Commit 129a7625 authored by Shengchen Kan's avatar Shengchen Kan
Browse files

[X86] Disable the NOP padding for branches when bundle is enabled 

When bundle is enabled, data fragment itself has a space to emit NOP
to bundle-align instructions. The behaviour makes it impossible for
us to determine whether the macro fusion really happen when emitting
instructions. In addition, boundary-align fragment is also used to
emit NOPs to align instructions, currently using them together sometimes
makes code crazy.

Differential Revision: https://reviews.llvm.org/D75346
parent 00925aad

llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp

+1 −3
Original line number Diff line number Diff line
@@ -364,10 +364,8 @@ bool X86AsmBackend::needAlign(MCObjectStreamer &OS) const { 
    return false;

  assert(allowAutoPadding() && "incorrect initialization!");



  MCAssembler &Assembler = OS.getAssembler();

  MCSection *Sec = OS.getCurrentSectionOnly();

  // To be Done: Currently don't deal with Bundle cases.

  if (Assembler.isBundlingEnabled() && Sec->isBundleLocked())

  if (OS.getAssembler().isBundlingEnabled())

    return false;



  // Branches only need to be aligned in 32-bit or 64-bit mode.

llvm/test/MC/X86/align-branch-64-7a.s

0 → 100644
+23 −0
Original line number Diff line number Diff line 
# Check using option --x86-align-branch-boundary=16 --x86-align-branch=fused+jcc --mc-relax-all with bundle won't make code crazy

# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown --x86-align-branch-boundary=16 --x86-align-branch=fused+jcc --mc-relax-all %s | llvm-objdump -d  - > %t1

# RUN: FileCheck --input-file=%t1 %s



# CHECK: 0000000000000000 foo:

# CHECK-NEXT:       0: 55                               pushq    %rbp

# CHECK-NEXT:       1: 48 f7 c2 02 00 00 00             testq    $2, %rdx

# CHECK-NEXT:       8: 0f 85 f2 ff ff ff                jne      {{.*}}

# CHECK-NEXT:       e: 90                               nop

# CHECK-NEXT:       f: 90                               nop

# CHECK-NEXT:      10: 0f 8e ea ff ff ff                jle      {{.*}}



    .text

    .p2align 4

foo:

  push %rbp

  # Will be bundle-aligning to 8 byte boundaries

  .bundle_align_mode 3

  test $2, %rdx

  jne   foo

# This jle is 6 bytes long and should have started at 0xe, so two bytes

# of nop padding are inserted instead and it starts at 0x10

  jle   foo