
@@ -3684,7 +3684,7 @@ define void @bcast_unfold_pcmp_v2i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} xmm0 = [1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB111_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu (%rdi,%rax,8), %xmm1
@@ -3719,7 +3719,7 @@ define void @bcast_unfold_pcmp_v4i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} ymm0 = [1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB112_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu (%rdi,%rax,8), %ymm1
@@ -3755,7 +3755,7 @@ define void @bcast_unfold_pcmp_v8i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} zmm0 = [1,1,1,1,1,1,1,1]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB113_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu64 (%rdi,%rax,8), %zmm1
@@ -3791,7 +3791,7 @@ define void @bcast_unfold_pcmpu_v4i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} xmm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB114_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu (%rdi,%rax,4), %xmm1
@@ -3826,7 +3826,7 @@ define void @bcast_unfold_pcmpu_v8i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} ymm0 = [2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB115_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu (%rdi,%rax,4), %ymm1
@@ -3862,7 +3862,7 @@ define void @bcast_unfold_pcmpu_v16i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} zmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB116_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu64 (%rdi,%rax,4), %zmm1
@@ -3898,7 +3898,7 @@ define void @bcast_unfold_pcmpu_v2i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} xmm0 = [2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB117_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu (%rdi,%rax,8), %xmm1
@@ -3933,7 +3933,7 @@ define void @bcast_unfold_pcmpu_v4i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} ymm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB118_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu (%rdi,%rax,8), %ymm1
@@ -3969,7 +3969,7 @@ define void @bcast_unfold_pcmpu_v8i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} zmm0 = [2,2,2,2,2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB119_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu64 (%rdi,%rax,8), %zmm1
@@ -4006,7 +4006,7 @@ define void @bcast_unfold_cmp_v4f32(ptr %arg) {
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} xmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0]
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} xmm1 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB120_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %xmm2
@@ -4041,7 +4041,7 @@ define void @bcast_unfold_cmp_v8f32(ptr %arg) {
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm1 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB121_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %ymm2
@@ -4077,7 +4077,7 @@ define void @bcast_unfold_cmp_v16f32(ptr %arg) {
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} zmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} zmm1 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB122_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups 4096(%rdi,%rax), %zmm2
@@ -4115,7 +4115,7 @@ define void @bcast_unfold_cmp_v2f64(ptr %arg) {
 ; CHECK-NEXT:    # xmm0 = mem[0,0]
 ; CHECK-NEXT:    vmovddup {{.*#+}} xmm1 = [3.0E+0,3.0E+0]
 ; CHECK-NEXT:    # xmm1 = mem[0,0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB123_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %xmm2
@@ -4150,7 +4150,7 @@ define void @bcast_unfold_cmp_v4f64(ptr %arg) {
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} ymm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0]
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} ymm1 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB124_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %ymm2
@@ -4186,7 +4186,7 @@ define void @bcast_unfold_cmp_v8f64(ptr %arg) {
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} zmm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
 ; CHECK-NEXT:    vbroadcastsd {{.*#+}} zmm1 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB125_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovupd 8192(%rdi,%rax), %zmm2
@@ -4222,7 +4222,7 @@ define void @bcast_unfold_cmp_v8f32_refold(ptr nocapture %0) {
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm0 = [2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0,2.0E+0]
 ; CHECK-NEXT:    vbroadcastss {{.*#+}} ymm1 = [3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0,3.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB126_1: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vcmpgtps 4096(%rdi,%rax), %ymm0, %k1
 ; CHECK-NEXT:    vblendmps {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to8}, %ymm1, %ymm2 {%k1}
@@ -4254,7 +4254,7 @@ define void @bcast_unfold_ptestm_v4i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} xmm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB127_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 4096(%rdi,%rax), %xmm1
@@ -4289,7 +4289,7 @@ define void @bcast_unfold_ptestnm_v4i32(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} xmm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB128_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 4096(%rdi,%rax), %xmm1
@@ -4324,7 +4324,7 @@ define void @bcast_unfold_ptestm_v4i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} ymm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB129_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 8192(%rdi,%rax), %ymm1
@@ -4360,7 +4360,7 @@ define void @bcast_unfold_ptestnm_v4i64(ptr %arg) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-8192, %rax # imm = 0xE000
 ; CHECK-NEXT:    vpbroadcastq {{.*#+}} ymm0 = [2,2,2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB130_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu 8192(%rdi,%rax), %ymm1
@@ -4396,7 +4396,7 @@ define void @bcast_unfold_vpternlog_v16i32(ptr %arg, ptr %arg1) {
 ; CHECK:       # %bb.0: # %bb
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; CHECK-NEXT:    vpbroadcastd {{.*#+}} zmm0 = [32767,32767,32767,32767,32767,32767,32767,32767,32767,32767,32767,32767,32767,32767,32767,32767]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB131_1: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqu64 4096(%rdi,%rax), %zmm1
diff --git a/llvm/test/CodeGen/X86/avx512-i1test.ll b/llvm/test/CodeGen/X86/avx512-i1test.ll
index bf31b2da56b62e..3cd733181599e4 100644
--- a/llvm/test/CodeGen/X86/avx512-i1test.ll
+++ b/llvm/test/CodeGen/X86/avx512-i1test.ll
@@ -15,7 +15,7 @@ define void @func() {
 ; CHECK-NEXT:    retq
 ; CHECK-NEXT:  .LBB0_1: # %bb56
 ; CHECK-NEXT:    xorl %eax, %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %bb33
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb %al, %al
diff --git a/llvm/test/CodeGen/X86/avx512vnni-combine.ll b/llvm/test/CodeGen/X86/avx512vnni-combine.ll
index c491a952682d53..b7d950e9942416 100644
--- a/llvm/test/CodeGen/X86/avx512vnni-combine.ll
+++ b/llvm/test/CodeGen/X86/avx512vnni-combine.ll
@@ -54,7 +54,7 @@ define <8 x i64> @foo_512(i32 %0, <8 x i64> %1, <8 x i64> %2, ptr %3) {
 ; CHECK-NEXT:    andl $-4, %edx
 ; CHECK-NEXT:    leaq 192(%rsi), %rdi
 ; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_8: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpdpwssd -192(%rdi), %zmm1, %zmm0
 ; CHECK-NEXT:    vpmaddwd -128(%rdi), %zmm1, %zmm2
@@ -75,7 +75,7 @@ define <8 x i64> @foo_512(i32 %0, <8 x i64> %1, <8 x i64> %2, ptr %3) {
 ; CHECK-NEXT:    addq %rcx, %rsi
 ; CHECK-NEXT:    shll $6, %eax
 ; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_5: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpdpwssd (%rsi,%rcx), %zmm1, %zmm0
 ; CHECK-NEXT:    addq $64, %rcx
@@ -179,7 +179,7 @@ define void @bar_512(i32 %0, ptr %1, <8 x i64> %2, ptr %3) {
 ; CHECK-NEXT:    andl $-2, %edi
 ; CHECK-NEXT:    movl $64, %r8d
 ; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB2_7: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovdqa64 (%rsi,%r8), %zmm1
 ; CHECK-NEXT:    vpmaddwd -64(%rdx,%r8), %zmm0, %zmm2
diff --git a/llvm/test/CodeGen/X86/avxvnni-combine.ll b/llvm/test/CodeGen/X86/avxvnni-combine.ll
index 158a1fdf44fc6a..45f9a6475244ee 100644
--- a/llvm/test/CodeGen/X86/avxvnni-combine.ll
+++ b/llvm/test/CodeGen/X86/avxvnni-combine.ll
@@ -59,7 +59,7 @@ define <2 x i64> @foo_128(i32 %0, <2 x i64> %1, <2 x i64> %2, ptr %3) {
 ; AVX-NEXT:    andl $-4, %edx
 ; AVX-NEXT:    leaq 48(%rsi), %rdi
 ; AVX-NEXT:    xorl %ecx, %ecx
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB1_8: # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    {vex} vpdpwssd -48(%rdi), %xmm1, %xmm0
 ; AVX-NEXT:    vpmaddwd -32(%rdi), %xmm1, %xmm2
@@ -80,7 +80,7 @@ define <2 x i64> @foo_128(i32 %0, <2 x i64> %1, <2 x i64> %2, ptr %3) {
 ; AVX-NEXT:    addq %rcx, %rsi
 ; AVX-NEXT:    shll $4, %eax
 ; AVX-NEXT:    xorl %ecx, %ecx
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB1_5: # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    {vex} vpdpwssd (%rsi,%rcx), %xmm1, %xmm0
 ; AVX-NEXT:    addq $16, %rcx
@@ -106,7 +106,7 @@ define <2 x i64> @foo_128(i32 %0, <2 x i64> %1, <2 x i64> %2, ptr %3) {
 ; AVX512-NEXT:    andl $-4, %edx
 ; AVX512-NEXT:    leaq 48(%rsi), %rdi
 ; AVX512-NEXT:    xorl %ecx, %ecx
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB1_8: # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vpdpwssd -48(%rdi), %xmm1, %xmm0
 ; AVX512-NEXT:    vpmaddwd -32(%rdi), %xmm1, %xmm2
@@ -127,7 +127,7 @@ define <2 x i64> @foo_128(i32 %0, <2 x i64> %1, <2 x i64> %2, ptr %3) {
 ; AVX512-NEXT:    addq %rcx, %rsi
 ; AVX512-NEXT:    shll $4, %eax
 ; AVX512-NEXT:    xorl %ecx, %ecx
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB1_5: # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vpdpwssd (%rsi,%rcx), %xmm1, %xmm0
 ; AVX512-NEXT:    addq $16, %rcx
@@ -225,7 +225,7 @@ define void @bar_128(i32 %0, ptr %1, <2 x i64> %2, ptr %3) {
 ; AVX-NEXT:    andl $-2, %edi
 ; AVX-NEXT:    movl $16, %r8d
 ; AVX-NEXT:    xorl %ecx, %ecx
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB2_7: # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    vmovdqa (%rsi,%r8), %xmm1
 ; AVX-NEXT:    vpmaddwd -16(%rdx,%r8), %xmm0, %xmm2
@@ -265,7 +265,7 @@ define void @bar_128(i32 %0, ptr %1, <2 x i64> %2, ptr %3) {
 ; AVX512-NEXT:    andl $-2, %edi
 ; AVX512-NEXT:    movl $16, %r8d
 ; AVX512-NEXT:    xorl %ecx, %ecx
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB2_7: # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vmovdqa (%rsi,%r8), %xmm1
 ; AVX512-NEXT:    vpmaddwd -16(%rdx,%r8), %xmm0, %xmm2
@@ -406,7 +406,7 @@ define <4 x i64> @foo_256(i32 %0, <4 x i64> %1, <4 x i64> %2, ptr %3) {
 ; AVX-NEXT:    andl $-4, %edx
 ; AVX-NEXT:    leaq 96(%rsi), %rdi
 ; AVX-NEXT:    xorl %ecx, %ecx
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB4_8: # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    {vex} vpdpwssd -96(%rdi), %ymm1, %ymm0
 ; AVX-NEXT:    vpmaddwd -64(%rdi), %ymm1, %ymm2
@@ -427,7 +427,7 @@ define <4 x i64> @foo_256(i32 %0, <4 x i64> %1, <4 x i64> %2, ptr %3) {
 ; AVX-NEXT:    addq %rcx, %rsi
 ; AVX-NEXT:    shll $5, %eax
 ; AVX-NEXT:    xorl %ecx, %ecx
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB4_5: # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    {vex} vpdpwssd (%rsi,%rcx), %ymm1, %ymm0
 ; AVX-NEXT:    addq $32, %rcx
@@ -453,7 +453,7 @@ define <4 x i64> @foo_256(i32 %0, <4 x i64> %1, <4 x i64> %2, ptr %3) {
 ; AVX512-NEXT:    andl $-4, %edx
 ; AVX512-NEXT:    leaq 96(%rsi), %rdi
 ; AVX512-NEXT:    xorl %ecx, %ecx
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB4_8: # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vpdpwssd -96(%rdi), %ymm1, %ymm0
 ; AVX512-NEXT:    vpmaddwd -64(%rdi), %ymm1, %ymm2
@@ -474,7 +474,7 @@ define <4 x i64> @foo_256(i32 %0, <4 x i64> %1, <4 x i64> %2, ptr %3) {
 ; AVX512-NEXT:    addq %rcx, %rsi
 ; AVX512-NEXT:    shll $5, %eax
 ; AVX512-NEXT:    xorl %ecx, %ecx
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB4_5: # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vpdpwssd (%rsi,%rcx), %ymm1, %ymm0
 ; AVX512-NEXT:    addq $32, %rcx
@@ -579,7 +579,7 @@ define void @bar_256(i32 %0, ptr %1, <4 x i64> %2, ptr %3) {
 ; AVX-NEXT:    andl $-2, %edi
 ; AVX-NEXT:    movl $32, %r8d
 ; AVX-NEXT:    xorl %ecx, %ecx
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB5_7: # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    vmovdqa (%rsi,%r8), %ymm1
 ; AVX-NEXT:    vpmaddwd -32(%rdx,%r8), %ymm0, %ymm2
@@ -620,7 +620,7 @@ define void @bar_256(i32 %0, ptr %1, <4 x i64> %2, ptr %3) {
 ; AVX512-NEXT:    andl $-2, %edi
 ; AVX512-NEXT:    movl $32, %r8d
 ; AVX512-NEXT:    xorl %ecx, %ecx
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB5_7: # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vmovdqa (%rsi,%r8), %ymm1
 ; AVX512-NEXT:    vpmaddwd -32(%rdx,%r8), %ymm0, %ymm2
diff --git a/llvm/test/CodeGen/X86/block-placement.ll b/llvm/test/CodeGen/X86/block-placement.ll
index e479ad20d6e4c2..675293410dfe71 100644
--- a/llvm/test/CodeGen/X86/block-placement.ll
+++ b/llvm/test/CodeGen/X86/block-placement.ll
@@ -251,7 +251,7 @@ define i32 @test_loop_align(i32 %i, ptr %a) {
 ; pass.
 ; CHECK-LABEL: test_loop_align:
 ; CHECK: %entry
-; CHECK: .p2align [[ALIGN:[0-9]+]],
+; CHECK: .p2align [[ALIGN:[0-9]+]]
 ; CHECK-NEXT: %body
 ; CHECK: %exit
 
@@ -276,9 +276,9 @@ define i32 @test_nested_loop_align(i32 %i, ptr %a, ptr %b) {
 ; Check that we provide nested loop body alignment.
 ; CHECK-LABEL: test_nested_loop_align:
 ; CHECK: %entry
-; CHECK: .p2align [[ALIGN]],
+; CHECK: .p2align [[ALIGN]]
 ; CHECK-NEXT: %loop.body.1
-; CHECK: .p2align [[ALIGN]],
+; CHECK: .p2align [[ALIGN]]
 ; CHECK-NEXT: %inner.loop.body
 ; CHECK-NOT: .p2align
 ; CHECK: %exit
diff --git a/llvm/test/CodeGen/X86/break-false-dep.ll b/llvm/test/CodeGen/X86/break-false-dep.ll
index 8ff7fb2d351ad1..0a367e1916ff62 100644
--- a/llvm/test/CodeGen/X86/break-false-dep.ll
+++ b/llvm/test/CodeGen/X86/break-false-dep.ll
@@ -138,7 +138,7 @@ define dso_local float @loopdep1(i32 %m) nounwind uwtable readnone ssp {
 ; SSE-LINUX-NEXT:    movl $1, %eax
 ; SSE-LINUX-NEXT:    xorps %xmm0, %xmm0
 ; SSE-LINUX-NEXT:    xorps %xmm1, %xmm1
-; SSE-LINUX-NEXT:    .p2align 4, 0x90
+; SSE-LINUX-NEXT:    .p2align 4
 ; SSE-LINUX-NEXT:  .LBB6_3: # %for.body
 ; SSE-LINUX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-LINUX-NEXT:    xorps %xmm2, %xmm2
@@ -167,7 +167,7 @@ define dso_local float @loopdep1(i32 %m) nounwind uwtable readnone ssp {
 ; SSE-WIN-NEXT:    movl $1, %eax
 ; SSE-WIN-NEXT:    xorps %xmm0, %xmm0
 ; SSE-WIN-NEXT:    xorps %xmm1, %xmm1
-; SSE-WIN-NEXT:    .p2align 4, 0x90
+; SSE-WIN-NEXT:    .p2align 4
 ; SSE-WIN-NEXT:  .LBB6_3: # %for.body
 ; SSE-WIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-WIN-NEXT:    xorps %xmm2, %xmm2
@@ -196,7 +196,7 @@ define dso_local float @loopdep1(i32 %m) nounwind uwtable readnone ssp {
 ; AVX1-NEXT:    movl $1, %eax
 ; AVX1-NEXT:    vxorps %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB6_3: # %for.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vcvtsi2ss %eax, %xmm4, %xmm2
@@ -223,7 +223,7 @@ define dso_local float @loopdep1(i32 %m) nounwind uwtable readnone ssp {
 ; AVX512VL-NEXT:    movl $1, %eax
 ; AVX512VL-NEXT:    vxorps %xmm0, %xmm0, %xmm0
 ; AVX512VL-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; AVX512VL-NEXT:    .p2align 4, 0x90
+; AVX512VL-NEXT:    .p2align 4
 ; AVX512VL-NEXT:  .LBB6_3: # %for.body
 ; AVX512VL-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512VL-NEXT:    vcvtsi2ss %eax, %xmm3, %xmm2
@@ -276,7 +276,7 @@ define i64 @loopdep2(ptr nocapture %x, ptr nocapture %y) nounwind {
 ; SSE-LINUX:       # %bb.0: # %entry
 ; SSE-LINUX-NEXT:    movq (%rdi), %rax
 ; SSE-LINUX-NEXT:    movl $1, %ecx
-; SSE-LINUX-NEXT:    .p2align 4, 0x90
+; SSE-LINUX-NEXT:    .p2align 4
 ; SSE-LINUX-NEXT:  .LBB7_1: # %loop
 ; SSE-LINUX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-LINUX-NEXT:    xorps %xmm0, %xmm0
@@ -310,7 +310,7 @@ define i64 @loopdep2(ptr nocapture %x, ptr nocapture %y) nounwind {
 ; SSE-WIN-NEXT:    movaps %xmm6, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
 ; SSE-WIN-NEXT:    movq (%rcx), %rax
 ; SSE-WIN-NEXT:    movl $1, %ecx
-; SSE-WIN-NEXT:    .p2align 4, 0x90
+; SSE-WIN-NEXT:    .p2align 4
 ; SSE-WIN-NEXT:  .LBB7_1: # %loop
 ; SSE-WIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-WIN-NEXT:    xorps %xmm0, %xmm0
@@ -355,7 +355,7 @@ define i64 @loopdep2(ptr nocapture %x, ptr nocapture %y) nounwind {
 ; AVX-NEXT:    vmovaps %xmm6, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
 ; AVX-NEXT:    movq (%rcx), %rax
 ; AVX-NEXT:    movl $1, %ecx
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB7_1: # %loop
 ; AVX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    vxorps %xmm1, %xmm1, %xmm1
@@ -418,12 +418,12 @@ define dso_local void @loopdep3() {
 ; SSE-LINUX-LABEL: loopdep3:
 ; SSE-LINUX:       # %bb.0: # %entry
 ; SSE-LINUX-NEXT:    xorl %eax, %eax
-; SSE-LINUX-NEXT:    .p2align 4, 0x90
+; SSE-LINUX-NEXT:    .p2align 4
 ; SSE-LINUX-NEXT:  .LBB8_1: # %for.cond1.preheader
 ; SSE-LINUX-NEXT:    # =>This Loop Header: Depth=1
 ; SSE-LINUX-NEXT:    # Child Loop BB8_2 Depth 2
 ; SSE-LINUX-NEXT:    movq $-4096, %rcx # imm = 0xF000
-; SSE-LINUX-NEXT:    .p2align 4, 0x90
+; SSE-LINUX-NEXT:    .p2align 4
 ; SSE-LINUX-NEXT:  .LBB8_2: # %for.body3
 ; SSE-LINUX-NEXT:    # Parent Loop BB8_1 Depth=1
 ; SSE-LINUX-NEXT:    # => This Inner Loop Header: Depth=2
@@ -478,13 +478,13 @@ define dso_local void @loopdep3() {
 ; SSE-WIN-NEXT:    leaq y(%rip), %r8
 ; SSE-WIN-NEXT:    leaq z(%rip), %r9
 ; SSE-WIN-NEXT:    leaq w(%rip), %r10
-; SSE-WIN-NEXT:    .p2align 4, 0x90
+; SSE-WIN-NEXT:    .p2align 4
 ; SSE-WIN-NEXT:  .LBB8_1: # %for.cond1.preheader
 ; SSE-WIN-NEXT:    # =>This Loop Header: Depth=1
 ; SSE-WIN-NEXT:    # Child Loop BB8_2 Depth 2
 ; SSE-WIN-NEXT:    movq %rcx, %r11
 ; SSE-WIN-NEXT:    xorl %esi, %esi
-; SSE-WIN-NEXT:    .p2align 4, 0x90
+; SSE-WIN-NEXT:    .p2align 4
 ; SSE-WIN-NEXT:  .LBB8_2: # %for.body3
 ; SSE-WIN-NEXT:    # Parent Loop BB8_1 Depth=1
 ; SSE-WIN-NEXT:    # => This Inner Loop Header: Depth=2
@@ -554,13 +554,13 @@ define dso_local void @loopdep3() {
 ; AVX-NEXT:    leaq y(%rip), %r8
 ; AVX-NEXT:    leaq z(%rip), %r9
 ; AVX-NEXT:    leaq w(%rip), %r10
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB8_1: # %for.cond1.preheader
 ; AVX-NEXT:    # =>This Loop Header: Depth=1
 ; AVX-NEXT:    # Child Loop BB8_2 Depth 2
 ; AVX-NEXT:    movq %rcx, %r11
 ; AVX-NEXT:    xorl %esi, %esi
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB8_2: # %for.body3
 ; AVX-NEXT:    # Parent Loop BB8_1 Depth=1
 ; AVX-NEXT:    # => This Inner Loop Header: Depth=2
@@ -1114,7 +1114,7 @@ define i64 @loopclearence(ptr nocapture %x, ptr nocapture %y) nounwind {
 ; SSE-LINUX:       # %bb.0: # %entry
 ; SSE-LINUX-NEXT:    movq (%rdi), %rax
 ; SSE-LINUX-NEXT:    movl $1, %ecx
-; SSE-LINUX-NEXT:    .p2align 4, 0x90
+; SSE-LINUX-NEXT:    .p2align 4
 ; SSE-LINUX-NEXT:  .LBB12_1: # %loop
 ; SSE-LINUX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-LINUX-NEXT:    xorps %xmm4, %xmm4
@@ -1155,7 +1155,7 @@ define i64 @loopclearence(ptr nocapture %x, ptr nocapture %y) nounwind {
 ; SSE-WIN-NEXT:    movaps %xmm8, (%rsp) # 16-byte Spill
 ; SSE-WIN-NEXT:    movq (%rcx), %rax
 ; SSE-WIN-NEXT:    movl $1, %ecx
-; SSE-WIN-NEXT:    .p2align 4, 0x90
+; SSE-WIN-NEXT:    .p2align 4
 ; SSE-WIN-NEXT:  .LBB12_1: # %loop
 ; SSE-WIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-WIN-NEXT:    xorps %xmm4, %xmm4
@@ -1205,7 +1205,7 @@ define i64 @loopclearence(ptr nocapture %x, ptr nocapture %y) nounwind {
 ; AVX-NEXT:    vmovaps %xmm8, (%rsp) # 16-byte Spill
 ; AVX-NEXT:    movq (%rcx), %rax
 ; AVX-NEXT:    movl $1, %ecx
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB12_1: # %loop
 ; AVX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    vcvtsi2sd %rcx, %xmm5, %xmm4
@@ -1288,7 +1288,7 @@ define dso_local void @loopclearance2(ptr nocapture %y, ptr %x, double %c1, doub
 ; SSE-LINUX-NEXT:    #NO_APP
 ; SSE-LINUX-NEXT:    movl $1, %eax
 ; SSE-LINUX-NEXT:    xorl %ecx, %ecx
-; SSE-LINUX-NEXT:    .p2align 4, 0x90
+; SSE-LINUX-NEXT:    .p2align 4
 ; SSE-LINUX-NEXT:  .LBB13_1: # %inner_loop
 ; SSE-LINUX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-LINUX-NEXT:    movq %rcx, %r8
@@ -1360,7 +1360,7 @@ define dso_local void @loopclearance2(ptr nocapture %y, ptr %x, double %c1, doub
 ; SSE-WIN-NEXT:    #NO_APP
 ; SSE-WIN-NEXT:    movl $1, %r8d
 ; SSE-WIN-NEXT:    xorl %r9d, %r9d
-; SSE-WIN-NEXT:    .p2align 4, 0x90
+; SSE-WIN-NEXT:    .p2align 4
 ; SSE-WIN-NEXT:  .LBB13_1: # %inner_loop
 ; SSE-WIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-WIN-NEXT:    movq %r9, %r10
@@ -1443,7 +1443,7 @@ define dso_local void @loopclearance2(ptr nocapture %y, ptr %x, double %c1, doub
 ; AVX1-NEXT:    #NO_APP
 ; AVX1-NEXT:    movl $1, %r8d
 ; AVX1-NEXT:    xorl %r9d, %r9d
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB13_1: # %inner_loop
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    movq %r9, %r10
@@ -1523,7 +1523,7 @@ define dso_local void @loopclearance2(ptr nocapture %y, ptr %x, double %c1, doub
 ; AVX512VL-NEXT:    #NO_APP
 ; AVX512VL-NEXT:    movl $1, %r8d
 ; AVX512VL-NEXT:    xorl %r9d, %r9d
-; AVX512VL-NEXT:    .p2align 4, 0x90
+; AVX512VL-NEXT:    .p2align 4
 ; AVX512VL-NEXT:  .LBB13_1: # %inner_loop
 ; AVX512VL-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512VL-NEXT:    movq %r9, %r10
diff --git a/llvm/test/CodeGen/X86/callbr-asm-blockplacement.ll b/llvm/test/CodeGen/X86/callbr-asm-blockplacement.ll
index 941f331833c199..7f91b846447b3b 100644
--- a/llvm/test/CodeGen/X86/callbr-asm-blockplacement.ll
+++ b/llvm/test/CodeGen/X86/callbr-asm-blockplacement.ll
@@ -29,7 +29,7 @@ define i32 @foo(i32 %arg, ptr %arg3) nounwind {
 ; CHECK-NEXT:    leaq global(%rax,%rax,2), %r14
 ; CHECK-NEXT:    leaq global+4(%rax,%rax,2), %r15
 ; CHECK-NEXT:    xorl %r13d, %r13d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %bb8
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    callq bar at PLT
diff --git a/llvm/test/CodeGen/X86/cast-vsel.ll b/llvm/test/CodeGen/X86/cast-vsel.ll
index 3067ea674c00d9..d5ccc152abc239 100644
--- a/llvm/test/CodeGen/X86/cast-vsel.ll
+++ b/llvm/test/CodeGen/X86/cast-vsel.ll
@@ -278,7 +278,7 @@ define dso_local void @example25() nounwind {
 ; SSE2-LABEL: example25:
 ; SSE2:       # %bb.0: # %vector.ph
 ; SSE2-NEXT:    movq $-4096, %rax # imm = 0xF000
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB5_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movaps da+4112(%rax), %xmm0
@@ -303,7 +303,7 @@ define dso_local void @example25() nounwind {
 ; SSE41-LABEL: example25:
 ; SSE41:       # %bb.0: # %vector.ph
 ; SSE41-NEXT:    movq $-4096, %rax # imm = 0xF000
-; SSE41-NEXT:    .p2align 4, 0x90
+; SSE41-NEXT:    .p2align 4
 ; SSE41-NEXT:  .LBB5_1: # %vector.body
 ; SSE41-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE41-NEXT:    movaps da+4112(%rax), %xmm0
@@ -329,7 +329,7 @@ define dso_local void @example25() nounwind {
 ; AVX1:       # %bb.0: # %vector.ph
 ; AVX1-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; AVX1-NEXT:    vbroadcastss {{.*#+}} ymm0 = [1,1,1,1,1,1,1,1]
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB5_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vmovups da+4096(%rax), %ymm1
@@ -348,7 +348,7 @@ define dso_local void @example25() nounwind {
 ; AVX2-LABEL: example25:
 ; AVX2:       # %bb.0: # %vector.ph
 ; AVX2-NEXT:    movq $-4096, %rax # imm = 0xF000
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB5_1: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vmovups da+4096(%rax), %ymm0
@@ -402,7 +402,7 @@ define dso_local void @example24(i16 signext %x, i16 signext %y) nounwind {
 ; SSE2-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
 ; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,0,0,0]
 ; SSE2-NEXT:    movq $-4096, %rax # imm = 0xF000
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB6_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movaps da+4096(%rax), %xmm2
@@ -434,7 +434,7 @@ define dso_local void @example24(i16 signext %x, i16 signext %y) nounwind {
 ; SSE41-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
 ; SSE41-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[0,0,0,0]
 ; SSE41-NEXT:    movq $-4096, %rax # imm = 0xF000
-; SSE41-NEXT:    .p2align 4, 0x90
+; SSE41-NEXT:    .p2align 4
 ; SSE41-NEXT:  .LBB6_1: # %vector.body
 ; SSE41-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE41-NEXT:    movaps da+4096(%rax), %xmm0
@@ -469,7 +469,7 @@ define dso_local void @example24(i16 signext %x, i16 signext %y) nounwind {
 ; AVX1-NEXT:    vpmovsxwd %xmm2, %xmm2
 ; AVX1-NEXT:    vpshufd {{.*#+}} xmm3 = xmm3[2,3,2,3]
 ; AVX1-NEXT:    vpmovsxwd %xmm3, %xmm3
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB6_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vmovups da+4096(%rax), %ymm4
@@ -494,7 +494,7 @@ define dso_local void @example24(i16 signext %x, i16 signext %y) nounwind {
 ; AVX2-NEXT:    movq $-4096, %rax # imm = 0xF000
 ; AVX2-NEXT:    vpmovsxwd %xmm0, %ymm0
 ; AVX2-NEXT:    vpmovsxwd %xmm1, %ymm1
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB6_1: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vmovups da+4096(%rax), %ymm2
diff --git a/llvm/test/CodeGen/X86/cmpxchg-clobber-flags.ll b/llvm/test/CodeGen/X86/cmpxchg-clobber-flags.ll
index 29751dcfca5d6b..4877d15e44a4fc 100644
--- a/llvm/test/CodeGen/X86/cmpxchg-clobber-flags.ll
+++ b/llvm/test/CodeGen/X86/cmpxchg-clobber-flags.ll
@@ -127,12 +127,12 @@ define i32 @test_control_flow(ptr %p, i32 %i, i32 %j) nounwind {
 ; X86-ALL-NEXT:    jle .LBB1_6
 ; X86-ALL-NEXT:  # %bb.1: # %loop_start
 ; X86-ALL-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X86-ALL-NEXT:    .p2align 4, 0x90
+; X86-ALL-NEXT:    .p2align 4
 ; X86-ALL-NEXT:  .LBB1_2: # %while.condthread-pre-split.i
 ; X86-ALL-NEXT:    # =>This Loop Header: Depth=1
 ; X86-ALL-NEXT:    # Child Loop BB1_3 Depth 2
 ; X86-ALL-NEXT:    movl (%ecx), %edx
-; X86-ALL-NEXT:    .p2align 4, 0x90
+; X86-ALL-NEXT:    .p2align 4
 ; X86-ALL-NEXT:  .LBB1_3: # %while.cond.i
 ; X86-ALL-NEXT:    # Parent Loop BB1_2 Depth=1
 ; X86-ALL-NEXT:    # => This Inner Loop Header: Depth=2
@@ -154,12 +154,12 @@ define i32 @test_control_flow(ptr %p, i32 %i, i32 %j) nounwind {
 ; X64-ALL-NEXT:    movl %esi, %eax
 ; X64-ALL-NEXT:    cmpl %edx, %esi
 ; X64-ALL-NEXT:    jle .LBB1_5
-; X64-ALL-NEXT:    .p2align 4, 0x90
+; X64-ALL-NEXT:    .p2align 4
 ; X64-ALL-NEXT:  .LBB1_1: # %while.condthread-pre-split.i
 ; X64-ALL-NEXT:    # =>This Loop Header: Depth=1
 ; X64-ALL-NEXT:    # Child Loop BB1_2 Depth 2
 ; X64-ALL-NEXT:    movl (%rdi), %ecx
-; X64-ALL-NEXT:    .p2align 4, 0x90
+; X64-ALL-NEXT:    .p2align 4
 ; X64-ALL-NEXT:  .LBB1_2: # %while.cond.i
 ; X64-ALL-NEXT:    # Parent Loop BB1_1 Depth=1
 ; X64-ALL-NEXT:    # => This Inner Loop Header: Depth=2
diff --git a/llvm/test/CodeGen/X86/cmpxchg-i128-i1.ll b/llvm/test/CodeGen/X86/cmpxchg-i128-i1.ll
index 3fb561d00f97d1..bb07640dd285fa 100644
--- a/llvm/test/CodeGen/X86/cmpxchg-i128-i1.ll
+++ b/llvm/test/CodeGen/X86/cmpxchg-i128-i1.ll
@@ -113,7 +113,7 @@ define i128 @cmpxchg_use_eflags_and_val(ptr %addr, i128 %offset) {
 ; CHECK-NEXT:    vmovdqa (%rdi), %xmm0
 ; CHECK-NEXT:    vpextrq $1, %xmm0, %rdx
 ; CHECK-NEXT:    vmovq %xmm0, %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB4_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rdx, %r9
diff --git a/llvm/test/CodeGen/X86/coalesce-esp.ll b/llvm/test/CodeGen/X86/coalesce-esp.ll
index 34964c0afcc696..0c495c9cf2b009 100644
--- a/llvm/test/CodeGen/X86/coalesce-esp.ll
+++ b/llvm/test/CodeGen/X86/coalesce-esp.ll
@@ -27,7 +27,7 @@ define void @_ZSt17__gslice_to_indexjRKSt8valarrayIjES2_RS0_(i32 %__o, ptr nocap
 ; CHECK-NEXT:  .LBB0_1: # %bb4.preheader
 ; CHECK-NEXT:    xorl %edx, %edx
 ; CHECK-NEXT:    jmp .LBB0_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_4: # %bb7.backedge
 ; CHECK-NEXT:    # in Loop: Header=BB0_2 Depth=1
 ; CHECK-NEXT:    addl $-4, %edx
diff --git a/llvm/test/CodeGen/X86/coalescer-breaks-subreg-to-reg-liveness-reduced.ll b/llvm/test/CodeGen/X86/coalescer-breaks-subreg-to-reg-liveness-reduced.ll
index a5295d44b07c8e..e9f529eea7d3f1 100644
--- a/llvm/test/CodeGen/X86/coalescer-breaks-subreg-to-reg-liveness-reduced.ll
+++ b/llvm/test/CodeGen/X86/coalescer-breaks-subreg-to-reg-liveness-reduced.ll
@@ -46,7 +46,7 @@ define void @foo(ptr %arg3, i1 %icmp16) #0 {
 ; CHECK-NEXT:    xorl %r12d, %r12d
 ; CHECK-NEXT:    # implicit-def: $r13
 ; CHECK-NEXT:    jmp .LBB0_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb5
 ; CHECK-NEXT:    # in Loop: Header=BB0_2 Depth=1
 ; CHECK-NEXT:    orl $1, %r12d
diff --git a/llvm/test/CodeGen/X86/coalescer-commute1.ll b/llvm/test/CodeGen/X86/coalescer-commute1.ll
index 93c6756131fd0f..28502782cf6426 100644
--- a/llvm/test/CodeGen/X86/coalescer-commute1.ll
+++ b/llvm/test/CodeGen/X86/coalescer-commute1.ll
@@ -13,7 +13,7 @@ define void @runcont(ptr %source) nounwind  {
 ; CHECK-NEXT:    movl (%ecx), %ecx
 ; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
 ; CHECK-NEXT:    xorl %edx, %edx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_1: ## %bb
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vcvtsi2ssl (%eax,%edx,4), %xmm2, %xmm1
diff --git a/llvm/test/CodeGen/X86/coalescer-commute4.ll b/llvm/test/CodeGen/X86/coalescer-commute4.ll
index 72ca9f17841b61..0ec99dcba88aeb 100644
--- a/llvm/test/CodeGen/X86/coalescer-commute4.ll
+++ b/llvm/test/CodeGen/X86/coalescer-commute4.ll
@@ -15,7 +15,7 @@ define float @foo(ptr %x, ptr %y, i32 %c) nounwind  {
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; CHECK-NEXT:    xorps %xmm0, %xmm0
 ; CHECK-NEXT:    xorl %esi, %esi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_3: ## %bb
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    xorps %xmm1, %xmm1
diff --git a/llvm/test/CodeGen/X86/coalescer-dead-flag-verifier-error.ll b/llvm/test/CodeGen/X86/coalescer-dead-flag-verifier-error.ll
index 4a396599a4444d..4d41c8406f6e0b 100644
--- a/llvm/test/CodeGen/X86/coalescer-dead-flag-verifier-error.ll
+++ b/llvm/test/CodeGen/X86/coalescer-dead-flag-verifier-error.ll
@@ -11,7 +11,7 @@ define void @_ZNK4llvm5APInt21multiplicativeInverseERKS0_(ptr %r) {
 ; CHECK-NEXT:    xorl %edx, %edx
 ; CHECK-NEXT:    xorl %ecx, %ecx
 ; CHECK-NEXT:    jmp .LBB0_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_4: # %_ZNK4llvm5APInt13getActiveBitsEv.exit.i.i
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    movl %edx, %edx
@@ -26,7 +26,7 @@ define void @_ZNK4llvm5APInt21multiplicativeInverseERKS0_(ptr %r) {
 ; CHECK-NEXT:    movq %rcx, %r8
 ; CHECK-NEXT:    testb %al, %al
 ; CHECK-NEXT:    jne .LBB0_4
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_3: # %for.body.i.i.i.i.i.3
 ; CHECK-NEXT:    # Parent Loop BB0_1 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
@@ -72,7 +72,7 @@ define void @_ZNK4llvm5APInt21multiplicativeInverseERKS0__assert(ptr %r) {
 ; CHECK-NEXT:    xorl %edx, %edx
 ; CHECK-NEXT:    xorl %ecx, %ecx
 ; CHECK-NEXT:    jmp .LBB1_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_4: # %_ZNK4llvm5APInt13getActiveBitsEv.exit.i.i
 ; CHECK-NEXT:    # in Loop: Header=BB1_1 Depth=1
 ; CHECK-NEXT:    movl %edx, %edx
@@ -89,7 +89,7 @@ define void @_ZNK4llvm5APInt21multiplicativeInverseERKS0__assert(ptr %r) {
 ; CHECK-NEXT:    xorl %r8d, %r8d
 ; CHECK-NEXT:    testb %al, %al
 ; CHECK-NEXT:    jne .LBB1_4
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_3: # %for.body.i.i.i.i.i.3
 ; CHECK-NEXT:    # Parent Loop BB1_1 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
diff --git a/llvm/test/CodeGen/X86/code-align-loops.ll b/llvm/test/CodeGen/X86/code-align-loops.ll
index 164df14df4173f..68ae49792ed189 100644
--- a/llvm/test/CodeGen/X86/code-align-loops.ll
+++ b/llvm/test/CodeGen/X86/code-align-loops.ll
@@ -20,19 +20,19 @@
 ; The difference between test1 and test2 is test2 only set one loop metadata node for the second loop.
 
