[llvm-branch-commits] [llvm] a048ce1 - [X86] Default to -x86-pad-for-align=false to drop assembler difference with or w/o -g

Fangrui Song via llvm-branch-commits llvm-branch-commits at lists.llvm.org
Sat Jan 16 16:44:09 PST 2021


Author: Fangrui Song
Date: 2021-01-16T16:39:54-08:00
New Revision: a048ce13e32daa255d26533c00da8abd0b67e819

URL: https://github.com/llvm/llvm-project/commit/a048ce13e32daa255d26533c00da8abd0b67e819
DIFF: https://github.com/llvm/llvm-project/commit/a048ce13e32daa255d26533c00da8abd0b67e819.diff

LOG: [X86] Default to -x86-pad-for-align=false to drop assembler difference with or w/o -g

Fix PR48742: the D75203 assembler optimization locates MCRelaxableFragment's
within two MCSymbol's and relaxes some MCRelaxableFragment's to reduce the size
of a MCAlignFragment.  A -g build has more MCSymbol's and therefore may have
different assembler output (e.g. a MCRelaxableFragment (jmp) may have 5 bytes
with -O1 while 2 bytes with -O1 -g).

`.p2align 4, 0x90` is common due to loops. For a larger program, with a
lot of temporary labels, the assembly output difference is somewhat
destined. The cost seems to overweigh the benefits so we default to
-x86-pad-for-align=false until the heuristic is improved.

Reviewed By: skan

Differential Revision: https://reviews.llvm.org/D94542

Added: 
    

Modified: 
    llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
    llvm/test/MC/X86/align-via-padding-corner.s
    llvm/test/MC/X86/align-via-padding.s
    llvm/test/MC/X86/align-via-relaxation.s
    llvm/test/MC/X86/prefix-padding-32.s
    llvm/test/MC/X86/prefix-padding-64.s

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp b/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
index a7d71bd35d29..95012a148d83 100644
--- a/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
+++ b/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
@@ -109,7 +109,7 @@ cl::opt<unsigned> X86PadMaxPrefixSize(
     cl::desc("Maximum number of prefixes to use for padding"));
 
 cl::opt<bool> X86PadForAlign(
-    "x86-pad-for-align", cl::init(true), cl::Hidden,
+    "x86-pad-for-align", cl::init(false), cl::Hidden,
     cl::desc("Pad previous instructions to implement align directives"));
 
 cl::opt<bool> X86PadForBranchAlign(
@@ -957,6 +957,9 @@ void X86AsmBackend::finishLayout(MCAssembler const &Asm,
   if (!X86PadForAlign && !X86PadForBranchAlign)
     return;
 
+  // The processed regions are delimitered by LabeledFragments. -g may have more
+  // MCSymbols and therefore 
diff erent relaxation results. X86PadForAlign is
+  // disabled by default to eliminate the -g vs non -g 
diff erence.
   DenseSet<MCFragment *> LabeledFragments;
   for (const MCSymbol &S : Asm.symbols())
     LabeledFragments.insert(S.getFragment(false));

diff  --git a/llvm/test/MC/X86/align-via-padding-corner.s b/llvm/test/MC/X86/align-via-padding-corner.s
index cc13ff7eed7f..6b8e02d198a5 100644
--- a/llvm/test/MC/X86/align-via-padding-corner.s
+++ b/llvm/test/MC/X86/align-via-padding-corner.s
@@ -1,4 +1,4 @@
-  # RUN: llvm-mc -mcpu=skylake -filetype=obj -triple x86_64-pc-linux-gnu %s -x86-pad-max-prefix-size=5 | llvm-objdump -d - | FileCheck %s
+  # RUN: llvm-mc -mcpu=skylake -filetype=obj -triple x86_64-pc-linux-gnu %s -x86-pad-max-prefix-size=5 -x86-pad-for-align=1 | llvm-objdump -d - | FileCheck %s
 
 
   # The first test check the correctness cornercase - can't add prefixes on a

diff  --git a/llvm/test/MC/X86/align-via-padding.s b/llvm/test/MC/X86/align-via-padding.s
index d5d86da6ddca..32495fe4a3ae 100644
--- a/llvm/test/MC/X86/align-via-padding.s
+++ b/llvm/test/MC/X86/align-via-padding.s
@@ -1,4 +1,4 @@
-# RUN: llvm-mc -mcpu=skylake -filetype=obj -triple x86_64-pc-linux-gnu %s -x86-pad-max-prefix-size=5 | llvm-objdump -d --section=.text - | FileCheck %s
+# RUN: llvm-mc -mcpu=skylake -filetype=obj -triple x86_64-pc-linux-gnu %s -x86-pad-max-prefix-size=5 -x86-pad-for-align=1 | llvm-objdump -d - | FileCheck %s
 
