summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--llvm/lib/Target/X86/X86FastISel.cpp2
-rw-r--r--llvm/lib/Target/X86/X86InstrInfo.cpp117
-rw-r--r--llvm/lib/Target/X86/X86InstrInfo.h2
-rw-r--r--llvm/test/CodeGen/X86/avx1-stack-reload-folding.ll16
4 files changed, 51 insertions, 86 deletions
diff --git a/llvm/lib/Target/X86/X86FastISel.cpp b/llvm/lib/Target/X86/X86FastISel.cpp
index b0cc17bc863..70eec08cce2 100644
--- a/llvm/lib/Target/X86/X86FastISel.cpp
+++ b/llvm/lib/Target/X86/X86FastISel.cpp
@@ -3337,7 +3337,7 @@ bool X86FastISel::tryToFoldLoadIntoMI(MachineInstr *MI, unsigned OpNo,
AM.getFullAddress(AddrOps);
MachineInstr *Result =
- XII.foldMemoryOperandImpl(*FuncInfo.MF, MI, OpNo, AddrOps, Size, Alignment, /*AllowCommute=*/ true);
+ XII.foldMemoryOperandImpl(*FuncInfo.MF, MI, OpNo, AddrOps, Size, Alignment);
if (!Result)
return false;
diff --git a/llvm/lib/Target/X86/X86InstrInfo.cpp b/llvm/lib/Target/X86/X86InstrInfo.cpp
index da011cb7892..a7637f9e65d 100644
--- a/llvm/lib/Target/X86/X86InstrInfo.cpp
+++ b/llvm/lib/Target/X86/X86InstrInfo.cpp
@@ -3926,34 +3926,55 @@ optimizeLoadInstr(MachineInstr *MI, const MachineRegisterInfo *MRI,
if (!DefMI->isSafeToMove(this, nullptr, SawStore))
return nullptr;
- // Collect information about virtual register operands of MI.
- unsigned SrcOperandId = 0;
- bool FoundSrcOperand = false;
- for (unsigned i = 0, e = MI->getDesc().getNumOperands(); i != e; ++i) {
- MachineOperand &MO = MI->getOperand(i);
- if (!MO.isReg())
- continue;
- unsigned Reg = MO.getReg();
- if (Reg != FoldAsLoadDefReg)
- continue;
- // Do not fold if we have a subreg use or a def or multiple uses.
- if (MO.getSubReg() || MO.isDef() || FoundSrcOperand)
- return nullptr;
+ // We try to commute MI if possible.
+ unsigned IdxEnd = (MI->isCommutable()) ? 2 : 1;
+ for (unsigned Idx = 0; Idx < IdxEnd; Idx++) {
+ // Collect information about virtual register operands of MI.
+ unsigned SrcOperandId = 0;
+ bool FoundSrcOperand = false;
+ for (unsigned i = 0, e = MI->getDesc().getNumOperands(); i != e; ++i) {
+ MachineOperand &MO = MI->getOperand(i);
+ if (!MO.isReg())
+ continue;
+ unsigned Reg = MO.getReg();
+ if (Reg != FoldAsLoadDefReg)
+ continue;
+ // Do not fold if we have a subreg use or a def or multiple uses.
+ if (MO.getSubReg() || MO.isDef() || FoundSrcOperand)
+ return nullptr;
- SrcOperandId = i;
- FoundSrcOperand = true;
- }
- if (!FoundSrcOperand) return nullptr;
+ SrcOperandId = i;
+ FoundSrcOperand = true;
+ }
+ if (!FoundSrcOperand) return nullptr;
+
+ // Check whether we can fold the def into SrcOperandId.
+ SmallVector<unsigned, 8> Ops;
+ Ops.push_back(SrcOperandId);
+ MachineInstr *FoldMI = foldMemoryOperand(MI, Ops, DefMI);
+ if (FoldMI) {
+ FoldAsLoadDefReg = 0;
+ return FoldMI;
+ }
- // Check whether we can fold the def into SrcOperandId.
- SmallVector<unsigned, 8> Ops;
- Ops.push_back(SrcOperandId);
- MachineInstr *FoldMI = foldMemoryOperand(MI, Ops, DefMI);
- if (FoldMI) {
- FoldAsLoadDefReg = 0;
- return FoldMI;
- }
+ if (Idx == 1) {
+ // MI was changed but it didn't help, commute it back!
+ commuteInstruction(MI, false);
+ return nullptr;
+ }
+ // Check whether we can commute MI and enable folding.
+ if (MI->isCommutable()) {
+ MachineInstr *NewMI = commuteInstruction(MI, false);
+ // Unable to commute.
+ if (!NewMI) return nullptr;
+ if (NewMI != MI) {
+ // New instruction. It doesn't need to be kept.