 ; CHECK-LABEL: test1:
-; ALIGN: .p2align 6, 0x90
+; ALIGN: .p2align 6
 ; ALIGN-NEXT: .LBB0_2: # %for.body
-; ALIGN: .p2align 9, 0x90
+; ALIGN: .p2align 9
 ; ALIGN-NEXT: .LBB0_3: # %for.body
 
-; ALIGN32: .p2align 6, 0x90
+; ALIGN32: .p2align 6
 ; ALIGN32-NEXT: .LBB0_2: # %for.body
-; ALIGN32: .p2align 9, 0x90
+; ALIGN32: .p2align 9
 ; ALIGN32-NEXT: .LBB0_3: # %for.body
 
-; ALIGN256: .p2align 8, 0x90
+; ALIGN256: .p2align 8
 ; ALIGN256-NEXT: .LBB0_2: # %for.body
-; ALIGN256: .p2align 9, 0x90
+; ALIGN256: .p2align 9
 ; ALIGN256-NEXT: .LBB0_3: # %for.body
 
 define void @test1(i32 %a) nounwind {
@@ -59,19 +59,19 @@ for.body5:                                        ; preds = %for.body, %for.body
 }
 
 ; CHECK-LABEL: test2:
-; ALIGN: .p2align 4, 0x90
+; ALIGN: .p2align 4
 ; ALIGN-NEXT: .LBB1_2: # %for.body
-; ALIGN: .p2align 9, 0x90
+; ALIGN: .p2align 9
 ; ALIGN-NEXT: .LBB1_3: # %for.body
 
-; ALIGN32: .p2align 5, 0x90
+; ALIGN32: .p2align 5
 ; ALIGN32-NEXT: .LBB1_2: # %for.body
-; ALIGN32: .p2align 9, 0x90
+; ALIGN32: .p2align 9
 ; ALIGN32-NEXT: .LBB1_3: # %for.body
 
-; ALIGN256: .p2align 8, 0x90
+; ALIGN256: .p2align 8
 ; ALIGN256-NEXT: .LBB1_2: # %for.body
-; ALIGN256: .p2align 9, 0x90
+; ALIGN256: .p2align 9
 ; ALIGN256-NEXT: .LBB1_3: # %for.body
 define void @test2(i32 %a) nounwind {
 entry:
@@ -111,7 +111,7 @@ for.body5:                                        ; preds = %for.body, %for.body
 ;     }
 ; }
 ; CHECK-LABEL: test3_multilatch:
-; ALIGN: .p2align 6, 0x90
+; ALIGN: .p2align 6
 ; ALIGN-NEXT: .LBB2_1: # %while.cond
 define dso_local i32 @test3_multilatch() #0 {
 entry:
@@ -147,7 +147,7 @@ while.end:                                        ; preds = %while.cond
 }
 
 ; CHECK-LABEL: test4_multilatch:
-; ALIGN: .p2align 6, 0x90
+; ALIGN: .p2align 6
 ; ALIGN-NEXT: .LBB3_4: # %bb4
 define void @test4_multilatch(i32 %a, i32 %b, i32 %c, i32 %d) nounwind {
 entry:
diff --git a/llvm/test/CodeGen/X86/code_placement_align_all.ll b/llvm/test/CodeGen/X86/code_placement_align_all.ll
index 11dc59a3bab9d5..0e57b0e8ebd32d 100644
--- a/llvm/test/CodeGen/X86/code_placement_align_all.ll
+++ b/llvm/test/CodeGen/X86/code_placement_align_all.ll
@@ -1,9 +1,9 @@
 ; RUN: llc  -mcpu=corei7 -mtriple=x86_64-linux -align-all-blocks=16 < %s | FileCheck %s
 
 ;CHECK-LABEL: foo:
-;CHECK: .p2align  16, 0x90
-;CHECK: .p2align  16, 0x90
-;CHECK: .p2align  16, 0x90
+;CHECK: .p2align  16
+;CHECK: .p2align  16
+;CHECK: .p2align  16
 ;CHECK: ret
 define i32 @foo(i32 %t, i32 %l) nounwind readnone ssp uwtable {
   %1 = icmp eq i32 %t, 0
diff --git a/llvm/test/CodeGen/X86/combine-pmuldq.ll b/llvm/test/CodeGen/X86/combine-pmuldq.ll
index aa3bea2791416a..2a52b9eabc7b48 100644
--- a/llvm/test/CodeGen/X86/combine-pmuldq.ll
+++ b/llvm/test/CodeGen/X86/combine-pmuldq.ll
@@ -157,7 +157,7 @@ define <8 x i64> @combine_zext_pmuludq_256(<8 x i32> %a) {
 define void @PR39398(i32 %a0) {
 ; SSE-LABEL: PR39398:
 ; SSE:       # %bb.0: # %bb
-; SSE-NEXT:    .p2align 4, 0x90
+; SSE-NEXT:    .p2align 4
 ; SSE-NEXT:  .LBB5_1: # %bb10
 ; SSE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-NEXT:    cmpl $232, %edi
@@ -167,7 +167,7 @@ define void @PR39398(i32 %a0) {
 ;
 ; AVX-LABEL: PR39398:
 ; AVX:       # %bb.0: # %bb
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB5_1: # %bb10
 ; AVX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    cmpl $232, %edi
@@ -338,7 +338,7 @@ define <8 x i32> @PR49658_zext(ptr %ptr, i32 %mul) {
 ; SSE-NEXT:    pxor %xmm0, %xmm0
 ; SSE-NEXT:    movq $-2097152, %rax # imm = 0xFFE00000
 ; SSE-NEXT:    pxor %xmm1, %xmm1
-; SSE-NEXT:    .p2align 4, 0x90
+; SSE-NEXT:    .p2align 4
 ; SSE-NEXT:  .LBB7_1: # %loop
 ; SSE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-NEXT:    pmovzxdq {{.*#+}} xmm3 = mem[0],zero,mem[1],zero
@@ -367,7 +367,7 @@ define <8 x i32> @PR49658_zext(ptr %ptr, i32 %mul) {
 ; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    movq $-2097152, %rax # imm = 0xFFE00000
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB7_1: # %loop
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm3 = mem[0],zero,mem[1],zero
@@ -396,7 +396,7 @@ define <8 x i32> @PR49658_zext(ptr %ptr, i32 %mul) {
 ; AVX2-NEXT:    vpbroadcastq %xmm0, %ymm1
 ; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX2-NEXT:    movq $-2097152, %rax # imm = 0xFFE00000
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB7_1: # %loop
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vpmovzxdq {{.*#+}} ymm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
@@ -418,7 +418,7 @@ define <8 x i32> @PR49658_zext(ptr %ptr, i32 %mul) {
 ; AVX512VL-NEXT:    vpbroadcastq %rax, %zmm1
 ; AVX512VL-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512VL-NEXT:    movq $-2097152, %rax # imm = 0xFFE00000
-; AVX512VL-NEXT:    .p2align 4, 0x90
+; AVX512VL-NEXT:    .p2align 4
 ; AVX512VL-NEXT:  .LBB7_1: # %loop
 ; AVX512VL-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512VL-NEXT:    vpmovzxdq {{.*#+}} zmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
@@ -437,7 +437,7 @@ define <8 x i32> @PR49658_zext(ptr %ptr, i32 %mul) {
 ; AVX512DQVL-NEXT:    vpbroadcastq %rax, %zmm1
 ; AVX512DQVL-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512DQVL-NEXT:    movq $-2097152, %rax # imm = 0xFFE00000
-; AVX512DQVL-NEXT:    .p2align 4, 0x90
+; AVX512DQVL-NEXT:    .p2align 4
 ; AVX512DQVL-NEXT:  .LBB7_1: # %loop
 ; AVX512DQVL-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512DQVL-NEXT:    vpmovzxdq {{.*#+}} zmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
@@ -482,7 +482,7 @@ define <8 x i32> @PR49658_sext(ptr %ptr, i32 %mul) {
 ; SSE-NEXT:    movdqa %xmm2, %xmm3
 ; SSE-NEXT:    psrlq $32, %xmm3
 ; SSE-NEXT:    pxor %xmm1, %xmm1
-; SSE-NEXT:    .p2align 4, 0x90
+; SSE-NEXT:    .p2align 4
 ; SSE-NEXT:  .LBB8_1: # %loop
 ; SSE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-NEXT:    pmovsxdq 2097176(%rdi,%rax), %xmm5
@@ -543,7 +543,7 @@ define <8 x i32> @PR49658_sext(ptr %ptr, i32 %mul) {
 ; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    movq $-2097152, %rax # imm = 0xFFE00000
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB8_1: # %loop
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vpmovsxdq 2097152(%rdi,%rax), %xmm3
@@ -572,7 +572,7 @@ define <8 x i32> @PR49658_sext(ptr %ptr, i32 %mul) {
 ; AVX2-NEXT:    vpbroadcastq %xmm0, %ymm1
 ; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX2-NEXT:    movq $-2097152, %rax # imm = 0xFFE00000
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB8_1: # %loop
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vpmovsxdq 2097168(%rdi,%rax), %ymm2
@@ -594,7 +594,7 @@ define <8 x i32> @PR49658_sext(ptr %ptr, i32 %mul) {
 ; AVX512VL-NEXT:    vpbroadcastq %rax, %zmm1
 ; AVX512VL-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512VL-NEXT:    movq $-2097152, %rax # imm = 0xFFE00000
-; AVX512VL-NEXT:    .p2align 4, 0x90
+; AVX512VL-NEXT:    .p2align 4
 ; AVX512VL-NEXT:  .LBB8_1: # %loop
 ; AVX512VL-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512VL-NEXT:    vpmovzxdq {{.*#+}} zmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
@@ -613,7 +613,7 @@ define <8 x i32> @PR49658_sext(ptr %ptr, i32 %mul) {
 ; AVX512DQVL-NEXT:    vpbroadcastq %rax, %zmm1
 ; AVX512DQVL-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512DQVL-NEXT:    movq $-2097152, %rax # imm = 0xFFE00000
-; AVX512DQVL-NEXT:    .p2align 4, 0x90
+; AVX512DQVL-NEXT:    .p2align 4
 ; AVX512DQVL-NEXT:  .LBB8_1: # %loop
 ; AVX512DQVL-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512DQVL-NEXT:    vpmovzxdq {{.*#+}} zmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
diff --git a/llvm/test/CodeGen/X86/constant-pool-sharing.ll b/llvm/test/CodeGen/X86/constant-pool-sharing.ll
index 062d87ed035fd6..9e0114c017419f 100644
--- a/llvm/test/CodeGen/X86/constant-pool-sharing.ll
+++ b/llvm/test/CodeGen/X86/constant-pool-sharing.ll
@@ -12,7 +12,7 @@ define void @share_v4i32_v4f32(ptr %p, ptr %q, i1 %t) nounwind {
 ; SSE-LINUX-LABEL: share_v4i32_v4f32:
 ; SSE-LINUX:       # %bb.0: # %entry
 ; SSE-LINUX-NEXT:    movaps {{.*#+}} xmm0 = [1073741824,1073741824,1073741824,1073741824]
-; SSE-LINUX-NEXT:    .p2align 4, 0x90
+; SSE-LINUX-NEXT:    .p2align 4
 ; SSE-LINUX-NEXT:  .LBB0_1: # %loop
 ; SSE-LINUX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-LINUX-NEXT:    movaps %xmm0, (%rdi)
@@ -25,7 +25,7 @@ define void @share_v4i32_v4f32(ptr %p, ptr %q, i1 %t) nounwind {
 ; SSE-MSVC-LABEL: share_v4i32_v4f32:
 ; SSE-MSVC:       # %bb.0: # %entry
 ; SSE-MSVC-NEXT:    movaps {{.*#+}} xmm0 = [1073741824,1073741824,1073741824,1073741824]
-; SSE-MSVC-NEXT:    .p2align 4, 0x90
+; SSE-MSVC-NEXT:    .p2align 4
 ; SSE-MSVC-NEXT:  .LBB0_1: # %loop
 ; SSE-MSVC-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-MSVC-NEXT:    movaps %xmm0, (%rcx)
@@ -39,7 +39,7 @@ define void @share_v4i32_v4f32(ptr %p, ptr %q, i1 %t) nounwind {
 ; AVX-LINUX:       # %bb.0: # %entry
 ; AVX-LINUX-NEXT:    vbroadcastss {{.*#+}} xmm0 = [1073741824,1073741824,1073741824,1073741824]
 ; AVX-LINUX-NEXT:    vbroadcastss {{.*#+}} xmm1 = [1073741824,1073741824,1073741824,1073741824]
-; AVX-LINUX-NEXT:    .p2align 4, 0x90
+; AVX-LINUX-NEXT:    .p2align 4
 ; AVX-LINUX-NEXT:  .LBB0_1: # %loop
 ; AVX-LINUX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX-LINUX-NEXT:    vmovaps %xmm0, (%rdi)
@@ -53,7 +53,7 @@ define void @share_v4i32_v4f32(ptr %p, ptr %q, i1 %t) nounwind {
 ; AVX-MSVC:       # %bb.0: # %entry
 ; AVX-MSVC-NEXT:    vbroadcastss {{.*#+}} xmm0 = [1073741824,1073741824,1073741824,1073741824]
 ; AVX-MSVC-NEXT:    vbroadcastss {{.*#+}} xmm1 = [1073741824,1073741824,1073741824,1073741824]
-; AVX-MSVC-NEXT:    .p2align 4, 0x90
+; AVX-MSVC-NEXT:    .p2align 4
 ; AVX-MSVC-NEXT:  .LBB0_1: # %loop
 ; AVX-MSVC-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX-MSVC-NEXT:    vmovaps %xmm0, (%rcx)
diff --git a/llvm/test/CodeGen/X86/copy-eflags.ll b/llvm/test/CodeGen/X86/copy-eflags.ll
index 6af80860401afd..e1711ccdbe13fb 100644
--- a/llvm/test/CodeGen/X86/copy-eflags.ll
+++ b/llvm/test/CodeGen/X86/copy-eflags.ll
@@ -211,7 +211,7 @@ define dso_local void @PR37100(i8 %arg1, i16 %arg2, i64 %arg3, i8 %arg4, ptr %pt
 ; X32-NEXT:    movb {{[0-9]+}}(%esp), %ch
 ; X32-NEXT:    movb {{[0-9]+}}(%esp), %cl
 ; X32-NEXT:    jmp .LBB3_1
-; X32-NEXT:    .p2align 4, 0x90
+; X32-NEXT:    .p2align 4
 ; X32-NEXT:  .LBB3_5: # %bb1
 ; X32-NEXT:    # in Loop: Header=BB3_1 Depth=1
 ; X32-NEXT:    movl %esi, %eax
@@ -250,7 +250,7 @@ define dso_local void @PR37100(i8 %arg1, i16 %arg2, i64 %arg3, i8 %arg4, ptr %pt
 ; X64-NEXT:    movq %rdx, %r10
 ; X64-NEXT:    movl {{[0-9]+}}(%rsp), %esi
 ; X64-NEXT:    movzbl %cl, %ecx
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB3_1: # %bb1
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movsbq %dil, %rax
diff --git a/llvm/test/CodeGen/X86/dag-update-nodetomatch.ll b/llvm/test/CodeGen/X86/dag-update-nodetomatch.ll
index adb7319fe80b11..bf6b09674e1870 100644
--- a/llvm/test/CodeGen/X86/dag-update-nodetomatch.ll
+++ b/llvm/test/CodeGen/X86/dag-update-nodetomatch.ll
@@ -144,7 +144,7 @@ define void @_Z2x6v() local_unnamed_addr {
 ; CHECK-NEXT:    movq x0 at GOTPCREL(%rip), %r15
 ; CHECK-NEXT:    movq %rsi, %r12
 ; CHECK-NEXT:    jmp .LBB1_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_15: # %for.cond1.for.inc3_crit_edge
 ; CHECK-NEXT:    # in Loop: Header=BB1_2 Depth=1
 ; CHECK-NEXT:    movl %edx, (%r8)
@@ -220,7 +220,7 @@ define void @_Z2x6v() local_unnamed_addr {
 ; CHECK-NEXT:    subq %rdx, %rax
 ; CHECK-NEXT:    addq %r13, %r10
 ; CHECK-NEXT:    leaq (%r11,%r10,8), %r10
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_12: # %vector.body
 ; CHECK-NEXT:    # Parent Loop BB1_2 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
@@ -237,7 +237,7 @@ define void @_Z2x6v() local_unnamed_addr {
 ; CHECK-NEXT:    cmpq %rdx, %rbp
 ; CHECK-NEXT:    movq %r13, %rdx
 ; CHECK-NEXT:    je .LBB1_15
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_14: # %for.body2
 ; CHECK-NEXT:    # Parent Loop BB1_2 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
diff --git a/llvm/test/CodeGen/X86/div-rem-pair-recomposition-signed.ll b/llvm/test/CodeGen/X86/div-rem-pair-recomposition-signed.ll
index c350ed64280dd2..f66d81c781fe0d 100644
--- a/llvm/test/CodeGen/X86/div-rem-pair-recomposition-signed.ll
+++ b/llvm/test/CodeGen/X86/div-rem-pair-recomposition-signed.ll
@@ -417,7 +417,7 @@ define i128 @scalar_i128(i128 %x, i128 %y, ptr %divdst) nounwind {
 ; X86-NEXT:    xorl %edx, %edx
 ; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %ecx # 4-byte Reload
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB4_3: # %udiv-do-while
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %edx, %esi
diff --git a/llvm/test/CodeGen/X86/div-rem-pair-recomposition-unsigned.ll b/llvm/test/CodeGen/X86/div-rem-pair-recomposition-unsigned.ll
index 16dc1d6b446cf7..6fdde0b14a9843 100644
--- a/llvm/test/CodeGen/X86/div-rem-pair-recomposition-unsigned.ll
+++ b/llvm/test/CodeGen/X86/div-rem-pair-recomposition-unsigned.ll
@@ -377,7 +377,7 @@ define i128 @scalar_i128(i128 %x, i128 %y, ptr %divdst) nounwind {
 ; X86-NEXT:    xorl %eax, %eax
 ; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X86-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB4_3: # %udiv-do-while
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
diff --git a/llvm/test/CodeGen/X86/fdiv-combine.ll b/llvm/test/CodeGen/X86/fdiv-combine.ll
index 322ef6b393922d..1abcdc3cca9b78 100644
--- a/llvm/test/CodeGen/X86/fdiv-combine.ll
+++ b/llvm/test/CodeGen/X86/fdiv-combine.ll
@@ -128,7 +128,7 @@ define void @PR24141() {
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    .cfi_def_cfa_offset 16
 ; CHECK-NEXT:    # implicit-def: $xmm0
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB8_1: # %while.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    callq g at PLT
diff --git a/llvm/test/CodeGen/X86/fixup-lea.ll b/llvm/test/CodeGen/X86/fixup-lea.ll
index 35c3976408f645..548e74de392956 100644
--- a/llvm/test/CodeGen/X86/fixup-lea.ll
+++ b/llvm/test/CodeGen/X86/fixup-lea.ll
@@ -165,7 +165,7 @@ define void @foo_nosize(i32 inreg %dns) {
 ; SLOW-LABEL: foo_nosize:
 ; SLOW:       # %bb.0: # %entry
 ; SLOW-NEXT:    movw $-1, %cx
-; SLOW-NEXT:    .p2align 4, 0x90
+; SLOW-NEXT:    .p2align 4
 ; SLOW-NEXT:  .LBB6_1: # %for.body
 ; SLOW-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SLOW-NEXT:    movzwl %cx, %edx
@@ -178,7 +178,7 @@ define void @foo_nosize(i32 inreg %dns) {
 ; FAST-LABEL: foo_nosize:
 ; FAST:       # %bb.0: # %entry
 ; FAST-NEXT:    movw $-1, %cx
-; FAST-NEXT:    .p2align 4, 0x90
+; FAST-NEXT:    .p2align 4
 ; FAST-NEXT:  .LBB6_1: # %for.body
 ; FAST-NEXT:    # =>This Inner Loop Header: Depth=1
 ; FAST-NEXT:    movzwl %cx, %edx
@@ -205,7 +205,7 @@ define void @bar_nosize(i32 inreg %dns) {
 ; SLOW-LABEL: bar_nosize:
 ; SLOW:       # %bb.0: # %entry
 ; SLOW-NEXT:    movw $1, %cx
-; SLOW-NEXT:    .p2align 4, 0x90
+; SLOW-NEXT:    .p2align 4
 ; SLOW-NEXT:  .LBB7_1: # %for.body
 ; SLOW-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SLOW-NEXT:    movzwl %cx, %edx
@@ -218,7 +218,7 @@ define void @bar_nosize(i32 inreg %dns) {
 ; FAST-LABEL: bar_nosize:
 ; FAST:       # %bb.0: # %entry
 ; FAST-NEXT:    movw $1, %cx
-; FAST-NEXT:    .p2align 4, 0x90
+; FAST-NEXT:    .p2align 4
 ; FAST-NEXT:  .LBB7_1: # %for.body
 ; FAST-NEXT:    # =>This Inner Loop Header: Depth=1
 ; FAST-NEXT:    movzwl %cx, %edx
diff --git a/llvm/test/CodeGen/X86/fma-commute-loop.ll b/llvm/test/CodeGen/X86/fma-commute-loop.ll
index d26aaaa71e28d9..ae0efa320f1e4f 100644
--- a/llvm/test/CodeGen/X86/fma-commute-loop.ll
+++ b/llvm/test/CodeGen/X86/fma-commute-loop.ll
@@ -30,7 +30,7 @@ define void @eggs(ptr %arg, ptr %arg1, ptr %arg2, ptr %arg3, ptr %arg4, ptr %arg
 ; CHECK-NEXT:    vxorpd %xmm5, %xmm5, %xmm5
 ; CHECK-NEXT:    vxorpd %xmm6, %xmm6, %xmm6
 ; CHECK-NEXT:    vxorpd %xmm7, %xmm7, %xmm7
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_1: ## %bb15
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vbroadcastsd (%r11,%rbx,8), %zmm9
diff --git a/llvm/test/CodeGen/X86/fma-intrinsics-phi-213-to-231.ll b/llvm/test/CodeGen/X86/fma-intrinsics-phi-213-to-231.ll
index a509e93ef3f83f..5f1c5a5690ef20 100644
--- a/llvm/test/CodeGen/X86/fma-intrinsics-phi-213-to-231.ll
+++ b/llvm/test/CodeGen/X86/fma-intrinsics-phi-213-to-231.ll
@@ -7,7 +7,7 @@ define <2 x double> @fmaddsubpd_loop_128(i32 %iter, <2 x double> %a, <2 x double
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB0_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmaddsub231pd {{.*#+}} xmm2 = (xmm0 * xmm1) +/- xmm2
@@ -44,7 +44,7 @@ define <2 x double> @fmsubaddpd_loop_128(i32 %iter, <2 x double> %a, <2 x double
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB1_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmsubadd231pd {{.*#+}} xmm2 = (xmm0 * xmm1) -/+ xmm2
@@ -81,7 +81,7 @@ define <2 x double> @fmaddpd_loop_128(i32 %iter, <2 x double> %a, <2 x double> %
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB2_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB2_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmadd231pd {{.*#+}} xmm2 = (xmm0 * xmm1) + xmm2
@@ -118,7 +118,7 @@ define <2 x double> @fmsubpd_loop_128(i32 %iter, <2 x double> %a, <2 x double> %
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB3_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB3_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmsub231pd {{.*#+}} xmm2 = (xmm0 * xmm1) - xmm2
@@ -155,7 +155,7 @@ define <2 x double> @fnmaddpd_loop_128(i32 %iter, <2 x double> %a, <2 x double>
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB4_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB4_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfnmadd231pd {{.*#+}} xmm2 = -(xmm0 * xmm1) + xmm2
@@ -192,7 +192,7 @@ define <2 x double> @fnmsubpd_loop_128(i32 %iter, <2 x double> %a, <2 x double>
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB5_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB5_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfnmsub231pd {{.*#+}} xmm2 = -(xmm0 * xmm1) - xmm2
@@ -236,7 +236,7 @@ define <4 x float> @fmaddsubps_loop_128(i32 %iter, <4 x float> %a, <4 x float> %
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB6_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB6_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmaddsub231ps {{.*#+}} xmm2 = (xmm0 * xmm1) +/- xmm2
@@ -273,7 +273,7 @@ define <4 x float> @fmsubaddps_loop_128(i32 %iter, <4 x float> %a, <4 x float> %
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB7_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB7_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmsubadd231ps {{.*#+}} xmm2 = (xmm0 * xmm1) -/+ xmm2
@@ -310,7 +310,7 @@ define <4 x float> @fmaddps_loop_128(i32 %iter, <4 x float> %a, <4 x float> %b,
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB8_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB8_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmadd231ps {{.*#+}} xmm2 = (xmm0 * xmm1) + xmm2
@@ -347,7 +347,7 @@ define <4 x float> @fmsubps_loop_128(i32 %iter, <4 x float> %a, <4 x float> %b,
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB9_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB9_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmsub231ps {{.*#+}} xmm2 = (xmm0 * xmm1) - xmm2
@@ -384,7 +384,7 @@ define <4 x float> @fnmaddps_loop_128(i32 %iter, <4 x float> %a, <4 x float> %b,
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB10_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB10_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfnmadd231ps {{.*#+}} xmm2 = -(xmm0 * xmm1) + xmm2
@@ -421,7 +421,7 @@ define <4 x float> @fnmsubps_loop_128(i32 %iter, <4 x float> %a, <4 x float> %b,
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB11_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB11_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfnmsub231ps {{.*#+}} xmm2 = -(xmm0 * xmm1) - xmm2
@@ -465,7 +465,7 @@ define <4 x double> @fmaddsubpd_loop_256(i32 %iter, <4 x double> %a, <4 x double
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB12_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB12_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmaddsub231pd {{.*#+}} ymm2 = (ymm0 * ymm1) +/- ymm2
@@ -502,7 +502,7 @@ define <4 x double> @fmsubaddpd_loop_256(i32 %iter, <4 x double> %a, <4 x double
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB13_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB13_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmsubadd231pd {{.*#+}} ymm2 = (ymm0 * ymm1) -/+ ymm2
@@ -539,7 +539,7 @@ define <4 x double> @fmaddpd_loop_256(i32 %iter, <4 x double> %a, <4 x double> %
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB14_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB14_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmadd231pd {{.*#+}} ymm2 = (ymm0 * ymm1) + ymm2
@@ -576,7 +576,7 @@ define <4 x double> @fmsubpd_loop_256(i32 %iter, <4 x double> %a, <4 x double> %
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB15_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB15_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmsub231pd {{.*#+}} ymm2 = (ymm0 * ymm1) - ymm2
@@ -613,7 +613,7 @@ define <4 x double> @fnmaddpd_loop_256(i32 %iter, <4 x double> %a, <4 x double>
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB16_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB16_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfnmadd231pd {{.*#+}} ymm2 = -(ymm0 * ymm1) + ymm2
@@ -650,7 +650,7 @@ define <4 x double> @fnmsubpd_loop_256(i32 %iter, <4 x double> %a, <4 x double>
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB17_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB17_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfnmsub231pd {{.*#+}} ymm2 = -(ymm0 * ymm1) - ymm2
@@ -694,7 +694,7 @@ define <8 x float> @fmaddsubps_loop_256(i32 %iter, <8 x float> %a, <8 x float> %
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB18_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB18_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmaddsub231ps {{.*#+}} ymm2 = (ymm0 * ymm1) +/- ymm2
@@ -731,7 +731,7 @@ define <8 x float> @fmsubaddps_loop_256(i32 %iter, <8 x float> %a, <8 x float> %
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB19_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB19_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmsubadd231ps {{.*#+}} ymm2 = (ymm0 * ymm1) -/+ ymm2
@@ -768,7 +768,7 @@ define <8 x float> @fmaddps_loop_256(i32 %iter, <8 x float> %a, <8 x float> %b,
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB20_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB20_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmadd231ps {{.*#+}} ymm2 = (ymm0 * ymm1) + ymm2
@@ -805,7 +805,7 @@ define <8 x float> @fmsubps_loop_256(i32 %iter, <8 x float> %a, <8 x float> %b,
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB21_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB21_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfmsub231ps {{.*#+}} ymm2 = (ymm0 * ymm1) - ymm2
@@ -842,7 +842,7 @@ define <8 x float> @fnmaddps_loop_256(i32 %iter, <8 x float> %a, <8 x float> %b,
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB22_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB22_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfnmadd231ps {{.*#+}} ymm2 = -(ymm0 * ymm1) + ymm2
@@ -879,7 +879,7 @@ define <8 x float> @fnmsubps_loop_256(i32 %iter, <8 x float> %a, <8 x float> %b,
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    cmpl %edi, %eax
 ; CHECK-NEXT:    jge .LBB23_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB23_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vfnmsub231ps {{.*#+}} ymm2 = -(ymm0 * ymm1) - ymm2
diff --git a/llvm/test/CodeGen/X86/fold-call-3.ll b/llvm/test/CodeGen/X86/fold-call-3.ll
index 691f46b9eeb0ef..1db5cba8892d12 100644
--- a/llvm/test/CodeGen/X86/fold-call-3.ll
+++ b/llvm/test/CodeGen/X86/fold-call-3.ll
@@ -22,7 +22,7 @@ define void @_Z25RawPointerPerformanceTestPvRN5clang6ActionE(ptr %Val, ptr %Acti
 ; CHECK-NEXT:    movq %rsi, %rbx
 ; CHECK-NEXT:    movq %rdi, %rax
 ; CHECK-NEXT:    xorl %ebp, %ebp
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_2: ## %bb
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq (%rbx), %rcx
@@ -52,7 +52,7 @@ define void @_Z25RawPointerPerformanceTestPvRN5clang6ActionE(ptr %Val, ptr %Acti
 ; pre-RA-NEXT:    movq %rsi, %rbx
 ; pre-RA-NEXT:    movq %rdi, %rax
 ; pre-RA-NEXT:    xorl %ebp, %ebp
-; pre-RA-NEXT:    .p2align 4, 0x90
+; pre-RA-NEXT:    .p2align 4
 ; pre-RA-NEXT:  LBB0_2: ## %bb
 ; pre-RA-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; pre-RA-NEXT:    movq (%rbx), %rcx
diff --git a/llvm/test/CodeGen/X86/fold-loop-of-urem.ll b/llvm/test/CodeGen/X86/fold-loop-of-urem.ll
index c4b130a8b4e717..c1beb7c803b2b3 100644
--- a/llvm/test/CodeGen/X86/fold-loop-of-urem.ll
+++ b/llvm/test/CodeGen/X86/fold-loop-of-urem.ll
@@ -24,7 +24,7 @@ define void @simple_urem_to_sel(i32 %N, i32 %rem_amt) nounwind {
 ; CHECK-NEXT:    xorl %r15d, %r15d
 ; CHECK-NEXT:    xorl %r14d, %r14d
 ; CHECK-NEXT:    xorl %r12d, %r12d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r14d, %edi
@@ -71,7 +71,7 @@ define void @simple_urem_to_sel_fail_not_in_loop(i32 %N, i32 %rem_amt) nounwind
 ; CHECK-NEXT:  # %bb.3: # %for.body.preheader
 ; CHECK-NEXT:    movl %edi, %r14d
 ; CHECK-NEXT:    xorl %ebp, %ebp
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_4: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %ebp, %edi
@@ -129,7 +129,7 @@ define void @simple_urem_to_sel_inner_loop(i32 %N, i32 %M) nounwind {
 ; CHECK-NEXT:    xorl %r15d, %r15d
 ; CHECK-NEXT:    xorl %r13d, %r13d
 ; CHECK-NEXT:    jmp .LBB2_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB2_5: # %for.inner.cond.cleanup
 ; CHECK-NEXT:    # in Loop: Header=BB2_2 Depth=1
 ; CHECK-NEXT:    incl %r15d
@@ -147,7 +147,7 @@ define void @simple_urem_to_sel_inner_loop(i32 %N, i32 %M) nounwind {
 ; CHECK-NEXT:  # %bb.3: # %for.inner.body.preheader
 ; CHECK-NEXT:    # in Loop: Header=BB2_2 Depth=1
 ; CHECK-NEXT:    movl %r12d, %ebx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB2_4: # %for.inner.body
 ; CHECK-NEXT:    # Parent Loop BB2_2 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
@@ -208,7 +208,7 @@ define void @simple_urem_to_sel_inner_loop_fail_not_invariant(i32 %N, i32 %M) no
 ; CHECK-NEXT:    movl %edi, %ebp
 ; CHECK-NEXT:    xorl %r14d, %r14d
 ; CHECK-NEXT:    jmp .LBB3_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB3_5: # %for.inner.cond.cleanup
 ; CHECK-NEXT:    # in Loop: Header=BB3_2 Depth=1
 ; CHECK-NEXT:    incl %r14d
@@ -224,7 +224,7 @@ define void @simple_urem_to_sel_inner_loop_fail_not_invariant(i32 %N, i32 %M) no
 ; CHECK-NEXT:    # in Loop: Header=BB3_2 Depth=1
 ; CHECK-NEXT:    movl %eax, %r15d
 ; CHECK-NEXT:    movl %ebx, %r12d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB3_4: # %for.inner.body
 ; CHECK-NEXT:    # Parent Loop BB3_2 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
@@ -288,7 +288,7 @@ define void @simple_urem_to_sel_nested2(i32 %N, i32 %rem_amt) nounwind {
 ; CHECK-NEXT:    xorl %r14d, %r14d
 ; CHECK-NEXT:    xorl %r12d, %r12d
 ; CHECK-NEXT:    jmp .LBB4_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB4_5: # %for.body1
 ; CHECK-NEXT:    # in Loop: Header=BB4_2 Depth=1
 ; CHECK-NEXT:    movl %r14d, %edi
@@ -363,7 +363,7 @@ define void @simple_urem_fail_bad_incr3(i32 %N, i32 %rem_amt) nounwind {
 ; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    movl %esi, %ebx
 ; CHECK-NEXT:    jmp .LBB5_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB5_6: # %for.body1
 ; CHECK-NEXT:    # in Loop: Header=BB5_2 Depth=1
 ; CHECK-NEXT:    movl %ebp, %eax
@@ -392,7 +392,7 @@ define void @simple_urem_fail_bad_incr3(i32 %N, i32 %rem_amt) nounwind {
 ; CHECK-NEXT:    movl %eax, %ebp
 ; CHECK-NEXT:    incl %ebp
 ; CHECK-NEXT:    jmp .LBB5_6
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB5_5: # %for.body2
 ; CHECK-NEXT:    # in Loop: Header=BB5_2 Depth=1
 ; CHECK-NEXT:    xorl %ebp, %ebp
@@ -442,7 +442,7 @@ define void @simple_urem_to_sel_vec(<2 x i64> %rem_amt) nounwind {
 ; CHECK-NEXT:    pxor %xmm1, %xmm1
 ; CHECK-NEXT:    pxor %xmm0, %xmm0
 ; CHECK-NEXT:    movdqa %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB6_1: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movdqa %xmm1, (%rsp) # 16-byte Spill
@@ -496,7 +496,7 @@ define void @simple_urem_fail_bad_incr(i32 %N, i32 %rem_amt) nounwind {
 ; CHECK-NEXT:    movl %edi, %ebp
 ; CHECK-NEXT:    xorl %r14d, %r14d
 ; CHECK-NEXT:    jmp .LBB7_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB7_4: # %for.body.tail
 ; CHECK-NEXT:    # in Loop: Header=BB7_2 Depth=1
 ; CHECK-NEXT:    movl %r14d, %eax
@@ -566,7 +566,7 @@ define void @simple_urem_to_sel_second_acc(i32 %N, i32 %rem_amt) nounwind {
 ; CHECK-NEXT:    xorl %r12d, %r12d
 ; CHECK-NEXT:    xorl %r14d, %r14d
 ; CHECK-NEXT:    xorl %r13d, %r13d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB8_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r14d, %edi
@@ -618,7 +618,7 @@ define void @simple_urem_fail_srem(i32 %N, i32 %rem_amt) nounwind {
 ; CHECK-NEXT:    movl %esi, %ebx
 ; CHECK-NEXT:    movl %edi, %ebp
 ; CHECK-NEXT:    xorl %r14d, %r14d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB9_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r14d, %eax
@@ -663,7 +663,7 @@ define void @simple_urem_fail_missing_nuw(i32 %N, i32 %rem_amt) nounwind {
 ; CHECK-NEXT:    movl %esi, %ebx
 ; CHECK-NEXT:    movl %edi, %ebp
 ; CHECK-NEXT:    xorl %r14d, %r14d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB10_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r14d, %eax
@@ -708,7 +708,7 @@ define void @simple_urem_fail_bad_incr2(i32 %N, i32 %rem_amt) nounwind {
 ; CHECK-NEXT:    movl %esi, %ebx
 ; CHECK-NEXT:    movl %edi, %ebp
 ; CHECK-NEXT:    xorl %r14d, %r14d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB11_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r14d, %eax
@@ -753,7 +753,7 @@ define void @simple_urem_non_zero_entry4(i32 %N, i32 %rem_amt) nounwind {
 ; CHECK-NEXT:    movl %esi, %ebx
 ; CHECK-NEXT:    movl %edi, %ebp
 ; CHECK-NEXT:    movl $4, %r14d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB12_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r14d, %eax
@@ -799,7 +799,7 @@ define void @simple_urem_skip_const_rem_amt(i32 %N) nounwind {
 ; CHECK-NEXT:    addl $-4, %ebx
 ; CHECK-NEXT:    movl $4, %ebp
 ; CHECK-NEXT:    movl $2938661835, %r14d # imm = 0xAF286BCB
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB13_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %ebp, %eax
@@ -855,7 +855,7 @@ define void @simple_urem_fail_no_preheader_non_canonical(i32 %N, i32 %rem_amt) n
 ; CHECK-NEXT:    jmp .LBB14_3
 ; CHECK-NEXT:  .LBB14_1:
 ; CHECK-NEXT:    xorl %r14d, %r14d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB14_3: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r14d, %eax
@@ -913,7 +913,7 @@ define void @simple_urem_multi_latch_non_canonical(i32 %N, i32 %rem_amt) nounwin
 ; CHECK-NEXT:    xorl %r14d, %r14d
 ; CHECK-NEXT:    xorl %r13d, %r13d
 ; CHECK-NEXT:    jmp .LBB15_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB15_3: # %for.body.backedge
 ; CHECK-NEXT:    # in Loop: Header=BB15_2 Depth=1
 ; CHECK-NEXT:    incl %r14d
@@ -1038,7 +1038,7 @@ define void @simple_urem_fail_intermediate_inc(i32 %N, i32 %rem_amt) nounwind {
 ; CHECK-NEXT:    movl %edi, %r14d
 ; CHECK-NEXT:    negl %r14d
 ; CHECK-NEXT:    movl $1, %r15d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB17_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r15d, %eax
@@ -1078,7 +1078,7 @@ for.body:
 define void @weird_loop(i64 %sub.ptr.div.i56) personality ptr null {
 ; CHECK-LABEL: weird_loop:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB18_1: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB18_1
@@ -1107,7 +1107,7 @@ define void @simple_urem_to_sel_non_zero_start_fail(i32 %N, i32 %rem_amt) nounwi
 ; CHECK-NEXT:    movl %esi, %ebx
 ; CHECK-NEXT:    movl %edi, %ebp
 ; CHECK-NEXT:    movl $2, %r14d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB19_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r14d, %eax
@@ -1157,7 +1157,7 @@ define void @simple_urem_to_sel_non_zero_start_okay(i32 %N, i32 %rem_amt_in) nou
 ; CHECK-NEXT:    movl $2, %r14d
 ; CHECK-NEXT:    xorl %r15d, %r15d
 ; CHECK-NEXT:    movl $2, %r12d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB20_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r14d, %edi
@@ -1207,7 +1207,7 @@ define void @simple_urem_to_sel_non_zero_start_through_add(i32 %N, i32 %rem_amt_
 ; CHECK-NEXT:    orl $16, %ebx
 ; CHECK-NEXT:    negl %r14d
 ; CHECK-NEXT:    movl $7, %r15d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB21_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r15d, %eax
@@ -1259,7 +1259,7 @@ define void @simple_urem_to_sel_non_zero_start_through_add_fail_missing_nuw(i32
 ; CHECK-NEXT:    orl $16, %ebx
 ; CHECK-NEXT:    negl %r14d
 ; CHECK-NEXT:    movl $7, %r15d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB22_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r15d, %eax
@@ -1310,7 +1310,7 @@ define void @simple_urem_to_sel_non_zero_start_through_add_fail_no_simplify_rem(
 ; CHECK-NEXT:    movl %edi, %r14d
 ; CHECK-NEXT:    negl %r14d
 ; CHECK-NEXT:    movl $7, %r15d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB23_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r15d, %eax
@@ -1363,7 +1363,7 @@ define void @simple_urem_to_sel_non_zero_start_through_sub(i32 %N, i32 %rem_amt,
 ; CHECK-NEXT:    xorl %r15d, %r15d
 ; CHECK-NEXT:    xorl %r14d, %r14d
 ; CHECK-NEXT:    xorl %r12d, %r12d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB24_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r14d, %edi
@@ -1412,7 +1412,7 @@ define void @simple_urem_to_sel_non_zero_start_through_sub_no_simplfy(i32 %N, i3
 ; CHECK-NEXT:    movl %edi, %r14d
 ; CHECK-NEXT:    negl %r14d
 ; CHECK-NEXT:    addl $-2, %r15d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB25_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %r15d, %eax
diff --git a/llvm/test/CodeGen/X86/fp-une-cmp.ll b/llvm/test/CodeGen/X86/fp-une-cmp.ll
index f1b1732f9092cd..dd32f23d3b9cb4 100644
--- a/llvm/test/CodeGen/X86/fp-une-cmp.ll
+++ b/llvm/test/CodeGen/X86/fp-une-cmp.ll
@@ -109,7 +109,7 @@ define void @pr27750(ptr %b, float %x, i1 %y) {
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    xorps %xmm1, %xmm1
 ; CHECK-NEXT:    jmp .LBB3_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB3_3: # %for.end
 ; CHECK-NEXT:    # in Loop: Header=BB3_1 Depth=1
 ; CHECK-NEXT:    ucomiss %xmm1, %xmm0
diff --git a/llvm/test/CodeGen/X86/hoist-invariant-load.ll b/llvm/test/CodeGen/X86/hoist-invariant-load.ll
index ee23c922174d64..68e10c0c988710 100644
--- a/llvm/test/CodeGen/X86/hoist-invariant-load.ll
+++ b/llvm/test/CodeGen/X86/hoist-invariant-load.ll
@@ -43,7 +43,7 @@ define void @test(ptr %x) uwtable ssp {
 ; CHECK-NEXT:    movl $10000, %ebp ## imm = 0x2710
 ; CHECK-NEXT:    movq L_OBJC_SELECTOR_REFERENCES_(%rip), %r14
 ; CHECK-NEXT:    movq _objc_msgSend at GOTPCREL(%rip), %r15
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_1: ## %for.body
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rbx, %rdi
@@ -94,7 +94,7 @@ define void @test_unordered(ptr %x) uwtable ssp {
 ; CHECK-NEXT:    movl $10000, %ebp ## imm = 0x2710
 ; CHECK-NEXT:    movq L_OBJC_SELECTOR_REFERENCES_(%rip), %r14
 ; CHECK-NEXT:    movq _objc_msgSend at GOTPCREL(%rip), %r15
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB1_1: ## %for.body
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rbx, %rdi
@@ -139,7 +139,7 @@ define void @test_volatile(ptr %x) uwtable ssp {
 ; CHECK-NEXT:    movq %rdi, %rbx
 ; CHECK-NEXT:    movl $10000, %ebp ## imm = 0x2710
 ; CHECK-NEXT:    movq _objc_msgSend at GOTPCREL(%rip), %r14
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB2_1: ## %for.body
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq L_OBJC_SELECTOR_REFERENCES_(%rip), %rsi
@@ -182,7 +182,7 @@ define void @test_seq_cst(ptr %x) uwtable ssp {
 ; CHECK-NEXT:    movq %rdi, %rbx
 ; CHECK-NEXT:    movl $10000, %ebp ## imm = 0x2710
 ; CHECK-NEXT:    movq _objc_msgSend at GOTPCREL(%rip), %r14
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB3_1: ## %for.body
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq L_OBJC_SELECTOR_REFERENCES_(%rip), %rsi
@@ -219,7 +219,7 @@ define void @test_multi_def(ptr dereferenceable(8) align(8) %x1,
 ; CHECK-NEXT:    xorl %r8d, %r8d
 ; CHECK-NEXT:    movq (%rdi), %rdx
 ; CHECK-NEXT:    movq (%rsi), %rsi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB4_2: ## %for.body
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    mulxq %rsi, %r9, %rdi
@@ -267,7 +267,7 @@ define void @test_div_def(ptr dereferenceable(8) align(8) %x1,
 ; CHECK-NEXT:    xorl %r9d, %r9d
 ; CHECK-NEXT:    movl (%rdi), %edi
 ; CHECK-NEXT:    movl (%rsi), %esi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB5_2: ## %for.body
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %edi, %eax
diff --git a/llvm/test/CodeGen/X86/i128-mul.ll b/llvm/test/CodeGen/X86/i128-mul.ll
index 9f58ed08433485..cffd88c55bb0a9 100644
--- a/llvm/test/CodeGen/X86/i128-mul.ll
+++ b/llvm/test/CodeGen/X86/i128-mul.ll
@@ -115,7 +115,7 @@ define i64 @mul1(i64 %n, ptr nocapture %z, ptr nocapture %x, i64 %y) nounwind {
 ; X86-NOBMI-NEXT:    xorl %edx, %edx
 ; X86-NOBMI-NEXT:    xorl %ecx, %ecx
 ; X86-NOBMI-NEXT:    movl $0, (%esp) # 4-byte Folded Spill
-; X86-NOBMI-NEXT:    .p2align 4, 0x90
+; X86-NOBMI-NEXT:    .p2align 4
 ; X86-NOBMI-NEXT:  .LBB1_2: # %for.body
 ; X86-NOBMI-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NOBMI-NEXT:    movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -194,7 +194,7 @@ define i64 @mul1(i64 %n, ptr nocapture %z, ptr nocapture %x, i64 %y) nounwind {
 ; X86-BMI-NEXT:    xorl %eax, %eax
 ; X86-BMI-NEXT:    xorl %ebx, %ebx
 ; X86-BMI-NEXT:    xorl %ebp, %ebp
-; X86-BMI-NEXT:    .p2align 4, 0x90
+; X86-BMI-NEXT:    .p2align 4
 ; X86-BMI-NEXT:  .LBB1_2: # %for.body
 ; X86-BMI-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-BMI-NEXT:    movl %ecx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
@@ -263,7 +263,7 @@ define i64 @mul1(i64 %n, ptr nocapture %z, ptr nocapture %x, i64 %y) nounwind {
 ; X64-NOBMI-NEXT:    movq %rdx, %r8
 ; X64-NOBMI-NEXT:    xorl %r10d, %r10d
 ; X64-NOBMI-NEXT:    xorl %r9d, %r9d
-; X64-NOBMI-NEXT:    .p2align 4, 0x90
+; X64-NOBMI-NEXT:    .p2align 4
 ; X64-NOBMI-NEXT:  .LBB1_2: # %for.body
 ; X64-NOBMI-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NOBMI-NEXT:    movq %rcx, %rax
@@ -287,7 +287,7 @@ define i64 @mul1(i64 %n, ptr nocapture %z, ptr nocapture %x, i64 %y) nounwind {
 ; X64-BMI-NEXT:    movq %rdx, %rax
 ; X64-BMI-NEXT:    xorl %r9d, %r9d
 ; X64-BMI-NEXT:    xorl %r8d, %r8d
-; X64-BMI-NEXT:    .p2align 4, 0x90
+; X64-BMI-NEXT:    .p2align 4
 ; X64-BMI-NEXT:  .LBB1_2: # %for.body
 ; X64-BMI-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-BMI-NEXT:    movq %rcx, %rdx
diff --git a/llvm/test/CodeGen/X86/i386-shrink-wrapping.ll b/llvm/test/CodeGen/X86/i386-shrink-wrapping.ll
index d282a8f42622b2..7bb3bf42d3361b 100644
--- a/llvm/test/CodeGen/X86/i386-shrink-wrapping.ll
+++ b/llvm/test/CodeGen/X86/i386-shrink-wrapping.ll
@@ -30,7 +30,7 @@ define i32 @eflagsLiveInPrologue() #0 {
 ; ENABLE-NEXT:    movl (%eax), %eax
 ; ENABLE-NEXT:    testl %eax, %eax
 ; ENABLE-NEXT:    je LBB0_4
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  LBB0_3: ## %for.body
 ; ENABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; ENABLE-NEXT:    jmp LBB0_3
@@ -70,7 +70,7 @@ define i32 @eflagsLiveInPrologue() #0 {
 ; DISABLE-NEXT:    movl (%eax), %eax
 ; DISABLE-NEXT:    testl %eax, %eax
 ; DISABLE-NEXT:    je LBB0_4
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  LBB0_3: ## %for.body
 ; DISABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; DISABLE-NEXT:    jmp LBB0_3
diff --git a/llvm/test/CodeGen/X86/icmp-shift-opt.ll b/llvm/test/CodeGen/X86/icmp-shift-opt.ll
index 1673649f5c07b3..c52b3ed6c926dd 100644
--- a/llvm/test/CodeGen/X86/icmp-shift-opt.ll
+++ b/llvm/test/CodeGen/X86/icmp-shift-opt.ll
@@ -18,7 +18,7 @@ define i128 @opt_setcc_lt_power_of_2(i128 %a) nounwind {
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB0_1: # %loop
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    addl $1, %edi
@@ -47,7 +47,7 @@ define i128 @opt_setcc_lt_power_of_2(i128 %a) nounwind {
 ; X64:       # %bb.0:
 ; X64-NEXT:    movq %rsi, %rdx
 ; X64-NEXT:    movq %rdi, %rax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB0_1: # %loop
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    addq $1, %rax
diff --git a/llvm/test/CodeGen/X86/ifunc-asm.ll b/llvm/test/CodeGen/X86/ifunc-asm.ll
index 6cfd37604ff5e1..a4c47da7f4c657 100644
--- a/llvm/test/CodeGen/X86/ifunc-asm.ll
+++ b/llvm/test/CodeGen/X86/ifunc-asm.ll
@@ -8,7 +8,7 @@ entry:
 ; ELF:             .type foo_resolver, at function
 ; ELF-NEXT:    foo_resolver:
 
