[llvm] 26271c8 - [AArch64InstrInfo] Ignore debug insts in canInstrSubstituteCmpInstr [6/14]

[Vedant Kumar via llvm-commits]

Author: Vedant Kumar
Date: 2020-04-22T17:03:40-07:00
New Revision: 26271c83849ba05982963bf5e85e54fc0de1389a

URL: https://github.com/llvm/llvm-project/commit/26271c83849ba05982963bf5e85e54fc0de1389a
DIFF: https://github.com/llvm/llvm-project/commit/26271c83849ba05982963bf5e85e54fc0de1389a.diff

LOG: [AArch64InstrInfo] Ignore debug insts in canInstrSubstituteCmpInstr [6/14]

Summary:
Fix an issue where the presence of debug info could disable a peephole
optimization in optimizeCompareInstr due to canInstrSubstituteCmpInstr
returning the wrong result.

Depends on D78137.

Reviewers: t.p.northover, eastig, paquette

Subscribers: kristof.beyls, hiraditya, danielkiss, aprantl, llvm-commits, dsanders

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D78151

Added: 
    

Modified: 
    llvm/lib/CodeGen/PeepholeOptimizer.cpp
    llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
    llvm/test/CodeGen/AArch64/arm64-arm64-dead-def-elimination-flag.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/CodeGen/PeepholeOptimizer.cpp b/llvm/lib/CodeGen/PeepholeOptimizer.cpp
index ae309a30e154..b9e8c692eeaf 100644
--- a/llvm/lib/CodeGen/PeepholeOptimizer.cpp
+++ b/llvm/lib/CodeGen/PeepholeOptimizer.cpp
@@ -614,6 +614,7 @@ bool PeepholeOptimizer::optimizeCmpInstr(MachineInstr &MI) {
     return false;
 
   // Attempt to optimize the comparison instruction.
+  LLVM_DEBUG(dbgs() << "Attempting to optimize compare: " << MI);
   if (TII->optimizeCompareInstr(MI, SrcReg, SrcReg2, CmpMask, CmpValue, MRI)) {
     ++NumCmps;
     return true;
@@ -635,6 +636,7 @@ bool PeepholeOptimizer::optimizeSelect(MachineInstr &MI,
     return false;
   if (!TII->optimizeSelect(MI, LocalMIs))
     return false;
+  LLVM_DEBUG(dbgs() << "Deleting select: " << MI);
   MI.eraseFromParent();
   ++NumSelects;
   return true;
@@ -1299,6 +1301,7 @@ bool PeepholeOptimizer::optimizeUncoalescableCopy(
   }
 
   // MI is now dead.
+  LLVM_DEBUG(dbgs() << "Deleting uncoalescable copy: " << MI);
   MI.eraseFromParent();
   ++NumUncoalescableCopies;
   return true;
@@ -1723,6 +1726,7 @@ bool PeepholeOptimizer::runOnMachineFunction(MachineFunction &MF) {
           (foldRedundantCopy(*MI, CopySrcRegs, CopySrcMIs) ||
            foldRedundantNAPhysCopy(*MI, NAPhysToVirtMIs))) {
         LocalMIs.erase(MI);
+        LLVM_DEBUG(dbgs() << "Deleting redundant copy: " << *MI << "\n");
         MI->eraseFromParent();
         Changed = true;
         continue;

diff  --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
index 564b7c801868..cd52d04385e8 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.cpp
@@ -1443,10 +1443,9 @@ static bool canInstrSubstituteCmpInstr(MachineInstr *MI, MachineInstr *CmpInstr,
     return false;
 
   UsedNZCV NZCVUsedAfterCmp;
-  for (auto I = std::next(CmpInstr->getIterator()),
-            E = CmpInstr->getParent()->instr_end();
-       I != E; ++I) {
-    const MachineInstr &Instr = *I;
+  for (const MachineInstr &Instr :
+       instructionsWithoutDebug(std::next(CmpInstr->getIterator()),
+                                CmpInstr->getParent()->instr_end())) {
     if (Instr.readsRegister(AArch64::NZCV, TRI)) {
       AArch64CC::CondCode CC = findCondCodeUsedByInstr(Instr);
       if (CC == AArch64CC::Invalid) // Unsupported conditional instruction

diff  --git a/llvm/test/CodeGen/AArch64/arm64-arm64-dead-def-elimination-flag.ll b/llvm/test/CodeGen/AArch64/arm64-arm64-dead-def-elimination-flag.ll
index 85aa9c44305f..2bf13606ba7d 100644
--- a/llvm/test/CodeGen/AArch64/arm64-arm64-dead-def-elimination-flag.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-arm64-dead-def-elimination-flag.ll
@@ -1,4 +1,4 @@
-; RUN: llc -mtriple=arm64-apple-ios7.0.0 -aarch64-enable-dead-defs=false < %s | FileCheck %s
+; RUN: llc -debugify-and-strip-all-safe -mtriple=arm64-apple-ios7.0.0 -aarch64-enable-dead-defs=false < %s | FileCheck %s
 
 target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"