 # This test file highlights the interactions between prefix padding and
 # relaxation padding.

diff  --git a/llvm/test/MC/X86/align-via-relaxation.s b/llvm/test/MC/X86/align-via-relaxation.s
index d768232655b7..394efaf6d75b 100644
--- a/llvm/test/MC/X86/align-via-relaxation.s
+++ b/llvm/test/MC/X86/align-via-relaxation.s
@@ -1,4 +1,5 @@
-# RUN: llvm-mc -mcpu=skylake -filetype=obj -triple x86_64-pc-linux-gnu -x86-pad-max-prefix-size=0 %s | llvm-objdump -d --section=.text - | FileCheck %s
+# RUN: llvm-mc -mcpu=skylake -filetype=obj -triple x86_64-pc-linux-gnu -x86-pad-max-prefix-size=0 %s | llvm-objdump -d - | FileCheck %s --check-prefix=NOPAD
+# RUN: llvm-mc -mcpu=skylake -filetype=obj -triple x86_64-pc-linux-gnu -x86-pad-max-prefix-size=0 -x86-pad-for-align=1 %s | llvm-objdump -d - | FileCheck %s
 
 # This test exercises only the padding via relaxation logic.  The  interaction
 # etween prefix padding and relaxation logic can be seen in align-via-padding.s
@@ -6,6 +7,19 @@
   .file "test.c"
   .text
   .section  .text
+
+# NOPAD-LABEL: <.text>:
+# NOPAD-NEXT:     0: eb 1f           jmp 0x21 <foo>
+# NOPAD-NEXT:     2: eb 1d           jmp 0x21 <foo>
+# NOPAD-NEXT:     4: eb 1b           jmp 0x21 <foo>
+# NOPAD-NEXT:     6: eb 19           jmp 0x21 <foo>
+# NOPAD-NEXT:     8: eb 17           jmp 0x21 <foo>
+# NOPAD-NEXT:     a: eb 15           jmp 0x21 <foo>
+# NOPAD-NEXT:     c: eb 13           jmp 0x21 <foo>
+# NOPAD-NEXT:     e: 66 66 66 66 66 66 2e 0f 1f 84 00 00 00 00 00  nopw    %cs:(%rax,%rax)
+# NOPAD-NEXT:    1d: 0f 1f 00        nopl (%rax)
+# NOPAD-NEXT:    20: cc              int3
+
   # Demonstrate that we can relax instructions to provide padding, not
   # just insert nops.  jmps are being used for ease of demonstration.
   # CHECK: .text

diff  --git a/llvm/test/MC/X86/prefix-padding-32.s b/llvm/test/MC/X86/prefix-padding-32.s
index b975bd5783c0..380c705908d5 100644
--- a/llvm/test/MC/X86/prefix-padding-32.s
+++ b/llvm/test/MC/X86/prefix-padding-32.s
@@ -1,4 +1,4 @@
-# RUN: llvm-mc -filetype=obj -triple i386-pc-linux-gnu %s -x86-pad-max-prefix-size=15 | llvm-objdump -d --section=.text - | FileCheck %s
+# RUN: llvm-mc -filetype=obj -triple i386-pc-linux-gnu %s -x86-pad-max-prefix-size=15 -x86-pad-for-align=1 | llvm-objdump -d - | FileCheck %s
 
 # Check prefix padding generation for all cases on 32 bit x86.
 

diff  --git a/llvm/test/MC/X86/prefix-padding-64.s b/llvm/test/MC/X86/prefix-padding-64.s
index fcffc772d25b..7ba618d8f233 100644
--- a/llvm/test/MC/X86/prefix-padding-64.s
+++ b/llvm/test/MC/X86/prefix-padding-64.s
@@ -1,4 +1,4 @@
-# RUN: llvm-mc -mcpu=skylake -filetype=obj -triple x86_64-pc-linux-gnu %s -x86-pad-max-prefix-size=15 | llvm-objdump -d --section=.text - | FileCheck %s
+# RUN: llvm-mc -mcpu=skylake -filetype=obj -triple x86_64-pc-linux-gnu %s -x86-pad-max-prefix-size=15 -x86-pad-for-align=1 | llvm-objdump -d - | FileCheck %s
 
 # Check prefix padding generation for all cases on 64 bit x86.
 


        


More information about the llvm-branch-commits mailing list