implement rdar://6653118 - fastisel should fold loads where possible.
Since mem2reg isn't run at -O0, we get a ton of reloads from the stack,
for example, before, this code:
int foo(int x, int y, int z) {
return x+y+z;
}
used to compile into:
_foo: ## @foo
subq $12, %rsp
movl %edi, 8(%rsp)
movl %esi, 4(%rsp)
movl %edx, (%rsp)
movl 8(%rsp), %edx
movl 4(%rsp), %esi
addl %edx, %esi
movl (%rsp), %edx
addl %esi, %edx
movl %edx, %eax
addq $12, %rsp
ret
Now we produce:
_foo: ## @foo
subq $12, %rsp
movl %edi, 8(%rsp)
movl %esi, 4(%rsp)
movl %edx, (%rsp)
movl 8(%rsp), %edx
addl 4(%rsp), %edx ## Folded load
addl (%rsp), %edx ## Folded load
movl %edx, %eax
addq $12, %rsp
ret
Fewer instructions and less register use = faster compiles.
llvm-svn: 113102
diff --git a/llvm/lib/Target/X86/X86InstrInfo.h b/llvm/lib/Target/X86/X86InstrInfo.h
index f336206..eb0e4b8 100644
--- a/llvm/lib/Target/X86/X86InstrInfo.h
+++ b/llvm/lib/Target/X86/X86InstrInfo.h
@@ -845,18 +845,18 @@
/// SetSSEDomain - Set the SSEDomain of MI.
void SetSSEDomain(MachineInstr *MI, unsigned Domain) const;
+ MachineInstr* foldMemoryOperandImpl(MachineFunction &MF,
+ MachineInstr* MI,
+ unsigned OpNum,
+ const SmallVectorImpl<MachineOperand> &MOs,
+ unsigned Size, unsigned Alignment) const;
+
private:
MachineInstr * convertToThreeAddressWithLEA(unsigned MIOpc,
MachineFunction::iterator &MFI,
MachineBasicBlock::iterator &MBBI,
LiveVariables *LV) const;
- MachineInstr* foldMemoryOperandImpl(MachineFunction &MF,
- MachineInstr* MI,
- unsigned OpNum,
- const SmallVectorImpl<MachineOperand> &MOs,
- unsigned Size, unsigned Alignment) const;
-
/// isFrameOperand - Return true and the FrameIndex if the specified
/// operand and follow operands form a reference to the stack frame.
bool isFrameOperand(const MachineInstr *MI, unsigned int Op,