-; MACHO:           .p2align 4, 0x90
+; MACHO:           .p2align 4
 ; MACHO-NEXT:  _foo_resolver
 
 
@@ -23,10 +23,10 @@ entry:
 ; MACHO-NEXT:      .quad _foo_ifunc.stub_helper
 ; MACHO-NEXT:      .section __TEXT,__text,regular,pure_instructions
 ; MACHO-NEXT:      .globl _foo_ifunc
-; MACHO-NEXT:      .p2align 0, 0x90
+; MACHO-NEXT:      .p2align 0
 ; MACHO-NEXT:  _foo_ifunc:
 ; MACHO-NEXT:      jmpl   *_foo_ifunc.lazy_pointer(%rip)
-; MACHO-NEXT:      .p2align 0, 0x90
+; MACHO-NEXT:      .p2align 0
 ; MACHO-NEXT:  _foo_ifunc.stub_helper:
 ; MACHO-NEXT:      pushq   %rax
 ; MACHO-NEXT:      pushq   %rdi
diff --git a/llvm/test/CodeGen/X86/innermost-loop-alignment.ll b/llvm/test/CodeGen/X86/innermost-loop-alignment.ll
index 113d5bffe983be..482c8141b97ba7 100644
--- a/llvm/test/CodeGen/X86/innermost-loop-alignment.ll
+++ b/llvm/test/CodeGen/X86/innermost-loop-alignment.ll
@@ -25,12 +25,12 @@ define void @test(i32 %n, i32 %m) {
 ; DEFAULT-NEXT:    xorl %esi, %esi
 ; DEFAULT-NEXT:    movl {{[0-9]+}}(%esp), %edi
 ; DEFAULT-NEXT:    movl {{[0-9]+}}(%esp), %ebx
-; DEFAULT-NEXT:    .p2align 4, 0x90
+; DEFAULT-NEXT:    .p2align 4
 ; DEFAULT-NEXT:  .LBB0_1: # %outer
 ; DEFAULT-NEXT:    # =>This Loop Header: Depth=1
 ; DEFAULT-NEXT:    # Child Loop BB0_2 Depth 2
 ; DEFAULT-NEXT:    movl %edi, %ebp
-; DEFAULT-NEXT:    .p2align 4, 0x90
+; DEFAULT-NEXT:    .p2align 4
 ; DEFAULT-NEXT:  .LBB0_2: # %inner
 ; DEFAULT-NEXT:    # Parent Loop BB0_1 Depth=1
 ; DEFAULT-NEXT:    # => This Inner Loop Header: Depth=2
@@ -74,12 +74,12 @@ define void @test(i32 %n, i32 %m) {
 ; ALIGN32-NEXT:    xorl %esi, %esi
 ; ALIGN32-NEXT:    movl {{[0-9]+}}(%esp), %edi
 ; ALIGN32-NEXT:    movl {{[0-9]+}}(%esp), %ebx
-; ALIGN32-NEXT:    .p2align 4, 0x90
+; ALIGN32-NEXT:    .p2align 4
 ; ALIGN32-NEXT:  .LBB0_1: # %outer
 ; ALIGN32-NEXT:    # =>This Loop Header: Depth=1
 ; ALIGN32-NEXT:    # Child Loop BB0_2 Depth 2
 ; ALIGN32-NEXT:    movl %edi, %ebp
-; ALIGN32-NEXT:    .p2align 5, 0x90
+; ALIGN32-NEXT:    .p2align 5
 ; ALIGN32-NEXT:  .LBB0_2: # %inner
 ; ALIGN32-NEXT:    # Parent Loop BB0_1 Depth=1
 ; ALIGN32-NEXT:    # => This Inner Loop Header: Depth=2
@@ -123,12 +123,12 @@ define void @test(i32 %n, i32 %m) {
 ; ALIGN64-NEXT:    xorl %esi, %esi
 ; ALIGN64-NEXT:    movl {{[0-9]+}}(%esp), %edi
 ; ALIGN64-NEXT:    movl {{[0-9]+}}(%esp), %ebx
-; ALIGN64-NEXT:    .p2align 5, 0x90
+; ALIGN64-NEXT:    .p2align 5
 ; ALIGN64-NEXT:  .LBB0_1: # %outer
 ; ALIGN64-NEXT:    # =>This Loop Header: Depth=1
 ; ALIGN64-NEXT:    # Child Loop BB0_2 Depth 2
 ; ALIGN64-NEXT:    movl %edi, %ebp
-; ALIGN64-NEXT:    .p2align 6, 0x90
+; ALIGN64-NEXT:    .p2align 6
 ; ALIGN64-NEXT:  .LBB0_2: # %inner
 ; ALIGN64-NEXT:    # Parent Loop BB0_1 Depth=1
 ; ALIGN64-NEXT:    # => This Inner Loop Header: Depth=2
diff --git a/llvm/test/CodeGen/X86/ins_subreg_coalesce-3.ll b/llvm/test/CodeGen/X86/ins_subreg_coalesce-3.ll
index 3660741fef3641..296694ca3c72d4 100644
--- a/llvm/test/CodeGen/X86/ins_subreg_coalesce-3.ll
+++ b/llvm/test/CodeGen/X86/ins_subreg_coalesce-3.ll
@@ -23,7 +23,7 @@ define void @FontChange(i1 %foo) nounwind {
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    testb $1, %dil
 ; CHECK-NEXT:    je .LBB0_9
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb366
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb $1, %dil
@@ -31,7 +31,7 @@ define void @FontChange(i1 %foo) nounwind {
 ; CHECK-NEXT:  # %bb.2: # %bb428
 ; CHECK-NEXT:    testb $1, %dil
 ; CHECK-NEXT:    je .LBB0_9
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_3: # %bb650
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpb $0, 0
diff --git a/llvm/test/CodeGen/X86/issue76416.ll b/llvm/test/CodeGen/X86/issue76416.ll
index d0f7fe684a8401..7193e54a6ad553 100644
--- a/llvm/test/CodeGen/X86/issue76416.ll
+++ b/llvm/test/CodeGen/X86/issue76416.ll
@@ -12,7 +12,7 @@ define dso_local void @vga_load_state() #0 {
 ; CHECK-NEXT:    movl $0, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    cmpl $3, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    jg .LBB0_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    xorl %eax, %eax
@@ -23,7 +23,7 @@ define dso_local void @vga_load_state() #0 {
 ; CHECK-NEXT:    jle .LBB0_2
 ; CHECK-NEXT:  .LBB0_3: # %for.end
 ; CHECK-NEXT:    movl $0, -{{[0-9]+}}(%rsp)
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_4: # %for.cond1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    #APP
diff --git a/llvm/test/CodeGen/X86/kcfi-patchable-function-prefix.ll b/llvm/test/CodeGen/X86/kcfi-patchable-function-prefix.ll
index e5d541f8ed9d97..1b7bd7835e890c 100644
--- a/llvm/test/CodeGen/X86/kcfi-patchable-function-prefix.ll
+++ b/llvm/test/CodeGen/X86/kcfi-patchable-function-prefix.ll
@@ -1,6 +1,6 @@
 ; RUN: llc -mtriple=x86_64-unknown-linux-gnu -verify-machineinstrs < %s | FileCheck %s
 
-; CHECK:          .p2align 4, 0x90
+; CHECK:          .p2align 4
 ; CHECK-LABEL:    __cfi_f1:
 ; CHECK-COUNT-11:   nop
 ; CHECK-NEXT:       movl $12345678, %eax
@@ -13,7 +13,7 @@ define void @f1(ptr noundef %x) !kcfi_type !1 {
   ret void
 }
 
-; CHECK:          .p2align 4, 0x90
+; CHECK:          .p2align 4
 ; CHECK-NOT:      __cfi_f2:
 ; CHECK-NOT:        nop
 ; CHECK-LABEL:    f2:
@@ -23,7 +23,7 @@ define void @f2(ptr noundef %x) {
   ret void
 }
 
-; CHECK:          .p2align 4, 0x90
+; CHECK:          .p2align 4
 ; CHECK-LABEL:    __cfi_f3:
 ; CHECK-NOT:        nop
 ; CHECK-NEXT:       movl $12345678, %eax
@@ -35,7 +35,7 @@ define void @f3(ptr noundef %x) #0 !kcfi_type !1 {
   ret void
 }
 
-; CHECK:          .p2align 4, 0x90
+; CHECK:          .p2align 4
 ; CHECK-NOT:      __cfi_f4:
 ; CHECK-COUNT-16:   nop
 ; CHECK-LABEL:    f4:
diff --git a/llvm/test/CodeGen/X86/kcfi.ll b/llvm/test/CodeGen/X86/kcfi.ll
index 566a88b76c4fc9..059efcc71b0eb8 100644
--- a/llvm/test/CodeGen/X86/kcfi.ll
+++ b/llvm/test/CodeGen/X86/kcfi.ll
@@ -2,7 +2,7 @@
 ; RUN: llc -mtriple=x86_64-unknown-linux-gnu -verify-machineinstrs -stop-after=finalize-isel < %s | FileCheck %s --check-prefixes=MIR,ISEL
 ; RUN: llc -mtriple=x86_64-unknown-linux-gnu -verify-machineinstrs -stop-after=kcfi < %s | FileCheck %s --check-prefixes=MIR,KCFI
 
-; ASM:       .p2align 4, 0x90
+; ASM:       .p2align 4
 ; ASM:       .type __cfi_f1, at function
 ; ASM-LABEL: __cfi_f1:
 ; ASM-NEXT:    nop
diff --git a/llvm/test/CodeGen/X86/known-bits.ll b/llvm/test/CodeGen/X86/known-bits.ll
index f7b2538e1de2f7..58a0595e4322a4 100644
--- a/llvm/test/CodeGen/X86/known-bits.ll
+++ b/llvm/test/CodeGen/X86/known-bits.ll
@@ -14,13 +14,13 @@ define void @knownbits_zext_in_reg(ptr) nounwind {
 ; X86-NEXT:    shrl $14, %edx
 ; X86-NEXT:    movzbl %al, %ecx
 ; X86-NEXT:    xorl %ebx, %ebx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB0_1: # %CF
 ; X86-NEXT:    # =>This Loop Header: Depth=1
 ; X86-NEXT:    # Child Loop BB0_2 Depth 2
 ; X86-NEXT:    movl %ecx, %eax
 ; X86-NEXT:    divb %dl
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB0_2: # %CF237
 ; X86-NEXT:    # Parent Loop BB0_1 Depth=1
 ; X86-NEXT:    # => This Inner Loop Header: Depth=2
@@ -37,13 +37,13 @@ define void @knownbits_zext_in_reg(ptr) nounwind {
 ; X64-NEXT:    shrl $14, %edx
 ; X64-NEXT:    movzbl %cl, %ecx
 ; X64-NEXT:    xorl %esi, %esi
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB0_1: # %CF
 ; X64-NEXT:    # =>This Loop Header: Depth=1
 ; X64-NEXT:    # Child Loop BB0_2 Depth 2
 ; X64-NEXT:    movl %ecx, %eax
 ; X64-NEXT:    divb %dl
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB0_2: # %CF237
 ; X64-NEXT:    # Parent Loop BB0_1 Depth=1
 ; X64-NEXT:    # => This Inner Loop Header: Depth=2
diff --git a/llvm/test/CodeGen/X86/lea-opt-cse2.ll b/llvm/test/CodeGen/X86/lea-opt-cse2.ll
index 258a12a8b54e95..e39d01f1447f84 100644
--- a/llvm/test/CodeGen/X86/lea-opt-cse2.ll
+++ b/llvm/test/CodeGen/X86/lea-opt-cse2.ll
@@ -7,7 +7,7 @@
 define void @foo(ptr nocapture %ctx, i32 %n) local_unnamed_addr #0 {
 ; X64-LABEL: foo:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB0_1: # %loop
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl (%rdi), %eax
@@ -32,7 +32,7 @@ define void @foo(ptr nocapture %ctx, i32 %n) local_unnamed_addr #0 {
 ; X86-NEXT:    .cfi_offset %edi, -8
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB0_1: # %loop
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl (%eax), %edx
diff --git a/llvm/test/CodeGen/X86/lea-opt-cse4.ll b/llvm/test/CodeGen/X86/lea-opt-cse4.ll
index ef8e030d6caf22..4fa9acd99bb2fa 100644
--- a/llvm/test/CodeGen/X86/lea-opt-cse4.ll
+++ b/llvm/test/CodeGen/X86/lea-opt-cse4.ll
@@ -59,7 +59,7 @@ define void @foo(ptr nocapture %ctx, i32 %n) local_unnamed_addr #0 {
 define void @foo_loop(ptr nocapture %ctx, i32 %n) local_unnamed_addr #0 {
 ; X64-LABEL: foo_loop:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB1_1: # %loop
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl (%rdi), %ecx
@@ -88,7 +88,7 @@ define void @foo_loop(ptr nocapture %ctx, i32 %n) local_unnamed_addr #0 {
 ; X86-NEXT:    .cfi_offset %edi, -8
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB1_1: # %loop
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl (%eax), %esi
diff --git a/llvm/test/CodeGen/X86/licm-symbol.ll b/llvm/test/CodeGen/X86/licm-symbol.ll
index 2e62ed9c8f6d93..e6b3f34ee9bb69 100644
--- a/llvm/test/CodeGen/X86/licm-symbol.ll
+++ b/llvm/test/CodeGen/X86/licm-symbol.ll
@@ -6,7 +6,7 @@
 ; CHECK: pushl
 ; CHECK: movl  $176, %esi
 ; CHECK: addl  L___sF$non_lazy_ptr, %esi
-; CHECK: .p2align  4, 0x90
+; CHECK: .p2align  4
 