+ NewMI->eraseFromParent();
+ return nullptr;
+ }
+ }
+ }
return nullptr;
}
@@ -4113,7 +4134,7 @@ MachineInstr*
X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
MachineInstr *MI, unsigned i,
const SmallVectorImpl<MachineOperand> &MOs,
- unsigned Size, unsigned Align, bool AllowCommute) const {
+ unsigned Size, unsigned Align) const {
const DenseMap<unsigned,
std::pair<unsigned,unsigned> > *OpcodeTablePtr = nullptr;
bool isCallRegIndirect = Subtarget.callRegIndirect();
@@ -4210,46 +4231,6 @@ X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
}
}
- // If the instruction and target operand are commutable, commute the instruction and try again.
- if (AllowCommute) {
- unsigned OriginalOpIdx = i, CommuteOpIdx1, CommuteOpIdx2;
- if (findCommutedOpIndices(MI, CommuteOpIdx1, CommuteOpIdx2)) {
- if ((CommuteOpIdx1 == OriginalOpIdx) || (CommuteOpIdx2 == OriginalOpIdx)) {
- MachineInstr* CommutedMI = commuteInstruction(MI, false);
- if (!CommutedMI) {
- // Unable to commute.
- return nullptr;
- }
- if (CommutedMI != MI) {
- // New instruction. We can't fold from this.
- CommutedMI->eraseFromParent();
- return nullptr;
- }
-
- // Attempt to fold with the commuted version of the instruction.
- unsigned CommuteOpIdx = (CommuteOpIdx1 == OriginalOpIdx ? CommuteOpIdx2 : CommuteOpIdx1);
- NewMI = foldMemoryOperandImpl(MF, MI, CommuteOpIdx, MOs, Size, Align, /*AllowCommute=*/ false);
- if (NewMI)
- return NewMI;
-
- // Folding failed again - undo the commute before returning.
- MachineInstr* UncommutedMI = commuteInstruction(MI, false);
- if (!UncommutedMI) {
- // Unable to commute.
- return nullptr;
- }
- if (UncommutedMI != MI) {
- // New instruction. It doesn't need to be kept.
- UncommutedMI->eraseFromParent();
- return nullptr;
- }
-
- // Return here to prevent duplicate fuse failure report.
- return nullptr;
- }
- }
- }
-
// No fusion
if (PrintFailedFusing && !MI->isCopy())
dbgs() << "We failed to fuse operand " << i << " in " << *MI;
@@ -4459,7 +4440,7 @@ X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF, MachineInstr *MI,
SmallVector<MachineOperand,4> MOs;
MOs.push_back(MachineOperand::CreateFI(FrameIndex));
- return foldMemoryOperandImpl(MF, MI, Ops[0], MOs, Size, Alignment, /*AllowCommute=*/ true);
+ return foldMemoryOperandImpl(MF, MI, Ops[0], MOs, Size, Alignment);
}
static bool isPartialRegisterLoad(const MachineInstr &LoadMI,
@@ -4612,7 +4593,7 @@ MachineInstr* X86InstrInfo::foldMemoryOperandImpl(MachineFunction &MF,
break;
}
}
- return foldMemoryOperandImpl(MF, MI, Ops[0], MOs, 0, Alignment, /*AllowCommute=*/ true);
+ return foldMemoryOperandImpl(MF, MI, Ops[0], MOs, 0, Alignment);
}
diff --git a/llvm/lib/Target/X86/X86InstrInfo.h b/llvm/lib/Target/X86/X86InstrInfo.h
index 01a80486ada..ca90976a83a 100644
--- a/llvm/lib/Target/X86/X86InstrInfo.h
+++ b/llvm/lib/Target/X86/X86InstrInfo.h
@@ -404,7 +404,7 @@ public:
MachineInstr* MI,
unsigned OpNum,
const SmallVectorImpl<MachineOperand> &MOs,
- unsigned Size, unsigned Alignment, bool AllowCommute) const;
+ unsigned Size, unsigned Alignment) const;
void
getUnconditionalBranch(MCInst &Branch,
diff --git a/llvm/test/CodeGen/X86/avx1-stack-reload-folding.ll b/llvm/test/CodeGen/X86/avx1-stack-reload-folding.ll
deleted file mode 100644
index 5da1b4c5767..00000000000
--- a/llvm/test/CodeGen/X86/avx1-stack-reload-folding.ll
+++ /dev/null
@@ -1,16 +0,0 @@
-; RUN: llc -O3 -disable-peephole -mcpu=corei7-avx -mattr=+avx < %s | FileCheck %s
-
-target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
-target triple = "x86_64-unknown-unknown"
-
-; Function Attrs: nounwind readonly uwtable
-define <32 x double> @_Z14vstack_foldDv32_dS_(<32 x double> %a, <32 x double> %b) #0 {
- %1 = fadd <32 x double> %a, %b
- %2 = fsub <32 x double> %a, %b
- %3 = fmul <32 x double> %1, %2
- ret <32 x double> %3
-
- ;CHECK-NOT: vmovapd {{.*#+}} 32-byte Reload
- ;CHECK: vmulpd {{[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
- ;CHECK-NOT: vmovapd {{.*#+}} 32-byte Reload
-}
OpenPOWER on IntegriCloud