 target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128-n8:16:32"
 target triple = "i386-apple-darwin8"
diff --git a/llvm/test/CodeGen/X86/loop-search.ll b/llvm/test/CodeGen/X86/loop-search.ll
index 4646452ffdc653..0d5f97d21fb3ad 100644
--- a/llvm/test/CodeGen/X86/loop-search.ll
+++ b/llvm/test/CodeGen/X86/loop-search.ll
@@ -12,7 +12,7 @@ define zeroext i1 @search(i32 %needle, ptr nocapture readonly %haystack, i32 %co
 ; CHECK-NEXT:  ## %bb.1: ## %for.body.preheader
 ; CHECK-NEXT:    movslq %edx, %rax
 ; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_2: ## %for.body
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpl %edi, (%rsi,%rcx,4)
diff --git a/llvm/test/CodeGen/X86/loop-strength-reduce5.ll b/llvm/test/CodeGen/X86/loop-strength-reduce5.ll
index 8b512fc94f78ba..ebae51fa2aa468 100644
--- a/llvm/test/CodeGen/X86/loop-strength-reduce5.ll
+++ b/llvm/test/CodeGen/X86/loop-strength-reduce5.ll
@@ -13,7 +13,7 @@ define void @foo(i32 %N) nounwind {
 ; CHECK-NEXT:  # %bb.1: # %bb.preheader
 ; CHECK-NEXT:    xorl %ecx, %ecx
 ; CHECK-NEXT:    xorl %edx, %edx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %bb
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movw %dx, X
diff --git a/llvm/test/CodeGen/X86/loop-strength-reduce7.ll b/llvm/test/CodeGen/X86/loop-strength-reduce7.ll
index 3687194972f27f..11473bacc56cf5 100644
--- a/llvm/test/CodeGen/X86/loop-strength-reduce7.ll
+++ b/llvm/test/CodeGen/X86/loop-strength-reduce7.ll
@@ -13,13 +13,13 @@ define fastcc void @outer_loop(ptr nocapture %gfp, ptr nocapture %xr, i32 %targ_
 ; CHECK-NEXT:    pushl %esi
 ; CHECK-NEXT:    movl $88, %eax
 ; CHECK-NEXT:    movl $168, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_2: ## %bb28.i37
 ; CHECK-NEXT:    ## =>This Loop Header: Depth=1
 ; CHECK-NEXT:    ## Child Loop BB0_3 Depth 2
 ; CHECK-NEXT:    xorl %edx, %edx
 ; CHECK-NEXT:    movl %eax, %esi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_3: ## %bb29.i38
 ; CHECK-NEXT:    ## Parent Loop BB0_2 Depth=1
 ; CHECK-NEXT:    ## => This Inner Loop Header: Depth=2
diff --git a/llvm/test/CodeGen/X86/lsr-addrecloops.ll b/llvm/test/CodeGen/X86/lsr-addrecloops.ll
index 963405c8b0b3d3..98c8f587784c2d 100644
--- a/llvm/test/CodeGen/X86/lsr-addrecloops.ll
+++ b/llvm/test/CodeGen/X86/lsr-addrecloops.ll
@@ -16,7 +16,7 @@ define void @in4dob_(ptr nocapture writeonly %0, ptr nocapture readonly %1, ptr
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
 ; CHECK-NEXT:    jmp .LBB0_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_20: # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    incq %r10
 ; CHECK-NEXT:    addq %r9, %rax
@@ -46,7 +46,7 @@ define void @in4dob_(ptr nocapture writeonly %0, ptr nocapture readonly %1, ptr
 ; CHECK-NEXT:    andq $-8, %r10
 ; CHECK-NEXT:    xorl %r9d, %r9d
 ; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_6: # %vector.body807
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    leaq (%rdi,%r9), %r11
@@ -68,7 +68,7 @@ define void @in4dob_(ptr nocapture writeonly %0, ptr nocapture readonly %1, ptr
 ; CHECK-NEXT:    addq %rdi, %r9
 ; CHECK-NEXT:    xorl %r10d, %r10d
 ; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_9: # %vector.body807.epil
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    leaq (%r9,%r10), %r11
@@ -95,7 +95,7 @@ define void @in4dob_(ptr nocapture writeonly %0, ptr nocapture readonly %1, ptr
 ; CHECK-NEXT:    andq $-8, %rdx
 ; CHECK-NEXT:    xorl %ecx, %ecx
 ; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_14: # %vector.body847
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    leaq (%rdi,%rcx), %r8
@@ -117,7 +117,7 @@ define void @in4dob_(ptr nocapture writeonly %0, ptr nocapture readonly %1, ptr
 ; CHECK-NEXT:    leaq 96(%rcx,%rdi), %rcx
 ; CHECK-NEXT:    xorl %edx, %edx
 ; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_17: # %vector.body847.epil
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    leaq (%rcx,%rdx), %rdi
diff --git a/llvm/test/CodeGen/X86/lsr-interesting-step.ll b/llvm/test/CodeGen/X86/lsr-interesting-step.ll
index b15c8c42959984..049d2640d25dbd 100644
--- a/llvm/test/CodeGen/X86/lsr-interesting-step.ll
+++ b/llvm/test/CodeGen/X86/lsr-interesting-step.ll
@@ -10,12 +10,12 @@ define void @foo() nounwind {
 ; CHECK-LABEL: foo:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    movl $2, %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb7
 ; CHECK-NEXT:    # =>This Loop Header: Depth=1
 ; CHECK-NEXT:    # Child Loop BB0_2 Depth 2
 ; CHECK-NEXT:    movl $2, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %bb11
 ; CHECK-NEXT:    # Parent Loop BB0_1 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
diff --git a/llvm/test/CodeGen/X86/lsr-loop-exit-cond.ll b/llvm/test/CodeGen/X86/lsr-loop-exit-cond.ll
index 14dfc046c029a6..4cd206adc31de5 100644
--- a/llvm/test/CodeGen/X86/lsr-loop-exit-cond.ll
+++ b/llvm/test/CodeGen/X86/lsr-loop-exit-cond.ll
@@ -22,7 +22,7 @@ define void @t(ptr nocapture %in, ptr nocapture %out, ptr nocapture %rk, i32 %r)
 ; GENERIC-NEXT:    movq _Te1 at GOTPCREL(%rip), %rax
 ; GENERIC-NEXT:    movq _Te3 at GOTPCREL(%rip), %r10
 ; GENERIC-NEXT:    movq %rcx, %r11
-; GENERIC-NEXT:    .p2align 4, 0x90
+; GENERIC-NEXT:    .p2align 4
 ; GENERIC-NEXT:  LBB0_1: ## %bb
 ; GENERIC-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; GENERIC-NEXT:    movzbl %r8b, %r14d
@@ -105,7 +105,7 @@ define void @t(ptr nocapture %in, ptr nocapture %out, ptr nocapture %rk, i32 %r)
 ; ATOM-NEXT:    movq _Te3 at GOTPCREL(%rip), %r10
 ; ATOM-NEXT:    decl %ecx
 ; ATOM-NEXT:    movq %rcx, %r11
-; ATOM-NEXT:    .p2align 4, 0x90
+; ATOM-NEXT:    .p2align 4
 ; ATOM-NEXT:  LBB0_1: ## %bb
 ; ATOM-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; ATOM-NEXT:    movl %r15d, %ebx
@@ -315,7 +315,7 @@ define i32 @f(i32 %i, ptr nocapture %a) nounwind uwtable readonly ssp {
 ; GENERIC-NEXT:    leaq (%rsi,%rax,4), %rcx
 ; GENERIC-NEXT:    xorl %eax, %eax
 ; GENERIC-NEXT:    xorl %edx, %edx
-; GENERIC-NEXT:    .p2align 4, 0x90
+; GENERIC-NEXT:    .p2align 4
 ; GENERIC-NEXT:  LBB1_2: ## %for.body
 ; GENERIC-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; GENERIC-NEXT:    movl (%rcx), %esi
@@ -339,7 +339,7 @@ define i32 @f(i32 %i, ptr nocapture %a) nounwind uwtable readonly ssp {
 ; ATOM-NEXT:    xorl %edx, %edx
 ; ATOM-NEXT:    leaq (%rsi,%rax,4), %rcx
 ; ATOM-NEXT:    xorl %eax, %eax
-; ATOM-NEXT:    .p2align 4, 0x90
+; ATOM-NEXT:    .p2align 4
 ; ATOM-NEXT:  LBB1_2: ## %for.body
 ; ATOM-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; ATOM-NEXT:    movl (%rcx), %esi
diff --git a/llvm/test/CodeGen/X86/lsr-negative-stride.ll b/llvm/test/CodeGen/X86/lsr-negative-stride.ll
index 26c6128ab48db5..1d5e208f3a3268 100644
--- a/llvm/test/CodeGen/X86/lsr-negative-stride.ll
+++ b/llvm/test/CodeGen/X86/lsr-negative-stride.ll
@@ -23,12 +23,12 @@ define i32 @t(i32 %a, i32 %b) nounwind {
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    movl %edx, %eax
 ; CHECK-NEXT:    retl
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %bb.outer
 ; CHECK-NEXT:    # =>This Loop Header: Depth=1
 ; CHECK-NEXT:    # Child Loop BB0_3 Depth 2
 ; CHECK-NEXT:    movl %edx, %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_3: # %bb
 ; CHECK-NEXT:    # Parent Loop BB0_2 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
@@ -40,7 +40,7 @@ define i32 @t(i32 %a, i32 %b) nounwind {
 ; CHECK-NEXT:    movl %eax, %edx
 ; CHECK-NEXT:    jne .LBB0_3
 ; CHECK-NEXT:    jmp .LBB0_6
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_5: # %cond_false
 ; CHECK-NEXT:    # in Loop: Header=BB0_2 Depth=1
 ; CHECK-NEXT:    subl %edx, %ecx
diff --git a/llvm/test/CodeGen/X86/lsr-sort.ll b/llvm/test/CodeGen/X86/lsr-sort.ll
index 9c7f5efaf74eb7..37cb6f996d34fe 100644
--- a/llvm/test/CodeGen/X86/lsr-sort.ll
+++ b/llvm/test/CodeGen/X86/lsr-sort.ll
@@ -9,7 +9,7 @@ define dso_local i32 @foo(i32 %N) nounwind {
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    testl %edi, %edi
 ; CHECK-NEXT:    jle .LBB0_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movw %ax, X(%rip)
diff --git a/llvm/test/CodeGen/X86/lsr-static-addr.ll b/llvm/test/CodeGen/X86/lsr-static-addr.ll
index a06ead491bf7df..c67ac7d909fa7d 100644
--- a/llvm/test/CodeGen/X86/lsr-static-addr.ll
+++ b/llvm/test/CodeGen/X86/lsr-static-addr.ll
@@ -12,7 +12,7 @@ define void @foo(i64 %n) nounwind {
 ; CHECK-NEXT:  # %bb.1: # %for.body.preheader
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [2.2999999999999998E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
@@ -31,7 +31,7 @@ define void @foo(i64 %n) nounwind {
 ; ATOM-NEXT:  # %bb.1: # %for.body.preheader
 ; ATOM-NEXT:    xorl %eax, %eax
 ; ATOM-NEXT:    movsd {{.*#+}} xmm0 = [2.2999999999999998E+0,0.0E+0]
-; ATOM-NEXT:    .p2align 4, 0x90
+; ATOM-NEXT:    .p2align 4
 ; ATOM-NEXT:  .LBB0_2: # %for.body
 ; ATOM-NEXT:    # =>This Inner Loop Header: Depth=1
 ; ATOM-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
diff --git a/llvm/test/CodeGen/X86/machine-cp.ll b/llvm/test/CodeGen/X86/machine-cp.ll
index f84960485840d8..c84a1159ad56a6 100644
--- a/llvm/test/CodeGen/X86/machine-cp.ll
+++ b/llvm/test/CodeGen/X86/machine-cp.ll
@@ -11,7 +11,7 @@ define i32 @t1(i32 %a, i32 %b) nounwind  {
 ; CHECK-NEXT:    je LBB0_4
 ; CHECK-NEXT:  ## %bb.1: ## %while.body.preheader
 ; CHECK-NEXT:    movl %esi, %edx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_2: ## %while.body
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %edx, %ecx
@@ -62,7 +62,7 @@ define i32 @t3(i64 %a, i64 %b) nounwind  {
 ; CHECK-NEXT:    je LBB2_4
 ; CHECK-NEXT:  ## %bb.1: ## %while.body.preheader
 ; CHECK-NEXT:    movq %rsi, %rdx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB2_2: ## %while.body
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rdx, %rcx
diff --git a/llvm/test/CodeGen/X86/machine-cse.ll b/llvm/test/CodeGen/X86/machine-cse.ll
index 431031136e4a42..e953f67651d552 100644
--- a/llvm/test/CodeGen/X86/machine-cse.ll
+++ b/llvm/test/CodeGen/X86/machine-cse.ll
@@ -68,7 +68,7 @@ define void @commute(i32 %test_case, i32 %scale) nounwind ssp {
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    callq printf at PLT
 ; CHECK-NEXT:    addq $8, %rsp
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_3: # %for.body53.us
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB1_3
@@ -141,7 +141,7 @@ define ptr @bsd_memchr(ptr %s, i32 %a, i32 %c, i64 %n) nounwind ssp {
 ; CHECK-NEXT:  # %bb.1: # %preheader
 ; CHECK-NEXT:    movq %rdi, %rax
 ; CHECK-NEXT:    movzbl %dl, %edx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB3_2: # %do.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpl %edx, %esi
diff --git a/llvm/test/CodeGen/X86/madd.ll b/llvm/test/CodeGen/X86/madd.ll
index f3b117c626c8cd..bdb7c307a57590 100644
--- a/llvm/test/CodeGen/X86/madd.ll
+++ b/llvm/test/CodeGen/X86/madd.ll
@@ -12,7 +12,7 @@ define i32 @_Z10test_shortPsS_i_128(ptr nocapture readonly, ptr nocapture readon
 ; SSE2-NEXT:    pxor %xmm0, %xmm0
 ; SSE2-NEXT:    xorl %ecx, %ecx
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB0_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movq {{.*#+}} xmm2 = mem[0],zero
@@ -37,7 +37,7 @@ define i32 @_Z10test_shortPsS_i_128(ptr nocapture readonly, ptr nocapture readon
 ; AVX-NEXT:    movl %edx, %eax
 ; AVX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX-NEXT:    xorl %ecx, %ecx
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB0_1: # %vector.body
 ; AVX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    vpmovzxwd {{.*#+}} xmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
@@ -91,7 +91,7 @@ define i32 @_Z10test_shortPsS_i_256(ptr nocapture readonly, ptr nocapture readon
 ; SSE2-NEXT:    pxor %xmm0, %xmm0
 ; SSE2-NEXT:    xorl %ecx, %ecx
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB1_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqu (%rdi,%rcx,2), %xmm2
@@ -115,7 +115,7 @@ define i32 @_Z10test_shortPsS_i_256(ptr nocapture readonly, ptr nocapture readon
 ; AVX1-NEXT:    movl %edx, %eax
 ; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    xorl %ecx, %ecx
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB1_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vmovdqu (%rsi,%rcx,2), %xmm1
@@ -141,7 +141,7 @@ define i32 @_Z10test_shortPsS_i_256(ptr nocapture readonly, ptr nocapture readon
 ; AVX256-NEXT:    movl %edx, %eax
 ; AVX256-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX256-NEXT:    xorl %ecx, %ecx
-; AVX256-NEXT:    .p2align 4, 0x90
+; AVX256-NEXT:    .p2align 4
 ; AVX256-NEXT:  .LBB1_1: # %vector.body
 ; AVX256-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX256-NEXT:    vmovdqu (%rsi,%rcx,2), %xmm1
@@ -200,7 +200,7 @@ define i32 @_Z10test_shortPsS_i_512(ptr nocapture readonly, ptr nocapture readon
 ; SSE2-NEXT:    xorl %ecx, %ecx
 ; SSE2-NEXT:    pxor %xmm2, %xmm2
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB2_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqu (%rdi,%rcx,2), %xmm3
@@ -231,7 +231,7 @@ define i32 @_Z10test_shortPsS_i_512(ptr nocapture readonly, ptr nocapture readon
 ; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    xorl %ecx, %ecx
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB2_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vmovdqu (%rsi,%rcx,2), %xmm2
@@ -265,7 +265,7 @@ define i32 @_Z10test_shortPsS_i_512(ptr nocapture readonly, ptr nocapture readon
 ; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX2-NEXT:    xorl %ecx, %ecx
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB2_1: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vmovdqu (%rsi,%rcx,2), %ymm2
@@ -291,7 +291,7 @@ define i32 @_Z10test_shortPsS_i_512(ptr nocapture readonly, ptr nocapture readon
 ; AVX512-NEXT:    movl %edx, %eax
 ; AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512-NEXT:    xorl %ecx, %ecx
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB2_1: # %vector.body
 ; AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vmovdqu (%rsi,%rcx,2), %ymm1
@@ -356,7 +356,7 @@ define i32 @_Z10test_shortPsS_i_1024(ptr nocapture readonly, ptr nocapture reado
 ; SSE2-NEXT:    pxor %xmm4, %xmm4
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
 ; SSE2-NEXT:    pxor %xmm3, %xmm3
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB3_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqu (%rdi,%rcx,2), %xmm5
@@ -400,7 +400,7 @@ define i32 @_Z10test_shortPsS_i_1024(ptr nocapture readonly, ptr nocapture reado
 ; AVX1-NEXT:    xorl %ecx, %ecx
 ; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB3_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vmovdqu (%rsi,%rcx,2), %xmm3
@@ -448,7 +448,7 @@ define i32 @_Z10test_shortPsS_i_1024(ptr nocapture readonly, ptr nocapture reado
 ; AVX2-NEXT:    xorl %ecx, %ecx
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB3_1: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vmovdqu (%rsi,%rcx,2), %ymm3
@@ -480,7 +480,7 @@ define i32 @_Z10test_shortPsS_i_1024(ptr nocapture readonly, ptr nocapture reado
 ; AVX512F-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512F-NEXT:    xorl %ecx, %ecx
 ; AVX512F-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX512F-NEXT:    .p2align 4, 0x90
+; AVX512F-NEXT:    .p2align 4
 ; AVX512F-NEXT:  .LBB3_1: # %vector.body
 ; AVX512F-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512F-NEXT:    vmovdqu (%rsi,%rcx,2), %ymm2
@@ -512,7 +512,7 @@ define i32 @_Z10test_shortPsS_i_1024(ptr nocapture readonly, ptr nocapture reado
 ; AVX512BW-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512BW-NEXT:    xorl %ecx, %ecx
 ; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX512BW-NEXT:    .p2align 4, 0x90
+; AVX512BW-NEXT:    .p2align 4
 ; AVX512BW-NEXT:  .LBB3_1: # %vector.body
 ; AVX512BW-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512BW-NEXT:    vmovdqu64 (%rsi,%rcx,2), %zmm2
@@ -576,7 +576,7 @@ define i32 @_Z9test_charPcS_i_128(ptr nocapture readonly, ptr nocapture readonly
 ; SSE2-NEXT:    movl %edx, %eax
 ; SSE2-NEXT:    pxor %xmm0, %xmm0
 ; SSE2-NEXT:    xorl %ecx, %ecx
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB4_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
@@ -605,7 +605,7 @@ define i32 @_Z9test_charPcS_i_128(ptr nocapture readonly, ptr nocapture readonly
 ; AVX-NEXT:    movl %edx, %eax
 ; AVX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX-NEXT:    xorl %ecx, %ecx
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB4_1: # %vector.body
 ; AVX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    vpmovsxbd (%rdi,%rcx), %xmm1
@@ -659,7 +659,7 @@ define i32 @_Z9test_charPcS_i_256(ptr nocapture readonly, ptr nocapture readonly
 ; SSE2-NEXT:    pxor %xmm0, %xmm0
 ; SSE2-NEXT:    xorl %ecx, %ecx
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB5_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movq {{.*#+}} xmm2 = mem[0],zero
@@ -687,7 +687,7 @@ define i32 @_Z9test_charPcS_i_256(ptr nocapture readonly, ptr nocapture readonly
 ; AVX1-NEXT:    movl %edx, %eax
 ; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    xorl %ecx, %ecx
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB5_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vpmovsxbw (%rdi,%rcx), %xmm1
@@ -714,7 +714,7 @@ define i32 @_Z9test_charPcS_i_256(ptr nocapture readonly, ptr nocapture readonly
 ; AVX256-NEXT:    movl %edx, %eax
 ; AVX256-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX256-NEXT:    xorl %ecx, %ecx
-; AVX256-NEXT:    .p2align 4, 0x90
+; AVX256-NEXT:    .p2align 4
 ; AVX256-NEXT:  .LBB5_1: # %vector.body
 ; AVX256-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX256-NEXT:    vpmovsxbw (%rdi,%rcx), %xmm1
@@ -774,7 +774,7 @@ define i32 @_Z9test_charPcS_i_512(ptr nocapture readonly, ptr nocapture readonly
 ; SSE2-NEXT:    xorl %ecx, %ecx
 ; SSE2-NEXT:    pxor %xmm2, %xmm2
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB6_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqu (%rdi,%rcx), %xmm3
@@ -811,7 +811,7 @@ define i32 @_Z9test_charPcS_i_512(ptr nocapture readonly, ptr nocapture readonly
 ; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    xorl %ecx, %ecx
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB6_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vpmovsxbw 8(%rdi,%rcx), %xmm2
@@ -847,7 +847,7 @@ define i32 @_Z9test_charPcS_i_512(ptr nocapture readonly, ptr nocapture readonly
 ; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX2-NEXT:    xorl %ecx, %ecx
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB6_1: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vpmovsxbw (%rdi,%rcx), %ymm2
@@ -874,7 +874,7 @@ define i32 @_Z9test_charPcS_i_512(ptr nocapture readonly, ptr nocapture readonly
 ; AVX512-NEXT:    movl %edx, %eax
 ; AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512-NEXT:    xorl %ecx, %ecx
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB6_1: # %vector.body
 ; AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vpmovsxbw (%rdi,%rcx), %ymm1
@@ -940,7 +940,7 @@ define i32 @_Z9test_charPcS_i_1024(ptr nocapture readonly, ptr nocapture readonl
 ; SSE2-NEXT:    pxor %xmm4, %xmm4
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
 ; SSE2-NEXT:    pxor %xmm3, %xmm3
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB7_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqu (%rdi,%rcx), %xmm7
@@ -996,7 +996,7 @@ define i32 @_Z9test_charPcS_i_1024(ptr nocapture readonly, ptr nocapture readonl
 ; AVX1-NEXT:    xorl %ecx, %ecx
 ; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB7_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vpmovsxbw 24(%rdi,%rcx), %xmm3
@@ -1048,7 +1048,7 @@ define i32 @_Z9test_charPcS_i_1024(ptr nocapture readonly, ptr nocapture readonl
 ; AVX2-NEXT:    xorl %ecx, %ecx
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB7_1: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vpmovsxbw 16(%rdi,%rcx), %ymm3
@@ -1082,7 +1082,7 @@ define i32 @_Z9test_charPcS_i_1024(ptr nocapture readonly, ptr nocapture readonl
 ; AVX512F-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512F-NEXT:    xorl %ecx, %ecx
 ; AVX512F-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX512F-NEXT:    .p2align 4, 0x90
+; AVX512F-NEXT:    .p2align 4
 ; AVX512F-NEXT:  .LBB7_1: # %vector.body
 ; AVX512F-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512F-NEXT:    vpmovsxbw (%rdi,%rcx), %ymm2
@@ -1116,7 +1116,7 @@ define i32 @_Z9test_charPcS_i_1024(ptr nocapture readonly, ptr nocapture readonl
 ; AVX512BW-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512BW-NEXT:    xorl %ecx, %ecx
 ; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX512BW-NEXT:    .p2align 4, 0x90
+; AVX512BW-NEXT:    .p2align 4
 ; AVX512BW-NEXT:  .LBB7_1: # %vector.body
 ; AVX512BW-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512BW-NEXT:    vpmovsxbw (%rdi,%rcx), %zmm2
@@ -1181,7 +1181,7 @@ define i32 @test_unsigned_short_128(ptr nocapture readonly, ptr nocapture readon
 ; SSE2-NEXT:    movl %edx, %eax
 ; SSE2-NEXT:    pxor %xmm0, %xmm0
 ; SSE2-NEXT:    xorl %ecx, %ecx
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB8_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movq {{.*#+}} xmm1 = mem[0],zero
@@ -1207,7 +1207,7 @@ define i32 @test_unsigned_short_128(ptr nocapture readonly, ptr nocapture readon
 ; AVX-NEXT:    movl %edx, %eax
 ; AVX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX-NEXT:    xorl %ecx, %ecx
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB8_1: # %vector.body
 ; AVX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    vpmovzxwd {{.*#+}} xmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
@@ -1261,7 +1261,7 @@ define i32 @test_unsigned_short_256(ptr nocapture readonly, ptr nocapture readon
 ; SSE2-NEXT:    pxor %xmm0, %xmm0
 ; SSE2-NEXT:    xorl %ecx, %ecx
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB9_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqu (%rdi,%rcx,2), %xmm2
@@ -1291,7 +1291,7 @@ define i32 @test_unsigned_short_256(ptr nocapture readonly, ptr nocapture readon
 ; AVX1-NEXT:    movl %edx, %eax
 ; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    xorl %ecx, %ecx
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB9_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
@@ -1323,7 +1323,7 @@ define i32 @test_unsigned_short_256(ptr nocapture readonly, ptr nocapture readon
 ; AVX256-NEXT:    movl %edx, %eax
 ; AVX256-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX256-NEXT:    xorl %ecx, %ecx
-; AVX256-NEXT:    .p2align 4, 0x90
+; AVX256-NEXT:    .p2align 4
 ; AVX256-NEXT:  .LBB9_1: # %vector.body
 ; AVX256-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX256-NEXT:    vpmovzxwd {{.*#+}} ymm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
@@ -1384,7 +1384,7 @@ define i32 @test_unsigned_short_512(ptr nocapture readonly, ptr nocapture readon
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
 ; SSE2-NEXT:    pxor %xmm3, %xmm3
 ; SSE2-NEXT:    pxor %xmm2, %xmm2
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB10_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqu (%rdi,%rcx,2), %xmm4
@@ -1427,7 +1427,7 @@ define i32 @test_unsigned_short_512(ptr nocapture readonly, ptr nocapture readon
 ; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    xorl %ecx, %ecx
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB10_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
@@ -1473,7 +1473,7 @@ define i32 @test_unsigned_short_512(ptr nocapture readonly, ptr nocapture readon
 ; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX2-NEXT:    xorl %ecx, %ecx
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB10_1: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
@@ -1504,7 +1504,7 @@ define i32 @test_unsigned_short_512(ptr nocapture readonly, ptr nocapture readon
 ; AVX512-NEXT:    movl %edx, %eax
 ; AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512-NEXT:    xorl %ecx, %ecx
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB10_1: # %vector.body
 ; AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vpmovzxwd {{.*#+}} zmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
@@ -1573,7 +1573,7 @@ define i32 @test_unsigned_short_1024(ptr nocapture readonly, ptr nocapture reado
 ; SSE2-NEXT:    pxor %xmm6, %xmm6
 ; SSE2-NEXT:    pxor %xmm5, %xmm5
 ; SSE2-NEXT:    pxor %xmm7, %xmm7
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB11_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqu 48(%rdi,%rcx,2), %xmm8
@@ -1642,7 +1642,7 @@ define i32 @test_unsigned_short_1024(ptr nocapture readonly, ptr nocapture reado
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
 ; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB11_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vpmovzxwd {{.*#+}} xmm4 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
@@ -1716,7 +1716,7 @@ define i32 @test_unsigned_short_1024(ptr nocapture readonly, ptr nocapture reado
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
 ; AVX2-NEXT:    vpxor %xmm3, %xmm3, %xmm3
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB11_1: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vpmovzxwd {{.*#+}} ymm4 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
@@ -1758,7 +1758,7 @@ define i32 @test_unsigned_short_1024(ptr nocapture readonly, ptr nocapture reado
 ; AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512-NEXT:    xorl %ecx, %ecx
 ; AVX512-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB11_1: # %vector.body
 ; AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vpmovzxwd {{.*#+}} zmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero,mem[8],zero,mem[9],zero,mem[10],zero,mem[11],zero,mem[12],zero,mem[13],zero,mem[14],zero,mem[15],zero
@@ -2742,7 +2742,7 @@ define i64 @sum_and_sum_of_squares(ptr %a, i32 %n) {
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
 ; SSE2-NEXT:    pxor %xmm2, %xmm2
 ; SSE2-NEXT:    pxor %xmm3, %xmm3
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB33_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movq {{.*#+}} xmm4 = mem[0],zero
@@ -2780,7 +2780,7 @@ define i64 @sum_and_sum_of_squares(ptr %a, i32 %n) {
 ; AVX1-NEXT:    movl %esi, %eax
 ; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB33_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vpmovzxbd {{.*#+}} xmm2 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
@@ -2823,7 +2823,7 @@ define i64 @sum_and_sum_of_squares(ptr %a, i32 %n) {
 ; AVX256-NEXT:    movl %esi, %eax
 ; AVX256-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX256-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX256-NEXT:    .p2align 4, 0x90
+; AVX256-NEXT:    .p2align 4
 ; AVX256-NEXT:  .LBB33_1: # %vector.body
 ; AVX256-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX256-NEXT:    vpmovzxbd {{.*#+}} ymm2 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero
@@ -2900,7 +2900,7 @@ define i32 @sum_of_square_differences(ptr %a, ptr %b, i32 %n) {
 ; SSE2-NEXT:    pxor %xmm0, %xmm0
 ; SSE2-NEXT:    xorl %ecx, %ecx
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB34_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movq {{.*#+}} xmm2 = mem[0],zero
@@ -2927,7 +2927,7 @@ define i32 @sum_of_square_differences(ptr %a, ptr %b, i32 %n) {
 ; AVX1-NEXT:    movl %edx, %eax
 ; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    xorl %ecx, %ecx
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB34_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vpmovzxbw {{.*#+}} xmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
@@ -2955,7 +2955,7 @@ define i32 @sum_of_square_differences(ptr %a, ptr %b, i32 %n) {
 ; AVX256-NEXT:    movl %edx, %eax
 ; AVX256-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX256-NEXT:    xorl %ecx, %ecx
-; AVX256-NEXT:    .p2align 4, 0x90
+; AVX256-NEXT:    .p2align 4
 ; AVX256-NEXT:  .LBB34_1: # %vector.body
 ; AVX256-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX256-NEXT:    vpmovzxbw {{.*#+}} xmm1 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
@@ -3105,7 +3105,7 @@ define i32 @add_used_by_loop_phi(ptr %a, ptr %b, i64 %offset_a, i64 %offset_b, i
 ; SSE2-NEXT:    xorl %eax, %eax
 ; SSE2-NEXT:    pxor %xmm2, %xmm2
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB38_1: # %loop
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqu (%rdi,%rax), %xmm3
@@ -3143,7 +3143,7 @@ define i32 @add_used_by_loop_phi(ptr %a, ptr %b, i64 %offset_a, i64 %offset_b, i
 ; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    xorl %eax, %eax
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB38_1: # %loop
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vpmovsxbw 8(%rdi,%rax), %xmm2
@@ -3180,7 +3180,7 @@ define i32 @add_used_by_loop_phi(ptr %a, ptr %b, i64 %offset_a, i64 %offset_b, i
 ; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX2-NEXT:    xorl %eax, %eax
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB38_1: # %loop
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vpmovsxbw (%rdi,%rax), %ymm2
@@ -3208,7 +3208,7 @@ define i32 @add_used_by_loop_phi(ptr %a, ptr %b, i64 %offset_a, i64 %offset_b, i
 ; AVX512-NEXT:    addq %rcx, %rsi
 ; AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512-NEXT:    xorl %eax, %eax
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB38_1: # %loop
 ; AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vpmovsxbw (%rdi,%rax), %ymm1
diff --git a/llvm/test/CodeGen/X86/masked-iv-safe.ll b/llvm/test/CodeGen/X86/masked-iv-safe.ll
index 4e4ad3a0161e03..a4f5e52a27d8a7 100644
--- a/llvm/test/CodeGen/X86/masked-iv-safe.ll
+++ b/llvm/test/CodeGen/X86/masked-iv-safe.ll
@@ -11,7 +11,7 @@ define void @count_up(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movsd {{.*#+}} xmm3 = mem[0],zero
@@ -57,7 +57,7 @@ define void @count_down(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movsd {{.*#+}} xmm3 = mem[0],zero
@@ -103,7 +103,7 @@ define void @count_up_signed(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB2_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movsd {{.*#+}} xmm3 = mem[0],zero
@@ -151,7 +151,7 @@ define void @count_down_signed(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB3_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movsd {{.*#+}} xmm3 = mem[0],zero
@@ -199,7 +199,7 @@ define void @another_count_up(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB4_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movsd {{.*#+}} xmm3 = mem[0],zero
@@ -251,7 +251,7 @@ define void @another_count_down(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
 ; CHECK-NEXT:    movq %rdi, %rcx
 ; CHECK-NEXT:    movq %rdi, %rdx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB5_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movsd {{.*#+}} xmm3 = mem[0],zero
@@ -303,7 +303,7 @@ define void @another_count_up_signed(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB6_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movsd {{.*#+}} xmm3 = mem[0],zero
@@ -351,7 +351,7 @@ define void @another_count_down_signed(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB7_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movsd {{.*#+}} xmm3 = mem[0],zero
diff --git a/llvm/test/CodeGen/X86/masked-iv-unsafe.ll b/llvm/test/CodeGen/X86/masked-iv-unsafe.ll
index f10db3424c2ea0..42bd6e9b754477 100644
--- a/llvm/test/CodeGen/X86/masked-iv-unsafe.ll
+++ b/llvm/test/CodeGen/X86/masked-iv-unsafe.ll
@@ -11,7 +11,7 @@ define void @count_up(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movzbl %al, %ecx
@@ -64,7 +64,7 @@ define void @count_down(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movzbl %al, %ecx
@@ -120,7 +120,7 @@ define void @count_up_signed(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB2_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rdx, %rsi
@@ -180,7 +180,7 @@ define void @count_down_signed(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB3_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rdx, %rsi
@@ -238,7 +238,7 @@ define void @another_count_up(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB4_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movzbl %al, %ecx
@@ -291,7 +291,7 @@ define void @another_count_down(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB5_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movzbl %sil, %eax
@@ -347,7 +347,7 @@ define void @another_count_up_signed(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
 ; CHECK-NEXT:    xorl %ecx, %ecx
 ; CHECK-NEXT:    movq %rdi, %rdx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB6_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rax, %r8
@@ -409,7 +409,7 @@ define void @another_count_down_signed(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB7_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rsi, %rdx
@@ -469,7 +469,7 @@ define void @yet_another_count_down(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
 ; CHECK-NEXT:    movq %rdi, %rcx
 ; CHECK-NEXT:    movq %rdi, %rdx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB8_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movsd {{.*#+}} xmm3 = mem[0],zero
@@ -521,7 +521,7 @@ define void @yet_another_count_up(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB9_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movzbl %al, %ecx
@@ -575,7 +575,7 @@ define void @still_another_count_down(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB10_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movzbl %al, %ecx
@@ -630,7 +630,7 @@ define void @yet_another_count_up_signed(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
 ; CHECK-NEXT:    xorl %edx, %edx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB11_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rcx, %rsi
@@ -690,7 +690,7 @@ define void @yet_another_count_down_signed(ptr %d, i64 %n) nounwind {
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [1.0000000000000001E-1,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = [2.2999999999999998E+0,0.0E+0]
 ; CHECK-NEXT:    movsd {{.*#+}} xmm2 = [4.5E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB12_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rdx, %rsi
diff --git a/llvm/test/CodeGen/X86/merge_store.ll b/llvm/test/CodeGen/X86/merge_store.ll
index 1cf3b9a83bac13..afe0ef969a40e7 100644
--- a/llvm/test/CodeGen/X86/merge_store.ll
+++ b/llvm/test/CodeGen/X86/merge_store.ll
@@ -6,7 +6,7 @@ define void @merge_store(ptr nocapture %a) {
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    movabsq $4294967297, %rcx # imm = 0x100000001
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rcx, (%rdi,%rax,4)
diff --git a/llvm/test/CodeGen/X86/min-legal-vector-width.ll b/llvm/test/CodeGen/X86/min-legal-vector-width.ll
index 1413a19b349357..e3d2ac659d4386 100644
--- a/llvm/test/CodeGen/X86/min-legal-vector-width.ll
+++ b/llvm/test/CodeGen/X86/min-legal-vector-width.ll
@@ -177,7 +177,7 @@ define dso_local i32 @_Z9test_charPcS_i_256(ptr nocapture readonly, ptr nocaptur
 ; CHECK-SKX-NEXT:    xorl %ecx, %ecx
 ; CHECK-SKX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; CHECK-SKX-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; CHECK-SKX-NEXT:    .p2align 4, 0x90
+; CHECK-SKX-NEXT:    .p2align 4
 ; CHECK-SKX-NEXT:  .LBB8_1: # %vector.body
 ; CHECK-SKX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-SKX-NEXT:    vpmovsxbw 16(%rdi,%rcx), %ymm3
@@ -212,7 +212,7 @@ define dso_local i32 @_Z9test_charPcS_i_256(ptr nocapture readonly, ptr nocaptur
 ; CHECK-AVX512-NEXT:    xorl %ecx, %ecx
 ; CHECK-AVX512-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; CHECK-AVX512-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; CHECK-AVX512-NEXT:    .p2align 4, 0x90
+; CHECK-AVX512-NEXT:    .p2align 4
 ; CHECK-AVX512-NEXT:  .LBB8_1: # %vector.body
 ; CHECK-AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-AVX512-NEXT:    vpmovsxbw 16(%rdi,%rcx), %ymm3
@@ -247,7 +247,7 @@ define dso_local i32 @_Z9test_charPcS_i_256(ptr nocapture readonly, ptr nocaptur
 ; CHECK-VBMI-NEXT:    xorl %ecx, %ecx
 ; CHECK-VBMI-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; CHECK-VBMI-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; CHECK-VBMI-NEXT:    .p2align 4, 0x90
+; CHECK-VBMI-NEXT:    .p2align 4
 ; CHECK-VBMI-NEXT:  .LBB8_1: # %vector.body
 ; CHECK-VBMI-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-VBMI-NEXT:    vpmovsxbw 16(%rdi,%rcx), %ymm3
@@ -317,7 +317,7 @@ define dso_local i32 @_Z9test_charPcS_i_512(ptr nocapture readonly, ptr nocaptur
 ; CHECK-SKX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; CHECK-SKX-NEXT:    xorl %ecx, %ecx
 ; CHECK-SKX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; CHECK-SKX-NEXT:    .p2align 4, 0x90
+; CHECK-SKX-NEXT:    .p2align 4
 ; CHECK-SKX-NEXT:  .LBB9_1: # %vector.body
 ; CHECK-SKX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-SKX-NEXT:    vpmovsxbw (%rdi,%rcx), %zmm2
@@ -347,7 +347,7 @@ define dso_local i32 @_Z9test_charPcS_i_512(ptr nocapture readonly, ptr nocaptur
 ; CHECK-AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; CHECK-AVX512-NEXT:    xorl %ecx, %ecx
 ; CHECK-AVX512-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; CHECK-AVX512-NEXT:    .p2align 4, 0x90
+; CHECK-AVX512-NEXT:    .p2align 4
 ; CHECK-AVX512-NEXT:  .LBB9_1: # %vector.body
 ; CHECK-AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-AVX512-NEXT:    vpmovsxbw (%rdi,%rcx), %zmm2
@@ -377,7 +377,7 @@ define dso_local i32 @_Z9test_charPcS_i_512(ptr nocapture readonly, ptr nocaptur
 ; CHECK-VBMI-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; CHECK-VBMI-NEXT:    xorl %ecx, %ecx
 ; CHECK-VBMI-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; CHECK-VBMI-NEXT:    .p2align 4, 0x90
+; CHECK-VBMI-NEXT:    .p2align 4
 ; CHECK-VBMI-NEXT:  .LBB9_1: # %vector.body
 ; CHECK-VBMI-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-VBMI-NEXT:    vpmovsxbw (%rdi,%rcx), %zmm2
@@ -445,7 +445,7 @@ define dso_local i32 @sad_16i8_256() "min-legal-vector-width"="256" {
 ; CHECK-SKX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; CHECK-SKX-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; CHECK-SKX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; CHECK-SKX-NEXT:    .p2align 4, 0x90
+; CHECK-SKX-NEXT:    .p2align 4
 ; CHECK-SKX-NEXT:  .LBB10_1: # %vector.body
 ; CHECK-SKX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-SKX-NEXT:    vmovdqu a+1024(%rax), %xmm2
@@ -470,7 +470,7 @@ define dso_local i32 @sad_16i8_256() "min-legal-vector-width"="256" {
 ; CHECK-AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; CHECK-AVX512-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; CHECK-AVX512-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; CHECK-AVX512-NEXT:    .p2align 4, 0x90
+; CHECK-AVX512-NEXT:    .p2align 4
 ; CHECK-AVX512-NEXT:  .LBB10_1: # %vector.body
 ; CHECK-AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-AVX512-NEXT:    vmovdqu a+1024(%rax), %xmm2
@@ -495,7 +495,7 @@ define dso_local i32 @sad_16i8_256() "min-legal-vector-width"="256" {
 ; CHECK-VBMI-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; CHECK-VBMI-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; CHECK-VBMI-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; CHECK-VBMI-NEXT:    .p2align 4, 0x90
+; CHECK-VBMI-NEXT:    .p2align 4
 ; CHECK-VBMI-NEXT:  .LBB10_1: # %vector.body
 ; CHECK-VBMI-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-VBMI-NEXT:    vmovdqu a+1024(%rax), %xmm2
@@ -555,7 +555,7 @@ define dso_local i32 @sad_16i8_512() "min-legal-vector-width"="512" {
 ; CHECK-SKX:       # %bb.0: # %entry
 ; CHECK-SKX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; CHECK-SKX-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; CHECK-SKX-NEXT:    .p2align 4, 0x90
+; CHECK-SKX-NEXT:    .p2align 4
 ; CHECK-SKX-NEXT:  .LBB11_1: # %vector.body
 ; CHECK-SKX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-SKX-NEXT:    vmovdqu a+1024(%rax), %xmm1
@@ -580,7 +580,7 @@ define dso_local i32 @sad_16i8_512() "min-legal-vector-width"="512" {
 ; CHECK-AVX512:       # %bb.0: # %entry
 ; CHECK-AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; CHECK-AVX512-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; CHECK-AVX512-NEXT:    .p2align 4, 0x90
+; CHECK-AVX512-NEXT:    .p2align 4
 ; CHECK-AVX512-NEXT:  .LBB11_1: # %vector.body
 ; CHECK-AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-AVX512-NEXT:    vmovdqu a+1024(%rax), %xmm1
@@ -605,7 +605,7 @@ define dso_local i32 @sad_16i8_512() "min-legal-vector-width"="512" {
 ; CHECK-VBMI:       # %bb.0: # %entry
 ; CHECK-VBMI-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; CHECK-VBMI-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; CHECK-VBMI-NEXT:    .p2align 4, 0x90
+; CHECK-VBMI-NEXT:    .p2align 4
 ; CHECK-VBMI-NEXT:  .LBB11_1: # %vector.body
 ; CHECK-VBMI-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-VBMI-NEXT:    vmovdqu a+1024(%rax), %xmm1
diff --git a/llvm/test/CodeGen/X86/mmx-arith.ll b/llvm/test/CodeGen/X86/mmx-arith.ll
index 5bb3b17fdf4219..73d459ba770264 100644
--- a/llvm/test/CodeGen/X86/mmx-arith.ll
+++ b/llvm/test/CodeGen/X86/mmx-arith.ll
@@ -409,7 +409,7 @@ define <1 x i64> @test3(ptr %a, ptr %b, i32 %count) nounwind {
 ; X86-NEXT:    xorl %ebx, %ebx
 ; X86-NEXT:    xorl %eax, %eax
 ; X86-NEXT:    xorl %edx, %edx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB3_3: # %bb26
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
@@ -442,7 +442,7 @@ define <1 x i64> @test3(ptr %a, ptr %b, i32 %count) nounwind {
 ; X64-NEXT:    xorl %eax, %eax
 ; X64-NEXT:    testl %edx, %edx
 ; X64-NEXT:    je .LBB3_2
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB3_1: # %bb26
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movslq %ecx, %rcx
diff --git a/llvm/test/CodeGen/X86/negative-stride-fptosi-user.ll b/llvm/test/CodeGen/X86/negative-stride-fptosi-user.ll
index d0d46b5f118365..96080d2d87cdf7 100644
--- a/llvm/test/CodeGen/X86/negative-stride-fptosi-user.ll
+++ b/llvm/test/CodeGen/X86/negative-stride-fptosi-user.ll
@@ -19,7 +19,7 @@ define void @foo(i32 %N) nounwind {
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    movl %edi, %ebx
 ; CHECK-NEXT:    xorl %ebp, %ebp
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %bb
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    xorps %xmm0, %xmm0
diff --git a/llvm/test/CodeGen/X86/optimize-max-0.ll b/llvm/test/CodeGen/X86/optimize-max-0.ll
index 81dafdffe31163..283c00e17f21aa 100644
--- a/llvm/test/CodeGen/X86/optimize-max-0.ll
+++ b/llvm/test/CodeGen/X86/optimize-max-0.ll
@@ -41,7 +41,7 @@ define void @foo(ptr %r, i32 %s, i32 %w, i32 %x, ptr %j, i32 %d) nounwind {
 ; CHECK-NEXT:    xorl %ecx, %ecx
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; CHECK-NEXT:    xorl %esi, %esi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_4: ## %bb6
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movzbl (%eax,%esi,2), %ebx
@@ -91,7 +91,7 @@ define void @foo(ptr %r, i32 %s, i32 %w, i32 %x, ptr %j, i32 %d) nounwind {
 ; CHECK-NEXT:    addl %esi, %ecx
 ; CHECK-NEXT:    xorl %esi, %esi
 ; CHECK-NEXT:    xorl %edi, %edi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_9: ## %bb13
 ; CHECK-NEXT:    ## =>This Loop Header: Depth=1
 ; CHECK-NEXT:    ## Child Loop BB0_10 Depth 2
@@ -102,7 +102,7 @@ define void @foo(ptr %r, i32 %s, i32 %w, i32 %x, ptr %j, i32 %d) nounwind {
 ; CHECK-NEXT:    imull {{[0-9]+}}(%esp), %edi
 ; CHECK-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %edi ## 4-byte Folded Reload
 ; CHECK-NEXT:    xorl %esi, %esi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_10: ## %bb14
 ; CHECK-NEXT:    ## Parent Loop BB0_9 Depth=1
 ; CHECK-NEXT:    ## => This Inner Loop Header: Depth=2
@@ -150,7 +150,7 @@ define void @foo(ptr %r, i32 %s, i32 %w, i32 %x, ptr %j, i32 %d) nounwind {
 ; CHECK-NEXT:    leal 15(%ebp), %eax
 ; CHECK-NEXT:    andl $-16, %eax
 ; CHECK-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_17: ## %bb23
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    subl $4, %esp
@@ -183,7 +183,7 @@ define void @foo(ptr %r, i32 %s, i32 %w, i32 %x, ptr %j, i32 %d) nounwind {
 ; CHECK-NEXT:    andl $-16, %eax
 ; CHECK-NEXT:    movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) ## 4-byte Spill
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %edi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_21: ## %bb30
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    subl $4, %esp
@@ -479,7 +479,7 @@ define void @bar(ptr %r, i32 %s, i32 %w, i32 %x, ptr %j, i32 %d) nounwind {
 ; CHECK-NEXT:    xorl %ecx, %ecx
 ; CHECK-NEXT:    movl %esi, %edx
 ; CHECK-NEXT:    xorl %esi, %esi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB1_4: ## %bb6
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movzbl (%eax,%esi,2), %ebx
@@ -524,7 +524,7 @@ define void @bar(ptr %r, i32 %s, i32 %w, i32 %x, ptr %j, i32 %d) nounwind {
 ; CHECK-NEXT:    addl %edx, %eax
 ; CHECK-NEXT:    xorl %edx, %edx
 ; CHECK-NEXT:    xorl %ebx, %ebx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB1_9: ## %bb13
 ; CHECK-NEXT:    ## =>This Loop Header: Depth=1
 ; CHECK-NEXT:    ## Child Loop BB1_10 Depth 2
@@ -535,7 +535,7 @@ define void @bar(ptr %r, i32 %s, i32 %w, i32 %x, ptr %j, i32 %d) nounwind {
 ; CHECK-NEXT:    imull {{[0-9]+}}(%esp), %ebx
 ; CHECK-NEXT:    addl {{[-0-9]+}}(%e{{[sb]}}p), %ebx ## 4-byte Folded Reload
 ; CHECK-NEXT:    xorl %esi, %esi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB1_10: ## %bb14
 ; CHECK-NEXT:    ## Parent Loop BB1_9 Depth=1
 ; CHECK-NEXT:    ## => This Inner Loop Header: Depth=2
@@ -584,7 +584,7 @@ define void @bar(ptr %r, i32 %s, i32 %w, i32 %x, ptr %j, i32 %d) nounwind {
 ; CHECK-NEXT:    movl {{[-0-9]+}}(%e{{[sb]}}p), %eax ## 4-byte Reload
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; CHECK-NEXT:    leal (%edx,%eax), %ebp
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB1_17: ## %bb23
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    subl $4, %esp
@@ -622,7 +622,7 @@ define void @bar(ptr %r, i32 %s, i32 %w, i32 %x, ptr %j, i32 %d) nounwind {
 ; CHECK-NEXT:    andl $-16, %eax
 ; CHECK-NEXT:    movl %eax, (%esp) ## 4-byte Spill
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %ebp
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB1_21: ## %bb30
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    subl $4, %esp
diff --git a/llvm/test/CodeGen/X86/optimize-max-1.ll b/llvm/test/CodeGen/X86/optimize-max-1.ll
index 4a49dc70d49958..1ac48586bf900b 100644
--- a/llvm/test/CodeGen/X86/optimize-max-1.ll
+++ b/llvm/test/CodeGen/X86/optimize-max-1.ll
@@ -10,7 +10,7 @@ define void @fs(ptr nocapture %p, i64 %n) nounwind {
 ; CHECK-LABEL: fs:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    xorl %eax, %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq $0, (%rdi,%rax,8)
@@ -40,7 +40,7 @@ define void @bs(ptr nocapture %p, i64 %n) nounwind {
 ; CHECK-LABEL: bs:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    xorl %eax, %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_1: # %bb
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq $0, (%rdi,%rax,8)
@@ -70,7 +70,7 @@ define void @fu(ptr nocapture %p, i64 %n) nounwind {
 ; CHECK-LABEL: fu:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    xorl %eax, %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB2_1: # %bb
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq $0, (%rdi,%rax,8)
@@ -100,7 +100,7 @@ define void @bu(ptr nocapture %p, i64 %n) nounwind {
 ; CHECK-LABEL: bu:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    xorl %eax, %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB3_1: # %bb
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq $0, (%rdi,%rax,8)
diff --git a/llvm/test/CodeGen/X86/optimize-max-2.ll b/llvm/test/CodeGen/X86/optimize-max-2.ll
index c83fe63883aae8..3533bfbc61e6d6 100644
--- a/llvm/test/CodeGen/X86/optimize-max-2.ll
+++ b/llvm/test/CodeGen/X86/optimize-max-2.ll
@@ -14,7 +14,7 @@ define void @foo(ptr nocapture %p, i64 %x, i64 %y) nounwind {
 ; CHECK-NEXT:    cmovneq %rdx, %rax
 ; CHECK-NEXT:    cmpq %rsi, %rax
 ; CHECK-NEXT:    cmovbeq %rsi, %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb4
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
diff --git a/llvm/test/CodeGen/X86/or-address.ll b/llvm/test/CodeGen/X86/or-address.ll
index ef1ea0ef5de952..6e59d3f70c3320 100644
--- a/llvm/test/CodeGen/X86/or-address.ll
+++ b/llvm/test/CodeGen/X86/or-address.ll
@@ -12,7 +12,7 @@ define void @test(ptr nocapture %array, i32 %r0) nounwind ssp noredzone {
 ; CHECK-NEXT:    xorl %ecx, %ecx
 ; CHECK-NEXT:    xorl %edx, %edx
 ; CHECK-NEXT:    xorl %r8d, %r8d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_1: ## %bb
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpb $4, %r8b
@@ -75,7 +75,7 @@ define void @test1(ptr nocapture %array, i32 %r0, i8 signext %k, i8 signext %i0)
 ; CHECK-NEXT:    ## kill: def $ecx killed $ecx def $rcx
 ; CHECK-NEXT:    movb $32, %al
 ; CHECK-NEXT:    xorl %r8d, %r8d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB1_1: ## %for.body
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpb $4, %cl
diff --git a/llvm/test/CodeGen/X86/overflowing-iv-codegen.ll b/llvm/test/CodeGen/X86/overflowing-iv-codegen.ll
index 3e4539d333474f..e5dd5b23bea969 100644
--- a/llvm/test/CodeGen/X86/overflowing-iv-codegen.ll
+++ b/llvm/test/CodeGen/X86/overflowing-iv-codegen.ll
@@ -6,7 +6,7 @@ define i32 @test_01(ptr %p, i64 %len, i32 %x) {
 ; CHECK-LABEL: test_01:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    addq $-4, %rdi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    subq $1, %rsi
@@ -48,7 +48,7 @@ define i32 @test_02(ptr %p, i64 %len, i32 %x) {
 ; CHECK-LABEL: test_02:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    addq $-4, %rdi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    subq $1, %rsi
@@ -90,7 +90,7 @@ define i32 @test_02_nopoison(ptr %p, i64 %len, i32 %x) {
 ; CHECK-LABEL: test_02_nopoison:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    addq $-4, %rdi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB2_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    subq $1, %rsi
@@ -134,7 +134,7 @@ define i32 @test_03(ptr %p, i64 %len, i32 %x) {
 ; CHECK-LABEL: test_03:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    addq $-4, %rdi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB3_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    subq $1, %rsi
@@ -176,7 +176,7 @@ define i32 @test_03_nopoison(ptr %p, i64 %len, i32 %x) {
 ; CHECK-LABEL: test_03_nopoison:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    addq $-4, %rdi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB4_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    subq $1, %rsi
diff --git a/llvm/test/CodeGen/X86/patchable-prologue.ll b/llvm/test/CodeGen/X86/patchable-prologue.ll
index aec76a359d267e..a6a6c0d20a1af7 100644
--- a/llvm/test/CodeGen/X86/patchable-prologue.ll
+++ b/llvm/test/CodeGen/X86/patchable-prologue.ll
@@ -12,7 +12,7 @@ define void @f0() "patchable-function"="prologue-short-redirect" {
 ; CHECK-LABEL: _f0{{>?}}:
 ; CHECK-NEXT:  66 90 	nop
 
-; CHECK-ALIGN: 	.p2align	4, 0x90
+; CHECK-ALIGN: 	.p2align	4
 ; CHECK-ALIGN: _f0:
 
 ; X86: f0:
@@ -35,7 +35,7 @@ define void @f1() "patchable-function"="prologue-short-redirect" "frame-pointer"
 ; CHECK-NEXT: 66 90     nop
 ; CHECK-NEXT: 55		pushq	%rbp
 
-; CHECK-ALIGN: 	.p2align	4, 0x90
+; CHECK-ALIGN: 	.p2align	4
 ; CHECK-ALIGN: _f1:
 
 ; X86: f1:
@@ -58,7 +58,7 @@ define void @f2() "patchable-function"="prologue-short-redirect" {
 ; CHECK-LABEL: _f2
 ; CHECK-NEXT: 48 81 ec a8 00 00 00 	subq	$168, %rsp
 
-; CHECK-ALIGN: 	.p2align	4, 0x90
+; CHECK-ALIGN: 	.p2align	4
 ; CHECK-ALIGN: _f2:
 
 ; X86: f2:
@@ -82,7 +82,7 @@ define void @f3() "patchable-function"="prologue-short-redirect" optsize {
 ; CHECK-LABEL: _f3
 ; CHECK-NEXT: 66 90 	nop
 
-; CHECK-ALIGN: 	.p2align	4, 0x90
+; CHECK-ALIGN: 	.p2align	4
 ; CHECK-ALIGN: _f3:
 
 ; X86: f3:
@@ -140,7 +140,7 @@ bb21:
 ; CHECK-LABEL: _emptyfunc
 ; CHECK-NEXT: 0f 0b 	ud2
 
-; CHECK-ALIGN: 	.p2align	4, 0x90
+; CHECK-ALIGN: 	.p2align	4
 ; CHECK-ALIGN: _emptyfunc:
 
 ; X86: emptyfunc:
@@ -166,7 +166,7 @@ define i32 @emptyfunc() "patchable-function"="prologue-short-redirect" {
 ;   } while ((++(*b++)));
 ; }
 
-; CHECK-ALIGN: 	.p2align	4, 0x90
+; CHECK-ALIGN: 	.p2align	4
 ; CHECK-ALIGN: _jmp_to_start:
 
 ; X86: jmp_to_start:
diff --git a/llvm/test/CodeGen/X86/pcsections-atomics.ll b/llvm/test/CodeGen/X86/pcsections-atomics.ll
index cfc9d50763af4a..672ebc1ec7275a 100644
--- a/llvm/test/CodeGen/X86/pcsections-atomics.ll
+++ b/llvm/test/CodeGen/X86/pcsections-atomics.ll
@@ -706,7 +706,7 @@ define void @atomic8_nand_monotonic(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection16:
 ; O1-NEXT:    movzbl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB16_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -727,7 +727,7 @@ define void @atomic8_nand_monotonic(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection16:
 ; O2-NEXT:    movzbl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB16_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -748,7 +748,7 @@ define void @atomic8_nand_monotonic(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection16:
 ; O3-NEXT:    movzbl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB16_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -1044,7 +1044,7 @@ define void @atomic8_nand_acquire(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection27:
 ; O1-NEXT:    movzbl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB23_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -1065,7 +1065,7 @@ define void @atomic8_nand_acquire(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection27:
 ; O2-NEXT:    movzbl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB23_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -1086,7 +1086,7 @@ define void @atomic8_nand_acquire(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection27:
 ; O3-NEXT:    movzbl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB23_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -1382,7 +1382,7 @@ define void @atomic8_nand_release(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection38:
 ; O1-NEXT:    movzbl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB30_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -1403,7 +1403,7 @@ define void @atomic8_nand_release(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection38:
 ; O2-NEXT:    movzbl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB30_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -1424,7 +1424,7 @@ define void @atomic8_nand_release(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection38:
 ; O3-NEXT:    movzbl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB30_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -1720,7 +1720,7 @@ define void @atomic8_nand_acq_rel(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection49:
 ; O1-NEXT:    movzbl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB37_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -1741,7 +1741,7 @@ define void @atomic8_nand_acq_rel(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection49:
 ; O2-NEXT:    movzbl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB37_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -1762,7 +1762,7 @@ define void @atomic8_nand_acq_rel(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection49:
 ; O3-NEXT:    movzbl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB37_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -2058,7 +2058,7 @@ define void @atomic8_nand_seq_cst(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection60:
 ; O1-NEXT:    movzbl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB44_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -2079,7 +2079,7 @@ define void @atomic8_nand_seq_cst(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection60:
 ; O2-NEXT:    movzbl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB44_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -2100,7 +2100,7 @@ define void @atomic8_nand_seq_cst(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection60:
 ; O3-NEXT:    movzbl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB44_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -3151,7 +3151,7 @@ define void @atomic16_nand_monotonic(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection109:
 ; O1-NEXT:    movzwl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB64_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -3176,7 +3176,7 @@ define void @atomic16_nand_monotonic(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection109:
 ; O2-NEXT:    movzwl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB64_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -3201,7 +3201,7 @@ define void @atomic16_nand_monotonic(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection109:
 ; O3-NEXT:    movzwl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB64_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -3505,7 +3505,7 @@ define void @atomic16_nand_acquire(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection122:
 ; O1-NEXT:    movzwl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB71_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -3530,7 +3530,7 @@ define void @atomic16_nand_acquire(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection122:
 ; O2-NEXT:    movzwl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB71_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -3555,7 +3555,7 @@ define void @atomic16_nand_acquire(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection122:
 ; O3-NEXT:    movzwl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB71_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -3859,7 +3859,7 @@ define void @atomic16_nand_release(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection135:
 ; O1-NEXT:    movzwl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB78_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -3884,7 +3884,7 @@ define void @atomic16_nand_release(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection135:
 ; O2-NEXT:    movzwl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB78_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -3909,7 +3909,7 @@ define void @atomic16_nand_release(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection135:
 ; O3-NEXT:    movzwl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB78_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -4213,7 +4213,7 @@ define void @atomic16_nand_acq_rel(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection148:
 ; O1-NEXT:    movzwl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB85_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -4238,7 +4238,7 @@ define void @atomic16_nand_acq_rel(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection148:
 ; O2-NEXT:    movzwl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB85_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -4263,7 +4263,7 @@ define void @atomic16_nand_acq_rel(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection148:
 ; O3-NEXT:    movzwl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB85_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -4567,7 +4567,7 @@ define void @atomic16_nand_seq_cst(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection161:
 ; O1-NEXT:    movzwl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB92_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -4592,7 +4592,7 @@ define void @atomic16_nand_seq_cst(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection161:
 ; O2-NEXT:    movzwl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB92_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -4617,7 +4617,7 @@ define void @atomic16_nand_seq_cst(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection161:
 ; O3-NEXT:    movzwl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB92_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -5623,7 +5623,7 @@ define void @atomic32_nand_monotonic(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection197:
 ; O1-NEXT:    movl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB112_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -5644,7 +5644,7 @@ define void @atomic32_nand_monotonic(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection197:
 ; O2-NEXT:    movl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB112_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -5665,7 +5665,7 @@ define void @atomic32_nand_monotonic(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection197:
 ; O3-NEXT:    movl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB112_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -5961,7 +5961,7 @@ define void @atomic32_nand_acquire(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection208:
 ; O1-NEXT:    movl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB119_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -5982,7 +5982,7 @@ define void @atomic32_nand_acquire(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection208:
 ; O2-NEXT:    movl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB119_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -6003,7 +6003,7 @@ define void @atomic32_nand_acquire(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection208:
 ; O3-NEXT:    movl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB119_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -6299,7 +6299,7 @@ define void @atomic32_nand_release(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection219:
 ; O1-NEXT:    movl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB126_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -6320,7 +6320,7 @@ define void @atomic32_nand_release(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection219:
 ; O2-NEXT:    movl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB126_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -6341,7 +6341,7 @@ define void @atomic32_nand_release(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection219:
 ; O3-NEXT:    movl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB126_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -6637,7 +6637,7 @@ define void @atomic32_nand_acq_rel(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection230:
 ; O1-NEXT:    movl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB133_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -6658,7 +6658,7 @@ define void @atomic32_nand_acq_rel(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection230:
 ; O2-NEXT:    movl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB133_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -6679,7 +6679,7 @@ define void @atomic32_nand_acq_rel(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection230:
 ; O3-NEXT:    movl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB133_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -6975,7 +6975,7 @@ define void @atomic32_nand_seq_cst(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection241:
 ; O1-NEXT:    movl (%rdi), %eax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB140_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -6996,7 +6996,7 @@ define void @atomic32_nand_seq_cst(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection241:
 ; O2-NEXT:    movl (%rdi), %eax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB140_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -7017,7 +7017,7 @@ define void @atomic32_nand_seq_cst(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection241:
 ; O3-NEXT:    movl (%rdi), %eax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB140_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -8145,7 +8145,7 @@ define void @atomic64_nand_monotonic(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection292:
 ; O1-NEXT:    movq (%rdi), %rax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB162_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -8166,7 +8166,7 @@ define void @atomic64_nand_monotonic(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection292:
 ; O2-NEXT:    movq (%rdi), %rax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB162_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -8187,7 +8187,7 @@ define void @atomic64_nand_monotonic(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection292:
 ; O3-NEXT:    movq (%rdi), %rax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB162_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -8486,7 +8486,7 @@ define void @atomic64_nand_acquire(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection303:
 ; O1-NEXT:    movq (%rdi), %rax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB169_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -8507,7 +8507,7 @@ define void @atomic64_nand_acquire(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection303:
 ; O2-NEXT:    movq (%rdi), %rax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB169_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -8528,7 +8528,7 @@ define void @atomic64_nand_acquire(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection303:
 ; O3-NEXT:    movq (%rdi), %rax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB169_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -8827,7 +8827,7 @@ define void @atomic64_nand_release(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection314:
 ; O1-NEXT:    movq (%rdi), %rax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB176_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -8848,7 +8848,7 @@ define void @atomic64_nand_release(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection314:
 ; O2-NEXT:    movq (%rdi), %rax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB176_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -8869,7 +8869,7 @@ define void @atomic64_nand_release(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection314:
 ; O3-NEXT:    movq (%rdi), %rax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB176_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -9168,7 +9168,7 @@ define void @atomic64_nand_acq_rel(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection325:
 ; O1-NEXT:    movq (%rdi), %rax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB183_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -9189,7 +9189,7 @@ define void @atomic64_nand_acq_rel(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection325:
 ; O2-NEXT:    movq (%rdi), %rax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB183_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -9210,7 +9210,7 @@ define void @atomic64_nand_acq_rel(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection325:
 ; O3-NEXT:    movq (%rdi), %rax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB183_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -9509,7 +9509,7 @@ define void @atomic64_nand_seq_cst(ptr %a) {
 ; O1-NEXT:    movq foo(%rip), %rax
 ; O1-NEXT:  .Lpcsection336:
 ; O1-NEXT:    movq (%rdi), %rax
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB190_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ecx
@@ -9530,7 +9530,7 @@ define void @atomic64_nand_seq_cst(ptr %a) {
 ; O2-NEXT:    movq foo(%rip), %rax
 ; O2-NEXT:  .Lpcsection336:
 ; O2-NEXT:    movq (%rdi), %rax
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB190_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ecx
@@ -9551,7 +9551,7 @@ define void @atomic64_nand_seq_cst(ptr %a) {
 ; O3-NEXT:    movq foo(%rip), %rax
 ; O3-NEXT:  .Lpcsection336:
 ; O3-NEXT:    movq (%rdi), %rax
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB190_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ecx
@@ -10561,7 +10561,7 @@ define void @atomic128_store_unordered(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection396:
 ; O1-NEXT:    movl $42, %ebx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB203_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:  .Lpcsection397:
@@ -10588,7 +10588,7 @@ define void @atomic128_store_unordered(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection396:
 ; O2-NEXT:    movl $42, %ebx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB203_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:  .Lpcsection397:
@@ -10615,7 +10615,7 @@ define void @atomic128_store_unordered(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection396:
 ; O3-NEXT:    movl $42, %ebx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB203_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:  .Lpcsection397:
@@ -10688,7 +10688,7 @@ define void @atomic128_store_monotonic(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection402:
 ; O1-NEXT:    movl $42, %ebx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB204_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:  .Lpcsection403:
@@ -10715,7 +10715,7 @@ define void @atomic128_store_monotonic(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection402:
 ; O2-NEXT:    movl $42, %ebx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB204_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:  .Lpcsection403:
@@ -10742,7 +10742,7 @@ define void @atomic128_store_monotonic(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection402:
 ; O3-NEXT:    movl $42, %ebx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB204_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:  .Lpcsection403:
@@ -10815,7 +10815,7 @@ define void @atomic128_store_release(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection408:
 ; O1-NEXT:    movl $42, %ebx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB205_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:  .Lpcsection409:
@@ -10842,7 +10842,7 @@ define void @atomic128_store_release(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection408:
 ; O2-NEXT:    movl $42, %ebx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB205_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:  .Lpcsection409:
@@ -10869,7 +10869,7 @@ define void @atomic128_store_release(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection408:
 ; O3-NEXT:    movl $42, %ebx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB205_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:  .Lpcsection409:
@@ -10942,7 +10942,7 @@ define void @atomic128_store_seq_cst(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection414:
 ; O1-NEXT:    movl $42, %ebx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB206_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:  .Lpcsection415:
@@ -10969,7 +10969,7 @@ define void @atomic128_store_seq_cst(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection414:
 ; O2-NEXT:    movl $42, %ebx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB206_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:  .Lpcsection415:
@@ -10996,7 +10996,7 @@ define void @atomic128_store_seq_cst(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection414:
 ; O3-NEXT:    movl $42, %ebx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB206_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:  .Lpcsection415:
@@ -11108,7 +11108,7 @@ define void @atomic128_xchg_monotonic(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection421:
 ; O1-NEXT:    movl $42, %ebx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB208_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:  .Lpcsection422:
@@ -11135,7 +11135,7 @@ define void @atomic128_xchg_monotonic(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection421:
 ; O2-NEXT:    movl $42, %ebx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB208_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:  .Lpcsection422:
@@ -11162,7 +11162,7 @@ define void @atomic128_xchg_monotonic(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection421:
 ; O3-NEXT:    movl $42, %ebx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB208_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:  .Lpcsection422:
@@ -11233,7 +11233,7 @@ define void @atomic128_add_monotonic(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection426:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB209_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -11262,7 +11262,7 @@ define void @atomic128_add_monotonic(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection426:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB209_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -11291,7 +11291,7 @@ define void @atomic128_add_monotonic(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection426:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB209_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -11366,7 +11366,7 @@ define void @atomic128_sub_monotonic(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection432:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB210_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -11395,7 +11395,7 @@ define void @atomic128_sub_monotonic(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection432:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB210_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -11424,7 +11424,7 @@ define void @atomic128_sub_monotonic(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection432:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB210_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -11501,7 +11501,7 @@ define void @atomic128_and_monotonic(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection438:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB211_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ebx
@@ -11529,7 +11529,7 @@ define void @atomic128_and_monotonic(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection438:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB211_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ebx
@@ -11557,7 +11557,7 @@ define void @atomic128_and_monotonic(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection438:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB211_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ebx
@@ -11629,7 +11629,7 @@ define void @atomic128_or_monotonic(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection444:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB212_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -11656,7 +11656,7 @@ define void @atomic128_or_monotonic(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection444:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB212_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -11683,7 +11683,7 @@ define void @atomic128_or_monotonic(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection444:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB212_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -11754,7 +11754,7 @@ define void @atomic128_xor_monotonic(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection449:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB213_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -11781,7 +11781,7 @@ define void @atomic128_xor_monotonic(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection449:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB213_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -11808,7 +11808,7 @@ define void @atomic128_xor_monotonic(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection449:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB213_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -11887,7 +11887,7 @@ define void @atomic128_nand_monotonic(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection455:
 ; O1-NEXT:    movq $-1, %rcx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB214_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ebx
@@ -11917,7 +11917,7 @@ define void @atomic128_nand_monotonic(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection455:
 ; O2-NEXT:    movq $-1, %rcx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB214_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ebx
@@ -11947,7 +11947,7 @@ define void @atomic128_nand_monotonic(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection455:
 ; O3-NEXT:    movq $-1, %rcx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB214_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ebx
@@ -12023,7 +12023,7 @@ define void @atomic128_xchg_acquire(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection462:
 ; O1-NEXT:    movl $42, %ebx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB215_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:  .Lpcsection463:
@@ -12050,7 +12050,7 @@ define void @atomic128_xchg_acquire(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection462:
 ; O2-NEXT:    movl $42, %ebx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB215_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:  .Lpcsection463:
@@ -12077,7 +12077,7 @@ define void @atomic128_xchg_acquire(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection462:
 ; O3-NEXT:    movl $42, %ebx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB215_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:  .Lpcsection463:
@@ -12148,7 +12148,7 @@ define void @atomic128_add_acquire(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection467:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB216_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -12177,7 +12177,7 @@ define void @atomic128_add_acquire(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection467:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB216_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -12206,7 +12206,7 @@ define void @atomic128_add_acquire(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection467:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB216_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -12281,7 +12281,7 @@ define void @atomic128_sub_acquire(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection473:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB217_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -12310,7 +12310,7 @@ define void @atomic128_sub_acquire(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection473:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB217_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -12339,7 +12339,7 @@ define void @atomic128_sub_acquire(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection473:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB217_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -12416,7 +12416,7 @@ define void @atomic128_and_acquire(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection479:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB218_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ebx
@@ -12444,7 +12444,7 @@ define void @atomic128_and_acquire(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection479:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB218_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ebx
@@ -12472,7 +12472,7 @@ define void @atomic128_and_acquire(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection479:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB218_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ebx
@@ -12544,7 +12544,7 @@ define void @atomic128_or_acquire(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection485:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB219_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -12571,7 +12571,7 @@ define void @atomic128_or_acquire(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection485:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB219_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -12598,7 +12598,7 @@ define void @atomic128_or_acquire(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection485:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB219_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -12669,7 +12669,7 @@ define void @atomic128_xor_acquire(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection490:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB220_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -12696,7 +12696,7 @@ define void @atomic128_xor_acquire(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection490:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB220_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -12723,7 +12723,7 @@ define void @atomic128_xor_acquire(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection490:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB220_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -12802,7 +12802,7 @@ define void @atomic128_nand_acquire(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection496:
 ; O1-NEXT:    movq $-1, %rcx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB221_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ebx
@@ -12832,7 +12832,7 @@ define void @atomic128_nand_acquire(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection496:
 ; O2-NEXT:    movq $-1, %rcx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB221_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ebx
@@ -12862,7 +12862,7 @@ define void @atomic128_nand_acquire(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection496:
 ; O3-NEXT:    movq $-1, %rcx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB221_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ebx
@@ -12938,7 +12938,7 @@ define void @atomic128_xchg_release(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection503:
 ; O1-NEXT:    movl $42, %ebx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB222_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:  .Lpcsection504:
@@ -12965,7 +12965,7 @@ define void @atomic128_xchg_release(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection503:
 ; O2-NEXT:    movl $42, %ebx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB222_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:  .Lpcsection504:
@@ -12992,7 +12992,7 @@ define void @atomic128_xchg_release(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection503:
 ; O3-NEXT:    movl $42, %ebx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB222_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:  .Lpcsection504:
@@ -13062,7 +13062,7 @@ define void @atomic128_add_release(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection508:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB223_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -13091,7 +13091,7 @@ define void @atomic128_add_release(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection508:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB223_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -13120,7 +13120,7 @@ define void @atomic128_add_release(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection508:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB223_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -13195,7 +13195,7 @@ define void @atomic128_sub_release(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection514:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB224_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -13224,7 +13224,7 @@ define void @atomic128_sub_release(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection514:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB224_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -13253,7 +13253,7 @@ define void @atomic128_sub_release(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection514:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB224_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -13330,7 +13330,7 @@ define void @atomic128_and_release(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection520:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB225_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ebx
@@ -13358,7 +13358,7 @@ define void @atomic128_and_release(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection520:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB225_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ebx
@@ -13386,7 +13386,7 @@ define void @atomic128_and_release(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection520:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB225_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ebx
@@ -13458,7 +13458,7 @@ define void @atomic128_or_release(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection526:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB226_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -13485,7 +13485,7 @@ define void @atomic128_or_release(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection526:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB226_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -13512,7 +13512,7 @@ define void @atomic128_or_release(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection526:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB226_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -13583,7 +13583,7 @@ define void @atomic128_xor_release(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection531:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB227_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -13610,7 +13610,7 @@ define void @atomic128_xor_release(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection531:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB227_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -13637,7 +13637,7 @@ define void @atomic128_xor_release(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection531:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB227_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -13716,7 +13716,7 @@ define void @atomic128_nand_release(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection537:
 ; O1-NEXT:    movq $-1, %rcx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB228_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ebx
@@ -13746,7 +13746,7 @@ define void @atomic128_nand_release(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection537:
 ; O2-NEXT:    movq $-1, %rcx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB228_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ebx
@@ -13776,7 +13776,7 @@ define void @atomic128_nand_release(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection537:
 ; O3-NEXT:    movq $-1, %rcx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB228_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ebx
@@ -13852,7 +13852,7 @@ define void @atomic128_xchg_acq_rel(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection544:
 ; O1-NEXT:    movl $42, %ebx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB229_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:  .Lpcsection545:
@@ -13879,7 +13879,7 @@ define void @atomic128_xchg_acq_rel(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection544:
 ; O2-NEXT:    movl $42, %ebx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB229_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:  .Lpcsection545:
@@ -13906,7 +13906,7 @@ define void @atomic128_xchg_acq_rel(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection544:
 ; O3-NEXT:    movl $42, %ebx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB229_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:  .Lpcsection545:
@@ -13977,7 +13977,7 @@ define void @atomic128_add_acq_rel(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection549:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB230_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -14006,7 +14006,7 @@ define void @atomic128_add_acq_rel(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection549:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB230_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -14035,7 +14035,7 @@ define void @atomic128_add_acq_rel(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection549:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB230_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -14110,7 +14110,7 @@ define void @atomic128_sub_acq_rel(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection555:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB231_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -14139,7 +14139,7 @@ define void @atomic128_sub_acq_rel(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection555:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB231_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -14168,7 +14168,7 @@ define void @atomic128_sub_acq_rel(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection555:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB231_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -14245,7 +14245,7 @@ define void @atomic128_and_acq_rel(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection561:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB232_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ebx
@@ -14273,7 +14273,7 @@ define void @atomic128_and_acq_rel(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection561:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB232_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ebx
@@ -14301,7 +14301,7 @@ define void @atomic128_and_acq_rel(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection561:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB232_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ebx
@@ -14373,7 +14373,7 @@ define void @atomic128_or_acq_rel(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection567:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB233_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -14400,7 +14400,7 @@ define void @atomic128_or_acq_rel(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection567:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB233_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -14427,7 +14427,7 @@ define void @atomic128_or_acq_rel(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection567:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB233_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -14498,7 +14498,7 @@ define void @atomic128_xor_acq_rel(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection572:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB234_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -14525,7 +14525,7 @@ define void @atomic128_xor_acq_rel(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection572:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB234_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -14552,7 +14552,7 @@ define void @atomic128_xor_acq_rel(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection572:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB234_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -14631,7 +14631,7 @@ define void @atomic128_nand_acq_rel(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection578:
 ; O1-NEXT:    movq $-1, %rcx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB235_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ebx
@@ -14661,7 +14661,7 @@ define void @atomic128_nand_acq_rel(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection578:
 ; O2-NEXT:    movq $-1, %rcx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB235_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ebx
@@ -14691,7 +14691,7 @@ define void @atomic128_nand_acq_rel(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection578:
 ; O3-NEXT:    movq $-1, %rcx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB235_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ebx
@@ -14767,7 +14767,7 @@ define void @atomic128_xchg_seq_cst(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection585:
 ; O1-NEXT:    movl $42, %ebx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB236_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:  .Lpcsection586:
@@ -14794,7 +14794,7 @@ define void @atomic128_xchg_seq_cst(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection585:
 ; O2-NEXT:    movl $42, %ebx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB236_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:  .Lpcsection586:
@@ -14821,7 +14821,7 @@ define void @atomic128_xchg_seq_cst(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection585:
 ; O3-NEXT:    movl $42, %ebx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB236_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:  .Lpcsection586:
@@ -14892,7 +14892,7 @@ define void @atomic128_add_seq_cst(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection590:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB237_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -14921,7 +14921,7 @@ define void @atomic128_add_seq_cst(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection590:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB237_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -14950,7 +14950,7 @@ define void @atomic128_add_seq_cst(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection590:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB237_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -15025,7 +15025,7 @@ define void @atomic128_sub_seq_cst(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection596:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB238_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -15054,7 +15054,7 @@ define void @atomic128_sub_seq_cst(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection596:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB238_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -15083,7 +15083,7 @@ define void @atomic128_sub_seq_cst(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection596:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB238_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -15160,7 +15160,7 @@ define void @atomic128_and_seq_cst(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection602:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB239_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ebx
@@ -15188,7 +15188,7 @@ define void @atomic128_and_seq_cst(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection602:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB239_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ebx
@@ -15216,7 +15216,7 @@ define void @atomic128_and_seq_cst(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection602:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB239_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ebx
@@ -15288,7 +15288,7 @@ define void @atomic128_or_seq_cst(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection608:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB240_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -15315,7 +15315,7 @@ define void @atomic128_or_seq_cst(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection608:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB240_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -15342,7 +15342,7 @@ define void @atomic128_or_seq_cst(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection608:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB240_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -15413,7 +15413,7 @@ define void @atomic128_xor_seq_cst(ptr %a) {
 ; O1-NEXT:    movq (%rdi), %rax
 ; O1-NEXT:  .Lpcsection613:
 ; O1-NEXT:    movq 8(%rdi), %rdx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB241_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movq %rax, %rbx
@@ -15440,7 +15440,7 @@ define void @atomic128_xor_seq_cst(ptr %a) {
 ; O2-NEXT:    movq (%rdi), %rax
 ; O2-NEXT:  .Lpcsection613:
 ; O2-NEXT:    movq 8(%rdi), %rdx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB241_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movq %rax, %rbx
@@ -15467,7 +15467,7 @@ define void @atomic128_xor_seq_cst(ptr %a) {
 ; O3-NEXT:    movq (%rdi), %rax
 ; O3-NEXT:  .Lpcsection613:
 ; O3-NEXT:    movq 8(%rdi), %rdx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB241_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movq %rax, %rbx
@@ -15546,7 +15546,7 @@ define void @atomic128_nand_seq_cst(ptr %a) {
 ; O1-NEXT:    movq 8(%rdi), %rdx
 ; O1-NEXT:  .Lpcsection619:
 ; O1-NEXT:    movq $-1, %rcx
-; O1-NEXT:    .p2align 4, 0x90
+; O1-NEXT:    .p2align 4
 ; O1-NEXT:  .LBB242_1: # %atomicrmw.start
 ; O1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O1-NEXT:    movl %eax, %ebx
@@ -15576,7 +15576,7 @@ define void @atomic128_nand_seq_cst(ptr %a) {
 ; O2-NEXT:    movq 8(%rdi), %rdx
 ; O2-NEXT:  .Lpcsection619:
 ; O2-NEXT:    movq $-1, %rcx
-; O2-NEXT:    .p2align 4, 0x90
+; O2-NEXT:    .p2align 4
 ; O2-NEXT:  .LBB242_1: # %atomicrmw.start
 ; O2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O2-NEXT:    movl %eax, %ebx
@@ -15606,7 +15606,7 @@ define void @atomic128_nand_seq_cst(ptr %a) {
 ; O3-NEXT:    movq 8(%rdi), %rdx
 ; O3-NEXT:  .Lpcsection619:
 ; O3-NEXT:    movq $-1, %rcx
-; O3-NEXT:    .p2align 4, 0x90
+; O3-NEXT:    .p2align 4
 ; O3-NEXT:  .LBB242_1: # %atomicrmw.start
 ; O3-NEXT:    # =>This Inner Loop Header: Depth=1
 ; O3-NEXT:    movl %eax, %ebx
diff --git a/llvm/test/CodeGen/X86/peep-test-0.ll b/llvm/test/CodeGen/X86/peep-test-0.ll
index 71dadf7edea3af..3a0ef86b64ee31 100644
--- a/llvm/test/CodeGen/X86/peep-test-0.ll
+++ b/llvm/test/CodeGen/X86/peep-test-0.ll
@@ -8,7 +8,7 @@ define void @loop(i64 %n, ptr nocapture %d) nounwind {
 ; CHECK-NEXT:    shlq $4, %rax
 ; CHECK-NEXT:    addq %rsi, %rax
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = [3.0E+0,0.0E+0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
diff --git a/llvm/test/CodeGen/X86/peep-test-1.ll b/llvm/test/CodeGen/X86/peep-test-1.ll
index 0d86bd4ec8c45b..730a7fdccbd7cc 100644
--- a/llvm/test/CodeGen/X86/peep-test-1.ll
+++ b/llvm/test/CodeGen/X86/peep-test-1.ll
@@ -6,7 +6,7 @@ define void @foo(i32 %n, ptr nocapture %p) nounwind {
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    fldl (%eax,%ecx,8)
diff --git a/llvm/test/CodeGen/X86/peephole-copy.ll b/llvm/test/CodeGen/X86/peephole-copy.ll
index 69112d0a1f471c..e7ca7c5cc63938 100644
--- a/llvm/test/CodeGen/X86/peephole-copy.ll
+++ b/llvm/test/CodeGen/X86/peephole-copy.ll
@@ -17,7 +17,7 @@ define void @foo(ptr %p1, ptr %p2, ptr %p3, ptr %p4) {
 ; CHECK-NEXT:    movl (%rax), %eax
 ; CHECK-NEXT:    shll %cl, %eax
 ; CHECK-NEXT:    movl %r8d, (%rdx)
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %loop2.header
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $5, %edi
diff --git a/llvm/test/CodeGen/X86/pic-load-remat.ll b/llvm/test/CodeGen/X86/pic-load-remat.ll
index 7737093d2ba076..2587b0379a0f76 100644
--- a/llvm/test/CodeGen/X86/pic-load-remat.ll
+++ b/llvm/test/CodeGen/X86/pic-load-remat.ll
@@ -12,7 +12,7 @@ define void @f() nounwind  {
 ; CHECK-NEXT:    movdqa {{.*#+}} xmm0 = [21183,21183,21183,21183,21183,21183,21183,21183]
 ; CHECK-NEXT:    paddsw %xmm0, %xmm0
 ; CHECK-NEXT:    paddw %xmm1, %xmm0
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_1: ## %bb
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movdqa %xmm0, 0
diff --git a/llvm/test/CodeGen/X86/postalloc-coalescing.ll b/llvm/test/CodeGen/X86/postalloc-coalescing.ll
index 68266fc4e158a3..7430d7a9baf260 100644
--- a/llvm/test/CodeGen/X86/postalloc-coalescing.ll
+++ b/llvm/test/CodeGen/X86/postalloc-coalescing.ll
@@ -7,7 +7,7 @@ define fastcc i32 @_Z18yy_get_next_bufferv() nounwind {
 ; CHECK-NEXT:    movl $42, %eax
 ; CHECK-NEXT:    cmpl $-1, %eax
 ; CHECK-NEXT:    je .LBB0_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb116
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movb %al, 0
diff --git a/llvm/test/CodeGen/X86/pr14314.ll b/llvm/test/CodeGen/X86/pr14314.ll
index c7dabf1f661cf3..bb1608e3cd9b29 100644
--- a/llvm/test/CodeGen/X86/pr14314.ll
+++ b/llvm/test/CodeGen/X86/pr14314.ll
@@ -13,7 +13,7 @@ define i64 @atomicSub(ptr %a, i64 %b) nounwind {
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %ebp
 ; CHECK-NEXT:    movl (%ebp), %eax
 ; CHECK-NEXT:    movl 4(%ebp), %edx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %eax, %ebx
diff --git a/llvm/test/CodeGen/X86/pr22338.ll b/llvm/test/CodeGen/X86/pr22338.ll
index 9ab5248a94602d..bf3967ca8fedee 100644
--- a/llvm/test/CodeGen/X86/pr22338.ll
+++ b/llvm/test/CodeGen/X86/pr22338.ll
@@ -21,7 +21,7 @@ define i32 @fn(i32 %a0, i32 %a1) {
 ; X86-NEXT:    addb %dl, %dl
 ; X86-NEXT:    movl %edx, %ecx
 ; X86-NEXT:    shll %cl, %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB0_1: # %bb1
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    testl %ebx, %ebx
@@ -46,7 +46,7 @@ define i32 @fn(i32 %a0, i32 %a1) {
 ; X64-NEXT:    addb %dl, %dl
 ; X64-NEXT:    movl %edx, %ecx
 ; X64-NEXT:    shll %cl, %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB0_1: # %bb1
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    testl %esi, %esi
diff --git a/llvm/test/CodeGen/X86/pr30562.ll b/llvm/test/CodeGen/X86/pr30562.ll
index 2745514cff8d42..e05a8672b1f811 100644
--- a/llvm/test/CodeGen/X86/pr30562.ll
+++ b/llvm/test/CodeGen/X86/pr30562.ll
@@ -10,7 +10,7 @@ define i32 @foo(ptr nocapture %perm, i32 %n) {
 ; CHECK-NEXT:    movl %esi, %ecx
 ; CHECK-NEXT:    andl $1, %ecx
 ; CHECK-NEXT:    movaps {{.*#+}} xmm1 = [2,3]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
diff --git a/llvm/test/CodeGen/X86/pr32108.ll b/llvm/test/CodeGen/X86/pr32108.ll
index dc14746440ae5f..32f8a7657a3f11 100644
--- a/llvm/test/CodeGen/X86/pr32108.ll
+++ b/llvm/test/CodeGen/X86/pr32108.ll
@@ -4,7 +4,7 @@
 define void @pr32108() {
 ; CHECK-LABEL: pr32108:
 ; CHECK:       # %bb.0: # %BB
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %CF244
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB0_1
diff --git a/llvm/test/CodeGen/X86/pr33290.ll b/llvm/test/CodeGen/X86/pr33290.ll
index 0e6f2e92f14008..3991080d75bc00 100644
--- a/llvm/test/CodeGen/X86/pr33290.ll
+++ b/llvm/test/CodeGen/X86/pr33290.ll
@@ -10,7 +10,7 @@ define dso_local void @e() {
 ; X86-LABEL: e:
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movl b, %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB0_1: # %for.cond
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movzbl c, %ecx
@@ -22,7 +22,7 @@ define dso_local void @e() {
 ; X64-LABEL: e:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movq b(%rip), %rax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB0_1: # %for.cond
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movzbl c(%rip), %ecx
diff --git a/llvm/test/CodeGen/X86/pr33747.ll b/llvm/test/CodeGen/X86/pr33747.ll
index c8ba2b2e3a7909..f6df42450e1879 100644
--- a/llvm/test/CodeGen/X86/pr33747.ll
+++ b/llvm/test/CodeGen/X86/pr33747.ll
@@ -12,10 +12,10 @@ define void @PR33747(ptr nocapture) {
 ; CHECK-NEXT:    setne %al
 ; CHECK-NEXT:    testb %cl, %al
 ; CHECK-NEXT:    je .LBB0_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB0_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB0_2
   %2 = getelementptr inbounds i32, ptr %0, i64 6
diff --git a/llvm/test/CodeGen/X86/pr37916.ll b/llvm/test/CodeGen/X86/pr37916.ll
index 2f8f0fdae1848c..e6639a11ca5ea4 100644
--- a/llvm/test/CodeGen/X86/pr37916.ll
+++ b/llvm/test/CodeGen/X86/pr37916.ll
@@ -7,7 +7,7 @@
 define void @fn1() local_unnamed_addr {
 ; CHECK-LABEL: fn1:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %if.end
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl a+4, %eax
diff --git a/llvm/test/CodeGen/X86/pr38185.ll b/llvm/test/CodeGen/X86/pr38185.ll
index e062302d4f0b56..d5591c50738fa1 100644
--- a/llvm/test/CodeGen/X86/pr38185.ll
+++ b/llvm/test/CodeGen/X86/pr38185.ll
@@ -5,7 +5,7 @@ define void @foo(ptr %a, ptr %b, ptr noalias %c, i64 %s) {
 ; CHECK-LABEL: foo:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movq $0, -{{[0-9]+}}(%rsp)
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq -{{[0-9]+}}(%rsp), %rax
diff --git a/llvm/test/CodeGen/X86/pr38217.ll b/llvm/test/CodeGen/X86/pr38217.ll
index f1538f3598aec6..02d2d9e02721a1 100644
--- a/llvm/test/CodeGen/X86/pr38217.ll
+++ b/llvm/test/CodeGen/X86/pr38217.ll
@@ -11,7 +11,7 @@ define dso_local void @_Z12d2s_bufferedmPc(i64 %arg, ptr nocapture %arg1) {
 ; CHECK-NEXT:  # %bb.1: # %bb2.preheader
 ; CHECK-NEXT:    xorl %ecx, %ecx
 ; CHECK-NEXT:    movabsq $3777893186295716171, %r8 # imm = 0x346DC5D63886594B
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %bb2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq %rdi, %rax
diff --git a/llvm/test/CodeGen/X86/pr38539.ll b/llvm/test/CodeGen/X86/pr38539.ll
index fb169a3777fb82..b633c28a214b70 100644
--- a/llvm/test/CodeGen/X86/pr38539.ll
+++ b/llvm/test/CodeGen/X86/pr38539.ll
@@ -168,7 +168,7 @@ define void @f() nounwind {
 ; X86-NEXT:    movl %edi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
 ; X86-NEXT:    movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
 ; X86-NEXT:    xorl %ecx, %ecx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB0_12: # %udiv-do-while
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    movl %ebx, %esi
diff --git a/llvm/test/CodeGen/X86/pr38795.ll b/llvm/test/CodeGen/X86/pr38795.ll
index f64c70e8fc79a4..c3c96e8228797a 100644
--- a/llvm/test/CodeGen/X86/pr38795.ll
+++ b/llvm/test/CodeGen/X86/pr38795.ll
@@ -30,7 +30,7 @@ define dso_local void @fn() {
 ; CHECK-NEXT:    # kill: killed $al
 ; CHECK-NEXT:    # implicit-def: $ebp
 ; CHECK-NEXT:    jmp .LBB0_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_15: # %for.inc
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    movb %dl, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
@@ -49,7 +49,7 @@ define dso_local void @fn() {
 ; CHECK-NEXT:    testl %edi, %edi
 ; CHECK-NEXT:    jne .LBB0_10
 ; CHECK-NEXT:    jmp .LBB0_6
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_3: # %if.end
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    movl %ecx, %eax
@@ -73,7 +73,7 @@ define dso_local void @fn() {
 ; CHECK-NEXT:    # implicit-def: $eax
 ; CHECK-NEXT:    movb %dh, {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Spill
 ; CHECK-NEXT:    jne .LBB0_15
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  # %bb.5: # %for.cond35
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    testl %edi, %edi
@@ -98,16 +98,16 @@ define dso_local void @fn() {
 ; CHECK-NEXT:    # implicit-def: $dl
 ; CHECK-NEXT:    # implicit-def: $ebp
 ; CHECK-NEXT:    jmp .LBB0_19
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_7: # %if.end21
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    # implicit-def: $ebp
 ; CHECK-NEXT:    jmp .LBB0_8
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_6: # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    xorl %edi, %edi
 ; CHECK-NEXT:    movb {{[-0-9]+}}(%e{{[sb]}}p), %dh # 1-byte Reload
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_19: # %for.cond47
 ; CHECK-NEXT:    # Parent Loop BB0_1 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
@@ -131,7 +131,7 @@ define dso_local void @fn() {
 ; CHECK-NEXT:    xorl %ecx, %ecx
 ; CHECK-NEXT:    xorl %ebp, %ebp
 ; CHECK-NEXT:    jmp .LBB0_15
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_9: # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    # implicit-def: $eax
 ; CHECK-NEXT:    testb %bl, %bl
@@ -264,7 +264,7 @@ define void @verifier_error_reduced_issue38788(i1 %cmp11) {
 ; CHECK-NEXT:    xorl %ecx, %ecx
 ; CHECK-NEXT:    xorl %ebx, %ebx
 ; CHECK-NEXT:    jmp .LBB1_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_7: # %if.end26
 ; CHECK-NEXT:    # in Loop: Header=BB1_1 Depth=1
 ; CHECK-NEXT:    movl %ecx, %edx
@@ -280,7 +280,7 @@ define void @verifier_error_reduced_issue38788(i1 %cmp11) {
 ; CHECK-NEXT:  # %bb.2: # in Loop: Header=BB1_1 Depth=1
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    jmp .LBB1_5
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_3: # %if.end
 ; CHECK-NEXT:    # in Loop: Header=BB1_1 Depth=1
 ; CHECK-NEXT:    testb $1, %al
@@ -293,7 +293,7 @@ define void @verifier_error_reduced_issue38788(i1 %cmp11) {
 ; CHECK-NEXT:    movl $0, %ebx
 ; CHECK-NEXT:    jne .LBB1_8
 ; CHECK-NEXT:    jmp .LBB1_5
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_4: # in Loop: Header=BB1_1 Depth=1
 ; CHECK-NEXT:    movl %ebx, %eax
 ; CHECK-NEXT:    xorl %ebx, %ebx
diff --git a/llvm/test/CodeGen/X86/pr42565.ll b/llvm/test/CodeGen/X86/pr42565.ll
index 33acf02135eab7..10071064057b88 100644
--- a/llvm/test/CodeGen/X86/pr42565.ll
+++ b/llvm/test/CodeGen/X86/pr42565.ll
@@ -7,7 +7,7 @@ define void @HUF_writeCTable_wksp()  {
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    movl $2, %eax
 ; CHECK-NEXT:    movb $-2, %cl
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    leal 1(%rcx), %edx
diff --git a/llvm/test/CodeGen/X86/pr42909.ll b/llvm/test/CodeGen/X86/pr42909.ll
index 47b85e144919db..8ff7caf4638541 100644
--- a/llvm/test/CodeGen/X86/pr42909.ll
+++ b/llvm/test/CodeGen/X86/pr42909.ll
@@ -4,7 +4,7 @@
 define void @autogen_SD31033(ptr %a0) {
 ; CHECK-LABEL: autogen_SD31033:
 ; CHECK:       # %bb.0: # %BB
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %CF
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB0_1
diff --git a/llvm/test/CodeGen/X86/pr43529.ll b/llvm/test/CodeGen/X86/pr43529.ll
index 3e9976c90449e8..ac5f7c84f82c39 100644
--- a/llvm/test/CodeGen/X86/pr43529.ll
+++ b/llvm/test/CodeGen/X86/pr43529.ll
@@ -12,7 +12,7 @@ define i32 @a() nounwind {
 ; CHECK-NEXT:    calll d at PLT
 ; CHECK-NEXT:    cmpl $a, %esi
 ; CHECK-NEXT:    jbe .LBB0_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %for.cond
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB0_1
diff --git a/llvm/test/CodeGen/X86/pr44140.ll b/llvm/test/CodeGen/X86/pr44140.ll
index 9455895a99b873..02525d73a786dd 100644
--- a/llvm/test/CodeGen/X86/pr44140.ll
+++ b/llvm/test/CodeGen/X86/pr44140.ll
@@ -17,7 +17,7 @@ define i32 @main() {
 ; CHECK-NEXT:    .cfi_def_cfa_offset 592
 ; CHECK-NEXT:    vmovaps {{.*#+}} xmm6 = [1010101010101010101,2020202020202020202]
 ; CHECK-NEXT:    xorl %esi, %esi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_1: # %fake-loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups {{[0-9]+}}(%rsp), %ymm0
diff --git a/llvm/test/CodeGen/X86/pr44412.ll b/llvm/test/CodeGen/X86/pr44412.ll
index 67579a5bb7c52d..546dbcc1561299 100644
--- a/llvm/test/CodeGen/X86/pr44412.ll
+++ b/llvm/test/CodeGen/X86/pr44412.ll
@@ -10,7 +10,7 @@ define void @bar(i32 %0, i32 %1) nounwind {
 ; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    movl %edi, %ebx
 ; CHECK-NEXT:    decl %ebx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %ebx, %edi
 ; CHECK-NEXT:    callq foo at PLT
@@ -43,7 +43,7 @@ define void @baz(i32 %0, i32 %1) nounwind {
 ; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    movl %edi, %ebx
 ; CHECK-NEXT:    decl %ebx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_2: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %ebx, %edi
 ; CHECK-NEXT:    callq foo at PLT
diff --git a/llvm/test/CodeGen/X86/pr47874.ll b/llvm/test/CodeGen/X86/pr47874.ll
index 2da3585357a1cc..ce3aaca59fae8c 100644
--- a/llvm/test/CodeGen/X86/pr47874.ll
+++ b/llvm/test/CodeGen/X86/pr47874.ll
@@ -11,7 +11,7 @@ define void @a(ptr %arg, i32 %arg1) {
 ; SSE2-NEXT:  ## %bb.1: ## %bb2
 ; SSE2-NEXT:    movl %esi, {{[-0-9]+}}(%r{{[sb]}}p) ## 4-byte Spill
 ; SSE2-NEXT:    movl %esi, %eax
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  LBB0_2: ## %bb6
 ; SSE2-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    ## InlineAsm Start
@@ -32,7 +32,7 @@ define void @a(ptr %arg, i32 %arg1) {
 ; AVX-NEXT:  ## %bb.1: ## %bb2
 ; AVX-NEXT:    movl %esi, {{[-0-9]+}}(%r{{[sb]}}p) ## 4-byte Spill
 ; AVX-NEXT:    movl %esi, %eax
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  LBB0_2: ## %bb6
 ; AVX-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    ## InlineAsm Start
@@ -77,7 +77,7 @@ define void @b(ptr %arg, i64 %arg1) {
 ; SSE2-NEXT:    jle LBB1_3
 ; SSE2-NEXT:  ## %bb.1: ## %bb2
 ; SSE2-NEXT:    movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  LBB1_2: ## %bb6
 ; SSE2-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    ## InlineAsm Start
@@ -97,7 +97,7 @@ define void @b(ptr %arg, i64 %arg1) {
 ; AVX-NEXT:    jle LBB1_3
 ; AVX-NEXT:  ## %bb.1: ## %bb2
 ; AVX-NEXT:    movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  LBB1_2: ## %bb6
 ; AVX-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    ## InlineAsm Start
@@ -142,7 +142,7 @@ define void @c(ptr %arg, ptr %arg1, i32 %arg2) {
 ; SSE2-NEXT:  ## %bb.1: ## %bb4
 ; SSE2-NEXT:    movl %edx, {{[-0-9]+}}(%r{{[sb]}}p) ## 4-byte Spill
 ; SSE2-NEXT:    movl %edx, %eax
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  LBB2_2: ## %bb8
 ; SSE2-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    ## InlineAsm Start
@@ -163,7 +163,7 @@ define void @c(ptr %arg, ptr %arg1, i32 %arg2) {
 ; AVX-NEXT:  ## %bb.1: ## %bb4
 ; AVX-NEXT:    movl %edx, {{[-0-9]+}}(%r{{[sb]}}p) ## 4-byte Spill
 ; AVX-NEXT:    movl %edx, %eax
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  LBB2_2: ## %bb8
 ; AVX-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    ## InlineAsm Start
@@ -210,7 +210,7 @@ define void @d(ptr %arg, ptr %arg1, i64 %arg2) {
 ; SSE2-NEXT:    jle LBB3_3
 ; SSE2-NEXT:  ## %bb.1: ## %bb3
 ; SSE2-NEXT:    movq %rdx, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  LBB3_2: ## %bb6
 ; SSE2-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    ## InlineAsm Start
@@ -230,7 +230,7 @@ define void @d(ptr %arg, ptr %arg1, i64 %arg2) {
 ; AVX-NEXT:    jle LBB3_3
 ; AVX-NEXT:  ## %bb.1: ## %bb3
 ; AVX-NEXT:    movq %rdx, {{[-0-9]+}}(%r{{[sb]}}p) ## 8-byte Spill
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  LBB3_2: ## %bb6
 ; AVX-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    ## InlineAsm Start
diff --git a/llvm/test/CodeGen/X86/pr49393.ll b/llvm/test/CodeGen/X86/pr49393.ll
index 3fb6a82f3fbb2c..512177246b5d99 100644
--- a/llvm/test/CodeGen/X86/pr49393.ll
+++ b/llvm/test/CodeGen/X86/pr49393.ll
@@ -9,7 +9,7 @@ define void @f() {
 ; CHECK-NEXT:    movapd %xmm0, %xmm1
 ; CHECK-NEXT:    mulsd %xmm0, %xmm1
 ; CHECK-NEXT:    subsd %xmm0, %xmm1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %for.cond
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    imull %eax, %eax
diff --git a/llvm/test/CodeGen/X86/pr49451.ll b/llvm/test/CodeGen/X86/pr49451.ll
index cc4607c5c55f3c..173c41140ebef1 100644
--- a/llvm/test/CodeGen/X86/pr49451.ll
+++ b/llvm/test/CodeGen/X86/pr49451.ll
@@ -15,7 +15,7 @@ define void @func_6(i8 %uc_8, i64 %uli_10) nounwind {
 ; X86-NEXT:    xorl %edx, %edx
 ; X86-NEXT:    xorl %ebx, %ebx
 ; X86-NEXT:    # implicit-def: $si
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB0_1: # %for.body612
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    testb %dl, %dl
@@ -37,7 +37,7 @@ define void @func_6(i8 %uc_8, i64 %uli_10) nounwind {
 ; X64-NEXT:    movl $23090, %eax # imm = 0x5A32
 ; X64-NEXT:    xorl %ecx, %ecx
 ; X64-NEXT:    # implicit-def: $dx
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB0_1: # %for.body612
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    testb %cl, %cl
diff --git a/llvm/test/CodeGen/X86/pr50374.ll b/llvm/test/CodeGen/X86/pr50374.ll
index 0db038f7d8595f..edb52c6e27bb6b 100644
--- a/llvm/test/CodeGen/X86/pr50374.ll
+++ b/llvm/test/CodeGen/X86/pr50374.ll
@@ -4,7 +4,7 @@
 define void @PR50374() {
 ; CHECK-LABEL: PR50374:
 ; CHECK:       # %bb.0: # %while.84.body.preheader
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %vector.body1999
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB0_1
diff --git a/llvm/test/CodeGen/X86/pr50782.ll b/llvm/test/CodeGen/X86/pr50782.ll
index c6dab7dc26fd58..591a33446d4e30 100644
--- a/llvm/test/CodeGen/X86/pr50782.ll
+++ b/llvm/test/CodeGen/X86/pr50782.ll
@@ -52,7 +52,7 @@ define void @h(float %i) {
 ; CHECK-NEXT:    fildl 12(%esi)
 ; CHECK-NEXT:    movl _c, %edx
 ; CHECK-NEXT:    jmp LBB0_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_5: # %for.inc
 ; CHECK-NEXT:    # in Loop: Header=BB0_3 Depth=1
 ; CHECK-NEXT:    fxch %st(5)
diff --git a/llvm/test/CodeGen/X86/pr51371.ll b/llvm/test/CodeGen/X86/pr51371.ll
index 9b63269e962070..8952f0967cde0e 100644
--- a/llvm/test/CodeGen/X86/pr51371.ll
+++ b/llvm/test/CodeGen/X86/pr51371.ll
@@ -9,7 +9,7 @@ define void @pmuldq(ptr nocapture %0, i32 %1, i64 %2) {
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    movd %esi, %xmm0
 ; CHECK-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movdqa (%rdi), %xmm1
 ; CHECK-NEXT:    pmuldq %xmm0, %xmm1
@@ -51,7 +51,7 @@ define void @pmuludq(ptr nocapture %0, i32 %1, i64 %2) {
 ; CHECK-NEXT:  # %bb.1:
 ; CHECK-NEXT:    movd %esi, %xmm0
 ; CHECK-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_2: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movdqa (%rdi), %xmm1
 ; CHECK-NEXT:    pmuludq %xmm0, %xmm1
diff --git a/llvm/test/CodeGen/X86/pr5145.ll b/llvm/test/CodeGen/X86/pr5145.ll
index 16398cb57061ff..5cb0ac9bc9821a 100644
--- a/llvm/test/CodeGen/X86/pr5145.ll
+++ b/llvm/test/CodeGen/X86/pr5145.ll
@@ -6,7 +6,7 @@ define void @atomic_maxmin_i8() {
 ; CHECK-LABEL: atomic_maxmin_i8:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    movzbl sc8(%rip), %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %atomicrmw.start14
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpb $6, %al
@@ -18,7 +18,7 @@ define void @atomic_maxmin_i8() {
 ; CHECK-NEXT:    jne .LBB0_1
 ; CHECK-NEXT:  # %bb.2: # %atomicrmw.end13
 ; CHECK-NEXT:    movzbl sc8(%rip), %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_3: # %atomicrmw.start8
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpb $7, %al
@@ -30,7 +30,7 @@ define void @atomic_maxmin_i8() {
 ; CHECK-NEXT:    jne .LBB0_3
 ; CHECK-NEXT:  # %bb.4: # %atomicrmw.end7
 ; CHECK-NEXT:    movzbl sc8(%rip), %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_5: # %atomicrmw.start2
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpb $8, %al
@@ -42,7 +42,7 @@ define void @atomic_maxmin_i8() {
 ; CHECK-NEXT:    jne .LBB0_5
 ; CHECK-NEXT:  # %bb.6: # %atomicrmw.end1
 ; CHECK-NEXT:    movzbl sc8(%rip), %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_7: # %atomicrmw.start
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpb $9, %al
diff --git a/llvm/test/CodeGen/X86/pr51615.ll b/llvm/test/CodeGen/X86/pr51615.ll
index 8b2cea73fd36c4..a062aa138a1e58 100644
--- a/llvm/test/CodeGen/X86/pr51615.ll
+++ b/llvm/test/CodeGen/X86/pr51615.ll
@@ -83,13 +83,13 @@ define void @elts_from_consecutive_loads(ptr %arg, ptr %arg12, ptr %arg13, float
 ; ALL-LABEL: elts_from_consecutive_loads:
 ; ALL:       # %bb.0: # %bb
 ; ALL-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; ALL-NEXT:    .p2align 4, 0x90
+; ALL-NEXT:    .p2align 4
 ; ALL-NEXT:  .LBB3_1: # %bb16
 ; ALL-NEXT:    # =>This Loop Header: Depth=1
 ; ALL-NEXT:    # Child Loop BB3_2 Depth 2
 ; ALL-NEXT:    testb $1, %cl
 ; ALL-NEXT:    je .LBB3_1
-; ALL-NEXT:    .p2align 4, 0x90
+; ALL-NEXT:    .p2align 4
 ; ALL-NEXT:  .LBB3_2: # %bb17
 ; ALL-NEXT:    # Parent Loop BB3_1 Depth=1
 ; ALL-NEXT:    # => This Inner Loop Header: Depth=2
diff --git a/llvm/test/CodeGen/X86/pr53842.ll b/llvm/test/CodeGen/X86/pr53842.ll
index 26d1a977c84c53..a962a9b3ddf2fb 100644
--- a/llvm/test/CodeGen/X86/pr53842.ll
+++ b/llvm/test/CodeGen/X86/pr53842.ll
@@ -14,7 +14,7 @@ define void @PR53842() {
 ; CHECK-NEXT:    vpcmpeqq %ymm3, %ymm2, %ymm2
 ; CHECK-NEXT:    vpcmpeqq %ymm3, %ymm1, %ymm1
 ; CHECK-NEXT:    vinserti64x4 $1, %ymm2, %zmm1, %zmm1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %vector.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vpsubq %zmm1, %zmm0, %zmm0
diff --git a/llvm/test/CodeGen/X86/pr53990-incorrect-machine-sink.ll b/llvm/test/CodeGen/X86/pr53990-incorrect-machine-sink.ll
index ac5ee4635d5063..f2f6e6934abeb6 100644
--- a/llvm/test/CodeGen/X86/pr53990-incorrect-machine-sink.ll
+++ b/llvm/test/CodeGen/X86/pr53990-incorrect-machine-sink.ll
@@ -16,7 +16,7 @@ define void @test(i1 %c, ptr %p, ptr noalias %p2) nounwind {
 ; CHECK-NEXT:    movq (%rsi), %r14
 ; CHECK-NEXT:    movb $1, %r15b
 ; CHECK-NEXT:    jmp .LBB0_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_4: # %sink
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    movq %r14, (%rbx)
diff --git a/llvm/test/CodeGen/X86/pr55648.ll b/llvm/test/CodeGen/X86/pr55648.ll
index 6e99643aecbd3a..da62b07915c868 100644
--- a/llvm/test/CodeGen/X86/pr55648.ll
+++ b/llvm/test/CodeGen/X86/pr55648.ll
@@ -4,7 +4,7 @@
 define void @PR55648() #0 {
 ; CHECK-LABEL: PR55648:
 ; CHECK:       # %bb.0: # %bb
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb38
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB0_1
diff --git a/llvm/test/CodeGen/X86/pr61923.ll b/llvm/test/CodeGen/X86/pr61923.ll
index 576b029cd03297..f9290b9743f47f 100644
--- a/llvm/test/CodeGen/X86/pr61923.ll
+++ b/llvm/test/CodeGen/X86/pr61923.ll
@@ -14,7 +14,7 @@ define void @test_loop(ptr align 1 %src, ptr align 1 %dest, i32 %len) {
 ; CHECK-NEXT:    movl %edx, %eax
 ; CHECK-NEXT:    andl $-32, %eax
 ; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %memcmp.loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    vmovups (%rsi,%rcx), %ymm0
diff --git a/llvm/test/CodeGen/X86/pr63108.ll b/llvm/test/CodeGen/X86/pr63108.ll
index b1576851ed0236..53f6fa697c452e 100644
--- a/llvm/test/CodeGen/X86/pr63108.ll
+++ b/llvm/test/CodeGen/X86/pr63108.ll
@@ -17,7 +17,7 @@ define i32 @PR63108() {
 ; SSE-NEXT:    pxor %xmm0, %xmm0
 ; SSE-NEXT:    movd {{.*#+}} xmm1 = [57339,0,0,0]
 ; SSE-NEXT:    xorl %eax, %eax
-; SSE-NEXT:    .p2align 4, 0x90
+; SSE-NEXT:    .p2align 4
 ; SSE-NEXT:  .LBB0_3: # %vector.body
 ; SSE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-NEXT:    movdqa %xmm1, %xmm2
@@ -52,7 +52,7 @@ define i32 @PR63108() {
 ; AVX1-NEXT:  .LBB0_2: # %vector.body.preheader
 ; AVX1-NEXT:    vmovss {{.*#+}} xmm0 = [57339,0,0,0]
 ; AVX1-NEXT:    xorl %eax, %eax
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB0_3: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vmovaps %ymm0, %ymm1
@@ -89,7 +89,7 @@ define i32 @PR63108() {
 ; AVX2-NEXT:  .LBB0_2: # %vector.body.preheader
 ; AVX2-NEXT:    vmovd {{.*#+}} xmm0 = [57339,0,0,0]
 ; AVX2-NEXT:    xorl %eax, %eax
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB0_3: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vmovdqa %ymm0, %ymm1
@@ -126,7 +126,7 @@ define i32 @PR63108() {
 ; AVX512-NEXT:  .LBB0_2: # %vector.body.preheader
 ; AVX512-NEXT:    vmovd {{.*#+}} xmm0 = [57339,0,0,0]
 ; AVX512-NEXT:    xorl %eax, %eax
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB0_3: # %vector.body
 ; AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vmovdqa %ymm0, %ymm1
diff --git a/llvm/test/CodeGen/X86/pr63692.ll b/llvm/test/CodeGen/X86/pr63692.ll
index fb3198743a3949..8cbd24240e1d8a 100644
--- a/llvm/test/CodeGen/X86/pr63692.ll
+++ b/llvm/test/CodeGen/X86/pr63692.ll
@@ -6,7 +6,7 @@ define void @prefault(ptr noundef %range_start, ptr noundef readnone %range_end)
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    cmpq %rsi, %rdi
 ; CHECK-NEXT:    jae .LBB0_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %while.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    lock orb $0, (%rdi)
diff --git a/llvm/test/CodeGen/X86/pr65895.ll b/llvm/test/CodeGen/X86/pr65895.ll
index ced60ee73cc84a..0990b10fa936de 100644
--- a/llvm/test/CodeGen/X86/pr65895.ll
+++ b/llvm/test/CodeGen/X86/pr65895.ll
@@ -16,7 +16,7 @@ define i32 @PR65895() {
 ; CHECK-NEXT:    je .LBB0_3
 ; CHECK-NEXT:  # %bb.1: # %for.body.lr.ph
 ; CHECK-NEXT:    movb %al, b(%rip)
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB0_2
diff --git a/llvm/test/CodeGen/X86/pr68539.ll b/llvm/test/CodeGen/X86/pr68539.ll
index 8c7e7792dc5f4c..5e3a7b8dbafb28 100644
--- a/llvm/test/CodeGen/X86/pr68539.ll
+++ b/llvm/test/CodeGen/X86/pr68539.ll
@@ -4,7 +4,7 @@
 define i32 @main(i1 %arg) {
 ; CHECK-LABEL: main:
 ; CHECK:       # %bb.0: # %bb
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB0_1
diff --git a/llvm/test/CodeGen/X86/pr93000.ll b/llvm/test/CodeGen/X86/pr93000.ll
index 0bd5da48847e84..d55332f81c2ca4 100644
--- a/llvm/test/CodeGen/X86/pr93000.ll
+++ b/llvm/test/CodeGen/X86/pr93000.ll
@@ -6,7 +6,7 @@ define void @PR93000(ptr %a0, ptr %a1, ptr %a2, <32 x i16> %a3) {
 ; CHECK:       # %bb.0: # %Entry
 ; CHECK-NEXT:    movl (%rdi), %eax
 ; CHECK-NEXT:    addq $4, %rdi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %Loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    kmovd %eax, %k1
diff --git a/llvm/test/CodeGen/X86/promote-sra-by-itself.ll b/llvm/test/CodeGen/X86/promote-sra-by-itself.ll
index e19f30b3863396..d57411f495b697 100644
--- a/llvm/test/CodeGen/X86/promote-sra-by-itself.ll
+++ b/llvm/test/CodeGen/X86/promote-sra-by-itself.ll
@@ -19,7 +19,7 @@ define i16 @basic(ptr %p) {
 define void @crash(i1 %cond, ptr %p) {
 ; CHECK-LABEL: crash:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_1: # %loop
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb $1, %dil
diff --git a/llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll b/llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll
index c0bfb71e189cd5..beb42f55b709cc 100644
--- a/llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll
+++ b/llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll
@@ -84,7 +84,7 @@ define ptr @SyFgets(ptr %line, i64 %length, i64 %fid) {
 ; CHECK-NEXT:    movq _syCTRO at GOTPCREL(%rip), %rax
 ; CHECK-NEXT:    movl $1, %r13d
 ; CHECK-NEXT:    movb $1, %cl
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_9: ## %do.body
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $0, (%rax)
@@ -108,7 +108,7 @@ define ptr @SyFgets(ptr %line, i64 %length, i64 %fid) {
 ; CHECK-NEXT:    ## in Loop: Header=BB0_13 Depth=1
 ; CHECK-NEXT:    testb %r12b, %r12b
 ; CHECK-NEXT:    je LBB0_54
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_20: ## %while.cond197.backedge
 ; CHECK-NEXT:    ## in Loop: Header=BB0_13 Depth=1
 ; CHECK-NEXT:    decl %r13d
@@ -141,7 +141,7 @@ define ptr @SyFgets(ptr %line, i64 %length, i64 %fid) {
 ; CHECK-NEXT:    ## in Loop: Header=BB0_13 Depth=1
 ; CHECK-NEXT:    ## implicit-def: $rax
 ; CHECK-NEXT:    jmp LBB0_28
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_31: ## %do.body479.backedge
 ; CHECK-NEXT:    ## in Loop: Header=BB0_28 Depth=2
 ; CHECK-NEXT:    leaq 1(%rbx), %rax
@@ -165,7 +165,7 @@ define ptr @SyFgets(ptr %line, i64 %length, i64 %fid) {
 ; CHECK-NEXT:    testb %r12b, %r12b
 ; CHECK-NEXT:    jne LBB0_31
 ; CHECK-NEXT:    jmp LBB0_33
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_14: ## %while.body200
 ; CHECK-NEXT:    ## in Loop: Header=BB0_13 Depth=1
 ; CHECK-NEXT:    leal 1(%rbp), %eax
@@ -223,7 +223,7 @@ define ptr @SyFgets(ptr %line, i64 %length, i64 %fid) {
 ; CHECK-NEXT:    ## in Loop: Header=BB0_13 Depth=1
 ; CHECK-NEXT:    movq _SyFgets.yank at GOTPCREL(%rip), %rax
 ; CHECK-NEXT:    movb $0, (%rax)
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_37: ## %for.cond534
 ; CHECK-NEXT:    ## Parent Loop BB0_13 Depth=1
 ; CHECK-NEXT:    ## => This Inner Loop Header: Depth=2
@@ -235,15 +235,15 @@ define ptr @SyFgets(ptr %line, i64 %length, i64 %fid) {
 ; CHECK-NEXT:    movb $0, (%rbx)
 ; CHECK-NEXT:    leaq LJTI0_0(%rip), %rdx
 ; CHECK-NEXT:    jmp LBB0_20
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_41: ## %while.cond864
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp LBB0_41
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_42: ## %while.cond962
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp LBB0_42
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_24: ## %for.cond357
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp LBB0_24
@@ -266,7 +266,7 @@ define ptr @SyFgets(ptr %line, i64 %length, i64 %fid) {
 ; CHECK-NEXT:    subq %rbx, %r14
 ; CHECK-NEXT:    movq _syHistory at GOTPCREL(%rip), %rax
 ; CHECK-NEXT:    leaq 8189(%r14,%rax), %rax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_48: ## %for.body1723
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    decq %rax
@@ -279,11 +279,11 @@ define ptr @SyFgets(ptr %line, i64 %length, i64 %fid) {
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    testb %al, %al
 ; CHECK-NEXT:    je LBB0_40
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_17: ## %for.body643.us
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp LBB0_17
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_40: ## %while.cond661
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp LBB0_40
@@ -300,7 +300,7 @@ define ptr @SyFgets(ptr %line, i64 %length, i64 %fid) {
 ; CHECK-NEXT:  ## %bb.51: ## %while.body1679.preheader
 ; CHECK-NEXT:    incl %ebp
 ; CHECK-NEXT:    xorl %ebx, %ebx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_52: ## %while.body1679
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movq (%r14), %rdi
diff --git a/llvm/test/CodeGen/X86/rdrand.ll b/llvm/test/CodeGen/X86/rdrand.ll
index 164145a789943a..52f767a4a419ce 100644
--- a/llvm/test/CodeGen/X86/rdrand.ll
+++ b/llvm/test/CodeGen/X86/rdrand.ll
@@ -89,7 +89,7 @@ define void @loop(ptr %p, i32 %n) nounwind {
 ; X86-NEXT:  # %bb.1: # %while.body.preheader
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    xorl %edx, %edx
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB3_2: # %while.body
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    rdrandl %esi
@@ -108,7 +108,7 @@ define void @loop(ptr %p, i32 %n) nounwind {
 ; X64-NEXT:  # %bb.1: # %while.body.preheader
 ; X64-NEXT:    movl %esi, %eax
 ; X64-NEXT:    xorl %ecx, %ecx
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB3_2: # %while.body
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    rdrandl %edx
diff --git a/llvm/test/CodeGen/X86/retpoline.ll b/llvm/test/CodeGen/X86/retpoline.ll
index d06ddc64044d04..ea9c9bc4fae22f 100644
--- a/llvm/test/CodeGen/X86/retpoline.ll
+++ b/llvm/test/CodeGen/X86/retpoline.ll
@@ -426,7 +426,7 @@ latch:
 ; X64-NEXT:          pause
 ; X64-NEXT:          lfence
 ; X64-NEXT:          jmp     [[CAPTURE_SPEC]]
-; X64-NEXT:          .p2align        4, 0x90
+; X64-NEXT:          .p2align        4
 ; X64-NEXT:  {{.*}}                                  # Block address taken
 ; X64-NEXT:                                          # %entry
 ; X64-NEXT:  [[CALL_TARGET]]:
@@ -445,7 +445,7 @@ latch:
 ; X86-NEXT:          pause
 ; X86-NEXT:          lfence
 ; X86-NEXT:          jmp     [[CAPTURE_SPEC]]
-; X86-NEXT:          .p2align        4, 0x90
+; X86-NEXT:          .p2align        4
 ; X86-NEXT:  {{.*}}                                  # Block address taken
 ; X86-NEXT:                                          # %entry
 ; X86-NEXT:  [[CALL_TARGET]]:
@@ -464,7 +464,7 @@ latch:
 ; X86-NEXT:          pause
 ; X86-NEXT:          lfence
 ; X86-NEXT:          jmp     [[CAPTURE_SPEC]]
-; X86-NEXT:          .p2align        4, 0x90
+; X86-NEXT:          .p2align        4
 ; X86-NEXT:  {{.*}}                                  # Block address taken
 ; X86-NEXT:                                          # %entry
 ; X86-NEXT:  [[CALL_TARGET]]:
@@ -483,7 +483,7 @@ latch:
 ; X86-NEXT:          pause
 ; X86-NEXT:          lfence
 ; X86-NEXT:          jmp     [[CAPTURE_SPEC]]
-; X86-NEXT:          .p2align        4, 0x90
+; X86-NEXT:          .p2align        4
 ; X86-NEXT:  {{.*}}                                  # Block address taken
 ; X86-NEXT:                                          # %entry
 ; X86-NEXT:  [[CALL_TARGET]]:
@@ -502,7 +502,7 @@ latch:
 ; X86-NEXT:          pause
 ; X86-NEXT:          lfence
 ; X86-NEXT:          jmp     [[CAPTURE_SPEC]]
-; X86-NEXT:          .p2align        4, 0x90
+; X86-NEXT:          .p2align        4
 ; X86-NEXT:  {{.*}}                                  # Block address taken
 ; X86-NEXT:                                          # %entry
 ; X86-NEXT:  [[CALL_TARGET]]:
diff --git a/llvm/test/CodeGen/X86/reverse_branches.ll b/llvm/test/CodeGen/X86/reverse_branches.ll
index d874a47356e3ce..93c82a4524ef9b 100644
--- a/llvm/test/CodeGen/X86/reverse_branches.ll
+++ b/llvm/test/CodeGen/X86/reverse_branches.ll
@@ -37,7 +37,7 @@ define i32 @test_branches_order() uwtable ssp {
 ; CHECK-NEXT:    leaq -{{[0-9]+}}(%rsp), %r14
 ; CHECK-NEXT:    movq %rsp, %r15
 ; CHECK-NEXT:    jmp LBB0_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_6: ## %for.inc9
 ; CHECK-NEXT:    ## in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    incl %ebx
@@ -51,7 +51,7 @@ define i32 @test_branches_order() uwtable ssp {
 ; CHECK-NEXT:    movl $-1, %ebp
 ; CHECK-NEXT:    movq %r15, %rdi
 ; CHECK-NEXT:    movq %r14, %r12
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_3: ## %for.cond1
 ; CHECK-NEXT:    ## Parent Loop BB0_1 Depth=1
 ; CHECK-NEXT:    ## => This Inner Loop Header: Depth=2
@@ -75,7 +75,7 @@ define i32 @test_branches_order() uwtable ssp {
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    movq %rsp, %rcx
 ; CHECK-NEXT:    jmp LBB0_8
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_15: ## %for.inc38
 ; CHECK-NEXT:    ## in Loop: Header=BB0_8 Depth=1
 ; CHECK-NEXT:    incl %eax
@@ -91,7 +91,7 @@ define i32 @test_branches_order() uwtable ssp {
 ; CHECK-NEXT:    xorl %esi, %esi
 ; CHECK-NEXT:    xorl %edi, %edi
 ; CHECK-NEXT:    jmp LBB0_10
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_14: ## %exit
 ; CHECK-NEXT:    ## in Loop: Header=BB0_10 Depth=2
 ; CHECK-NEXT:    addq %rsi, %r8
@@ -109,7 +109,7 @@ define i32 @test_branches_order() uwtable ssp {
 ; CHECK-NEXT:  ## %bb.11: ## %for.body20
 ; CHECK-NEXT:    ## in Loop: Header=BB0_10 Depth=2
 ; CHECK-NEXT:    movq $-1000, %r8 ## imm = 0xFC18
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_12: ## %do.body.i
 ; CHECK-NEXT:    ## Parent Loop BB0_8 Depth=1
 ; CHECK-NEXT:    ## Parent Loop BB0_10 Depth=2
diff --git a/llvm/test/CodeGen/X86/sad.ll b/llvm/test/CodeGen/X86/sad.ll
index ca319687da54d4..245516974d15b5 100644
--- a/llvm/test/CodeGen/X86/sad.ll
+++ b/llvm/test/CodeGen/X86/sad.ll
@@ -14,7 +14,7 @@ define dso_local i32 @sad_16i8() nounwind {
 ; SSE2-NEXT:    pxor %xmm0, %xmm0
 ; SSE2-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB0_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqu a+1024(%rax), %xmm2
@@ -39,7 +39,7 @@ define dso_local i32 @sad_16i8() nounwind {
 ; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB0_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vmovdqu a+1024(%rax), %xmm2
@@ -67,7 +67,7 @@ define dso_local i32 @sad_16i8() nounwind {
 ; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX2-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB0_1: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vmovdqu a+1024(%rax), %xmm2
@@ -91,7 +91,7 @@ define dso_local i32 @sad_16i8() nounwind {
 ; AVX512:       # %bb.0: # %entry
 ; AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB0_1: # %vector.body
 ; AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vmovdqu a+1024(%rax), %xmm1
@@ -154,7 +154,7 @@ define dso_local i32 @sad_32i8() nounwind {
 ; SSE2-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
 ; SSE2-NEXT:    pxor %xmm2, %xmm2
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB1_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqa a+1024(%rax), %xmm3
@@ -184,7 +184,7 @@ define dso_local i32 @sad_32i8() nounwind {
 ; AVX1-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX1-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB1_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vmovdqa a+1024(%rax), %xmm2
@@ -220,7 +220,7 @@ define dso_local i32 @sad_32i8() nounwind {
 ; AVX2-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX2-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB1_1: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vmovdqa a+1024(%rax), %ymm2
@@ -247,7 +247,7 @@ define dso_local i32 @sad_32i8() nounwind {
 ; AVX512-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX512-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX512-NEXT:    .p2align 4, 0x90
+; AVX512-NEXT:    .p2align 4
 ; AVX512-NEXT:  .LBB1_1: # %vector.body
 ; AVX512-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512-NEXT:    vmovdqa a+1024(%rax), %ymm2
@@ -315,7 +315,7 @@ define dso_local i32 @sad_avx64i8() nounwind {
 ; SSE2-NEXT:    pxor %xmm3, %xmm3
 ; SSE2-NEXT:    pxor %xmm2, %xmm2
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB2_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqa a+1024(%rax), %xmm5
@@ -359,7 +359,7 @@ define dso_local i32 @sad_avx64i8() nounwind {
 ; AVX1-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB2_1: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vmovdqa a+1024(%rax), %xmm3
@@ -411,7 +411,7 @@ define dso_local i32 @sad_avx64i8() nounwind {
 ; AVX2-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB2_1: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vmovdqa a+1024(%rax), %ymm3
@@ -444,7 +444,7 @@ define dso_local i32 @sad_avx64i8() nounwind {
 ; AVX512F-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512F-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX512F-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX512F-NEXT:    .p2align 4, 0x90
+; AVX512F-NEXT:    .p2align 4
 ; AVX512F-NEXT:  .LBB2_1: # %vector.body
 ; AVX512F-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512F-NEXT:    vmovdqa a+1024(%rax), %ymm2
@@ -476,7 +476,7 @@ define dso_local i32 @sad_avx64i8() nounwind {
 ; AVX512BW-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX512BW-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX512BW-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX512BW-NEXT:    .p2align 4, 0x90
+; AVX512BW-NEXT:    .p2align 4
 ; AVX512BW-NEXT:  .LBB2_1: # %vector.body
 ; AVX512BW-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512BW-NEXT:    vmovdqa64 a+1024(%rax), %zmm2
@@ -545,7 +545,7 @@ define dso_local i32 @sad_2i8() nounwind {
 ; SSE2-NEXT:    pxor %xmm0, %xmm0
 ; SSE2-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; SSE2-NEXT:    movd {{.*#+}} xmm1 = [65535,0,0,0]
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB3_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
@@ -567,7 +567,7 @@ define dso_local i32 @sad_2i8() nounwind {
 ; AVX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB3_1: # %vector.body
 ; AVX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    vmovd {{.*#+}} xmm2 = mem[0],zero,zero,zero
@@ -618,7 +618,7 @@ define dso_local i32 @sad_4i8() nounwind {
 ; SSE2:       # %bb.0: # %entry
 ; SSE2-NEXT:    pxor %xmm0, %xmm0
 ; SSE2-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB4_1: # %vector.body
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
@@ -639,7 +639,7 @@ define dso_local i32 @sad_4i8() nounwind {
 ; AVX:       # %bb.0: # %entry
 ; AVX-NEXT:    vpxor %xmm0, %xmm0, %xmm0
 ; AVX-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  .LBB4_1: # %vector.body
 ; AVX-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    vmovd {{.*#+}} xmm1 = mem[0],zero,zero,zero
diff --git a/llvm/test/CodeGen/X86/saddo-redundant-add.ll b/llvm/test/CodeGen/X86/saddo-redundant-add.ll
index e89d81a8423181..f132ef8baab924 100644
--- a/llvm/test/CodeGen/X86/saddo-redundant-add.ll
+++ b/llvm/test/CodeGen/X86/saddo-redundant-add.ll
@@ -6,7 +6,7 @@ define void @redundant_add(i64 %n) {
 ; CHECK-LABEL: redundant_add:
 ; CHECK:       ## %bb.0: ## %entry
 ; CHECK-NEXT:    xorl %eax, %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_1: ## %exit_check
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpq %rdi, %rax
diff --git a/llvm/test/CodeGen/X86/same-align-bytes-with-llasm-llobj.ll b/llvm/test/CodeGen/X86/same-align-bytes-with-llasm-llobj.ll
new file mode 100644
index 00000000000000..2b85b45dc4f853
--- /dev/null
+++ b/llvm/test/CodeGen/X86/same-align-bytes-with-llasm-llobj.ll
@@ -0,0 +1,46 @@
+; RUN: llc %s -o - -filetype=obj --mcpu=znver2 | llvm-objdump -dr  - | FileCheck %s
+; RUN: llc %s -o - -filetype=asm --mcpu=znver2 | llvm-mc - -o - --mcpu=znver2 -filetype=obj | llvm-objdump -dr  - | FileCheck %s
+; RUN: llc %s -o - -filetype=asm --mcpu=znver2 | FileCheck %s --check-prefix=ASM
+
+;; Check that we produce a push, then an align-to-16-bytes p2align.
+;
+; ASM:        # %bb.0:
+; ASM-NEXT:   pushq   %rax
+; ASM-NEXT:   .cfi_def_cfa_offset 16
+; ASM-NEXT:   .p2align        4
+
+;; When we assemble the file, either using the built-in asssembler or going
+;; via a textual assembly file, we should get the same padding between the
+;; initial push and the next block for alignment. It's a single 15 byte
+;; nop.
+
+; CHECK:        0:   50
+; CHECK-NEXT:   66 66 66 66 66 66 2e 0f 1f 84 00 00 00 00 00 nopw %cs:(%rax,%rax)
+
+;; Note that we specify a CPU to ensure the same nop patterns are selected
+;; between llvm-mc and llc, just in case defaults changed, which one isn't
+;; important.
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: noreturn nounwind uwtable
+define dso_local void @b() local_unnamed_addr {
+entry:
+  br label %for.cond
+
+for.cond:
+  tail call void (...) @a()
+  br label %for.cond
+}
+
+declare void @a(...) local_unnamed_addr
+
+!llvm.module.flags = !{!0, !1, !2, !3}
+!llvm.ident = !{!4}
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{i32 8, !"PIC Level", i32 2}
+!2 = !{i32 7, !"PIE Level", i32 2}
+!3 = !{i32 7, !"uwtable", i32 2}
+!4 = !{!"clang"}
diff --git a/llvm/test/CodeGen/X86/scalar_widen_div.ll b/llvm/test/CodeGen/X86/scalar_widen_div.ll
index 23e3d0c5c43213..1d98b4f62069d0 100644
--- a/llvm/test/CodeGen/X86/scalar_widen_div.ll
+++ b/llvm/test/CodeGen/X86/scalar_widen_div.ll
@@ -394,7 +394,7 @@ define void @test_int_div(ptr %dest, ptr %old, i32 %n) {
 ; CHECK-NEXT:  # %bb.1: # %bb.nph
 ; CHECK-NEXT:    movl %edx, %ecx
 ; CHECK-NEXT:    xorl %r10d, %r10d
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB12_2: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl (%rdi,%r10), %r8d
diff --git a/llvm/test/CodeGen/X86/setcc-lowering.ll b/llvm/test/CodeGen/X86/setcc-lowering.ll
index 5bbc73eacd968e..bf31df20887d03 100644
--- a/llvm/test/CodeGen/X86/setcc-lowering.ll
+++ b/llvm/test/CodeGen/X86/setcc-lowering.ll
@@ -54,7 +54,7 @@ define void @pr26232(i64 %a, <16 x i1> %b) nounwind {
 ; AVX1-LABEL: pr26232:
 ; AVX1:       # %bb.0: # %allocas
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB1_1: # %for_loop599
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    cmpq $65536, %rdi # imm = 0x10000
@@ -71,7 +71,7 @@ define void @pr26232(i64 %a, <16 x i1> %b) nounwind {
 ;
 ; AVX2-LABEL: pr26232:
 ; AVX2:       # %bb.0: # %allocas
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB1_1: # %for_loop599
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    cmpq $65536, %rdi # imm = 0x10000
@@ -93,7 +93,7 @@ define void @pr26232(i64 %a, <16 x i1> %b) nounwind {
 ; KNL-32-NEXT:    vptestmd %zmm0, %zmm0, %k0
 ; KNL-32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; KNL-32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; KNL-32-NEXT:    .p2align 4, 0x90
+; KNL-32-NEXT:    .p2align 4
 ; KNL-32-NEXT:  .LBB1_1: # %for_loop599
 ; KNL-32-NEXT:    # =>This Inner Loop Header: Depth=1
 ; KNL-32-NEXT:    cmpl $65536, %ecx # imm = 0x10000
diff --git a/llvm/test/CodeGen/X86/setcc-non-simple-type.ll b/llvm/test/CodeGen/X86/setcc-non-simple-type.ll
index 76cf2423a254fe..2ac2be5545dfdc 100644
--- a/llvm/test/CodeGen/X86/setcc-non-simple-type.ll
+++ b/llvm/test/CodeGen/X86/setcc-non-simple-type.ll
@@ -48,14 +48,14 @@ define void @failing(ptr %0, ptr %1) nounwind {
 ; CHECK-NEXT:    movdqa {{.*#+}} xmm0 = [0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0]
 ; CHECK-NEXT:    movdqa {{.*#+}} xmm1 = [1,1]
 ; CHECK-NEXT:    movdqa {{.*#+}} xmm2 = [2,2]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %vector.ph
 ; CHECK-NEXT:    # =>This Loop Header: Depth=1
 ; CHECK-NEXT:    # Child Loop BB0_2 Depth 2
 ; CHECK-NEXT:    xorpd %xmm3, %xmm3
 ; CHECK-NEXT:    movq $-1024, %rsi # imm = 0xFC00
 ; CHECK-NEXT:    movdqa %xmm0, %xmm4
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %vector.body
 ; CHECK-NEXT:    # Parent Loop BB0_1 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
@@ -108,14 +108,14 @@ define void @failing(ptr %0, ptr %1) nounwind {
 ; CHECK-AVX2-NEXT:    vpmovsxbq {{.*#+}} xmm0 = [0,1]
 ; CHECK-AVX2-NEXT:    vpmovsxbq {{.*#+}} xmm1 = [1,1]
 ; CHECK-AVX2-NEXT:    vpmovsxbq {{.*#+}} xmm2 = [2,2]
-; CHECK-AVX2-NEXT:    .p2align 4, 0x90
+; CHECK-AVX2-NEXT:    .p2align 4
 ; CHECK-AVX2-NEXT:  .LBB0_1: # %vector.ph
 ; CHECK-AVX2-NEXT:    # =>This Loop Header: Depth=1
 ; CHECK-AVX2-NEXT:    # Child Loop BB0_2 Depth 2
 ; CHECK-AVX2-NEXT:    vpxor %xmm3, %xmm3, %xmm3
 ; CHECK-AVX2-NEXT:    movq $-1024, %rsi # imm = 0xFC00
 ; CHECK-AVX2-NEXT:    vmovdqa %xmm0, %xmm4
-; CHECK-AVX2-NEXT:    .p2align 4, 0x90
+; CHECK-AVX2-NEXT:    .p2align 4
 ; CHECK-AVX2-NEXT:  .LBB0_2: # %vector.body
 ; CHECK-AVX2-NEXT:    # Parent Loop BB0_1 Depth=1
 ; CHECK-AVX2-NEXT:    # => This Inner Loop Header: Depth=2
diff --git a/llvm/test/CodeGen/X86/shift-parts.ll b/llvm/test/CodeGen/X86/shift-parts.ll
index c48f7c5a0c0ba0..62d86909ffca27 100644
--- a/llvm/test/CodeGen/X86/shift-parts.ll
+++ b/llvm/test/CodeGen/X86/shift-parts.ll
@@ -13,7 +13,7 @@ define i32 @int87(i32 %uint64p_8, i1 %cond) nounwind {
 ; CHECK-NEXT:    movq g_144+16(%rip), %rcx
 ; CHECK-NEXT:    movzbl %sil, %edx
 ; CHECK-NEXT:    shll $6, %edx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %for.cond
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb $64, %dl
diff --git a/llvm/test/CodeGen/X86/sink-out-of-loop.ll b/llvm/test/CodeGen/X86/sink-out-of-loop.ll
index 55d8c7bb03697f..4634d34a7536cd 100644
--- a/llvm/test/CodeGen/X86/sink-out-of-loop.ll
+++ b/llvm/test/CodeGen/X86/sink-out-of-loop.ll
@@ -9,19 +9,19 @@ define i32 @sink_succ(i32 %argc, ptr nocapture %argv) nounwind uwtable ssp {
 ; CHECK-LABEL: sink_succ:
 ; CHECK:       ## %bb.0: ## %entry
 ; CHECK-NEXT:    xorl %eax, %eax
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_1: ## %preheader
 ; CHECK-NEXT:    ## =>This Loop Header: Depth=1
 ; CHECK-NEXT:    ## Child Loop BB0_2 Depth 2
 ; CHECK-NEXT:    ## Child Loop BB0_3 Depth 3
 ; CHECK-NEXT:    movl $1, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_2: ## %for.body1.lr
 ; CHECK-NEXT:    ## Parent Loop BB0_1 Depth=1
 ; CHECK-NEXT:    ## => This Loop Header: Depth=2
 ; CHECK-NEXT:    ## Child Loop BB0_3 Depth 3
 ; CHECK-NEXT:    movl %ecx, %edx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_3: ## %for.body1
 ; CHECK-NEXT:    ## Parent Loop BB0_1 Depth=1
 ; CHECK-NEXT:    ## Parent Loop BB0_2 Depth=2
@@ -40,7 +40,7 @@ define i32 @sink_succ(i32 %argc, ptr nocapture %argv) nounwind uwtable ssp {
 ; CHECK-NEXT:    jne LBB0_1
 ; CHECK-NEXT:  ## %bb.6: ## %for.body2.preheader
 ; CHECK-NEXT:    movl $2048, %eax ## imm = 0x800
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_7: ## %for.body2
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    decl %eax
@@ -91,7 +91,7 @@ define i32 @sink_out_of_loop(i32 %n, ptr %output) {
 ; CHECK-LABEL: sink_out_of_loop:
 ; CHECK:       ## %bb.0: ## %entry
 ; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB1_1: ## %loop
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %ecx, %eax
diff --git a/llvm/test/CodeGen/X86/speculative-load-hardening.ll b/llvm/test/CodeGen/X86/speculative-load-hardening.ll
index 45da777ea4e2a2..5fd1f77e166d43 100644
--- a/llvm/test/CodeGen/X86/speculative-load-hardening.ll
+++ b/llvm/test/CodeGen/X86/speculative-load-hardening.ll
@@ -217,7 +217,7 @@ define void @test_basic_loop(i32 %a, i32 %b, ptr %ptr1, ptr %ptr2) nounwind spec
 ; X64-NEXT:    movl %esi, %ebp
 ; X64-NEXT:    cmovneq %r15, %rax
 ; X64-NEXT:    xorl %r12d, %r12d
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB2_3: # %l.header
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movslq (%r14), %rcx
@@ -267,7 +267,7 @@ define void @test_basic_loop(i32 %a, i32 %b, ptr %ptr1, ptr %ptr2) nounwind spec
 ; X64-LFENCE-NEXT:    movl %esi, %ebp
 ; X64-LFENCE-NEXT:    lfence
 ; X64-LFENCE-NEXT:    xorl %r15d, %r15d
-; X64-LFENCE-NEXT:    .p2align 4, 0x90
+; X64-LFENCE-NEXT:    .p2align 4
 ; X64-LFENCE-NEXT:  .LBB2_2: # %l.header
 ; X64-LFENCE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-LFENCE-NEXT:    lfence
@@ -331,11 +331,11 @@ define void @test_basic_nested_loop(i32 %a, i32 %b, i32 %c, ptr %ptr1, ptr %ptr2
 ; X64-NEXT:    movl %esi, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
 ; X64-NEXT:    testl %r15d, %r15d
 ; X64-NEXT:    jle .LBB3_4
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB3_5: # %l2.header.preheader
 ; X64-NEXT:    cmovleq %r12, %rax
 ; X64-NEXT:    xorl %r15d, %r15d
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB3_6: # %l2.header
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movslq (%r14), %rcx
@@ -358,12 +358,12 @@ define void @test_basic_nested_loop(i32 %a, i32 %b, i32 %c, ptr %ptr1, ptr %ptr2
 ; X64-NEXT:  # %bb.11: # in Loop: Header=BB3_6 Depth=1
 ; X64-NEXT:    cmovgeq %r12, %rax
 ; X64-NEXT:    jmp .LBB3_6
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB3_7:
 ; X64-NEXT:    cmovlq %r12, %rax
 ; X64-NEXT:    movl {{[-0-9]+}}(%r{{[sb]}}p), %r15d # 4-byte Reload
 ; X64-NEXT:    jmp .LBB3_8
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB3_4:
 ; X64-NEXT:    cmovgq %r12, %rax
 ; X64-NEXT:  .LBB3_8: # %l1.latch
@@ -432,7 +432,7 @@ define void @test_basic_nested_loop(i32 %a, i32 %b, i32 %c, ptr %ptr1, ptr %ptr2
 ; X64-LFENCE-NEXT:    lfence
 ; X64-LFENCE-NEXT:    xorl %r12d, %r12d
 ; X64-LFENCE-NEXT:    jmp .LBB3_2
-; X64-LFENCE-NEXT:    .p2align 4, 0x90
+; X64-LFENCE-NEXT:    .p2align 4
 ; X64-LFENCE-NEXT:  .LBB3_5: # %l1.latch
 ; X64-LFENCE-NEXT:    # in Loop: Header=BB3_2 Depth=1
 ; X64-LFENCE-NEXT:    lfence
@@ -452,7 +452,7 @@ define void @test_basic_nested_loop(i32 %a, i32 %b, i32 %c, ptr %ptr1, ptr %ptr2
 ; X64-LFENCE-NEXT:    # in Loop: Header=BB3_2 Depth=1
 ; X64-LFENCE-NEXT:    lfence
 ; X64-LFENCE-NEXT:    xorl %r13d, %r13d
-; X64-LFENCE-NEXT:    .p2align 4, 0x90
+; X64-LFENCE-NEXT:    .p2align 4
 ; X64-LFENCE-NEXT:  .LBB3_4: # %l2.header
 ; X64-LFENCE-NEXT:    # Parent Loop BB3_2 Depth=1
 ; X64-LFENCE-NEXT:    # => This Inner Loop Header: Depth=2
diff --git a/llvm/test/CodeGen/X86/split-extend-vector-inreg.ll b/llvm/test/CodeGen/X86/split-extend-vector-inreg.ll
index 08088496b74287..8a6c2f851a6d69 100644
--- a/llvm/test/CodeGen/X86/split-extend-vector-inreg.ll
+++ b/llvm/test/CodeGen/X86/split-extend-vector-inreg.ll
@@ -9,7 +9,7 @@ define <4 x i64> @autogen_SD88863() {
 ; CHECK-NEXT:    vxorpd %xmm1, %xmm1, %xmm1
 ; CHECK-NEXT:    vshufpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[3],ymm1[3]
 ; CHECK-NEXT:    movb $1, %al
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %CF
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb %al, %al
diff --git a/llvm/test/CodeGen/X86/sse-domains.ll b/llvm/test/CodeGen/X86/sse-domains.ll
index 116efa69bb319b..249425ec4dc9e9 100644
--- a/llvm/test/CodeGen/X86/sse-domains.ll
+++ b/llvm/test/CodeGen/X86/sse-domains.ll
@@ -18,7 +18,7 @@ define void @f(ptr nocapture %p, i32 %n) nounwind uwtable ssp {
 ; CHECK-NEXT:    addq $16, %rdi
 ; CHECK-NEXT:    pxor %xmm1, %xmm1
 ; CHECK-NEXT:    pmovsxbd {{.*#+}} xmm0 = [127,127,127,127]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB0_1: ## %while.body
 ; CHECK-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    pand %xmm0, %xmm1
diff --git a/llvm/test/CodeGen/X86/stack-coloring-wineh.ll b/llvm/test/CodeGen/X86/stack-coloring-wineh.ll
index 79057e0ea78d39..aa2f9e1cd2b1ed 100644
--- a/llvm/test/CodeGen/X86/stack-coloring-wineh.ll
+++ b/llvm/test/CodeGen/X86/stack-coloring-wineh.ll
@@ -42,7 +42,7 @@ define void @pr66984(ptr %arg) personality ptr @__CxxFrameHandler3 {
 ; I686-NEXT:    .scl 3;
 ; I686-NEXT:    .type 32;
 ; I686-NEXT:    .endef
-; I686-NEXT:    .p2align 4, 0x90
+; I686-NEXT:    .p2align 4
 ; I686-NEXT:  "?catch$2@?0?pr66984 at 4HA":
 ; I686-NEXT:  LBB0_2: # %bb17
 ; I686-NEXT:    pushl %ebp
@@ -58,7 +58,7 @@ define void @pr66984(ptr %arg) personality ptr @__CxxFrameHandler3 {
 ; I686-NEXT:    .scl 3;
 ; I686-NEXT:    .type 32;
 ; I686-NEXT:    .endef
-; I686-NEXT:    .p2align 4, 0x90
+; I686-NEXT:    .p2align 4
 ; I686-NEXT:  "?dtor$5@?0?pr66984 at 4HA":
 ; I686-NEXT:  LBB0_5: # %bb8
 ; I686-NEXT:    pushl %ebp
@@ -101,7 +101,7 @@ define void @pr66984(ptr %arg) personality ptr @__CxxFrameHandler3 {
 ; X86_64-NEXT:    .scl 3;
 ; X86_64-NEXT:    .type 32;
 ; X86_64-NEXT:    .endef
-; X86_64-NEXT:    .p2align 4, 0x90
+; X86_64-NEXT:    .p2align 4
 ; X86_64-NEXT:  "?catch$2@?0?pr66984 at 4HA":
 ; X86_64-NEXT:  .seh_proc "?catch$2@?0?pr66984 at 4HA"
 ; X86_64-NEXT:    .seh_handler __CxxFrameHandler3, @unwind, @except
@@ -127,7 +127,7 @@ define void @pr66984(ptr %arg) personality ptr @__CxxFrameHandler3 {
 ; X86_64-NEXT:    .scl 3;
 ; X86_64-NEXT:    .type 32;
 ; X86_64-NEXT:    .endef
-; X86_64-NEXT:    .p2align 4, 0x90
+; X86_64-NEXT:    .p2align 4
 ; X86_64-NEXT:  "?dtor$4@?0?pr66984 at 4HA":
 ; X86_64-NEXT:  .seh_proc "?dtor$4@?0?pr66984 at 4HA"
 ; X86_64-NEXT:  .LBB0_4: # %bb8
diff --git a/llvm/test/CodeGen/X86/switch.ll b/llvm/test/CodeGen/X86/switch.ll
index b00044a1e4f795..629ba48fcae6bd 100644
--- a/llvm/test/CodeGen/X86/switch.ll
+++ b/llvm/test/CodeGen/X86/switch.ll
@@ -1304,7 +1304,7 @@ return: ret void
 define void @phi_node_trouble(ptr %s) {
 ; CHECK-LABEL: phi_node_trouble:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB13_1: # %header
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testq %rdi, %rdi
diff --git a/llvm/test/CodeGen/X86/tail-dup-merge-loop-headers.ll b/llvm/test/CodeGen/X86/tail-dup-merge-loop-headers.ll
index 8d84e887d3f279..72e4fe410e2694 100644
--- a/llvm/test/CodeGen/X86/tail-dup-merge-loop-headers.ll
+++ b/llvm/test/CodeGen/X86/tail-dup-merge-loop-headers.ll
@@ -6,7 +6,7 @@ define void @tail_dup_merge_loops(i32 %a, ptr %b, ptr %c) local_unnamed_addr #0
 ; CHECK-LABEL: tail_dup_merge_loops:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    jmp .LBB0_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_3: # %inner_loop_exit
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    incq %rsi
@@ -15,7 +15,7 @@ define void @tail_dup_merge_loops(i32 %a, ptr %b, ptr %c) local_unnamed_addr #0
 ; CHECK-NEXT:    # Child Loop BB0_4 Depth 2
 ; CHECK-NEXT:    testl %edi, %edi
 ; CHECK-NEXT:    je .LBB0_5
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  # %bb.2: # %inner_loop_top
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    cmpb $0, (%rsi)
@@ -118,7 +118,7 @@ define i32 @loop_shared_header(ptr %exe, i32 %exesz, i32 %headsize, i32 %min, i3
 ; CHECK-NEXT:    movb $32, %cl
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    jmp .LBB1_4
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_15: # %merge_predecessor_split
 ; CHECK-NEXT:    # in Loop: Header=BB1_4 Depth=1
 ; CHECK-NEXT:    movb $32, %cl
@@ -127,7 +127,7 @@ define i32 @loop_shared_header(ptr %exe, i32 %exesz, i32 %headsize, i32 %min, i3
 ; CHECK-NEXT:    # Child Loop BB1_8 Depth 2
 ; CHECK-NEXT:    testl %r12d, %r12d
 ; CHECK-NEXT:    je .LBB1_5
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_8: # %shared_loop_header
 ; CHECK-NEXT:    # Parent Loop BB1_4 Depth=1
 ; CHECK-NEXT:    # => This Inner Loop Header: Depth=2
diff --git a/llvm/test/CodeGen/X86/tail-dup-multiple-latch-loop.ll b/llvm/test/CodeGen/X86/tail-dup-multiple-latch-loop.ll
index fdcad3c1973e70..862f60c063804f 100644
--- a/llvm/test/CodeGen/X86/tail-dup-multiple-latch-loop.ll
+++ b/llvm/test/CodeGen/X86/tail-dup-multiple-latch-loop.ll
@@ -16,7 +16,7 @@ define ptr @large_loop_switch(ptr %p) {
 ; CHECK-NEXT:    popq %rbx
 ; CHECK-NEXT:    .cfi_def_cfa_offset 8
 ; CHECK-NEXT:    jmp ccc at PLT # TAILCALL
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %sw.bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    .cfi_def_cfa_offset 16
@@ -26,7 +26,7 @@ define ptr @large_loop_switch(ptr %p) {
 ; CHECK-NEXT:    decl %ebx
 ; CHECK-NEXT:    movl %ebx, %ecx
 ; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_3: # %sw.bb3
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $532, %edi # imm = 0x214
@@ -35,7 +35,7 @@ define ptr @large_loop_switch(ptr %p) {
 ; CHECK-NEXT:    decl %ebx
 ; CHECK-NEXT:    movl %ebx, %ecx
 ; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_4: # %sw.bb5
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $533, %edi # imm = 0x215
@@ -44,7 +44,7 @@ define ptr @large_loop_switch(ptr %p) {
 ; CHECK-NEXT:    decl %ebx
 ; CHECK-NEXT:    movl %ebx, %ecx
 ; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_5: # %sw.bb7
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $535, %edi # imm = 0x217
@@ -53,7 +53,7 @@ define ptr @large_loop_switch(ptr %p) {
 ; CHECK-NEXT:    decl %ebx
 ; CHECK-NEXT:    movl %ebx, %ecx
 ; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_6: # %sw.bb9
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $536, %edi # imm = 0x218
@@ -62,7 +62,7 @@ define ptr @large_loop_switch(ptr %p) {
 ; CHECK-NEXT:    decl %ebx
 ; CHECK-NEXT:    movl %ebx, %ecx
 ; CHECK-NEXT:    jmpq *.LJTI0_0(,%rcx,8)
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_7: # %sw.bb11
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl $658, %edi # imm = 0x292
@@ -136,7 +136,7 @@ define i32 @interp_switch(ptr nocapture readonly %0, i32 %1) {
 ; CHECK-NEXT:  .LBB1_7: # in Loop: Header=BB1_1 Depth=1
 ; CHECK-NEXT:    addl $7, %eax
 ; CHECK-NEXT:    incq %rdi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_1: # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movzbl (%rdi), %ecx
 ; CHECK-NEXT:    decl %ecx
diff --git a/llvm/test/CodeGen/X86/tail-dup-partial.ll b/llvm/test/CodeGen/X86/tail-dup-partial.ll
index 3b506fc6fce86d..292d59d3450d30 100644
--- a/llvm/test/CodeGen/X86/tail-dup-partial.ll
+++ b/llvm/test/CodeGen/X86/tail-dup-partial.ll
@@ -8,7 +8,7 @@
 define void @partial_tail_dup(i1 %a1, i1 %a2, ptr %a4, ptr %a5, ptr %a6, i32 %a7) #0 align 2  !prof !1 {
 ; CHECK-LABEL: partial_tail_dup:
 ; CHECK:        # %bb.0: # %entry
-; CHECK-NEXT:   .p2align 4, 0x90
+; CHECK-NEXT:   .p2align 4
 ; CHECK-NEXT:   .LBB0_1: # %for.cond
 ; CHECK-NEXT:   # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:	  testb	$1, %dil
@@ -20,14 +20,14 @@ define void @partial_tail_dup(i1 %a1, i1 %a2, ptr %a4, ptr %a5, ptr %a6, i32 %a7
 ; CHECK-NEXT:	  testl	%r9d, %r9d
 ; CHECK-NEXT:	  je	.LBB0_1
 ; CHECK-NEXT:	  jmp	.LBB0_8
-; CHECK-NEXT:	  .p2align	4, 0x90
+; CHECK-NEXT:	  .p2align	4
 ; CHECK-NEXT:   .LBB0_6: # %dup2
 ; CHECK-NEXT:   # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:	  movl	$2, (%rcx)
 ; CHECK-NEXT:	  testl	%r9d, %r9d
 ; CHECK-NEXT:	  je	.LBB0_1
 ; CHECK-NEXT:	  jmp	.LBB0_8
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_3: # %if.end56
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    testb $1, %sil
diff --git a/llvm/test/CodeGen/X86/tail-dup-repeat.ll b/llvm/test/CodeGen/X86/tail-dup-repeat.ll
index 5e0096a028d855..7a9eb0c3fb85fe 100644
--- a/llvm/test/CodeGen/X86/tail-dup-repeat.ll
+++ b/llvm/test/CodeGen/X86/tail-dup-repeat.ll
@@ -11,7 +11,7 @@ define void @repeated_tail_dup(i1 %a1, i1 %a2, ptr %a4, ptr %a5, ptr %a6, i32 %a
 ; CHECK-LABEL: repeated_tail_dup:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    jmp .LBB0_1
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %land.lhs.true
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    movl $10, (%rdx)
@@ -34,7 +34,7 @@ define void @repeated_tail_dup(i1 %a1, i1 %a2, ptr %a4, ptr %a5, ptr %a6, i32 %a
 ; CHECK-NEXT:    testl %r9d, %r9d
 ; CHECK-NEXT:    je .LBB0_1
 ; CHECK-NEXT:    jmp .LBB0_8
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_5: # %if.end70
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    movl $12, (%rdx)
diff --git a/llvm/test/CodeGen/X86/tailcall-cgp-dup.ll b/llvm/test/CodeGen/X86/tailcall-cgp-dup.ll
index 8a9ee60f341c2b..f96ba351f53f79 100644
--- a/llvm/test/CodeGen/X86/tailcall-cgp-dup.ll
+++ b/llvm/test/CodeGen/X86/tailcall-cgp-dup.ll
@@ -32,7 +32,7 @@ define i32 @foo(i32 %x) nounwind ssp {
 ; CHECK-NEXT:  LBB0_8: ## %return
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    retq
-; CHECK-NEXT:    .p2align 2, 0x90
+; CHECK-NEXT:    .p2align 2
 ; CHECK-NEXT:    .data_region jt32
 ; CHECK-NEXT:  .set L0_0_set_2, LBB0_2-LJTI0_0
 ; CHECK-NEXT:  .set L0_0_set_3, LBB0_3-LJTI0_0
diff --git a/llvm/test/CodeGen/X86/tls-loads-control3.ll b/llvm/test/CodeGen/X86/tls-loads-control3.ll
index 4e521b1c696a4d..92dccee296ad77 100644
--- a/llvm/test/CodeGen/X86/tls-loads-control3.ll
+++ b/llvm/test/CodeGen/X86/tls-loads-control3.ll
@@ -51,7 +51,7 @@ define i32 @_Z2f1i(i32 %c) local_unnamed_addr #0 {
 ; HOIST0-NEXT:    rex64
 ; HOIST0-NEXT:    callq __tls_get_addr at PLT
 ; HOIST0-NEXT:    movq %rax, %r15
-; HOIST0-NEXT:    .p2align 4, 0x90
+; HOIST0-NEXT:    .p2align 4
 ; HOIST0-NEXT:  .LBB0_2: # %while.body
 ; HOIST0-NEXT:    # =>This Inner Loop Header: Depth=1
 ; HOIST0-NEXT:    movl (%r15), %edi
@@ -86,7 +86,7 @@ define i32 @_Z2f1i(i32 %c) local_unnamed_addr #0 {
 ; HOIST2-NEXT:    je .LBB0_4
 ; HOIST2-NEXT:  # %bb.1:
 ; HOIST2-NEXT:    movl %edi, %ebx
-; HOIST2-NEXT:    .p2align 4, 0x90
+; HOIST2-NEXT:    .p2align 4
 ; HOIST2-NEXT:  .LBB0_2: # %while.body
 ; HOIST2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; HOIST2-NEXT:    data16
@@ -185,7 +185,7 @@ define i32 @_Z2f2i(i32 %c) local_unnamed_addr #0 {
 ; HOIST0-NEXT:    callq __tls_get_addr at PLT
 ; HOIST0-NEXT:    leaq _ZZ2f2iE2st.0 at DTPOFF(%rax), %r15
 ; HOIST0-NEXT:    leaq _ZZ2f2iE2st.1 at DTPOFF(%rax), %r12
-; HOIST0-NEXT:    .p2align 4, 0x90
+; HOIST0-NEXT:    .p2align 4
 ; HOIST0-NEXT:  .LBB1_2: # %while.body
 ; HOIST0-NEXT:    # =>This Inner Loop Header: Depth=1
 ; HOIST0-NEXT:    callq _Z5gfuncv at PLT
@@ -225,7 +225,7 @@ define i32 @_Z2f2i(i32 %c) local_unnamed_addr #0 {
 ; HOIST2-NEXT:    je .LBB1_3
 ; HOIST2-NEXT:  # %bb.1: # %while.body.preheader
 ; HOIST2-NEXT:    movl %edi, %ebx
-; HOIST2-NEXT:    .p2align 4, 0x90
+; HOIST2-NEXT:    .p2align 4
 ; HOIST2-NEXT:  .LBB1_2: # %while.body
 ; HOIST2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; HOIST2-NEXT:    callq _Z5gfuncv at PLT
diff --git a/llvm/test/CodeGen/X86/trunc-store.ll b/llvm/test/CodeGen/X86/trunc-store.ll
index fbdf966dc76aed..3ce06f7caa28e5 100644
--- a/llvm/test/CodeGen/X86/trunc-store.ll
+++ b/llvm/test/CodeGen/X86/trunc-store.ll
@@ -29,7 +29,7 @@
 define void @fn1(i64 %a0) {
 ; CHECK-LABEL: fn1:
 ; CHECK:       # %bb.0: # %for.cond
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %vector.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    cmpq $8, %rdi
diff --git a/llvm/test/CodeGen/X86/twoaddr-coalesce.ll b/llvm/test/CodeGen/X86/twoaddr-coalesce.ll
index a7bdfbc7bb25f1..fbedd92517da68 100644
--- a/llvm/test/CodeGen/X86/twoaddr-coalesce.ll
+++ b/llvm/test/CodeGen/X86/twoaddr-coalesce.ll
@@ -9,7 +9,7 @@ define i32 @foo() nounwind {
 ; CHECK:       # %bb.0: # %bb1.thread
 ; CHECK-NEXT:    pushl %ebx
 ; CHECK-NEXT:    xorl %ebx, %ebx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl %ebx, %eax
diff --git a/llvm/test/CodeGen/X86/twoaddr-lea.ll b/llvm/test/CodeGen/X86/twoaddr-lea.ll
index 2f6b943ca72753..f20b777531c5a4 100644
--- a/llvm/test/CodeGen/X86/twoaddr-lea.ll
+++ b/llvm/test/CodeGen/X86/twoaddr-lea.ll
@@ -71,14 +71,14 @@ define void @ham() {
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    testb %cl, %cl
 ; CHECK-NEXT:    je LBB3_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB3_6: ## %bb2
 ; CHECK-NEXT:    ## =>This Loop Header: Depth=1
 ; CHECK-NEXT:    ## Child Loop BB3_7 Depth 2
 ; CHECK-NEXT:    movl (%rdx), %edi
 ; CHECK-NEXT:    leal (%rdi,%rax), %r8d
 ; CHECK-NEXT:    movslq %r8d, %r8
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB3_7: ## %bb6
 ; CHECK-NEXT:    ## Parent Loop BB3_6 Depth=1
 ; CHECK-NEXT:    ## => This Inner Loop Header: Depth=2
@@ -94,7 +94,7 @@ define void @ham() {
 ; CHECK-NEXT:    jne LBB3_6
 ; CHECK-NEXT:  LBB3_2: ## %bb3.preheader
 ; CHECK-NEXT:    xorl %ecx, %ecx
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB3_3: ## %bb3
 ; CHECK-NEXT:    ## =>This Loop Header: Depth=1
 ; CHECK-NEXT:    ## Child Loop BB3_4 Depth 2
@@ -102,7 +102,7 @@ define void @ham() {
 ; CHECK-NEXT:    addq $4, %rcx
 ; CHECK-NEXT:    movl %eax, %esi
 ; CHECK-NEXT:    subl %edx, %esi
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  LBB3_4: ## %bb4
 ; CHECK-NEXT:    ## Parent Loop BB3_3 Depth=1
 ; CHECK-NEXT:    ## => This Inner Loop Header: Depth=2
diff --git a/llvm/test/CodeGen/X86/unaligned-load.ll b/llvm/test/CodeGen/X86/unaligned-load.ll
index c95cb3fe9d9c2e..2310cb228f0634 100644
--- a/llvm/test/CodeGen/X86/unaligned-load.ll
+++ b/llvm/test/CodeGen/X86/unaligned-load.ll
@@ -12,7 +12,7 @@ define void @func() nounwind ssp {
 ; I386-LABEL: func:
 ; I386:       ## %bb.0: ## %entry
 ; I386-NEXT:    subl $32, %esp
-; I386-NEXT:    .p2align 4, 0x90
+; I386-NEXT:    .p2align 4
 ; I386-NEXT:  LBB0_1: ## %bb
 ; I386-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; I386-NEXT:    movl $4673097, {{[0-9]+}}(%esp) ## imm = 0x474E49
@@ -31,7 +31,7 @@ define void @func() nounwind ssp {
 ; CORE2-NEXT:    movabsq $2325069237881678925, %rcx ## imm = 0x20444E2732202C4D
 ; CORE2-NEXT:    movabsq $4706902966564560965, %rdx ## imm = 0x4152474F52502045
 ; CORE2-NEXT:    movabsq $5642821575076104260, %rsi ## imm = 0x4E4F545359524844
-; CORE2-NEXT:    .p2align 4, 0x90
+; CORE2-NEXT:    .p2align 4
 ; CORE2-NEXT:  LBB0_1: ## %bb
 ; CORE2-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CORE2-NEXT:    movq %rax, -{{[0-9]+}}(%rsp)
@@ -44,7 +44,7 @@ define void @func() nounwind ssp {
 ; COREI7:       ## %bb.0: ## %entry
 ; COREI7-NEXT:    movups _.str3+15(%rip), %xmm0
 ; COREI7-NEXT:    movups _.str3(%rip), %xmm1
-; COREI7-NEXT:    .p2align 4, 0x90
+; COREI7-NEXT:    .p2align 4
 ; COREI7-NEXT:  LBB0_1: ## %bb
 ; COREI7-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; COREI7-NEXT:    movups %xmm0, -{{[0-9]+}}(%rsp)
@@ -67,7 +67,7 @@ define void @func_aligned() nounwind ssp {
 ; I386:       ## %bb.0: ## %entry
 ; I386-NEXT:    subl $44, %esp
 ; I386-NEXT:    movaps {{.*#+}} xmm0 = [1498564676,1313821779,1380982853,1095911247]
-; I386-NEXT:    .p2align 4, 0x90
+; I386-NEXT:    .p2align 4
 ; I386-NEXT:  LBB1_1: ## %bb
 ; I386-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; I386-NEXT:    movaps %xmm0, (%esp)
@@ -83,7 +83,7 @@ define void @func_aligned() nounwind ssp {
 ; CORE2-NEXT:    movabsq $2325069237881678925, %rcx ## imm = 0x20444E2732202C4D
 ; CORE2-NEXT:    movabsq $4706902966564560965, %rdx ## imm = 0x4152474F52502045
 ; CORE2-NEXT:    movabsq $5642821575076104260, %rsi ## imm = 0x4E4F545359524844
-; CORE2-NEXT:    .p2align 4, 0x90
+; CORE2-NEXT:    .p2align 4
 ; CORE2-NEXT:  LBB1_1: ## %bb
 ; CORE2-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; CORE2-NEXT:    movq %rax, -{{[0-9]+}}(%rsp)
@@ -96,7 +96,7 @@ define void @func_aligned() nounwind ssp {
 ; COREI7:       ## %bb.0: ## %entry
 ; COREI7-NEXT:    movups _.str3+15(%rip), %xmm0
 ; COREI7-NEXT:    movups _.str3(%rip), %xmm1
-; COREI7-NEXT:    .p2align 4, 0x90
+; COREI7-NEXT:    .p2align 4
 ; COREI7-NEXT:  LBB1_1: ## %bb
 ; COREI7-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; COREI7-NEXT:    movups %xmm0, -{{[0-9]+}}(%rsp)
diff --git a/llvm/test/CodeGen/X86/undef-label.ll b/llvm/test/CodeGen/X86/undef-label.ll
index 4cacaec85e7c08..a2d9bc571f5827 100644
--- a/llvm/test/CodeGen/X86/undef-label.ll
+++ b/llvm/test/CodeGen/X86/undef-label.ll
@@ -15,7 +15,7 @@ define dso_local void @xyz() {
 ; CHECK-NEXT:    ucomisd %xmm1, %xmm0
 ; CHECK-NEXT:    jne .LBB0_1
 ; CHECK-NEXT:    jnp .LBB0_2
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %foo
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    ucomisd %xmm1, %xmm0
diff --git a/llvm/test/CodeGen/X86/vec_setcc-2.ll b/llvm/test/CodeGen/X86/vec_setcc-2.ll
index edf726a1e37c4f..5a71878ea45796 100644
--- a/llvm/test/CodeGen/X86/vec_setcc-2.ll
+++ b/llvm/test/CodeGen/X86/vec_setcc-2.ll
@@ -13,7 +13,7 @@ define void @loop_no_const_reload(ptr  %in, ptr %out, i32 %n) {
 ; SSE2-NEXT:    xorl %eax, %eax
 ; SSE2-NEXT:    movdqa {{.*#+}} xmm0 = [25,25,25,25,25,25,25,25]
 ; SSE2-NEXT:    pxor %xmm1, %xmm1
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  LBB0_2: ## %for.body
 ; SSE2-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqa (%rdi,%rax), %xmm2
@@ -33,7 +33,7 @@ define void @loop_no_const_reload(ptr  %in, ptr %out, i32 %n) {
 ; SSE41-NEXT:  ## %bb.1: ## %for.body.preheader
 ; SSE41-NEXT:    xorl %eax, %eax
 ; SSE41-NEXT:    pmovsxbw {{.*#+}} xmm0 = [25,25,25,25,25,25,25,25]
-; SSE41-NEXT:    .p2align 4, 0x90
+; SSE41-NEXT:    .p2align 4
 ; SSE41-NEXT:  LBB0_2: ## %for.body
 ; SSE41-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; SSE41-NEXT:    movdqa (%rdi,%rax), %xmm1
@@ -80,7 +80,7 @@ define void @loop_const_folding_underflow(ptr  %in, ptr %out, i32 %n) {
 ; SSE2-NEXT:    xorl %eax, %eax
 ; SSE2-NEXT:    movdqa {{.*#+}} xmm0 = [32768,32768,32768,32768,32768,32768,32768,32768]
 ; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [32768,32794,32794,32794,32794,32794,32794,32794]
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  LBB1_2: ## %for.body
 ; SSE2-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movdqa (%rdi,%rax), %xmm2
@@ -102,7 +102,7 @@ define void @loop_const_folding_underflow(ptr  %in, ptr %out, i32 %n) {
 ; SSE41-NEXT:    xorl %eax, %eax
 ; SSE41-NEXT:    pmovsxbw {{.*#+}} xmm0 = [0,26,26,26,26,26,26,26]
 ; SSE41-NEXT:    pcmpeqd %xmm1, %xmm1
-; SSE41-NEXT:    .p2align 4, 0x90
+; SSE41-NEXT:    .p2align 4
 ; SSE41-NEXT:  LBB1_2: ## %for.body
 ; SSE41-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; SSE41-NEXT:    movdqa (%rdi,%rax), %xmm2
diff --git a/llvm/test/CodeGen/X86/vector-fshl-128.ll b/llvm/test/CodeGen/X86/vector-fshl-128.ll
index c7cff092c5a4fe..28b3d7c7d717ec 100644
--- a/llvm/test/CodeGen/X86/vector-fshl-128.ll
+++ b/llvm/test/CodeGen/X86/vector-fshl-128.ll
@@ -1454,7 +1454,7 @@ define void @sink_splatvar(ptr %p, i32 %shift_amt) {
 ; SSE-NEXT:    movd %esi, %xmm0
 ; SSE-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; SSE-NEXT:    pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
-; SSE-NEXT:    .p2align 4, 0x90
+; SSE-NEXT:    .p2align 4
 ; SSE-NEXT:  .LBB8_1: # %loop
 ; SSE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-NEXT:    movdqu 1024(%rdi,%rax), %xmm1
@@ -1474,7 +1474,7 @@ define void @sink_splatvar(ptr %p, i32 %shift_amt) {
 ; AVX1-NEXT:    vmovd %esi, %xmm0
 ; AVX1-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX1-NEXT:    vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB8_1: # %loop
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vmovdqu 1024(%rdi,%rax), %xmm1
@@ -1498,7 +1498,7 @@ define void @sink_splatvar(ptr %p, i32 %shift_amt) {
 ; AVX2-NEXT:    vpand %xmm1, %xmm0, %xmm0
 ; AVX2-NEXT:    vpbroadcastd {{.*#+}} xmm1 = [32,32,32,32]
 ; AVX2-NEXT:    vpsubd %xmm0, %xmm1, %xmm1
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB8_1: # %loop
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vmovdqu 1024(%rdi,%rax), %xmm2
@@ -1516,7 +1516,7 @@ define void @sink_splatvar(ptr %p, i32 %shift_amt) {
 ; AVX512F-NEXT:    vmovd %esi, %xmm0
 ; AVX512F-NEXT:    vpbroadcastd %xmm0, %xmm0
 ; AVX512F-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; AVX512F-NEXT:    .p2align 4, 0x90
+; AVX512F-NEXT:    .p2align 4
 ; AVX512F-NEXT:  .LBB8_1: # %loop
 ; AVX512F-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512F-NEXT:    vmovdqu 1024(%rdi,%rax), %xmm1
@@ -1532,7 +1532,7 @@ define void @sink_splatvar(ptr %p, i32 %shift_amt) {
 ; AVX512VL:       # %bb.0: # %entry
 ; AVX512VL-NEXT:    vpbroadcastd %esi, %xmm0
 ; AVX512VL-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; AVX512VL-NEXT:    .p2align 4, 0x90
+; AVX512VL-NEXT:    .p2align 4
 ; AVX512VL-NEXT:  .LBB8_1: # %loop
 ; AVX512VL-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512VL-NEXT:    vmovdqu 1024(%rdi,%rax), %xmm1
@@ -1548,7 +1548,7 @@ define void @sink_splatvar(ptr %p, i32 %shift_amt) {
 ; AVX512BW-NEXT:    vmovd %esi, %xmm0
 ; AVX512BW-NEXT:    vpbroadcastd %xmm0, %xmm0
 ; AVX512BW-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; AVX512BW-NEXT:    .p2align 4, 0x90
+; AVX512BW-NEXT:    .p2align 4
 ; AVX512BW-NEXT:  .LBB8_1: # %loop
 ; AVX512BW-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512BW-NEXT:    vmovdqu 1024(%rdi,%rax), %xmm1
@@ -1565,7 +1565,7 @@ define void @sink_splatvar(ptr %p, i32 %shift_amt) {
 ; AVX512VBMI2-NEXT:    vmovd %esi, %xmm0
 ; AVX512VBMI2-NEXT:    vpbroadcastd %xmm0, %xmm0
 ; AVX512VBMI2-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; AVX512VBMI2-NEXT:    .p2align 4, 0x90
+; AVX512VBMI2-NEXT:    .p2align 4
 ; AVX512VBMI2-NEXT:  .LBB8_1: # %loop
 ; AVX512VBMI2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512VBMI2-NEXT:    vmovdqu 1024(%rdi,%rax), %xmm1
@@ -1581,7 +1581,7 @@ define void @sink_splatvar(ptr %p, i32 %shift_amt) {
 ; AVX512VLBW:       # %bb.0: # %entry
 ; AVX512VLBW-NEXT:    vpbroadcastd %esi, %xmm0
 ; AVX512VLBW-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; AVX512VLBW-NEXT:    .p2align 4, 0x90
+; AVX512VLBW-NEXT:    .p2align 4
 ; AVX512VLBW-NEXT:  .LBB8_1: # %loop
 ; AVX512VLBW-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512VLBW-NEXT:    vmovdqu 1024(%rdi,%rax), %xmm1
@@ -1596,7 +1596,7 @@ define void @sink_splatvar(ptr %p, i32 %shift_amt) {
 ; AVX512VLVBMI2:       # %bb.0: # %entry
 ; AVX512VLVBMI2-NEXT:    vpbroadcastd %esi, %xmm0
 ; AVX512VLVBMI2-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; AVX512VLVBMI2-NEXT:    .p2align 4, 0x90
+; AVX512VLVBMI2-NEXT:    .p2align 4
 ; AVX512VLVBMI2-NEXT:  .LBB8_1: # %loop
 ; AVX512VLVBMI2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512VLVBMI2-NEXT:    vmovdqu 1024(%rdi,%rax), %xmm1
@@ -1612,7 +1612,7 @@ define void @sink_splatvar(ptr %p, i32 %shift_amt) {
 ; XOPAVX1-NEXT:    vmovd %esi, %xmm0
 ; XOPAVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
 ; XOPAVX1-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; XOPAVX1-NEXT:    .p2align 4, 0x90
+; XOPAVX1-NEXT:    .p2align 4
 ; XOPAVX1-NEXT:  .LBB8_1: # %loop
 ; XOPAVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; XOPAVX1-NEXT:    vprotd %xmm0, 1024(%rdi,%rax), %xmm1
@@ -1627,7 +1627,7 @@ define void @sink_splatvar(ptr %p, i32 %shift_amt) {
 ; XOPAVX2-NEXT:    vmovd %esi, %xmm0
 ; XOPAVX2-NEXT:    vpbroadcastd %xmm0, %xmm0
 ; XOPAVX2-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; XOPAVX2-NEXT:    .p2align 4, 0x90
+; XOPAVX2-NEXT:    .p2align 4
 ; XOPAVX2-NEXT:  .LBB8_1: # %loop
 ; XOPAVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; XOPAVX2-NEXT:    vprotd %xmm0, 1024(%rdi,%rax), %xmm1
@@ -1647,7 +1647,7 @@ define void @sink_splatvar(ptr %p, i32 %shift_amt) {
 ; X86-SSE2-NEXT:    movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
 ; X86-SSE2-NEXT:    pand {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
 ; X86-SSE2-NEXT:    xorl %edx, %edx
-; X86-SSE2-NEXT:    .p2align 4, 0x90
+; X86-SSE2-NEXT:    .p2align 4
 ; X86-SSE2-NEXT:  .LBB8_1: # %loop
 ; X86-SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-SSE2-NEXT:    movdqu (%eax,%ecx,4), %xmm1
diff --git a/llvm/test/CodeGen/X86/vector-fshl-256.ll b/llvm/test/CodeGen/X86/vector-fshl-256.ll
index b26580541fe401..fca72cad474cd1 100644
--- a/llvm/test/CodeGen/X86/vector-fshl-256.ll
+++ b/llvm/test/CodeGen/X86/vector-fshl-256.ll
@@ -1279,7 +1279,7 @@ define void @fancierRotate2(ptr %arr, ptr %control, i32 %rot0, i32 %rot1) {
 ; AVX1-NEXT:    vpmovsxbq {{.*#+}} xmm3 = [31,0]
 ; AVX1-NEXT:    vpand %xmm3, %xmm1, %xmm1
 ; AVX1-NEXT:    vpand %xmm3, %xmm2, %xmm2
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB8_1: # %loop
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vmovq {{.*#+}} xmm3 = mem[0],zero
@@ -1325,7 +1325,7 @@ define void @fancierRotate2(ptr %arr, ptr %control, i32 %rot0, i32 %rot1) {
 ; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
 ; AVX2-NEXT:    vbroadcastss {{.*#+}} ymm3 = [31,31,31,31,31,31,31,31]
 ; AVX2-NEXT:    vpbroadcastd {{.*#+}} ymm4 = [32,32,32,32,32,32,32,32]
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB8_1: # %loop
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vpmovzxbd {{.*#+}} ymm5 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero
@@ -1352,7 +1352,7 @@ define void @fancierRotate2(ptr %arr, ptr %control, i32 %rot0, i32 %rot1) {
 ; AVX512F-NEXT:    vpbroadcastd %xmm1, %ymm1
 ; AVX512F-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX512F-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; AVX512F-NEXT:    .p2align 4, 0x90
+; AVX512F-NEXT:    .p2align 4
 ; AVX512F-NEXT:  .LBB8_1: # %loop
 ; AVX512F-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512F-NEXT:    vpmovzxbd {{.*#+}} ymm3 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero
@@ -1372,7 +1372,7 @@ define void @fancierRotate2(ptr %arr, ptr %control, i32 %rot0, i32 %rot1) {
 ; AVX512VL-NEXT:    vpbroadcastd %edx, %ymm0
 ; AVX512VL-NEXT:    vpbroadcastd %ecx, %ymm1
 ; AVX512VL-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; AVX512VL-NEXT:    .p2align 4, 0x90
+; AVX512VL-NEXT:    .p2align 4
 ; AVX512VL-NEXT:  .LBB8_1: # %loop
 ; AVX512VL-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512VL-NEXT:    vpmovzxbd {{.*#+}} ymm2 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero
@@ -1395,7 +1395,7 @@ define void @fancierRotate2(ptr %arr, ptr %control, i32 %rot0, i32 %rot1) {
 ; AVX512BW-NEXT:    vpbroadcastd %xmm1, %ymm1
 ; AVX512BW-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX512BW-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; AVX512BW-NEXT:    .p2align 4, 0x90
+; AVX512BW-NEXT:    .p2align 4
 ; AVX512BW-NEXT:  .LBB8_1: # %loop
 ; AVX512BW-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512BW-NEXT:    vpmovzxbd {{.*#+}} ymm3 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero
@@ -1418,7 +1418,7 @@ define void @fancierRotate2(ptr %arr, ptr %control, i32 %rot0, i32 %rot1) {
 ; AVX512VBMI2-NEXT:    vpbroadcastd %xmm1, %ymm1
 ; AVX512VBMI2-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; AVX512VBMI2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; AVX512VBMI2-NEXT:    .p2align 4, 0x90
+; AVX512VBMI2-NEXT:    .p2align 4
 ; AVX512VBMI2-NEXT:  .LBB8_1: # %loop
 ; AVX512VBMI2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512VBMI2-NEXT:    vpmovzxbd {{.*#+}} ymm3 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero
@@ -1438,7 +1438,7 @@ define void @fancierRotate2(ptr %arr, ptr %control, i32 %rot0, i32 %rot1) {
 ; AVX512VLBW-NEXT:    vpbroadcastd %edx, %ymm0
 ; AVX512VLBW-NEXT:    vpbroadcastd %ecx, %ymm1
 ; AVX512VLBW-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; AVX512VLBW-NEXT:    .p2align 4, 0x90
+; AVX512VLBW-NEXT:    .p2align 4
 ; AVX512VLBW-NEXT:  .LBB8_1: # %loop
 ; AVX512VLBW-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX512VLBW-NEXT:    vmovq {{.*#+}} xmm2 = mem[0],zero
@@ -1458,7 +1458,7 @@ define void @fancierRotate2(ptr %arr, ptr %control, i32 %rot0, i32 %rot1) {
 ; AVX10-NEXT:    vpbroadcastd %edx, %ymm0
 ; AVX10-NEXT:    vpbroadcastd %ecx, %ymm1
 ; AVX10-NEXT:    movq $-1024, %rax # imm = 0xFC00
-; AVX10-NEXT:    .p2align 4, 0x90
+; AVX10-NEXT:    .p2align 4
 ; AVX10-NEXT:  .LBB8_1: # %loop
 ; AVX10-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX10-NEXT:    vmovq {{.*#+}} xmm2 = mem[0],zero
@@ -1485,7 +1485,7 @@ define void @fancierRotate2(ptr %arr, ptr %control, i32 %rot0, i32 %rot1) {
 ; XOPAVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
 ; XOPAVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
 ; XOPAVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
-; XOPAVX1-NEXT:    .p2align 4, 0x90
+; XOPAVX1-NEXT:    .p2align 4
 ; XOPAVX1-NEXT:  .LBB8_1: # %loop
 ; XOPAVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; XOPAVX1-NEXT:    vmovq {{.*#+}} xmm5 = mem[0],zero
@@ -1513,7 +1513,7 @@ define void @fancierRotate2(ptr %arr, ptr %control, i32 %rot0, i32 %rot1) {
 ; XOPAVX2-NEXT:    vpbroadcastd %xmm1, %ymm1
 ; XOPAVX2-NEXT:    movq $-1024, %rax # imm = 0xFC00
 ; XOPAVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; XOPAVX2-NEXT:    .p2align 4, 0x90
+; XOPAVX2-NEXT:    .p2align 4
 ; XOPAVX2-NEXT:  .LBB8_1: # %loop
 ; XOPAVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; XOPAVX2-NEXT:    vpmovzxbd {{.*#+}} ymm3 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero
diff --git a/llvm/test/CodeGen/X86/vector-pack-128.ll b/llvm/test/CodeGen/X86/vector-pack-128.ll
index d11e1a70b684cd..f58f19ecd24819 100644
--- a/llvm/test/CodeGen/X86/vector-pack-128.ll
+++ b/llvm/test/CodeGen/X86/vector-pack-128.ll
@@ -327,7 +327,7 @@ define <16 x i8> @concat_trunc_packuswb_128(<8 x i16> %a0, <8 x i16> %a1) nounwi
 define void @autogen_SD10339(<1 x i32> %I49) {
 ; CHECK-LABEL: autogen_SD10339:
 ; CHECK:       # %bb.0: # %BB
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB8_1: # %CF
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movw $1, 0
diff --git a/llvm/test/CodeGen/X86/vector-shift-by-select-loop.ll b/llvm/test/CodeGen/X86/vector-shift-by-select-loop.ll
index e33c99be0ed093..177d8f78b5a8d4 100644
--- a/llvm/test/CodeGen/X86/vector-shift-by-select-loop.ll
+++ b/llvm/test/CodeGen/X86/vector-shift-by-select-loop.ll
@@ -33,7 +33,7 @@ define void @vector_variable_shift_left_loop(ptr nocapture %arr, ptr nocapture r
 ; SSE-NEXT:    pxor %xmm8, %xmm8
 ; SSE-NEXT:    pmovzxdq {{.*#+}} xmm9 = xmm0[0],zero,xmm0[1],zero
 ; SSE-NEXT:    pmovzxdq {{.*#+}} xmm10 = xmm1[0],zero,xmm1[1],zero
-; SSE-NEXT:    .p2align 4, 0x90
+; SSE-NEXT:    .p2align 4
 ; SSE-NEXT:  .LBB0_4: # %vector.body
 ; SSE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-NEXT:    movq {{.*#+}} xmm0 = mem[0],zero
@@ -119,7 +119,7 @@ define void @vector_variable_shift_left_loop(ptr nocapture %arr, ptr nocapture r
 ; SSE-NEXT:    jne .LBB0_6
 ; SSE-NEXT:  .LBB0_9: # %for.cond.cleanup
 ; SSE-NEXT:    retq
-; SSE-NEXT:    .p2align 4, 0x90
+; SSE-NEXT:    .p2align 4
 ; SSE-NEXT:  .LBB0_8: # %for.body
 ; SSE-NEXT:    # in Loop: Header=BB0_6 Depth=1
 ; SSE-NEXT:    # kill: def $cl killed $cl killed $ecx
@@ -167,7 +167,7 @@ define void @vector_variable_shift_left_loop(ptr nocapture %arr, ptr nocapture r
 ; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm6 = xmm8[0],zero,xmm8[1],zero
 ; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm7 = xmm7[0],zero,xmm7[1],zero
 ; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm8 = xmm8[0],zero,xmm8[1],zero
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB0_4: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vmovq {{.*#+}} xmm9 = mem[0],zero
@@ -244,7 +244,7 @@ define void @vector_variable_shift_left_loop(ptr nocapture %arr, ptr nocapture r
 ; AVX1-NEXT:  .LBB0_9: # %for.cond.cleanup
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB0_8: # %for.body
 ; AVX1-NEXT:    # in Loop: Header=BB0_6 Depth=1
 ; AVX1-NEXT:    # kill: def $cl killed $cl killed $ecx
@@ -283,7 +283,7 @@ define void @vector_variable_shift_left_loop(ptr nocapture %arr, ptr nocapture r
 ; AVX2-NEXT:    vpbroadcastd %xmm1, %ymm1
 ; AVX2-NEXT:    xorl %ecx, %ecx
 ; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB0_4: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vpmovzxbd {{.*#+}} ymm3 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero,mem[4],zero,zero,zero,mem[5],zero,zero,zero,mem[6],zero,zero,zero,mem[7],zero,zero,zero
@@ -319,7 +319,7 @@ define void @vector_variable_shift_left_loop(ptr nocapture %arr, ptr nocapture r
 ; AVX2-NEXT:  .LBB0_9: # %for.cond.cleanup
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB0_8: # %for.body
 ; AVX2-NEXT:    # in Loop: Header=BB0_6 Depth=1
 ; AVX2-NEXT:    # kill: def $cl killed $cl killed $ecx
@@ -362,7 +362,7 @@ define void @vector_variable_shift_left_loop(ptr nocapture %arr, ptr nocapture r
 ; XOP-NEXT:    vpxor %xmm2, %xmm2, %xmm2
 ; XOP-NEXT:    vextractf128 $1, %ymm0, %xmm3
 ; XOP-NEXT:    vextractf128 $1, %ymm1, %xmm4
-; XOP-NEXT:    .p2align 4, 0x90
+; XOP-NEXT:    .p2align 4
 ; XOP-NEXT:  .LBB0_4: # %vector.body
 ; XOP-NEXT:    # =>This Inner Loop Header: Depth=1
 ; XOP-NEXT:    vmovq {{.*#+}} xmm5 = mem[0],zero
@@ -418,7 +418,7 @@ define void @vector_variable_shift_left_loop(ptr nocapture %arr, ptr nocapture r
 ; XOP-NEXT:  .LBB0_9: # %for.cond.cleanup
 ; XOP-NEXT:    vzeroupper
 ; XOP-NEXT:    retq
-; XOP-NEXT:    .p2align 4, 0x90
+; XOP-NEXT:    .p2align 4
 ; XOP-NEXT:  .LBB0_8: # %for.body
 ; XOP-NEXT:    # in Loop: Header=BB0_6 Depth=1
 ; XOP-NEXT:    # kill: def $cl killed $cl killed $ecx
@@ -547,7 +547,7 @@ define void @vector_variable_shift_left_loop_simpler(ptr nocapture %arr, ptr noc
 ; SSE-NEXT:    pmovzxdq {{.*#+}} xmm0 = xmm3[0],zero,xmm3[1],zero
 ; SSE-NEXT:    pslld %xmm0, %xmm1
 ; SSE-NEXT:    pxor %xmm3, %xmm3
-; SSE-NEXT:    .p2align 4, 0x90
+; SSE-NEXT:    .p2align 4
 ; SSE-NEXT:  .LBB1_2: # %vector.body
 ; SSE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE-NEXT:    pmovzxbd {{.*#+}} xmm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
@@ -578,7 +578,7 @@ define void @vector_variable_shift_left_loop_simpler(ptr nocapture %arr, ptr noc
 ; AVX1-NEXT:    vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
 ; AVX1-NEXT:    vpslld %xmm1, %xmm2, %xmm1
 ; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
-; AVX1-NEXT:    .p2align 4, 0x90
+; AVX1-NEXT:    .p2align 4
 ; AVX1-NEXT:  .LBB1_2: # %vector.body
 ; AVX1-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX1-NEXT:    vpmovzxbd {{.*#+}} xmm3 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
@@ -606,7 +606,7 @@ define void @vector_variable_shift_left_loop_simpler(ptr nocapture %arr, ptr noc
 ; AVX2-NEXT:    vpbroadcastd %xmm2, %xmm2
 ; AVX2-NEXT:    xorl %ecx, %ecx
 ; AVX2-NEXT:    vpxor %xmm3, %xmm3, %xmm3
-; AVX2-NEXT:    .p2align 4, 0x90
+; AVX2-NEXT:    .p2align 4
 ; AVX2-NEXT:  .LBB1_2: # %vector.body
 ; AVX2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; AVX2-NEXT:    vpmovzxbd {{.*#+}} xmm4 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
@@ -635,7 +635,7 @@ define void @vector_variable_shift_left_loop_simpler(ptr nocapture %arr, ptr noc
 ; XOP-NEXT:    vpshufd {{.*#+}} xmm2 = xmm2[0,0,0,0]
 ; XOP-NEXT:    xorl %ecx, %ecx
 ; XOP-NEXT:    vpxor %xmm3, %xmm3, %xmm3
-; XOP-NEXT:    .p2align 4, 0x90
+; XOP-NEXT:    .p2align 4
 ; XOP-NEXT:  .LBB1_2: # %vector.body
 ; XOP-NEXT:    # =>This Inner Loop Header: Depth=1
 ; XOP-NEXT:    vpmovzxbd {{.*#+}} xmm4 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining.ll
index 36c4be5f1939ec..07c770abc65d6c 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-combining.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-combining.ll
@@ -3656,7 +3656,7 @@ entry:
 define void @autogen_SD25931() {
 ; CHECK-LABEL: autogen_SD25931:
 ; CHECK:       # %bb.0: # %BB
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB142_1: # %CF242
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    jmp .LBB142_1
diff --git a/llvm/test/CodeGen/X86/vselect-avx.ll b/llvm/test/CodeGen/X86/vselect-avx.ll
index 364390a4a60e56..a2c3613ecca12d 100644
--- a/llvm/test/CodeGen/X86/vselect-avx.ll
+++ b/llvm/test/CodeGen/X86/vselect-avx.ll
@@ -187,7 +187,7 @@ define <32 x i8> @PR22706(<32 x i1> %x) {
 define void @PR59003(<2 x float> %0, <2 x float> %1, <8 x i1> %shuffle108) {
 ; AVX-LABEL: PR59003:
 ; AVX:       ## %bb.0: ## %entry
-; AVX-NEXT:    .p2align 4, 0x90
+; AVX-NEXT:    .p2align 4
 ; AVX-NEXT:  LBB4_1: ## %for.body.i
 ; AVX-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; AVX-NEXT:    jmp LBB4_1
diff --git a/llvm/test/CodeGen/X86/widen_arith-1.ll b/llvm/test/CodeGen/X86/widen_arith-1.ll
index f6be700645fb33..e08df8f76d1a61 100644
--- a/llvm/test/CodeGen/X86/widen_arith-1.ll
+++ b/llvm/test/CodeGen/X86/widen_arith-1.ll
@@ -7,7 +7,7 @@ define void @update(ptr %dst, ptr %src, i32 %n) nounwind {
 ; CHECK-NEXT:    pushl %eax
 ; CHECK-NEXT:    movl $0, (%esp)
 ; CHECK-NEXT:    pcmpeqd %xmm0, %xmm0
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %forcond
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl (%esp), %eax
diff --git a/llvm/test/CodeGen/X86/widen_arith-2.ll b/llvm/test/CodeGen/X86/widen_arith-2.ll
index a0f78db8746f45..260b87cc461a98 100644
--- a/llvm/test/CodeGen/X86/widen_arith-2.ll
+++ b/llvm/test/CodeGen/X86/widen_arith-2.ll
@@ -10,7 +10,7 @@ define void @update(ptr %dst_i, ptr %src_i, i32 %n) nounwind {
 ; CHECK-NEXT:    movl $0, (%esp)
 ; CHECK-NEXT:    pcmpeqd %xmm0, %xmm0
 ; CHECK-NEXT:    movdqa {{.*#+}} xmm1 = [4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %forcond
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl (%esp), %eax
diff --git a/llvm/test/CodeGen/X86/widen_arith-3.ll b/llvm/test/CodeGen/X86/widen_arith-3.ll
index 85640a0af597a3..9031588f2690d5 100644
--- a/llvm/test/CodeGen/X86/widen_arith-3.ll
+++ b/llvm/test/CodeGen/X86/widen_arith-3.ll
@@ -17,7 +17,7 @@ define void @update(ptr %dst, ptr %src, i32 %n) nounwind {
 ; CHECK-NEXT:    movw $1, {{[0-9]+}}(%esp)
 ; CHECK-NEXT:    movl $65537, {{[0-9]+}}(%esp) # imm = 0x10001
 ; CHECK-NEXT:    movl $0, {{[0-9]+}}(%esp)
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %forcond
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %eax
diff --git a/llvm/test/CodeGen/X86/widen_arith-4.ll b/llvm/test/CodeGen/X86/widen_arith-4.ll
index 8bb716374b4822..c49882ffe0b389 100644
--- a/llvm/test/CodeGen/X86/widen_arith-4.ll
+++ b/llvm/test/CodeGen/X86/widen_arith-4.ll
@@ -16,7 +16,7 @@ define void @update(ptr %dst, ptr %src, i32 %n) nounwind {
 ; SSE2-NEXT:    movl $0, -{{[0-9]+}}(%rsp)
 ; SSE2-NEXT:    movdqa {{.*#+}} xmm0 = [271,271,271,271,271,u,u,u]
 ; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [2,4,2,2,2,u,u,u]
-; SSE2-NEXT:    .p2align 4, 0x90
+; SSE2-NEXT:    .p2align 4
 ; SSE2-NEXT:  .LBB0_1: # %forcond
 ; SSE2-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE2-NEXT:    movl -{{[0-9]+}}(%rsp), %eax
@@ -49,7 +49,7 @@ define void @update(ptr %dst, ptr %src, i32 %n) nounwind {
 ; SSE41-NEXT:    movw $0, -{{[0-9]+}}(%rsp)
 ; SSE41-NEXT:    movl $0, -{{[0-9]+}}(%rsp)
 ; SSE41-NEXT:    movdqa {{.*#+}} xmm0 = [271,271,271,271,271,u,u,u]
-; SSE41-NEXT:    .p2align 4, 0x90
+; SSE41-NEXT:    .p2align 4
 ; SSE41-NEXT:  .LBB0_1: # %forcond
 ; SSE41-NEXT:    # =>This Inner Loop Header: Depth=1
 ; SSE41-NEXT:    movl -{{[0-9]+}}(%rsp), %eax
diff --git a/llvm/test/CodeGen/X86/widen_arith-5.ll b/llvm/test/CodeGen/X86/widen_arith-5.ll
index dd75a4ea2cf229..466249d1bf1d42 100644
--- a/llvm/test/CodeGen/X86/widen_arith-5.ll
+++ b/llvm/test/CodeGen/X86/widen_arith-5.ll
@@ -14,7 +14,7 @@ define void @update(ptr %dst, ptr %src, i32 %n) nounwind {
 ; CHECK-NEXT:    movl $1, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movl $0, -{{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    pmovsxbd {{.*#+}} xmm0 = [3,3,3,3]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %forcond
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl -{{[0-9]+}}(%rsp), %eax
diff --git a/llvm/test/CodeGen/X86/widen_arith-6.ll b/llvm/test/CodeGen/X86/widen_arith-6.ll
index 239fe25b0c4a9a..6fa232f4d3227d 100644
--- a/llvm/test/CodeGen/X86/widen_arith-6.ll
+++ b/llvm/test/CodeGen/X86/widen_arith-6.ll
@@ -15,7 +15,7 @@ define void @update(ptr %dst, ptr %src, i32 %n) nounwind {
 ; CHECK-NEXT:    movl $1065353216, {{[0-9]+}}(%esp) # imm = 0x3F800000
 ; CHECK-NEXT:    movl $0, {{[0-9]+}}(%esp)
 ; CHECK-NEXT:    movaps {{.*#+}} xmm0 = [1.97604004E+3,1.97604004E+3,1.97604004E+3,u]
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %forcond
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %eax
diff --git a/llvm/test/CodeGen/X86/widen_cast-1.ll b/llvm/test/CodeGen/X86/widen_cast-1.ll
index 58f0d2c2da5749..566dde0ca13d3c 100644
--- a/llvm/test/CodeGen/X86/widen_cast-1.ll
+++ b/llvm/test/CodeGen/X86/widen_cast-1.ll
@@ -14,7 +14,7 @@ define void @convert(ptr %dst, ptr %src) nounwind {
 ; CHECK-NEXT:    pcmpeqd %xmm0, %xmm0
 ; CHECK-NEXT:    cmpl $3, (%esp)
 ; CHECK-NEXT:    jg .LBB0_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %forbody
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl (%esp), %eax
@@ -37,7 +37,7 @@ define void @convert(ptr %dst, ptr %src) nounwind {
 ; ATOM-NEXT:    movl $0, (%esp)
 ; ATOM-NEXT:    cmpl $3, (%esp)
 ; ATOM-NEXT:    jg .LBB0_3
-; ATOM-NEXT:    .p2align 4, 0x90
+; ATOM-NEXT:    .p2align 4
 ; ATOM-NEXT:  .LBB0_2: # %forbody
 ; ATOM-NEXT:    # =>This Inner Loop Header: Depth=1
 ; ATOM-NEXT:    movl (%esp), %eax
diff --git a/llvm/test/CodeGen/X86/widen_cast-2.ll b/llvm/test/CodeGen/X86/widen_cast-2.ll
index 6e174180d04a7e..cd06f27dcc55c2 100644
--- a/llvm/test/CodeGen/X86/widen_cast-2.ll
+++ b/llvm/test/CodeGen/X86/widen_cast-2.ll
@@ -10,7 +10,7 @@ define void @convert(ptr %dst, ptr %src) nounwind {
 ; CHECK-NEXT:    pcmpeqd %xmm0, %xmm0
 ; CHECK-NEXT:    cmpl $3, (%esp)
 ; CHECK-NEXT:    jg .LBB0_3
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_2: # %forbody
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl (%esp), %eax
diff --git a/llvm/test/CodeGen/X86/widen_cast-4.ll b/llvm/test/CodeGen/X86/widen_cast-4.ll
index 7dd92ce874aefe..7468e229e3a841 100644
--- a/llvm/test/CodeGen/X86/widen_cast-4.ll
+++ b/llvm/test/CodeGen/X86/widen_cast-4.ll
@@ -11,7 +11,7 @@ define void @update(ptr %dst_i, ptr %src_i, i32 %n) nounwind {
 ; WIDE-NEXT:    pcmpeqd %xmm0, %xmm0
 ; WIDE-NEXT:    movdqa {{.*#+}} xmm1 = [63,63,63,63,63,63,63,63,63,63,63,63,63,63,63,63]
 ; WIDE-NEXT:    movdqa {{.*#+}} xmm2 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32]
-; WIDE-NEXT:    .p2align 4, 0x90
+; WIDE-NEXT:    .p2align 4
 ; WIDE-NEXT:  .LBB0_1: # %forcond
 ; WIDE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; WIDE-NEXT:    movl (%esp), %eax
diff --git a/llvm/test/CodeGen/X86/x86-shrink-wrapping.ll b/llvm/test/CodeGen/X86/x86-shrink-wrapping.ll
index fab3847b3a2c51..fe7459ea45e141 100644
--- a/llvm/test/CodeGen/X86/x86-shrink-wrapping.ll
+++ b/llvm/test/CodeGen/X86/x86-shrink-wrapping.ll
@@ -80,7 +80,7 @@ define i32 @freqSaveAndRestoreOutsideLoop(i32 %cond, i32 %N) {
 ; ENABLE-NEXT:    ## InlineAsm End
 ; ENABLE-NEXT:    xorl %eax, %eax
 ; ENABLE-NEXT:    movl $10, %ecx
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  LBB1_2: ## %for.body
 ; ENABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; ENABLE-NEXT:    ## InlineAsm Start
@@ -111,7 +111,7 @@ define i32 @freqSaveAndRestoreOutsideLoop(i32 %cond, i32 %N) {
 ; DISABLE-NEXT:    ## InlineAsm End
 ; DISABLE-NEXT:    xorl %eax, %eax
 ; DISABLE-NEXT:    movl $10, %ecx
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  LBB1_2: ## %for.body
 ; DISABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; DISABLE-NEXT:    ## InlineAsm Start
@@ -174,7 +174,7 @@ define i32 @freqSaveAndRestoreOutsideLoop2(i32 %cond) {
 ; ENABLE-NEXT:    ## InlineAsm End
 ; ENABLE-NEXT:    xorl %eax, %eax
 ; ENABLE-NEXT:    movl $10, %ecx
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  LBB2_1: ## %for.body
 ; ENABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; ENABLE-NEXT:    ## InlineAsm Start
@@ -200,7 +200,7 @@ define i32 @freqSaveAndRestoreOutsideLoop2(i32 %cond) {
 ; DISABLE-NEXT:    ## InlineAsm End
 ; DISABLE-NEXT:    xorl %eax, %eax
 ; DISABLE-NEXT:    movl $10, %ecx
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  LBB2_1: ## %for.body
 ; DISABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; DISABLE-NEXT:    ## InlineAsm Start
@@ -255,7 +255,7 @@ define i32 @loopInfoSaveOutsideLoop(i32 %cond, i32 %N) {
 ; ENABLE-NEXT:    ## InlineAsm End
 ; ENABLE-NEXT:    xorl %eax, %eax
 ; ENABLE-NEXT:    movl $10, %ecx
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  LBB3_2: ## %for.body
 ; ENABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; ENABLE-NEXT:    ## InlineAsm Start
@@ -289,7 +289,7 @@ define i32 @loopInfoSaveOutsideLoop(i32 %cond, i32 %N) {
 ; DISABLE-NEXT:    ## InlineAsm End
 ; DISABLE-NEXT:    xorl %eax, %eax
 ; DISABLE-NEXT:    movl $10, %ecx
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  LBB3_2: ## %for.body
 ; DISABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; DISABLE-NEXT:    ## InlineAsm Start
@@ -355,7 +355,7 @@ define i32 @loopInfoRestoreOutsideLoop(i32 %cond, i32 %N) nounwind {
 ; ENABLE-NEXT:    ## InlineAsm End
 ; ENABLE-NEXT:    xorl %eax, %eax
 ; ENABLE-NEXT:    movl $10, %ecx
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  LBB4_2: ## %for.body
 ; ENABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; ENABLE-NEXT:    ## InlineAsm Start
@@ -384,7 +384,7 @@ define i32 @loopInfoRestoreOutsideLoop(i32 %cond, i32 %N) nounwind {
 ; DISABLE-NEXT:    ## InlineAsm End
 ; DISABLE-NEXT:    xorl %eax, %eax
 ; DISABLE-NEXT:    movl $10, %ecx
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  LBB4_2: ## %for.body
 ; DISABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; DISABLE-NEXT:    ## InlineAsm Start
@@ -461,7 +461,7 @@ define i32 @inlineAsm(i32 %cond, i32 %N) {
 ; ENABLE-NEXT:    nop
 ; ENABLE-NEXT:    ## InlineAsm End
 ; ENABLE-NEXT:    movl $10, %eax
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  LBB6_2: ## %for.body
 ; ENABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; ENABLE-NEXT:    ## InlineAsm Start
@@ -493,7 +493,7 @@ define i32 @inlineAsm(i32 %cond, i32 %N) {
 ; DISABLE-NEXT:    nop
 ; DISABLE-NEXT:    ## InlineAsm End
 ; DISABLE-NEXT:    movl $10, %eax
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  LBB6_2: ## %for.body
 ; DISABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; DISABLE-NEXT:    ## InlineAsm Start
@@ -824,7 +824,7 @@ define void @infiniteloop() {
 ; ENABLE-NEXT:    ## InlineAsm Start
 ; ENABLE-NEXT:    movl $1, %edx
 ; ENABLE-NEXT:    ## InlineAsm End
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  LBB10_2: ## %for.body
 ; ENABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; ENABLE-NEXT:    addl %edx, %eax
@@ -856,7 +856,7 @@ define void @infiniteloop() {
 ; DISABLE-NEXT:    ## InlineAsm Start
 ; DISABLE-NEXT:    movl $1, %edx
 ; DISABLE-NEXT:    ## InlineAsm End
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  LBB10_2: ## %for.body
 ; DISABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; DISABLE-NEXT:    addl %edx, %eax
@@ -906,7 +906,7 @@ define void @infiniteloop2() {
 ; ENABLE-NEXT:    movq %rcx, %rsp
 ; ENABLE-NEXT:    xorl %edx, %edx
 ; ENABLE-NEXT:    jmp LBB11_2
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  LBB11_4: ## %body2
 ; ENABLE-NEXT:    ## in Loop: Header=BB11_2 Depth=1
 ; ENABLE-NEXT:    ## InlineAsm Start
@@ -954,7 +954,7 @@ define void @infiniteloop2() {
 ; DISABLE-NEXT:    movq %rcx, %rsp
 ; DISABLE-NEXT:    xorl %edx, %edx
 ; DISABLE-NEXT:    jmp LBB11_2
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  LBB11_4: ## %body2
 ; DISABLE-NEXT:    ## in Loop: Header=BB11_2 Depth=1
 ; DISABLE-NEXT:    ## InlineAsm Start
@@ -1024,7 +1024,7 @@ define void @infiniteloop3() {
 ; ENABLE-NEXT:    xorl %ecx, %ecx
 ; ENABLE-NEXT:    movq %rax, %rsi
 ; ENABLE-NEXT:    jmp LBB12_4
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  LBB12_3: ## %loop2b
 ; ENABLE-NEXT:    ## in Loop: Header=BB12_4 Depth=1
 ; ENABLE-NEXT:    movq %rdx, (%rsi)
@@ -1056,7 +1056,7 @@ define void @infiniteloop3() {
 ; DISABLE-NEXT:    xorl %ecx, %ecx
 ; DISABLE-NEXT:    movq %rax, %rsi
 ; DISABLE-NEXT:    jmp LBB12_4
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  LBB12_3: ## %loop2b
 ; DISABLE-NEXT:    ## in Loop: Header=BB12_4 Depth=1
 ; DISABLE-NEXT:    movq %rdx, (%rsi)
@@ -1188,7 +1188,7 @@ define i32 @useLEAForPrologue(i32 %d, i32 %a, i8 %c) #3 {
 ; ENABLE-NEXT:    ## InlineAsm Start
 ; ENABLE-NEXT:    nop
 ; ENABLE-NEXT:    ## InlineAsm End
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  LBB14_2: ## %for.body
 ; ENABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; ENABLE-NEXT:    cmpl %esi, %edi
@@ -1223,7 +1223,7 @@ define i32 @useLEAForPrologue(i32 %d, i32 %a, i8 %c) #3 {
 ; DISABLE-NEXT:    ## InlineAsm Start
 ; DISABLE-NEXT:    nop
 ; DISABLE-NEXT:    ## InlineAsm End
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  LBB14_2: ## %for.body
 ; DISABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; DISABLE-NEXT:    cmpl %esi, %edi
@@ -1375,7 +1375,7 @@ define i32 @irreducibleCFG() #4 {
 ; ENABLE-NEXT:    movq _irreducibleCFGf at GOTPCREL(%rip), %rax
 ; ENABLE-NEXT:    cmpb $0, (%rax)
 ; ENABLE-NEXT:    je LBB16_2
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  LBB16_1: ## %preheader
 ; ENABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; ENABLE-NEXT:    jmp LBB16_1
@@ -1392,7 +1392,7 @@ define i32 @irreducibleCFG() #4 {
 ; ENABLE-NEXT:    jmp LBB16_5
 ; ENABLE-NEXT:  LBB16_3:
 ; ENABLE-NEXT:    xorl %ebx, %ebx
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  LBB16_5: ## %for.inc
 ; ENABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; ENABLE-NEXT:    incl %ebx
@@ -1418,7 +1418,7 @@ define i32 @irreducibleCFG() #4 {
 ; DISABLE-NEXT:    movq _irreducibleCFGf at GOTPCREL(%rip), %rax
 ; DISABLE-NEXT:    cmpb $0, (%rax)
 ; DISABLE-NEXT:    je LBB16_2
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  LBB16_1: ## %preheader
 ; DISABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; DISABLE-NEXT:    jmp LBB16_1
@@ -1435,7 +1435,7 @@ define i32 @irreducibleCFG() #4 {
 ; DISABLE-NEXT:    jmp LBB16_5
 ; DISABLE-NEXT:  LBB16_3:
 ; DISABLE-NEXT:    xorl %ebx, %ebx
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  LBB16_5: ## %for.inc
 ; DISABLE-NEXT:    ## =>This Inner Loop Header: Depth=1
 ; DISABLE-NEXT:    incl %ebx
@@ -1515,7 +1515,7 @@ define void @infiniteLoopNoSuccessor() #5 {
 ; ENABLE-NEXT:  LBB17_3:
 ; ENABLE-NEXT:    xorl %eax, %eax
 ; ENABLE-NEXT:    callq _something
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  LBB17_4: ## =>This Inner Loop Header: Depth=1
 ; ENABLE-NEXT:    xorl %eax, %eax
 ; ENABLE-NEXT:    callq _somethingElse
@@ -1542,7 +1542,7 @@ define void @infiniteLoopNoSuccessor() #5 {
 ; DISABLE-NEXT:  LBB17_3:
 ; DISABLE-NEXT:    xorl %eax, %eax
 ; DISABLE-NEXT:    callq _something
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  LBB17_4: ## =>This Inner Loop Header: Depth=1
 ; DISABLE-NEXT:    xorl %eax, %eax
 ; DISABLE-NEXT:    callq _somethingElse
diff --git a/llvm/test/CodeGen/X86/x86-win64-shrink-wrapping.ll b/llvm/test/CodeGen/X86/x86-win64-shrink-wrapping.ll
index 6ed23b0d770cd4..d52990e753d3eb 100644
--- a/llvm/test/CodeGen/X86/x86-win64-shrink-wrapping.ll
+++ b/llvm/test/CodeGen/X86/x86-win64-shrink-wrapping.ll
@@ -27,7 +27,7 @@ define i32 @loopInfoSaveOutsideLoop(i32 %cond, i32 %N) #0 {
 ; ENABLE-NEXT:    #APP
 ; ENABLE-NEXT:    movl $1, %edx
 ; ENABLE-NEXT:    #NO_APP
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  .LBB0_2: # %for.body
 ; ENABLE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; ENABLE-NEXT:    addl %edx, %eax
@@ -63,7 +63,7 @@ define i32 @loopInfoSaveOutsideLoop(i32 %cond, i32 %N) #0 {
 ; DISABLE-NEXT:    #APP
 ; DISABLE-NEXT:    movl $1, %edx
 ; DISABLE-NEXT:    #NO_APP
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  .LBB0_2: # %for.body
 ; DISABLE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; DISABLE-NEXT:    addl %edx, %eax
@@ -129,7 +129,7 @@ define i32 @loopInfoSaveOutsideLoop2(i32 %cond, i32 %N) #0 {
 ; ENABLE-NEXT:    #NO_APP
 ; ENABLE-NEXT:    xorl %eax, %eax
 ; ENABLE-NEXT:    movl $10, %ecx
-; ENABLE-NEXT:    .p2align 4, 0x90
+; ENABLE-NEXT:    .p2align 4
 ; ENABLE-NEXT:  .LBB1_2: # %for.body
 ; ENABLE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; ENABLE-NEXT:    #APP
@@ -164,7 +164,7 @@ define i32 @loopInfoSaveOutsideLoop2(i32 %cond, i32 %N) #0 {
 ; DISABLE-NEXT:    #NO_APP
 ; DISABLE-NEXT:    xorl %eax, %eax
 ; DISABLE-NEXT:    movl $10, %ecx
-; DISABLE-NEXT:    .p2align 4, 0x90
+; DISABLE-NEXT:    .p2align 4
 ; DISABLE-NEXT:  .LBB1_2: # %for.body
 ; DISABLE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; DISABLE-NEXT:    #APP
diff --git a/llvm/test/CodeGen/X86/xor.ll b/llvm/test/CodeGen/X86/xor.ll
index 7f4006792ef1a8..2bef66825d8c02 100644
--- a/llvm/test/CodeGen/X86/xor.ll
+++ b/llvm/test/CodeGen/X86/xor.ll
@@ -59,7 +59,7 @@ define i32 @test4(i32 %a, i32 %b) nounwind  {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB3_1: # %bb
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    xorl %ecx, %eax
@@ -75,7 +75,7 @@ define i32 @test4(i32 %a, i32 %b) nounwind  {
 ; X64-LIN-LABEL: test4:
 ; X64-LIN:       # %bb.0: # %entry
 ; X64-LIN-NEXT:    movl %edi, %eax
-; X64-LIN-NEXT:    .p2align 4, 0x90
+; X64-LIN-NEXT:    .p2align 4
 ; X64-LIN-NEXT:  .LBB3_1: # %bb
 ; X64-LIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-LIN-NEXT:    xorl %esi, %eax
@@ -91,7 +91,7 @@ define i32 @test4(i32 %a, i32 %b) nounwind  {
 ; X64-WIN-LABEL: test4:
 ; X64-WIN:       # %bb.0: # %entry
 ; X64-WIN-NEXT:    movl %ecx, %eax
-; X64-WIN-NEXT:    .p2align 4, 0x90
+; X64-WIN-NEXT:    .p2align 4
 ; X64-WIN-NEXT:  .LBB3_1: # %bb
 ; X64-WIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-WIN-NEXT:    xorl %edx, %eax
@@ -123,7 +123,7 @@ define i16 @test5(i16 %a, i16 %b) nounwind  {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movzwl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movzwl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB4_1: # %bb
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    xorl %ecx, %eax
@@ -141,7 +141,7 @@ define i16 @test5(i16 %a, i16 %b) nounwind  {
 ; X64-LIN-LABEL: test5:
 ; X64-LIN:       # %bb.0: # %entry
 ; X64-LIN-NEXT:    movl %edi, %eax
-; X64-LIN-NEXT:    .p2align 4, 0x90
+; X64-LIN-NEXT:    .p2align 4
 ; X64-LIN-NEXT:  .LBB4_1: # %bb
 ; X64-LIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-LIN-NEXT:    xorl %esi, %eax
@@ -160,7 +160,7 @@ define i16 @test5(i16 %a, i16 %b) nounwind  {
 ; X64-WIN:       # %bb.0: # %entry
 ; X64-WIN-NEXT:    # kill: def $dx killed $dx def $edx
 ; X64-WIN-NEXT:    movl %ecx, %eax
-; X64-WIN-NEXT:    .p2align 4, 0x90
+; X64-WIN-NEXT:    .p2align 4
 ; X64-WIN-NEXT:  .LBB4_1: # %bb
 ; X64-WIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-WIN-NEXT:    xorl %edx, %eax
@@ -194,7 +194,7 @@ define i8 @test6(i8 %a, i8 %b) nounwind  {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB5_1: # %bb
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    xorb %cl, %al
@@ -210,7 +210,7 @@ define i8 @test6(i8 %a, i8 %b) nounwind  {
 ; X64-LIN-LABEL: test6:
 ; X64-LIN:       # %bb.0: # %entry
 ; X64-LIN-NEXT:    movl %edi, %eax
-; X64-LIN-NEXT:    .p2align 4, 0x90
+; X64-LIN-NEXT:    .p2align 4
 ; X64-LIN-NEXT:  .LBB5_1: # %bb
 ; X64-LIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-LIN-NEXT:    xorb %sil, %al
@@ -227,7 +227,7 @@ define i8 @test6(i8 %a, i8 %b) nounwind  {
 ; X64-WIN-LABEL: test6:
 ; X64-WIN:       # %bb.0: # %entry
 ; X64-WIN-NEXT:    movl %ecx, %eax
-; X64-WIN-NEXT:    .p2align 4, 0x90
+; X64-WIN-NEXT:    .p2align 4
 ; X64-WIN-NEXT:  .LBB5_1: # %bb
 ; X64-WIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-WIN-NEXT:    xorb %dl, %al
@@ -259,7 +259,7 @@ define i32 @test7(i32 %a, i32 %b) nounwind  {
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X86-NEXT:    .p2align 4, 0x90
+; X86-NEXT:    .p2align 4
 ; X86-NEXT:  .LBB6_1: # %bb
 ; X86-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X86-NEXT:    xorl %ecx, %eax
@@ -275,7 +275,7 @@ define i32 @test7(i32 %a, i32 %b) nounwind  {
 ; X64-LIN-LABEL: test7:
 ; X64-LIN:       # %bb.0: # %entry
 ; X64-LIN-NEXT:    movl %edi, %eax
-; X64-LIN-NEXT:    .p2align 4, 0x90
+; X64-LIN-NEXT:    .p2align 4
 ; X64-LIN-NEXT:  .LBB6_1: # %bb
 ; X64-LIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-LIN-NEXT:    xorl %esi, %eax
@@ -291,7 +291,7 @@ define i32 @test7(i32 %a, i32 %b) nounwind  {
 ; X64-WIN-LABEL: test7:
 ; X64-WIN:       # %bb.0: # %entry
 ; X64-WIN-NEXT:    movl %ecx, %eax
-; X64-WIN-NEXT:    .p2align 4, 0x90
+; X64-WIN-NEXT:    .p2align 4
 ; X64-WIN-NEXT:  .LBB6_1: # %bb
 ; X64-WIN-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-WIN-NEXT:    xorl %edx, %eax
diff --git a/llvm/test/CodeGen/X86/xray-attribute-instrumentation.ll b/llvm/test/CodeGen/X86/xray-attribute-instrumentation.ll
index 9cebffc3abe9ab..fc1f3352ce8183 100644
--- a/llvm/test/CodeGen/X86/xray-attribute-instrumentation.ll
+++ b/llvm/test/CodeGen/X86/xray-attribute-instrumentation.ll
@@ -3,12 +3,12 @@
 ; RUN: llc -mtriple=x86_64-darwin-unknown                          < %s | FileCheck %s --check-prefixes=CHECK,CHECK-MACOS
 
 define i32 @foo() nounwind noinline uwtable "function-instrument"="xray-always" {
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_0:
 ; CHECK:       .ascii "\353\t"
 ; CHECK-NEXT:  nopw 512(%rax,%rax)
   ret i32 0
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_1:
 ; CHECK:       retq
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
@@ -38,7 +38,7 @@ define i32 @foo() nounwind noinline uwtable "function-instrument"="xray-always"
 ; We test multiple returns in a single function to make sure we're getting all
 ; of them with XRay instrumentation.
 define i32 @bar(i32 %i) nounwind noinline uwtable "function-instrument"="xray-always" {
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_2:
 ; CHECK:       .ascii "\353\t"
 ; CHECK-NEXT:  nopw 512(%rax,%rax)
@@ -47,13 +47,13 @@ Test:
   br i1 %cond, label %IsEqual, label %NotEqual
 IsEqual:
   ret i32 0
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_3:
 ; CHECK:       retq
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
 NotEqual:
   ret i32 1
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_4:
 ; CHECK:       retq
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
diff --git a/llvm/test/CodeGen/X86/xray-custom-log.ll b/llvm/test/CodeGen/X86/xray-custom-log.ll
index 9ccda8ecb04809..8f23055aca97c3 100644
--- a/llvm/test/CodeGen/X86/xray-custom-log.ll
+++ b/llvm/test/CodeGen/X86/xray-custom-log.ll
@@ -84,7 +84,7 @@ define void @leaf_func() "function-instrument"="xray-always" "frame-pointer"="no
   ; CHECK:         pushq %rax
   ; CHECK:         movl $leaf_func.event_id, %eax
   ; CHECK-NEXT:    movl $4, %ecx
-  ; CHECK-NEXT:    .p2align 1, 0x90
+  ; CHECK-NEXT:    .p2align 1
   ; CHECK-NEXT:  .Lxray_event_sled_1:
   call void @llvm.xray.customevent(ptr @leaf_func.event_id, i64 4)
   ret void
diff --git a/llvm/test/CodeGen/X86/xray-partial-instrumentation-skip-entry.ll b/llvm/test/CodeGen/X86/xray-partial-instrumentation-skip-entry.ll
index f58d743d465ddd..51b047c5a0e635 100644
--- a/llvm/test/CodeGen/X86/xray-partial-instrumentation-skip-entry.ll
+++ b/llvm/test/CodeGen/X86/xray-partial-instrumentation-skip-entry.ll
@@ -5,7 +5,7 @@
 define i32 @foo() nounwind noinline uwtable "function-instrument"="xray-always" "xray-skip-entry" {
 ; CHECK-NOT: Lxray_sled_0:
   ret i32 0
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_0:
 ; CHECK:       retq
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
@@ -39,13 +39,13 @@ Test:
   br i1 %cond, label %IsEqual, label %NotEqual
 IsEqual:
   ret i32 0
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_1:
 ; CHECK:       retq
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
 NotEqual:
   ret i32 1
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_2:
 ; CHECK:       retq
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
diff --git a/llvm/test/CodeGen/X86/xray-partial-instrumentation-skip-exit.ll b/llvm/test/CodeGen/X86/xray-partial-instrumentation-skip-exit.ll
index 3d631d73b68c50..ab841d734a23ed 100644
--- a/llvm/test/CodeGen/X86/xray-partial-instrumentation-skip-exit.ll
+++ b/llvm/test/CodeGen/X86/xray-partial-instrumentation-skip-exit.ll
@@ -4,7 +4,7 @@
 ; RUN: llc -mtriple=x86_64-darwin-unknown    < %s | FileCheck %s
 
 define i32 @foo() nounwind noinline uwtable "function-instrument"="xray-always" "xray-skip-exit" {
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_0:
 ; CHECK:       .ascii "\353\t"
 ; CHECK-NEXT:  nopw 512(%rax,%rax)
@@ -35,7 +35,7 @@ define i32 @foo() nounwind noinline uwtable "function-instrument"="xray-always"
 ; We test multiple returns in a single function to make sure we're skipping all
 ; of them with XRay instrumentation.
 define i32 @bar(i32 %i) nounwind noinline uwtable "function-instrument"="xray-always" "xray-skip-exit" {
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_1:
 ; CHECK:       .ascii "\353\t"
 ; CHECK-NEXT:  nopw 512(%rax,%rax)
diff --git a/llvm/test/CodeGen/X86/xray-selective-instrumentation.ll b/llvm/test/CodeGen/X86/xray-selective-instrumentation.ll
index 7bf47ea2894c0f..868c35363f6e96 100644
--- a/llvm/test/CodeGen/X86/xray-selective-instrumentation.ll
+++ b/llvm/test/CodeGen/X86/xray-selective-instrumentation.ll
@@ -7,12 +7,12 @@ target triple = "x86_64-apple-darwin8"
 define i32 @foo() nounwind uwtable "xray-instruction-threshold"="1" {
 ; CHECK-LABEL: foo:
 ; CHECK:       ## %bb.0: ## %entry
-; CHECK-NEXT:    .p2align 1, 0x90
+; CHECK-NEXT:    .p2align 1
 ; CHECK-NEXT:  Lxray_sled_0:
 ; CHECK-NEXT:    .ascii "\353\t"
 ; CHECK-NEXT:    nopw 512(%rax,%rax)
 ; CHECK-NEXT:    xorl %eax, %eax
-; CHECK-NEXT:    .p2align 1, 0x90
+; CHECK-NEXT:    .p2align 1
 ; CHECK-NEXT:  Lxray_sled_1:
 ; CHECK-NEXT:    retq
 ; CHECK-NEXT:    nopw %cs:512(%rax,%rax)
diff --git a/llvm/test/CodeGen/X86/xray-tail-call-sled.ll b/llvm/test/CodeGen/X86/xray-tail-call-sled.ll
index 126e5db52a5b73..91b91f5360f928 100644
--- a/llvm/test/CodeGen/X86/xray-tail-call-sled.ll
+++ b/llvm/test/CodeGen/X86/xray-tail-call-sled.ll
@@ -2,12 +2,12 @@
 ; RUN: llc -mtriple=x86_64-darwin-unknown    < %s | FileCheck %s --check-prefixes=CHECK,CHECK-MACOS
 
 define dso_local i32 @callee() nounwind noinline uwtable "function-instrument"="xray-always" {
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_0:
 ; CHECK:       .ascii "\353\t"
 ; CHECK-NEXT:  nopw 512(%rax,%rax)
   ret i32 0
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_1:
 ; CHECK:       retq
 ; CHECK-NEXT:  nopw %cs:512(%rax,%rax)
@@ -34,11 +34,11 @@ define dso_local i32 @callee() nounwind noinline uwtable "function-instrument"="
 ; CHECK-MACOS-NEXT:    .quad 2
 
 define dso_local i32 @caller() nounwind noinline uwtable "function-instrument"="xray-always" {
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_2:
 ; CHECK:       .ascii "\353\t"
 ; CHECK-NEXT:  nopw 512(%rax,%rax)
-; CHECK:       .p2align 1, 0x90
+; CHECK:       .p2align 1
 ; CHECK-LABEL: Lxray_sled_3:
 ; CHECK-NEXT:  .ascii "\353\t"
 ; CHECK-NEXT:  nopw 512(%rax,%rax)
@@ -69,13 +69,13 @@ define dso_local i32 @caller() nounwind noinline uwtable "function-instrument"="
 
 define dso_local i32 @conditional_tail_call(i32 %cond) nounwind noinline uwtable "function-instrument"="xray-always" {
 ; CHECK-LABEL: conditional_tail_call:
-; CHECK:         .p2align 1, 0x90
+; CHECK:         .p2align 1
 ; CHECK-LABEL: Lxray_sled_4:
 ; CHECK:         .ascii "\353\t"
 ; CHECK-NEXT:    nopw 512(%rax,%rax)
 ; CHECK-NEXT:    testl %edi, %edi
 ; CHECK-NEXT:    je {{\.?Ltmp5}}
-; CHECK:         .p2align 1, 0x90
+; CHECK:         .p2align 1
 ; CHECK-LABEL: Lxray_sled_5:
 ; CHECK-NEXT:    .ascii "\353\t"
 ; CHECK-NEXT:    nopw 512(%rax,%rax)
@@ -83,7 +83,7 @@ define dso_local i32 @conditional_tail_call(i32 %cond) nounwind noinline uwtable
 ; CHECK-NEXT:    jmp {{.*}}callee {{.*}}# TAILCALL
 ; CHECK-LABEL: Ltmp5:
 ; CHECK:         xorl %eax, %eax
-; CHECK-NEXT:   .p2align  1, 0x90
+; CHECK-NEXT:   .p2align  1
 ; CHECK-LABEL: Lxray_sled_6:
 ; CHECK-NEXT:    retq
 ; CHECK-NEXT:    nopw %cs:512(%rax,%rax)
diff --git a/llvm/test/DebugInfo/COFF/pieces.ll b/llvm/test/DebugInfo/COFF/pieces.ll
index 8f5b6b2d7c1afd..8e62ad0093aa3b 100644
--- a/llvm/test/DebugInfo/COFF/pieces.ll
+++ b/llvm/test/DebugInfo/COFF/pieces.ll
@@ -41,7 +41,7 @@
 ; ASM:         xorl    %edi, %edi
 ; ASM:         xorl    %esi, %esi
 ; ASM: [[oy_ox_start:\.Ltmp[0-9]+]]:
-; ASM:         .p2align        4, 0x90
+; ASM:         .p2align        4
 ; ASM: .LBB0_3:                                # %for.body
 ; ASM:        #DEBUG_VALUE: loop_csr:o <- [DW_OP_LLVM_fragment 0 32] $edi
 ; ASM:        #DEBUG_VALUE: loop_csr:o <- [DW_OP_LLVM_fragment 32 32] $esi
diff --git a/llvm/test/DebugInfo/X86/header.ll b/llvm/test/DebugInfo/X86/header.ll
index 3f3d9f95419c1d..f90aa3b50f4671 100644
--- a/llvm/test/DebugInfo/X86/header.ll
+++ b/llvm/test/DebugInfo/X86/header.ll
@@ -5,7 +5,7 @@
 ; CHECK:       .text
 ; CHECK-NEXT: .file	"<stdin>"
 ; CHECK-NEXT: .globl	f
-; CHECK-NEXT: .p2align	4, 0x90
+; CHECK-NEXT: .p2align	4
 ; CHECK-NEXT: .type	f, at function
 ; CHECK-NEXT: f:                                      # @f
 
diff --git a/llvm/test/DebugInfo/X86/loop-align-debug.ll b/llvm/test/DebugInfo/X86/loop-align-debug.ll
index a0302d08faa0c3..d6f6395b26544a 100644
--- a/llvm/test/DebugInfo/X86/loop-align-debug.ll
+++ b/llvm/test/DebugInfo/X86/loop-align-debug.ll
@@ -13,7 +13,7 @@
 
 ; ASM:      .loc    0 0 0 is_stmt 0
 ; ASM-NEXT: .L{{.*}}:
-; ASM-NEXT: .p2align        4, 0x90
+; ASM-NEXT: .p2align        4
 
 ;; $ cat test.cpp
 ;; void g();
diff --git a/llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll b/llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll
index 841836c7d2dd86..7ae78ae6a1fd40 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/X86/2011-11-29-postincphi.ll
@@ -17,7 +17,7 @@ define i64 @sqlite3DropTriggerPtr() nounwind {
 ; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    movl $1, %ebx
 ; CHECK-NEXT:    callq check at PLT
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %bb1
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    testb %al, %al
diff --git a/llvm/test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll b/llvm/test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll
index 39e2d6f1acca45..93203ef6e17f53 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/X86/ivchain-X86.ll
@@ -20,7 +20,7 @@ define i32 @simple(ptr %a, ptr %b, i32 %x) nounwind {
 ; X64-NEXT:    shlq $2, %rcx
 ; X64-NEXT:    xorl %eax, %eax
 ; X64-NEXT:    leaq (%rcx,%rcx), %rdx
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB0_1: # %loop
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    addl (%rdi), %eax
@@ -47,7 +47,7 @@ define i32 @simple(ptr %a, ptr %b, i32 %x) nounwind {
 ; X32-NEXT:    shll $2, %edx
 ; X32-NEXT:    xorl %eax, %eax
 ; X32-NEXT:    leal (%edx,%edx), %esi
-; X32-NEXT:    .p2align 4, 0x90
+; X32-NEXT:    .p2align 4
 ; X32-NEXT:  .LBB0_1: # %loop
 ; X32-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X32-NEXT:    addl (%edi), %eax
@@ -101,7 +101,7 @@ define i32 @user(ptr %a, ptr %b, i32 %x) nounwind {
 ; X64-NEXT:    leaq (,%rcx,4), %rax
 ; X64-NEXT:    leaq (%rax,%rax,2), %r8
 ; X64-NEXT:    xorl %eax, %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB1_1: # %loop
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    addl (%rdi), %eax
@@ -128,7 +128,7 @@ define i32 @user(ptr %a, ptr %b, i32 %x) nounwind {
 ; X32-NEXT:    leal (,%ecx,4), %eax
 ; X32-NEXT:    leal (%eax,%eax,2), %ebx
 ; X32-NEXT:    xorl %eax, %eax
-; X32-NEXT:    .p2align 4, 0x90
+; X32-NEXT:    .p2align 4
 ; X32-NEXT:  .LBB1_1: # %loop
 ; X32-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X32-NEXT:    addl (%esi), %eax
@@ -200,7 +200,7 @@ define void @extrastride(ptr nocapture %main, i32 %main_stride, ptr nocapture %r
 ; X64-NEXT:    movslq %r8d, %r8
 ; X64-NEXT:    shlq $2, %r8
 ; X64-NEXT:    movslq %ebx, %r11
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB2_2: # %for.body
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl (%rdi,%rsi), %ebx
@@ -235,7 +235,7 @@ define void @extrastride(ptr nocapture %main, i32 %main_stride, ptr nocapture %r
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %edi
 ; X32-NEXT:    addl %esi, %edi
 ; X32-NEXT:    shll $2, %ecx
-; X32-NEXT:    .p2align 4, 0x90
+; X32-NEXT:    .p2align 4
 ; X32-NEXT:  .LBB2_2: # %for.body
 ; X32-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X32-NEXT:    movl (%ebx,%esi), %ebp
@@ -309,7 +309,7 @@ define void @foldedidx(ptr nocapture %a, ptr nocapture %b, ptr nocapture %c) nou
 ; X64-LABEL: foldedidx:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    movl $3, %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB3_1: # %for.body
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movzbl -3(%rdi,%rax), %ecx
@@ -343,7 +343,7 @@ define void @foldedidx(ptr nocapture %a, ptr nocapture %b, ptr nocapture %c) nou
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %esi
-; X32-NEXT:    .p2align 4, 0x90
+; X32-NEXT:    .p2align 4
 ; X32-NEXT:  .LBB3_1: # %for.body
 ; X32-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X32-NEXT:    movzbl -3(%esi,%eax), %edi
@@ -433,7 +433,7 @@ define void @multioper(ptr %a, i32 %n) nounwind {
 ; X64-LABEL: multioper:
 ; X64:       # %bb.0: # %entry
 ; X64-NEXT:    xorl %eax, %eax
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB4_1: # %for.body
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movl %eax, (%rdi,%rax,4)
@@ -455,7 +455,7 @@ define void @multioper(ptr %a, i32 %n) nounwind {
 ; X32-NEXT:    xorl %eax, %eax
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
-; X32-NEXT:    .p2align 4, 0x90
+; X32-NEXT:    .p2align 4
 ; X32-NEXT:  .LBB4_1: # %for.body
 ; X32-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X32-NEXT:    movl %eax, (%edx,%eax,4)
@@ -511,7 +511,7 @@ define void @testCmpZero(ptr %src, ptr %dst, i32 %srcidx, i32 %dstidx, i32 %len)
 ; X64-NEXT:    movslq %r8d, %rcx
 ; X64-NEXT:    subq %rdx, %rcx
 ; X64-NEXT:    xorl %edx, %edx
-; X64-NEXT:    .p2align 4, 0x90
+; X64-NEXT:    .p2align 4
 ; X64-NEXT:  .LBB5_1: # %for.body82.us
 ; X64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X64-NEXT:    movzbl (%rax,%rdx,4), %esi
@@ -532,7 +532,7 @@ define void @testCmpZero(ptr %src, ptr %dst, i32 %srcidx, i32 %dstidx, i32 %len)
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %edx
 ; X32-NEXT:    addl {{[0-9]+}}(%esp), %edx
 ; X32-NEXT:    xorl %esi, %esi
-; X32-NEXT:    .p2align 4, 0x90
+; X32-NEXT:    .p2align 4
 ; X32-NEXT:  .LBB5_1: # %for.body82.us
 ; X32-NEXT:    # =>This Inner Loop Header: Depth=1
 ; X32-NEXT:    movzbl (%edx,%esi,4), %ebx
diff --git a/llvm/test/Transforms/LoopStrengthReduce/X86/lsr-insns-1.ll b/llvm/test/Transforms/LoopStrengthReduce/X86/lsr-insns-1.ll
index 753aaed7d77c0b..1c953515a31083 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/X86/lsr-insns-1.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/X86/lsr-insns-1.ll
@@ -65,7 +65,7 @@ define void @foo(ptr nocapture readonly %x, ptr nocapture readonly %y, ptr nocap
 ; CHECK-LABEL: foo:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    movq $-4096, %rax # imm = 0xF000
-; CHECK-NEXT:    .p2align 4, 0x90
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %for.body
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    movl 4096(%rsi,%rax), %ecx
diff --git a/llvm/test/Transforms/LoopStrengthReduce/X86/macro-fuse-cmp.ll b/llvm/test/Transforms/LoopStrengthReduce/X86/macro-fuse-cmp.ll
index feff010300c1e1..ef2ed1f0e87e20 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/X86/macro-fuse-cmp.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/X86/macro-fuse-cmp.ll
@@ -79,7 +79,7 @@ define void @maxArray(ptr noalias nocapture %x, ptr noalias nocapture readonly %
 ; BASE-LABEL: maxArray:
 ; BASE:       # %bb.0: # %entry
 ; BASE-NEXT:    movq $-524288, %rax # imm = 0xFFF80000
-; BASE-NEXT:    .p2align 4, 0x90
+; BASE-NEXT:    .p2align 4
 ; BASE-NEXT:  .LBB0_1: # %vector.body
 ; BASE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; BASE-NEXT:    movupd 524288(%rdi,%rax), %xmm0
@@ -93,7 +93,7 @@ define void @maxArray(ptr noalias nocapture %x, ptr noalias nocapture readonly %
 ; FUSE-LABEL: maxArray:
 ; FUSE:       # %bb.0: # %entry
 ; FUSE-NEXT:    xorl %eax, %eax
-; FUSE-NEXT:    .p2align 4, 0x90
+; FUSE-NEXT:    .p2align 4
 ; FUSE-NEXT:  .LBB0_1: # %vector.body
 ; FUSE-NEXT:    # =>This Inner Loop Header: Depth=1
 ; FUSE-NEXT:    movupd (%rdi,%rax,8), %xmm0



More information about the llvm-commits mailing list